HELMET DETECTION AND BIOMETRIC BASED VEHICLESECURITY USING MACHINE LEARNING.docx

HELMET DETECTION AND BIOMETRIC BASED VEHICLESECURITY USING MACHINE LEARNING.docx

1. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE LEARNING

A
Project Report
On
HELMET DETECTION AND BIOMETRIC BASED VEHICLE
SECURITY USING MACHINE LEARNING
A Dissertation submitted in Partial Fulfilment of the Requirement for the Award
of Bachelor’s Degree in
Electronics and Communication Engineering
Submitted By
R.Sanjay Kumar (21K91A04M3)
S.Raj Kumar (21K91A04N1)
Nouseen (22K95A0421)
Under the esteemed guidance of
Mrs.K.Sudha Rani
Associate Professor, ECE Dept.
2021-2025
TKR COLLEGE OF ENGINEERING AND TECHNOLOGY
(AUTONOMOUS)
DEPARTMENT OF ELECTRONICS AND COMMUNICATION
ENGINEERING
(Accredited By NBA, Approved by AICTE)
Accredited by NAAC with “A+” grade
(MEDBOWLI, MEERPET, SAROORNAGAR, HYDERABAD-500097)
DEPARTMENT OF ECE, TKRCET 1

2. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE LEARNING
TKR COLLEGE OF ENGINEERING AND TECHNOLOGY
(Sponsored By TKR Education Society, Approved by AICTE, Affiliated by JNTUH)
Autonomous, Accredited by NAAC with ‘A+’ Grade. Accredited by NBA
CERTIFICATE
This is to certify that the project report entitled “HELMET DETECTION AND
BIOMETRIC BASED VEHICLE SECURITY USING MACHINE LEARING”
Submitted by
R.Sanjay Kumar (21K91A04M3)
S.Raj Kumar (21K91A04N1)
Nouseen (22K95A0421)
This record is a Bonafede work carried out by them during the academic year 2021-
2025, Under the guidance and supervision of
Mrs.K.Sudha Rani
Associate Professor
(Internal Guide)
Dr. M. Mahesh
Head of the Department
ECE
DEPARTMENT OF ECE, TKRCET 2

3. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE LEARNING
DEPARTMENT OF ECE, TKRCET 3

4. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE LEARNING
ACKNOWLEDGEMENT
Any attempt at any level can't be satisfied completely without the report
and guidance of learned people. These words are not enough to show our
gratitude towards them. We would like to express our token of thanks to
them.
We would like to express our immense gratitude to Mrs.K.SUDHA
RANI, Associate Professor, ECE for guiding and correcting various
document with lot of attention and care.
We our gratitude to our Co-Ordinator's Mr. G. MAHESH, Ms. Ch.
DIVYA Dr. P. VENKATA LAVANYA, who took keen interest on our
project and guided us all along, till the completion of our project by
providing all the necessary information for developing a good project.
We would like to convey our sincere thanks to Dr. M. MAHESH, HoD
OF ECE department for his support and motivation that has encouraged
us to come up with project.
We express our sincere gratitude to the Principal Dr. V. RAVI
SHANKAR for the conductive environment created by him in the college
for effective completion of project undertaken by us.
We would also like to thank our faculty members without who this
project would have been a distant reality.
DEPARTMENT OF ECE, TKRCET 4

5. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE LEARNING
DECLARATION
We hereby declare that the Project Report entitled “HELMET
DETECTION AND BIOMETRIC BASED VEHICLE SECURITY
USING MACHINE LEARING” is original and bonafede work carried
out by us for the award of degree of Bachelor of Technology under the
guidance of MRS.K.SUDHA RANI, ASSOCIATE PROFESSOR.
Submitted By
R.Sanjay Kumar (21K91A04M3)
S.Raj Kumar (21K91A04N1)
Nouseen (22K95A0421)
DEPARTMENT OF ECE, TKRCET 5

6. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE LEARNING
ABSTRACT
In recent years, the rise in road accidents and vehicle
thefts has become a serious concern, urging the need for
innovative solutions to enhance road safety and vehicle security.
This paper presents a novel approach combining helmet
detection and biometric-based vehicle security using machine
learning techniques to address these issues. This system provides
two steps of security in first step it validates biometric
(fingerprint scanning), in second step it identifies helmet
wearing. If any one of these two will fail then vehicle will not
start or stop.
This proposed project title is helmet detection and biometric
based vehicle security using machine learning with Arduino and
ESP32 camera.

DEPARTMENT OF ECE, TKRCET 6

7. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE LEARNING
INDEX
S.NO. CHAPTER NAME PAGE.NO.

1 INTRODUCTION 9
2 BLOCK DIAGRAM
2.1.Proposed Model
2.2 Block Diagram of an Embedded System
3 HARDWARE DESCRIPTION
3.1 Power supply
3.2 ESP32
3.3 Liquid Crystal Display (lcd)
3.4 ESP32_Camera
3.5 Relay
3.6 Buzzer
3.7 Introduction about IOT

4 SOFTWARE SPECIFICATION
5 ALGORITHM & FLOWCHART
5.1 Algorithm
5.2 Flowchart

DEPARTMENT OF ECE, TKRCET 7

8. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE LEARNING
6 RESULT & ANALYSIS
6.1 Procedure
6.2 Result
6.3 Advantages and applications
6.4 Limitations of this project
7 CONCLUSION
DEPARTMENT OF ECE, TKRCET 8

9. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE LEARNING
LIST OF FIGURES
FIGURE TITLE PAGE NO.
1 proposed model 11
2 Block diagram of an embedded system 14
3 Embedded system having heterogeneous architectures 16
4 Block diagram of power supply 19
5 Bridge rectifier 20
6 Output waveform of DC 21
7 circuit diagram of power supply 22
8 ESP32-S2 25
9 16x2 Lcd 26
10 ESP32-CAM 32
11 Relay 36
12 Representation of relay 37
13 Buzzer 38
14 Internet of things 40
15 Example of IoT 41
16 IOT architecture 42
17 Embedded devices system in IoT 45
18 Basic embedded system 46
19 IoT ecosystem 47
20 The IoT technology stack 48
21 Decision area of the IoT decision framework 49
22 Stages of IoT solutions architecture 51
23 The 4 stage IoT solutions architecture 52
24 Interconnected among them and facilitate our daily life 53
25 Internet of things devices 54
DEPARTMENT OF ECE, TKRCET 9

10. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE LEARNING
26 IoT devices and technologies 55
CHAPTER-1
INTRODUCTION
  In recent years, the rise in road accidents and vehicle thefts has become
a serious concern, urging the need for innovative solutions to enhance road safety and
vehicle security. This paper presents a novel approach combining helmet detection
and biometric-based vehicle security using machine learning techniques to address
these issues. This system provides two steps of security in first step it validates
biometric (fingerprint scanning), in second step it identifies helmet wearing. If any
one of these two will fail then vehicle will not start or stop. This proposed project title
is helmet detection and biometric based vehicle security using machine learning with
Arduino and ESP32 camera.
DESCRIPTION:
Biometric module (R307) and ESP32 camera are connected to ESP32
controller UART port. Assume motor as vehicle engine and it will control by relay.
Relay connected with Arduino digital pin.
Initially we have to enroll our fingers into fingerprint module. We can enroll two or
more number of fingerprints we can enroll for demonstration. We use CNN AI
Algorithm to detect helmet status. Create Hotspot with username IOT server and
Password IOT server 123.
ESP32 controller monitors finger print scanner when user pressed ignition key. ESP32
camera enabled with AI and ML program, this will detect helmet wearing. ESP32
camera uses Tensor flow and deep learning techniques to identify helmet wearing.
Image classification plays major role to detect and identify particular objects. If user
have valid fingerprint and helmet wearing then only vehicle will start. If any of them
fails then vehicle will stop automatically.
DEPARTMENT OF ECE, TKRCET 10

11. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE LEARNING
CHAPTER-2
BLOCK DIAGRAM
2.1. Proposed Model

