Fundamental of Remote Sensing Chapter_3.ppt material for Geographers.

Fundamental of Remote Sensing Chapter_4.ppt material for Geographers.

1. By: Andualem F.(MA)
University of Kebridehar
Geography Department
Fundamental of Remote Sensing
GeES 3032

2. Unit four
4.1 Image enhancement and visualization

•Image enhancements: are used to make it easier for visual
interpretation and understanding of imagery.
•Image enhancement deals with the procedure of making raw
images better interpretable/suitable for a particular application.

3. Remote Sensing Data Pre-processing
(a) Atmospheric correction
(b) Radiometric correction
(c) Geometric correction

4. Cont’
Methods of Geometric correction
1.Using satellite header file (satellite onboard GPS)
2.Image to image registration
3.Image to map registration
4.Manually entered GCPs (Ground Control Points)

5. 4.2 Image classification
•Image classification refers to the computer-assisted
interpretation of remotely sensed images.
•Image classification is based on the different spectral
characteristics of different materials on the Earth’s surface.

6. Cont’

7. Principles of image classification
A digital image is a 2D-array of elements. In each element the
energy reflected or emitted from the corresponding area on the
Earth’s surface is stored.
The spatial arrangement of the measurements defines the image
or image space.

E.g. image spaces

8. Feature space: In one pixel, the value in (for example) two bands can be
regarded as components of a two-dimensional vector, the feature vector.
The feature vector can be plotted in a two-dimensional graph.
Similarly, this approach can be visualized for a three band situation in a
three-dimensional graph.

9. Image classification process
1. Selection and preparation of image data: select the most appropriate sensor, date
(s) and wavelength bands
2. Definition of clusters in the feature space:
- Supervised classification: operator defined the clusters during the training process
- Unsupervised classification: a cluster algorithm automatically finds and defines a
number of clusters in the feature space
3. Selection of classification algorithms: the operator needs to decide on how the
pixels are assigned to the classes
4. Running the actual classification: based on its DN-values, each individual pixel
in the image is assigned to one of the predefined classes
5. Validation of the result: Once the classified image has been produced its quality is
assessed by comparing it to reference data (ground truth). This requires selection of a
sampling technique, generation of an error matrix, and the calculation of error
parameters

10. The process of image classification typically involves five steps.

11. •Common classification procedures can be broken down into two broad
subdivisions based on the method used: supervised classification and
unsupervised classification.
1. Supervised classification: is the most used technique for the quantitative
analysis of RS image data depending on their reflectance properties. It uses
the spectral signature obtained from training samples to classify an image.
•Thus, the analyst is“ supervising" the categorization of a set of specific classes.

12. Supervised classification

13. 2. Unsupervised Classification: Unsupervised classification in essence
reverses the supervised classification process.
•This is a computerized method without direction from the analyst in which
pixels with similar digital numbers are grouped together into spectral classes
using statistical procedures such as nearest neighbour and cluster analysis.
•unsupervised classification is not completely without human intervention.
Because need the analyst to specifies how many groups or clusters are to be
looked for in the data.

14. Cont’
•Unsupervised classification is used for statistical clustering methods to
conglomerate pixels into groups according to the amount of similarity for
reflectance value in each spectral band.