DEPARTMENT OF ECE, TKRCET 11
POWE SUUPPLY
ESP32
FINGER
PRINT Sensor 
KEY lock
 
Relay
ESP32 CAM 
Motor
IOT

12. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE LEARNING
2.1 OVERVIEW OF EMBEDDED SYSTEMS
An embedded system is a special-purpose computer system designed to
perform one or a few dedicated functions, often with real-time computing constraints.
It is usually embedded as part of a complete device including hardware and
mechanical parts. In contrast, a general-purpose computer, such as a personal
computer, can do many different tasks depending on programming. Embedded
systems have become very important today as they control many of the common
devices we use.
Since the embedded system is dedicated to specific tasks, design engineers
can optimize it, reducing the size and cost of the product, or increasing the reliability
and performance. Some embedded systems are mass-produced, benefiting from
economies of scale.
Physically, embedded systems range from portable devices such as digital
watches and MP3 players, to large stationary installations like traffic lights, factory
controllers, or the systems controlling nuclear power plants. Complexity varies from
low, with a single microcontroller chip, to very high with multiple units, peripherals
and networks mounted inside a large chassis or enclosure.
In general, "embedded system" is not an exactly defined term, as many
systems have some element of programmability. For example, Handheld computers
share some elements with embedded systems — such as the operating systems and
microprocessors which power them — but are not truly embedded systems, because
they allow different applications to be loaded and peripherals to be connected.
Embedded systems provide several functions
• Monitor the environment; embedded systems read data from input sensors. This data
is then processed and the results displayed in some format to a user or users
•Control the environment; embedded systems generate and transmit commands for
actuators.
DEPARTMENT OF ECE, TKRCET 12

13. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE LEARNING
•Transform the information; embedded systems transform the data collected in some
meaningful way, such as data compression / decompression
DEPARTMENT OF ECE, TKRCET 13

14. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE LEARNING
Although interaction with the external world via sensors and actuators is
an important aspect of embedded systems, these systems also provide functionality
specific to their applications. Embedded systems typically execute applications such
as control laws, finite state machines, and signal processing algorithms. These systems
must also detect and react to faults in both the internal computing environment as well
as the surrounding electromechanical systems.
There are many categories of embedded systems, from communication
devices to home appliances to control systems. Examples include;
•Communication devices
e.g.: modems, cellular phones
•Home Appliances
e.g.: CD player, VCR, microwave oven
•Control Systems
e.g.: Automobile anti-lock braking systems, robotics, satellite control
DEPARTMENT OF ECE, TKRCET 14

15. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE LEARNING
2.2 BLOCK DIAGRAM OF AN EMBEDDED SYSTEM
An embedded system usually contains an embedded processor. Many
appliances that have a digital interface -- microwaves, VCRs, cars -- utilize embedded
systems. Some embedded systems include an operating system. Others are very
specialized resulting in the entire logic being implemented as a single program. These
systems are embedded into some device for some specific purpose other than to
provide general purpose computing. A typical embedded system is shown in Figure
4.1.
Fig:2 Block diagram of a typical embedded system
Characteristics of Embedded Systems
Embedded systems are characterized by a unique set of characteristics.
Each of these characteristics imposed a specific set of design constraints on embedded
systems designers. The challenge to designing embedded systems is to conform to the
specific set of constraints for the application.
DEPARTMENT OF ECE, TKRCET 15

16. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE LEARNING
Application Specific Systems
Embedded systems are not general-purpose computers. Embedded system
designs are optimized for a specific application. Many of the job characteristics are
known before the hardware is designed. This allows the designer to focus on the
specific design constraints of a well-defined application. As such, there is limited user
reprogram ability. Some embedded systems, however, require the flexibility of
reprogram ability. Programmable DSPs are common for such applications.
Reactive Systems
As mentioned earlier, a typical embedded systems model responds to the
environment via sensors and control the environment using actuators. This requires
embedded systems to run at the speed of the environment. This characteristic of
embedded system is called “reactive”. Reactive computation means that the system
(primarily the software component) executes in response to external events. External
events can be either periodic or aperiodic. Periodic events make it easier to schedule
processing to guarantee performance. Aperiodic events are harder to schedule. The
maximum event arrival rate must be estimated in order to accommodate worst case
situations. Most embedded systems have a significant reactive component. One of the
biggest challenges for embedded system designers is performing an accurate worst
case design analysis on systems with statistical performance characteristics (e.g.,
cache memory on a DSP or other embedded processor). Real time system operation
means that the correctness of a computation depends, in part, on the time at which it is
delivered. Systems with this requirement must often design to worst case
performance. But accurately predicting the worst case may be difficult on complicated
architectures. This often leads to overly pessimistic estimates erring on the side of
caution. Many embedded systems have a significant requirement for real time
operation in order to meet external I/O and control stability requirements. Many real-
time systems are also reactive systems.
DEPARTMENT OF ECE, TKRCET 16

17. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
Distributed Systems
A common characteristic of an embedded system is one that consists of
communicating processes executing on several CPUs or ASICs which are connected
by communication links. The reason for this is economy. Economical 4 8-bit
microcontrollers may be cheaper than a 32-bit processors. Even after adding the cost
of the communication links, this approach may be preferable. In this approach,
multiple processors are usually required to handle multiple time-critical tasks. Devices
under control of embedded systems may also be physically distributed.
Heterogeneous Architectures
Embedded systems often are composed of heterogeneous architectures
(Figure 4.2). They may contain different processors in the same system solution. They
may also be mixed signal systems. The combination of I/O interfaces, local and
remote memories, and sensors and actuators makes embedded system design truly
unique. Embedded systems also have tight design constraints, and heterogeneity
provides better design flexibility.

Fig:3 Embedded Systems having Heterogeneous Architectures
Harsh environment
Many embedded systems do not operate in a controlled environment.
Excessive heat is often a problem, especially in applications involving combustion
DEPARTMENT OF ECE, TKRCET 17

18. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
(e.g., many transportation applications). Additional problems can be caused for
DEPARTMENT OF ECE, TKRCET 18

19. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
embedded computing by a need for protection from vibration, shock, lightning,
power supply fluctuations, water, corrosion, fire, and general physical abuse.
System safety and reliability
As embedded system complexity and computing power continue to grow,
they are starting to control more and more of the safety aspects of the overall system.
These safety measures may be in the form of software as well as hardware control.
Mechanical safety backups are normally activated when the computer system loses
control in order to safely shut down system operation. Software safety and reliability
is a bigger issue. Software doesn't normally "break" in the sense of hardware.
However software may be so complex that a set of unexpected circumstances can
cause software failures leading to unsafe situations. Discussion of this topic is outside
the scope of this book, but the challenges for embedded designers include designing
reliable software and building cheap, available systems using unreliable components.
The main challenge for embedded system designers is to obtain low-cost reliability
with minimal redundancy.
Control of physical systems
One of the main reasons for embedding a computer is to interact with the
environment. This is often done by monitoring and controlling external machinery.
Embedded computers transform the analog signals from sensors into digital form for
processing. Outputs must be transformed back to analog signal levels. When
controlling physical equipment, large current loads may need to be switched in order
to operate motors and other actuators. To meet these needs, embedded systems may
need large computer circuit boards with many non-digital components. Embedded
system designers must carefully balance system tradeoffs among analog components,
power, mechanical, network, and digital hardware with corresponding software.
Small and low weight
Many embedded computers are physically located within some larger
system. The form factor for the embedded system may be dictated by aesthetics.
DEPARTMENT OF ECE, TKRCET 19

20. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
For example, the form factor for a missile may have to fit inside the nose of the
missile. One of the challenges for embedded systems designers is to develop non-
rectangular geometries for certain solutions. Weight can also be a critical constraint.
Embedded automobile control systems, for example, must be light weight for fuel
economy. Portable CD players must be light weight for portability purposes.
Cost sensitivity
Cost is an issue in most systems, but the sensitivity to cost changes can
vary dramatically in embedded systems. This is mainly due to the effect of computer
costs have on profitability and is more a function of the proportion of cost changes
compared to the total system cost.
Power management
Embedded systems have strict constraints on power. Given the portability
requirements of many embedded systems, the need to conserve power is important to
maintain battery life as long as possible. Minimization of heat production is another
obvious concern for embedded systems.
DEPARTMENT OF ECE, TKRCET 20

21. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
CHAPTER-3
HARDWARE DESCRIPTION
3.1. POWER SUPPLY
The power supply section is the section which provides +5V for the
components to work. IC LM7805 is used for providing a constant power of +5V.
The ac voltage, typically 220V, is connected to a transformer, which steps down the
ac voltage down to the level of the desired dc output. A diode rectifier then provides a
full-wave rectified voltage that is initially filtered by a simple capacitor filter to
produce a dc voltage. This resulting dc voltage usually has some ripple or ac voltage
variation.
A regulator circuit removes the ripples and also retains the same dc value even if the
input dc voltage varies, or the load connected to the output dc voltage changes. This
voltage regulation is usually obtained using one of the popular voltage regulator IC
units.
Fig4: Block Diagram of Power Supply
Transformer
Transformers convert AC electricity from one voltage to another with little
loss of power. Transformers work only with AC and this is one of the reasons why
mains electricity is AC.
DEPARTMENT OF ECE, TKRCET 21

22. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
Step-up transformers increase voltage, step-down transformers reduce voltage. Most
power supplies use a step-down transformer to reduce the dangerously high mains
voltage (230V in India) to a safer low voltage.
The input coil is called the primary and the output coil is called the secondary. There
is no electrical connection between the two coils; instead they are linked by an
alternating magnetic field created in the soft-iron core of the transformer.
Transformers waste very little power so the power out is (almost) equal to the power
in. Note that as voltage is stepped down current is stepped up.
The transformer will step down the power supply voltage (0-230V) to (0- 6V) level.
Then the secondary of the potential transformer will be connected to the bridge
rectifier, which is constructed with the help of PN junction diodes. The advantages of
using a bridge rectifier are it will give peak voltage output as DC.
Rectifier
There are several ways of connecting diodes to make a rectifier to convert AC
to DC. The bridge rectifier is the most important and it produces full-wave varying
DC. A full-wave rectifier can also be made from just two diodes if a centre-tap
transformer is used, but this method is rarely used now that diodes are cheaper. A
single diode can be used as a rectifier but it only uses the positive (+) parts of the AC
wave to produce half-wave varying DC
Bridge Rectifier
When four diodes are connected as shown in figure, the circuit is called as
bridge rectifier. The input to the circuit is applied to the diagonally opposite corners of
the network, and the output is taken from the remaining two corners. Let us assume
that the transformer is working properly and there is a positive potential at point A and
a negative potential at point B. the positive potential at point A will forward bias D3
and reverse bias D4.
DEPARTMENT OF ECE, TKRCET 22

23. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING

Fig5: Bridge Rectifier
The negative potential at point B will forward bias D1 and reverse D2. At this time D3
and D1 are forward biased and will allow current flow to pass through them; D4 and
D2 are reverse biased and will block current flow.
One advantage of a bridge rectifier over a conventional full-wave rectifier is that with
a given transformer the bridge rectifier produces a voltage output that is nearly twice
that of the conventional full-wave circuit.
The main advantage of this bridge circuit is that it does not require a special centre
tapped transformer, thereby reducing its size and cost.
The single secondary winding is connected to one side of the diode bridge network
and the load to the other side as shown below.
The result is still a pulsating direct current but with double the frequency.
Fig6: Output Waveform of DC
Smoothing
Smoothing is performed by a large value electrolytic capacitor connected
across the DC supply to act as a reservoir, supplying current to the output when the
DEPARTMENT OF ECE, TKRCET 23

24. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
varying DC voltage from the rectifier is falling. The capacitor charges quickly near the
peak of the varying DC, and then discharges as it supplies current to the output.
Voltage Regulators
Voltage regulators comprise a class of widely used ICs. Regulator IC units
contain the circuitry for reference source, comparator amplifier, control device, and
overload protection all in a single IC. IC units provide regulation of either a fixed
positive voltage, a fixed negative voltage, or an adjustable set voltage. The regulators
can be selected for operation with load currents from hundreds of milli amperes to
tens of amperes, corresponding to power ratings from milli watts to tens of watts.
A fixed three-terminal voltage regulator has an unregulated dc input voltage, Vi,
applied to one input terminal, a regulated dc output voltage, Vo, from a second
terminal, with the third terminal connected to ground.
The series 78 regulators provide fixed positive regulated voltages from 5 to 24 volts.
Similarly, the series 79 regulators provide fixed negative regulated voltages from 5 to
24 volts. Voltage regulator ICs are available with fixed (typically 5, 12 and 15V) or
variable output voltages. They are also rated by the maximum current they can pass.
Negative voltage regulators are available, mainly for use in dual supplies. Most
regulators include some automatic protection from excessive current ('overload
protection') and overheating ('thermal protection').
Many of the fixed voltage regulator ICs have 3 leads and look like power transistors,
such as the 7805 +5V 1Amp regulator. They include a hole for attaching a heat sink if
necessary.
Regulator
DEPARTMENT OF ECE, TKRCET 24

25. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING

Fig7: Circuit Diagram of Power Supply
DEPARTMENT OF ECE, TKRCET 25

26. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
3.2 ESP32 
ESP32 is a series of low-cost, low-power system on a
chip microcontrollers with integrated Wi-Fi and dual-mode Bluetooth. The ESP32
series employs either a Tensilica Xtensa LX6 microprocessor in both dual-core
and single-core variations, Xtensa LX7 dual-core microprocessor or a single-
core RISC-V microprocessor and includes built-in antenna switches, RF balun, power
amplifier, low-noise receive amplifier, filters, and power-management modules.
ESP32 is created and developed by Espressif Systems, a Shanghai-based Chinese
company, and is manufactured by TSMC using their 40 nm process.
[2]
 It is a successor
to the ESP8266 microcontroller.
Processors:
CPU: Xtensa dual-core (or single-core) 32-bit LX6 microprocessor, operating at 160
or 240 MHz and performing at up to 600 DMIPS
Ultra low power (ULP) co-processor
Memory: 320 KiB RAM, 448 KiB ROM
Wireless connectivity:
Wi-Fi: 802.11 b/g/n
Bluetooth: v4.2 BR/EDR and BLE (shares the radio with Wi-Fi)
Peripheral interfaces:
34 × programmable GPIOs
12-bit SAR ADC up to 18 channels
2 × 8-bit DACs
10 × touch sensors (capacitive sensing GPIOs)
4 × SPI
2 × I²S interfaces
2 × I²C interfaces
3 × UART
SD/SDIO/CE-ATA/MMC/eMMC host controller
SDIO/SPI slave controller
Ethernet MAC interface with dedicated DMA and planned IEEE 1588
Precision Time Protocol support[4]
DEPARTMENT OF ECE, TKRCET 26

27. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
CAN bus 2.0
Infrared remote controller (TX/RX, up to 8 channels)
Motor PWM
LED PWM (up to 16 channels)
Hall effect sensor
Ultra-low power analog pre-amplifier
Security:
IEEE 802.11 standard security features all supported, including WPA, WPA2, WPA3
(depending on version) and WLAN Authentication and Privacy Infrastructure (WAPI)
Secure boot
Flash encryption
1024-bit OTP, up to 768-bit for customers
Cryptographic hardware acceleration: AES, SHA-2, RSA, elliptic curve cryptography
(ECC), random number generator (RNG)
Power management:
Internal low-dropout regulator
Individual power domain for RTC
5 μA deep sleep current
Wake up from GPIO interrupt, timer, ADC measurements, capacitive touch sensor
interrupt
ESP32-S2
Single-core Xtensa LX7 CPU, up to 240 MHz[6]
320 kiB SRAM, 128 kiB ROM, and 16 kiB of RTC memory
WiFi 2.4 Ghz (IEEE 802.11b/g/n)[7]
No Bluetooth
43 programmable GPIOs
USB OTG
This keyestudio ESP32 core board is a Mini development board based on the
ESP-WROOM-32 module. The board has brought out most I/O ports to pin headers of
2.54mm pitch. These provide an easy way of connecting peripherals according to your
own needs. When it comes to developing and debugging with the development board,
DEPARTMENT OF ECE, TKRCET 27

28. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
the both side standard pin headers can make your operation more simple and handy.
The ESP-WROOM-32 module is the industry's leading integrated WiFi + Bluetooth
solution with less than 10 external components. It integrates antenna switch, RF balun,
power amplifiers, low noise amplifiers, filters and power management modules. At the
same time, it also integrates with TSMC's low-power 40nm technology, so that power
performance and RF performance are safe and reliable, easy to expand to a variety of
applications.
The Pin Map below shows the functions that can be used on each pin. Many pins can
be used for multiple functions.
Microcontroller: ESP-WROOM-32 module
USB to Serial Port Chip: CP2102-GMR
Operating Voltage: DC 5V
Operating Current: 80mA (average)
Current Supply: 500mA (Minimum)
Operating Temperature Range: -40? ~ +85?
WiFi mode: Station/SoftAP/SoftAP+Station/P2P
WiFi protocol: 802.11 b/g/n/e/i (802.11n, speed up to 150 Mbps
WiFi frequency range: 2.4 GHz ~ 2.5 GHz
Bluetooth protocol: conform to Bluetooth v4.2 BR/EDR and BLE standards
Dimensions: 55mm*26mm*13mm
Weight: 9.3g
DEPARTMENT OF ECE, TKRCET 28

29. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
Fig:8
3.3 LIQUID CRYSTAL DISPLAY (LCD)
LCD (Liquid Crystal Display) screen is an electronic display module and find
a wide range of applications. A 16x2 LCD display is very basic module and is very
commonly used in various devices and circuits. These modules are preferred over
seven segments and other multi segment LEDs. The reasons being: LCDs are
economical; easily programmable; have no limitation of displaying special & even
custom characters (unlike in seven segments), animations and so on.
A 16x2 LCD means it can display 16 characters per line and there are 2 such lines. In
this LCD each character is displayed in 5x7 pixel matrix. This LCD has two registers,
namely, Command and Data.
The command register stores the command instructions given to the LCD. A
command is an instruction given to LCD to do a predefined task like initializing it,
clearing its screen, setting the cursor position, controlling display etc. The data
register stores the data to be displayed on the LCD. The data is the ASCII value of the
character to be displayed on the LCD.
Fig9: 16x2 LCD
Introduction
The most commonly used Character based LCDs are based on Hitachi's
HD44780 controller or other which are compatible with HD44580.
Pin Description
DEPARTMENT OF ECE, TKRCET 29

30. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
Most LCDs with 1 controller has 14 Pins and LCDs with 2 controller has 16
Pins (two pins are extra in both for back-light LED connections). Pin description is
shown in the table below.
Pin Configuration table for a 16X2 LCD character display:-
Pin
Number
Symbol Function
1 Vss Ground Terminal
2 Vcc Positive Supply
3 Vdd Contrast adjustment
4 RS Register Select; 0→Instruction Register, 1→Data Register
5 R/W Read/write Signal; 1→Read, 0→ Write
6 E Enable; Falling edge
7 DB0
Bi-directional data bus, data transfer is performed once, thru DB0
to DB7, in the case of interface data length is 8-bits; and twice,
through DB4 to DB7 in the case of interface data length is 4-bits.
Upper four bits first then lower four bits.
8 DB1
9 DB2
10 DB3
11 DB4
12 DB5
13 DB6
14 DB7
15 LED-(K) Back light LED cathode terminal
16 LED+(A) Back Light LED anode terminal
Table Pin Description Of LCD
Data/Signals/Execution of LCD
Coming to data, signals and execution.
LCD accepts two types of signals, one is data, and another is control. These
signals are recognized by the LCD module from status of the RS pin. Now data can be
read also from the LCD display, by pulling the R/W pin high. As soon as the E pin is
pulsed, LCD display reads data at the falling edge of the pulse and executes it, same
for the case of transmission.
DEPARTMENT OF ECE, TKRCET 30

31. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
                LCD display takes a time of 39-43µS to place a character or execute a
command. Except for clearing display and to seek cursor to home position it takes
1.53ms to 1.64ms. Any attempt to send any data before this interval may lead to
failure to read data or execution of the current data in some devices. Some devices
compensate the speed by storing the incoming data to some temporary registers.
Instruction Register (IR) and Data Register (DR)
There are two 8-bit registers in HD44780 controller Instruction and Data
register. Instruction register corresponds to the register where you send commands to
LCD e.g LCD shift command, LCD clear, LCD address etc. and Data register is used
for storing data which is to be displayed on LCD. when send the enable signal of the
LCD is asserted, the data on the pins is latched in to the data register and data is then
moved automatically to the DDRAM and hence is displayed on the LCD. Data
Register is not only used for sending data to DDRAM but also for CGRAM, the
address where you want to send the data, is decided by the instruction you send to
LCD. We will discuss more on LCD instruction set further in this tutorial.
Commands and Instruction set
Only the instruction register (IR) and the data register (DR) of the LCD can
be controlled by the MCU. Before starting the internal operation of the LCD, control
information is temporarily stored into these registers to allow interfacing with various
MCUs, which operate at different speeds, or various peripheral control devices. The
internal operation of the LCD is determined by signals sent from the MCU. These
signals, which include register selection signal (RS), read/write signal (R/W), and the
data bus (DB0 to DB7), make up the LCD instructions (Table 3). There are four
categories of instructions that: 
Designate LCD functions, such as display format, data length, etc.
Set internal RAM addresses
Perform data transfer with internal RAM
Perform miscellaneous functions
DEPARTMENT OF ECE, TKRCET 31

32. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
Table Showing various LCD Command Description
Although looking at the table you can make your own commands and test them.
Below is a brief list of useful commands which are used frequently while working on
the LCD.
DEPARTMENT OF ECE, TKRCET 32

33. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
List Of Command
No.Instruction Hex Decimal
1Function Set: 8-bit, 1 Line, 5x7 Dots0x30 48
2Function Set: 8-bit, 2 Line, 5x7 Dots0x38 56
3Function Set: 4-bit, 1 Line, 5x7 Dots0x20 32
4Function Set: 4-bit, 2 Line, 5x7 Dots0x28 40
5Entry Mode 0x06 6
6
Display off Cursor off
(clearing display without clearing DDRAM
content)
0x08 8
7Display on Cursor on 0x0E 14
8Display on Cursor off 0x0C 12
9Display on Cursor blinking 0x0F 15
10Shift entire display left 0x18 24
12Shift entire display right 0x1C 30
13Move cursor left by one character 0x10 16
14Move cursor right by one character0x14 20
15Clear Display (also clear DDRAM content)0x01 1
16
Set DDRAM address or coursor position on
display
0x80+add*128+add*
17
Set CGRAM address or set pointer to
CGRAM location
0x40+add**64+add**
Table : Frequently Used Commands And Instructions For Lcd
* DDRAM address given in LCD basics section see Figure 2,3,4
** CGRAM address from 0x00 to 0x3F, 0x00 to 0x07 for char1 and so on.
Liquid crystal displays interfacing with Controller
DEPARTMENT OF ECE, TKRCET 33

34. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
The LCD standard requires 3 control lines and 8 I/O lines for the data bus.
• 8 data pins D7:D0
Bi-directional data/command pins.
Alphanumeric characters are sent in ASCII format.
 
• RS:  Register Select
RS = 0 -> Command Register is selected
RS = 1 -> Data Register is selected
 
• R/W: Read or Write
0 -> Write,  1 -> Read
 
• E: Enable (Latch data)
Used to latch the data present on the data pins.
A high-to-low edge is needed to latch the data.
3.4 ESP32_CAMERA
ESP32-CAM is a development board module with a size of 27×40mm. It
can be integrated into a camera system with an ESP32 module and camera. ESP32-
CAM can be widely used in various IOT applications. It is suitable for home smart
devices, industrial wireless control, wireless monitoring, QR wireless identification,
wireless positioning system signals and other IoT applications. It is an ideal solution
for IoT applications.
DEPARTMENT OF ECE, TKRCET 34

35. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
Fig10.
Requirements
Serial Tool
DuPont Wires
Camera Adapter Board
Download Preparation: connect all parts as the diagram below.

1. Build ESP32 Development environment
Build the environment:
https://esp-idf.readthedocs.io/zh_CN/latest/get-started/index.html
Operations in virtual machine:
To help developers to get started easily, we integrate esp32 and esp8266 into lubuntu
32bit virtual machine. Please open the virtual machine on VMware12 environment
above. Users need to download it by themselves.
Overview
The ESP32-CAM is a small size, low power consumption camera module based on
ESP32. It comes with an OV2640 camera and provides onboard TF card slot.
The ESP32-CAM can be widely used in intelligent IoT applications such as wireless
video monitoring, WiFi image upload, QR identification, and so on.
Features
• Onboard ESP32-S module, supports WiFi + Bluetooth
• OV2640 camera with flash
DEPARTMENT OF ECE, TKRCET 35

36. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
• Onboard TF card slot, supports up to 4G TF card for data storage
• Supports WiFi video monitoring and WiFi image upload
• Supports multi sleep modes, deep sleep current as low as 6mA
• Control interface is accessible via pinheader, easy to be integrated and
embedded into user products
Specifications
WIFI module: ESP-32S
Processor: ESP32-D0WD
•Built-in Flash: 32Mbit
•RAM: Internal 512KB + External 4M PSRAM
•Antenna: Onboard PCB antenna
•WiFi protocol: IEEE 802.11 b/g/n/e/i
•Bluetooth: Bluetooth 4.2 BR/EDR and BLE
•WIFI mode: Station / SoftAP / SoftAP+Station
•Security: WPA/WPA2/WPA2-Enterprise/WPS
•Output image format: JPEG (OV2640 support only), BMP, GRAYSCALE
•Supported TF card: up to 4G
•Peripheral interface: UART/SPI/I2C/PWM
•IO port: 9
•UART baudrate rate: default 115200bps
•Power supply: 5V
Transmitting power:
11b: 17 ±2dBm(@11Mbps)
11g: 14 ±2dBm(@54Mbps)
11n: 13 ±2dBm(@HT20,MCS7)
Receiving sensitivity:
CCK,1Mbps: -90 dBm
CCK,11Mbps: -85 dBm
6Mbps(1/2 BPSK): -88 dBm
DEPARTMENT OF ECE, TKRCET 36

37. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
54Mbps(3/4 64-QAM): -70 dBm
HT20,MCS7(65Mbps, 72.2Mbps): -67 dBm
Power consumption:
Flash off: 180mA@5V
Flash on and brightness max: 310mA@5V
Deep-Sleep: as low as 6mA@5V
Modern-Sleep: as low as 20mA@5V
Light-Sleep: as low as 6.7mA@5V
• Operating temperature: -20 ~ 85
℃ ℃
• Storage environment: -40 ~ 90 , <90%RH
℃ ℃
• Dimensions: 40.5mm x 27mm x 4.5mm
Applications
•The ESP32-CAM suit for IOT applications such as:
•Smart home devices image upload
•Wireless monitoring
•Intelligent agriculture
•QR wireless identification
•facial recognition

DEPARTMENT OF ECE, TKRCET 37

38. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
Pinouts
Development Resources
Package Content
•ESP32-CAM x
•OV2640 camera x1
3.5 RELAY
INTRODUCTION
A relay is an electromechanical switch, which perform ON and OFF
operations without any human interaction. General representation of double contact
DEPARTMENT OF ECE, TKRCET 38

39. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
relay is shown in fig.  Relays are used where it is necessary to control a circuit by a
low-power signal (with complete electrical isolation between control and controlled
circuits), or where several circuits must be controlled by one signal.
Fig11: Relay
History
The first relay was invented by Joseph Henry in 1835. The name relay derives
from the French noun relays’ that indicates the horse exchange place of the postman.
Generally a relay is an electrical hardware device having an input and output gate. The
output gate consists in one or more electrical contacts that switch when the input gate
is electrically excited. It can implement a decoupled, a router or breaker for the
electrical power, a negation, and, on the base of the wiring, complicated logical
functions containing and, or, and flip-flop. In the past relays had a wide use, for
instance the telephone switching or the railway routing and crossing systems. In spite
of electronic progresses (as programmable devices), relays are still used in
applications where ruggedness, simplicity, long life and high reliability are important
factors (for instance in safety applications)
DEPARTMENT OF ECE, TKRCET 39

40. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
Working
Generally, the relay consists a inductor coil, a spring (not shown in the figure),
Swing terminal, and two high power contacts named as normally closed (NC) and
normally opened (NO). Relay uses an Electromagnet to move swing terminal between
two contacts (NO and NC). When there is no power applied to the inductor coil (Relay
is OFF), the spring holds the swing terminal is attached to NC contact.
Fig12: Representation of Relay
Whenever required power is applied to the inductor coil, the current flowing
through the coil generates a magnetic field which is helpful to move the
swing terminal and attached it to the normally open (NO) contact. Again when power
is OFF, the spring restores the swing terminal position to NC.
Advantage of relay:
A relay takes small power to turn ON, but it can control high power devices to
switch ON and OFF. Consider an example; a relay is used t control the ceiling FAN at
our home. The ceiling FAN may runs at 230V AC and draws a current maximum of
4A. Therefore the power required is 4X230 = 920 watts. Off course we can control
AC, lights, etc., depend up on the relay ratings. Relays can be used to control DC
motors in ROBOTICs.
DEPARTMENT OF ECE, TKRCET 40

41. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
DEPARTMENT OF ECE, TKRCET 41

42. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
3.6 Buzzer
A buzzer or beeper is a signaling device, usually electronic, typically used in
automobiles, house hold appliances such as a microwave oven, or game shows.
It most commonly consists of a number of switches or sensors connected to a control
unit that determines if and which button was pushed or a preset time has lapsed, and
usually illuminates a light on the appropriate button or control panel, and sounds a
warning in the form of a continuous or intermittent buzzing or beeping sound. Initially
this device was based on an electromechanical system which was identical to an
electric bell without the metal gong (which makes the ringing noise). Often these units
were anchored to a wall or ceiling and used the ceiling or wall as a sounding board.
Another implementation with some AC-connected devices was to implement a circuit
to make the AC current into a noise loud enough to drive a loudspeaker and hook this
circuit up to a cheap 8-ohm speaker. Nowadays, it is more popular to use a ceramic-
based piezoelectric sounder like a Sonalert which makes a high-pitched tone. Usually
these were hooked up to “driver” circuits which varied the pitch of the sound or
pulsed the sound on and off.
In game shows it is also known as a “lockout system,” because when one person
signals (“buzzes in”), all others are locked out from signalling. Several game shows
have large buzzer buttons which are identified as “plungers”.
Fig13: Buzzer
DEPARTMENT OF ECE, TKRCET 42

43. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
DEPARTMENT OF ECE, TKRCET 43

44. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
USES
 Annunciator panels
 Electronic metronomes
 Game shows
 Microwave ovens and other household appliances
 Sporting events such as basketball games
 Electrical alarms

3.7 INTRODUCTION ABOUT IOT
IOT stands for Internet of Things, which means accessing and controlling
daily usable equipment’s and devices using Internet.
Our IOT tutorial includes all topics of IOT such as introduction, features,
advantage and disadvantage, ecosystem, decision framework, architecture and
domains, biometric, security camera and door unlock system, devices, etc.
WHAT IS AN INTERNET OF THINGS (IOT)
Let's us look closely at our mobile device which contains GPS Tracking,
Mobile Gyroscope, Adaptive brightness, Voice detection, Face detection etc. These
components have their own individual features, but what about if these all
communicate with each other to provide a better environment? For example, the
phone brightness is adjusted based on my GPS location or my direction.
Connecting everyday things embedded with electronics, software, and
sensors to internet enabling to collect and exchange data without human interaction
called as the Internet of Things (IOT).
The term "Things" in the Internet of Things refers to anything and
everything in day to day life which is accessed or connected through the internet.
DEPARTMENT OF ECE, TKRCET 44

45. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
Fig14:Internet of Things
IoT is an advanced automation and analytics system which deals with
artificial intelligence, sensor, networking, electronic, cloud messaging etc. to deliver
complete systems for the product or services. The system created by IoT has greater
transparency, control, and performance.
As we have a platform such as a cloud that contains all the data through
which we connect all the things around us. For example, a house, where we can
connect our home appliances such as air conditioner, light, etc. through each other and
all these things are managed at the same platform. Since we have a platform, we can
connect our
car, track its
fuel meter,
speed level,
and also
track the
location of
the car.
DEPARTMENT OF ECE, TKRCET 45

46. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
Fig15: Example of IoT
If there is a common platform where all these things can connect to each
other would be great because based on my preference, I can set the room temperature.
For example, if I love the room temperature to to be set at 25 or 26 degree Celsius
when I reach back home from my office, then according to my car location, my AC
would start before 10 minutes I arrive at home. This can be done through the Internet
of Things (IOT).
HOW DOES INTERNET OF THING (IOT) WORK
The working of IOT is different for different IOT echo system
(architecture). However, the key concept of there working are similar. The entire
working process of IOT starts with the device themselves, such as smartphones,
digital watches, electronic appliances, which securely communicate with the IOT
platform. The platforms collect and analyze the data from all multiple devices and
platforms and transfer the most valuable data with applications to devices.
Fig16:IOT Architecture
DEPARTMENT OF ECE, TKRCET 46

47. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
FEATURES OF IOT
The most important features of IoT on which it works are connectivity,
analyzing, integrating, active engagement, and many more. Some of them are listed
below:
Connectivity: Connectivity refers to establish a proper connection
between all the things of IoT to IoT platform it may be server or cloud. After
connecting the IoT devices, it needs a high speed messaging between the devices and
cloud to enable reliable, secure and bi-directional communication.
Analyzing: After connecting all the relevant things, it comes to real-time
analyzing the data collected and use them to build effective business intelligence. If
we have a good insight into data gathered from all these things, then we call our
system has a smart system.
Integrating: IoT integrating the various models to improve the user
experience as well.
Artificial Intelligence: IoT makes things smart and enhances life through
the use of data. For example, if we have a coffee machine whose beans have going to
end, then the coffee machine itself order the coffee beans of your choice from the
retailer.
Sensing: The sensor devices used in IoT technologies detect and measure
any change in the environment and report on their status. IoT technology brings
passive networks to active networks. Without sensors, there could not hold an
effective or true IoT environment.
Active Engagement: IoT makes the connected technology, product, or
services to active engagement between each other.
Endpoint Management: It is important to be the endpoint management
DEPARTMENT OF ECE, TKRCET 47

48. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
of all the IoT system otherwise, it makes the complete failure of the system. For
example, if a coffee machine itself order the coffee beans when it goes to end but what
happens when it orders the beans from a retailer and we are not present at home for a
few days, it leads to the failure of the IoT system. So, there must be a need for
endpoint management.
ADVANTAGES AND DISADVANTAGES OF IoT
Any technology available today has not reached to its 100 % capability. It
always has a gap to go. So, we can say that Internet of Things has a significant
technology in a world that can help other technologies to reach its accurate and
complete 100 % capability as well.
Let's take a look over the major, advantages, and disadvantages of the Internet of
Things.
Advantages of IoT
Internet of things facilitates the several advantages in day-to-day life in the
business sector. Some of its benefits are given below:
oEfficient resource utilization: If we know the functionality and the way that how
each device work we definitely increase the efficient resource utilization as well as
monitor natural resources.
oMinimize human effort: As the devices of IoT interact and communicate with each
other and do lot of task for us, then they minimize the human effort.
oSave time: As it reduces the human effort then it definitely saves out time. Time is the
primary factor which can save through IoT platform.
oEnhance Data Collection:
DEPARTMENT OF ECE, TKRCET 48

49. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
oImprove security:
Now, if we have a system
that all these things are
interconnected then we
can make the system
more secure and efficient.
Disadvantages of IOT
As the
Internet of things facilitates
a set of benefits, it also
creates a
significant set of
challenges. Some of the IoT challenges are given below:
EMBEDDED DEVICES SYSTEM IN IOT
It is essential to know about the embedded devices while learning the IOT
or building the projects on IOT. The embedded devices are the objects that build the
unique computing system. These systems may or may not connect to the Internet.
An embedded device system generally runs as a single application.
However, these devices can connect through the internet connection, and able
communicate through other network devices.
Embedded Devices System in (IoT)
Embedded System Hardware
The embedded system can be of type microcontroller or type
microprocessor. Both of these types contain an integrated circuit (IC).
The essential component of the embedded system is a RISC family
DEPARTMENT OF ECE, TKRCET 49

50. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
microcontroller like Motorola 68HC11, PIC 16F84, Atmel 8051 and many more. The
most important factor that differentiates these microcontrollers with the
microprocessor like 8085 is their internal read and writable memory. The essential
embedded device components and system architecture are specified below.
Fig18:Basic Embedded System
Embedded System Software
The embedded system that uses the devices for the operating system is
based on the language platform, mainly where the real-time operation would be
performed. Manufacturers build embedded software in electronics, e.g., cars,
telephones, modems, appliances, etc. The embedded system software can be as
simple as lighting controls running using an 8-bit microcontroller. It can also be
complicated software for missiles, process control systems, airplanes etc.
IOT ECOSYSTEM
The IOT ecosystem is not easy to define. It is also difficult to capture
DEPARTMENT OF ECE, TKRCET 50

51. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
its proper image due to the vastness and emerging possibility and the rapidity with
which it is expanding in the entire sector. However, the IOT ecosystem is a
connection of various kind of devices that sense and analyze the data and
communicates with each other over the networks.
DEPARTMENT OF ECE, TKRCET 51

52. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
In the IOT ecosystem, the user uses smart devices such as smartphones,
tablet, sensors, etc. to send the command or request to devices for information over
the networks. The device response and performs the command to send information
back to the user through networks after analyzed.
The typical IOT ecosystem is shown in below image, where the smarter
devices send and receive data from the devices themselves in the environment that
are integrate over network and Cloud Computing.
Fig19:IOT Ecosystem
The IOT is itself an ecosystem of network devices that transfer the data.
It is also well interconnected with Big Data and Cloud Computing.
oSensing, Embedded processing, Connectivity: The IOT ecosystem senses its
surrounding like temperature, gyroscope, pressure, etc. and make the embedded
processing using devices. These devices are connected through any type of devices
such as GPS, WiFi, RFID, etc. over the networks.
oSmart devices and environment, Cloud Computing, Big Data: The data
transfer or receive through smart devices and
DEPARTMENT OF ECE, TKRCET 52

53. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
environments are communicated through Cloud Computing or others Servers and
stored as Big Data.
oTechnology, Software, Application: The IOT ecosystem uses any of different
technologies, software and application to communicate and connect with smart
devices and environment.
oUsers or groups of community: The product or services generated by the IOT
ecosystem are consumed by the users or the group of communities to serve the smart
life.
IoT DECISION FRAMEWORK
The IOT decision framework provides a structured approach to create a
powerful IOT product strategy. The IOT decision framework is all about the strategic
decision making. The IOT Decision Framework helps us to understand the areas
where we need to make decisions and ensures consistency across all of our strategic
business decision, technical and more.
The IOT decision framework is much more important as the product or
services communicates over networks goes through five different layers of complexity
of technology.
1.Device Hardware
2.Device Software
3.Communications
4.Cloud Platform
5.Cloud Application
DEPARTMENT OF ECE, TKRCET 53

54. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
Fig20:The IoT Technology stack
DEPARTMENT OF ECE, TKRCET 54

55. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
Decision Area
The IoT decision framework pays attention to six key decision areas in
any IoT product. These decision areas are:
1.User Experience (UX)
2.Data
3.Business
4.Technology
5.Security
6.Standards & Regulations
Each of these decision areas is evaluated at each of the IoT Technology
Stack. The User Experience will be evaluated at Device Hardware, Device Software
and so to provide the better user experience. Then at the next step Data Decision Area,
we have to explore data considerations for all the stages of IoT Technology Stack.
Fig21:Decision Area of the IoT Decision Framework
DEPARTMENT OF ECE, TKRCET 55

56. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
Let's see each of the Decision Area of IoT Decision Framework in detail:
1.User Experience Decision Area: This is the area where we concentrate about who are
the users, what are their requirements and how to provide a great experience at each
step of IoT stack without worrying about the technical details.
2.Data Decision Area: In this area, we make the overall data strategy such as the data
flow over the entire IoT stack to fulfill the user's requirements.
3.Business Decision Area: Based on the previous decisions area, we make the decision
how product or services will became financial potential. At each of the IoT Stack level
are monetized about the costs of providing services.
4.Technology Decision Area: In this area, we work with the technology for each layer
to facilitate the final solution.
5.Security Decision Area: After going through the implementation of technology it is
important to decide and provide the security at each stage of the IoT Stack.
6.Standards & Regulations Decision Area: At the last stage of IoT Decision Area, we
identify the standards and regulations of product or services that will affect your
product at each layer of the IoT Stack.
IoT ARCHITECTURE
There is not such a unique or standard consensus on the Internet of Things
(IoT) architecture which is universally defined. The IoT architecture differs from their
functional area and their solutions. However, the IoT architecture technology mainly
consists of four major components:
DEPARTMENT OF ECE, TKRCET 56

57. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
Components of IoT Architecture
oSensors/Devices
oGateways and Networks
oCloud/Management Service Layer
oApplication Layer
Fig22:Stages of IoT Solutions Architecture
There are several layers of IoT built upon the capability and performance
of IoT elements that provides the optimal solution to the business enterprises and end-
users. The IoT architecture is a fundamental way to design the various elements of
IoT, so that it can deliver services over the networks and serve the needs for the future.
Following are the primary stages (layers) of IoT that provides the solution for IoT
architecture.
1.Sensors/Actuators: Sensors or Actuators are the devices that are able to emit, accept
and process data over the network. These sensors or actuators may be connected either
through wired or wireless. This contains GPS, Electrochemical, Gyroscope, RFID, etc.
Most of the sensors need connectivity through sensors gateways. The connection of
sensors or actuators can be through a Local Area Network (LAN) or Personal Area
Network.
DEPARTMENT OF ECE, TKRCET 57

58. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
2.Gateways and Data Acquisition: As the large numbers of data are produced by this
sensors and actuators need the high-speed Gateways and Networks to transfer the data.
This network can be of type Local Area Network (LAN such as WiFi, Ethernet, etc.),
Wide Area Network (WAN such as GSM, 5G, etc.).
3.Edge IT: Edge in the IoT Architecture is the hardware and software gateways that
analyze and pre-process the data before transferring it to the cloud. If the data read from
the sensors and gateways are not changed from its previous reading value then it does
not transfer over the cloud, this saves the data used.
4.Data center/ Cloud: The Data Center or Cloud comes under the Management Services
which process the information through analytics, management of device and security
controls. Beside this security controls and device management the cloud transfer the data
to the end users application such as Retail, Healthcare, Emergency, Environment, and
Energy, etc.
Fig23:The 4 stage IoT Solutions Architecture
DEPARTMENT OF ECE, TKRCET 58

59. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
What are Smarts Objects in IoT
The concept of smart in IoT is used for physical objects that are active,
digital, networked, can operate to some extent autonomously, reconfigurable and has
local control of the resources. The smart objects need energy, data storage, etc.
A smart object is an object that enhances the interaction with other smart
objects as well as with people also. The world of IoT is the network of interconnected
heterogeneous objects (such as smart devices, smart objects, sensors, actuators, RFID,
embedded computers, etc.) uniquely addressable and based on standard
communication protocols.
In a day to day life, people have a lot of object with internet or wireless or
wired connection. Such as:
oSmartphone
oTablets
oTV computer
These objects can be interconnected among them and facilitate our daily
life (smart home, smart cities) no matter the situation, localization, accessibility to a
sensor, size, scenario or the risk of danger.
Fig24:Interconnected among them and facilitate our daily life
Smart objects are utilized widely to transform the physical environment
DEPARTMENT OF ECE, TKRCET 59

60. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
around us to a digital world using the Internet of things (IoT) technologies.
DEPARTMENT OF ECE, TKRCET 60

61. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
A smart object carries blocks of application logic that make sense for their
local situation and interact with human users. A smart object sense, log, and interpret
the occurrence within themselves and the environment, and intercommunicate with
each other and exchange information with people.
The work of smart object has focused on technical aspects (such as
software infrastructure, hardware platforms, etc.) and application scenarios.
Application areas range from supply-chain management and enterprise applications
(home and hospital) to healthcare and industrial workplace support. As for human
interface aspects of smart-object technologies are just beginning to receive attention
from the environment.
IoT DEVICES
Internet of Things Devices is non-standard devices that connect wirelessly
to a network with each other and able to transfer the data. IoT devices are enlarging
the internet connectivity beyond standard devices such as smartphones, laptops,
tablets, and desktops. Embedding these devices with technology enable us to
communicate and interact over the networks and they can be remotely monitored and
controlled.
DEPARTMENT OF ECE, TKRCET 61

62. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
Fig25:Internet of Things Devices
DEPARTMENT OF ECE, TKRCET 62

63. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
There are large varieties of IoT devices available based on IEEE
802.15.4 standard. These devices range from wireless motes, attachable sensor- boards
to interface-board which are useful for researchers and developers.
IoT devices include computer devices, software, wireless sensors, and
actuators. These IoT devices are connected over the internet and enabling the data
transfer among objects or people automatically without human intervention.
Some of the common and popular IoT devices are given below:
Fig26:IoT Devices and Technologies
DEPARTMENT OF ECE, TKRCET 63

64. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
CHAPTER-4
SOFTWARE SPECIFICATION
IDLE
Arduino Software
You’ll need to download the Arduino Software package for your operating system.
When you’ve downloaded and opened the application you should see something like
this:
DEPARTMENT OF ECE, TKRCET 64

65. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
This is where you type the code you want to compile and send to the Arduino board.
The Initial Setup
We need to setup the environment to Tools menu and select Board.
Then select the type of Arduino you want to program, in our case it’s the Arduino Uno.
The Code
The code you write for your Arduino are known as sketches. They are written in C++.
DEPARTMENT OF ECE, TKRCET 65

66. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
Every sketch needs two void type functions, setup() and loop(). A void type function
doesn’t return any value.
The setup() method is ran once at the just after the Arduino is powered up and the
loop() method is ran continuously afterwards. The setup() is where you want to do any
initialisation steps, and in loop() you want to run the code you want to run over and
over again.
So, your basic sketch or program should look like this:
void setup()
{
}
void loop()
{
}
Now we have the basic skeleton in place we can now do the Hello, World program of
microcontrollers, a blinking an LED.
Headers and Pins
If you notice on the top edge of the board there’s two black rectangles with several
squares in. These are called headers. Headers make it easy to connect components to
the the Arduino. Where they connect to the board is called pins. Knowing what pin
something is connected to is essential for programming an Arduino.
The pin numbers are listed next to the headers on the board in white.
The onboard LED we want to control is on pin 13.
In our code above the setup() method let’s create a variable called ledPin. In C++ we
need to state why type our variable is before hand, in this case it’s an integer, so it’s of
type int.
int ledPin = 13;
void setup()
DEPARTMENT OF ECE, TKRCET 66

67. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
{
}
void loop()
{
}
Each line is ended with a semicolon (;).
In the setup() method we want to set the ledPin to the output mode. We do this by
calling a special function called pinMode() which takes two variables, the first the pin
number, and second, whether it’s an input or output pin. Since we’re dealing with an
output we need to set it to a constant called OUTPUT. If you were working with a
sensor or input it would be INPUT.
int ledPin = 13;
void setup()
{
pinMode(ledPin, OUTPUT);
}
void loop()
{
}
In our loop we are going to first switch off the LED to make sure our program is being
transferred to the chip and overriding the default.
We do this by calling another special method called digitalWrite(). This also takes two
values, the pin number and the level, HIGH or the on state or LOW the off state.
int ledPin = 13;
void setup()
{
pinMode(ledPin, OUTPUT);
DEPARTMENT OF ECE, TKRCET 67

68. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
}
void loop()
{
digitalWrite(ledPin, LOW);
}
Next we want to compile to machine code and deploy or upload it to the Arduino.
Compiling the Code
If this is your first time you’ve ever compiled code to your Arduino before plugging it
in to the computer go to the Tools menu, then Serial Port and take note of what
appears there.
Here’s what mine looks like before plugging in the Arduino UNO:
Plug your Arduino UNO board in to the USB cable and into your computer. Now go
back to the Tools > Serial Port menu and you should see at least 1 new option. On
my Mac 2 new serial ports appear.
They tty and cu are two ways that computers can talk over a serial port. Both seem to
work with the Arduino software so I selected the tty.* one. On Windows you should
see COM followed by a number. Select the new one that appears.
Once you have selected your serial or COM port you can then press the button with
the arrow pointing to the right.
DEPARTMENT OF ECE, TKRCET 68

69. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
Once that happens you should see the TX and RX LEDs below the L LED flash. This
is the communication going on between the computer and the Arduino. The L may
flicker too. Once this dance is complete your program should be running. And your
LED should be off.
Now let’s try and switch it on using the HIGH constant.
int ledPin = 13;
void setup()
{
pinMode(ledPin, OUTPUT);
}
DEPARTMENT OF ECE, TKRCET 69

70. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
void loop()
{
digitalWrite(ledPin, HIGH);
}
Press Upload again and you should see your LED is now on!
Let’s make this a little more interesting now. We’re going to use another method
called delay() which takes an integer of a time interval in milliseconds, meaning the
integer of 1000 is 1 second.
So after where we switch the LED on let’s add delay(2000) which is two seconds,
then digitalWrite(ledPin, LOW) to switch it off and delay(2000) again.
int ledPin = 13;
void setup()
{
pinMode(ledPin, OUTPUT);
}
void loop()
{
digitalWrite(ledPin, HIGH);
delay(2000);
digitalWrite(ledPin, LOW);
delay(2000);
}
DEPARTMENT OF ECE, TKRCET 70

71. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
Arduino Software
The ESP32 is a low-cost, low-power system on a chip (SoC) series created by
Espressif Systems. It is known for its integrated Wi-Fi and dual-mode Bluetooth
capabilities, making it an ideal choice for Internet of Things (IoT) projects and other
connected applications. ESP32 is widely used in the maker community for building
digital devices and interactive objects.
The ESP32 hardware and software design is open-source, with hardware
specifications available under the Creative Commons Attribution-Share Alike license.
The software is licensed under the MIT License, allowing anyone to manufacture
ESP32 boards and distribute software.
ESP32 boards feature a variety of digital and analog input/output (I/O) pins that can
interface with expansion boards, sensors, and other circuits. These boards also support
serial communications interfaces, including Universal Serial Bus (USB) for
programming and debugging purposes. The microcontrollers on ESP32 boards can be
programmed using the C and C++ programming languages (Embedded C), and there
are additional support and libraries for other languages like MicroPython and
JavaScript.
Programming for the ESP32 is commonly done using the Arduino IDE, which
provides a familiar and user-friendly environment for those experienced with Arduino
boards. Espressif also offers the ESP-IDF (Espressif IoT Development Framework), a
powerful and feature-rich development framework for advanced users. This
framework allows the use of traditional compiler toolchains and includes a command
line tool for more complex development workflows.
The ESP32 project started as a solution to meet the growing demand for connected
devices and IoT applications, providing a versatile and affordable platform for both
beginners and professionals. Common projects for hobbyists using ESP32 include
smart home devices, wearable electronics, and networked sensors.
DEPARTMENT OF ECE, TKRCET 71

72. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
To install the ESP32 board in your Arduino IDE, follow these next instructions:
In your Arduino IDE, go to File> Preferences
Enter the following into the “Additional Board Manager URLs” field:
DEPARTMENT OF ECE, TKRCET 72

73. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
Open the Boards Manager. Go to Tools > Board > Boards Manager
DEPARTMENT OF ECE, TKRCET 73

74. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING

Testing the Installation
The Code
The code you write for your Arduino are known as sketches. They are written in C++.
Every sketch needs two void type functions, setup() and loop(). A void type function
doesn’t return any value.
The setup() method is ran once at the just after the Arduino is powered up and the
loop() method is ran continuously afterwards. The setup() is where you want to do any
initialisation steps, and in loop() you want to run the code you want to run over and
over again.
DEPARTMENT OF ECE, TKRCET 74

75. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
So, your basic sketch or program should look like this:
void setup()
{
}
void loop()
{
}
Now we have the basic skeleton in place we can now do the Hello, World program of
microcontrollers, a blinking an LED.
DEPARTMENT OF ECE, TKRCET 75

76. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
Headers and Pins
If you notice on the top edge of the board there’s two black rectangles with several
squares in. These are called headers. Headers make it easy to connect components to
the the controller.
Where they connect to the board is called pins. Knowing what pin something is
connected to is essential for programming an Arduino.
The pin numbers are listed next to the headers on the board in white.
The onboard LED we want to control is on pin 2.
In our code above the setup() method let’s create a variable called ledPin. In C++ we
need to state why type our variable is before hand, in this case it’s an integer, so it’s of
type int.
int ledPin = 2;
void setup()
{
}
void loop()
{
DEPARTMENT OF ECE, TKRCET 76

77. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
}
Each line is ended with a semicolon (;).
In the setup() method we want to set the ledPin to the output mode. We do this by
calling a special function called pinMode() which takes two variables, the first the pin
number, and second, whether it’s an input or output pin. Since we’re dealing with an
output we need to set it to a constant called OUTPUT. If you were working with a
sensor or input it would be INPUT.
int ledPin = 2;
void setup()
{
pinMode(ledPin, OUTPUT);
}
void loop()
{
}
In our loop we are going to first switch off the LED to make sure our program is being
transferred to the chip and overriding the default.
We do this by calling another special method called digitalWrite(). This also takes two
values, the pin number and the level, HIGH or the on state or LOW the off state.
int ledPin = 2;
void setup()
{
pinMode(ledPin, OUTPUT);
}
void loop()
DEPARTMENT OF ECE, TKRCET 77

78. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
{
digitalWrite(ledPin, LOW);
}
Next we want to compile to machine code and deploy or upload it to the Arduino.
Compiling the Code
If this is your first time you’ve ever compiled code to your ESP32 before plugging it
in to the computer go to the Tools menu, then Serial Port and take note of what
appears there.
Plug your ESP32 board in to the USB cable and into your computer. Now go back to
the Tools > Serial Port menu and you should see at least 1 new option. On my Mac 2
new serial ports appear.
They tty and cu are two ways that computers can talk over a serial port. Both seem to
work with the Arduino software so I selected the tty.* one. On Windows you should
see COM followed by a number. Select the new one that appears.
Once you have selected your serial or COM port you can then press the button with
the arrow pointing to the right.
Once that happens you should see the TX and RX LEDs below the L LED flash. This
is the communication going on between the computer and the Arduino. The L may
flicker too. Once this dance is complete your program should be running. And your
LED should be off.
Now let’s try and switch it on using the HIGH constant.
int ledPin = 13;
void setup()
{
DEPARTMENT OF ECE, TKRCET 78

79. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
pinMode(ledPin, OUTPUT);
}
void loop()
{
digitalWrite(ledPin, HIGH);
}
Press Upload again and you should see your LED is now on!
DEPARTMENT OF ECE, TKRCET 79

80. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
DEPARTMENT OF ECE, TKRCET 80

81. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
CHAPTER-5
ALGORITHM & FLOWCHART
5.1. ALGORITHM:
Step 1 - Initialization Fingerprint, ESP32 CAM, LCD module
Step 2 – Waiting for the valid finger and trigger the ESP32-cam for helmet
Step 3 – If the helmet detected enable to start the vehicle
Step 4 – If the start is triggered turn on the motor
Step 5 – If the button pressed long time trigger buzzer
Step6 – Stop
DEPARTMENT OF ECE, TKRCET 81

82. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
5.2. FLOWCHART:

DEPARTMENT OF ECE, TKRCET 82
START
Init controller,
LCD, finger
print sensor
If finger
sensor
triggered
Trigger the ESP32 cam
Wait for the sensor
If esp32 cam
is triggered
If helmet detected, enable the
start button for the load
Wait for the start button to
be pressed
STOP
NO YES
NO YES
If button
pressed
Turn on/off the motor
Wait for the button to be
pressed or Trigger buzzer
NO
YES

83. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
CHAPTER-6
RESULT & ANALYSIS
We have finally reached our goal. We have to implement the hardware as all
equipment is at our hands. So, in a nutshell the whole procedure is as follows
6.1. PROCEDURE
1. Initialization Finger print sensor, Esp32 cam and start buttons
2. Checking for input signal from sensors or the buttons and cam
3. Trigger the motor and the buzzer if required for control the load
4. Stop
DEPARTMENT OF ECE, TKRCET 83

84. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
6.2. Result
DEPARTMENT OF ECE, TKRCET 84

85. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
6.3. Advantages and applications:
Advantages:
1.Rental cars
2.Travellers vehicles
6.4. Limitations of this project
●Works with the configured person only
DEPARTMENT OF ECE, TKRCET 85

86. HELMET DETECTION AND BIOMETRIC BASED VEHICLE SECURITY USING MACHINE
LEARNING
CHAPTER-7
CONCLUSION
The project “HELMET DETECTION AND BIOMETRIC
BASED VEHICLE SECURITY USING MACHINE
LEARNING” has been successfully designed and tested. It has been developed
by integrating features of all the hardware components used. Presence of every
module has been reasoned out and placed carefully thus contributing to the best
working of the unit. Secondly using highly advanced IC’s and with the help of
growing technology the project has been successfully implemented.

FUTURE SCOPE
●Scope for heavy vehicles
●Can be implemented in Security vehicles
DEPARTMENT OF ECE, TKRCET 86