Color Composites and Image Classification.pptx

ggghrfh

1. Color Composites and Image Classification  

2. A. Natural or True Color Composites A natural or true color composite is an image displaying a combination of visible red, green and blue bands to the corresponding red, green and blue channels on the computer. The resulting composite resembles what would be observed naturally by the human eye, vegetation appears green, water dark is blue to black and bare ground and impervious surfaces appear light grey and brown. Many people prefer true color composites, as colors appear natural to our eyes, but often subtle differences in features are difficult to recognize. Natural color images can be low in contrast and somewhat hazy due the scattering of blue light by the atmosphere.

3. B. False Color Composites False color images are a representation of a multi-spectral image produced using bands other than visible red, green and blue as the red, green and blue components of an image display. False color composites allow us to visualize wavelengths that the human eye can not see (i.e. near-infrared). Using bands such as near infra-red increases the spectral separation and often increases the interpretability of the data. There are many different false colored composites which can highlight many different features.

4. C. Standard False Colour Composite A standard False Colour Composite (FCC) is an image created by combining data from multiple spectral bands of a satellite or other image sensor. Unlike natural color composites, which use the red, green and blue (RGB) bands, FCCs use different combinations of bands to create a composite image that emphasizes features of interest. By assigning different colors to different wavelengths of light, FCCs can reveal features that may be invisible or difficult to see in a natural color image. Here's a breakdown of a standard FCC: Near Infrared (NIR) assigned as Red:  Healthy vegetation reflects strongly in the NIR band, so it appears bright red in an FCC. This makes it easy to distinguish healthy vegetation from other features in the image. Red assigned as Green:  In a standard FCC, the red band is often assigned to the green channel. This can help to highlight features that are red in color , such as iron oxides or blood. Green assigned as Blue:  The green band is frequently assigned to the blue channel in a standard FCC. This can help to distinguish between different types of vegetation, as some plants reflect more green light than others.

5. S. No Earth Surface Features. Color (In Standard FCC) 1 Healthy Vegetation and Cultivated Areas     Evergreen Red to magenta   Deciduous Brown to red   Scrubs Light brown with red patches   Cropped land Pink to Bright red   Fallow land Light blue to white   Wetland vegetation Blue to grey 2 Waterbody     Clear water Dark blue to black   Turbid waterbody Light blue 3 Built – up area     . High density Dark blue to bluish green   Low density Light blue 4 Waste lands/Rock outcrops     Rock outcrops Light brown   Sandy deserts/River sand/ Light blue to white   Salt affected Deep ravines Dark green   Shallow ravines Light green   Water logged /Wet lands Motel led black

6. Image Classification Techniques in Remote Sensing A. Supervised Classification: It is the process of identification of classes within a remote sensing data with inputs from and as directed by the user in the form of training data. Supervised image classification is a powerful technique used to categorize pixels in a satellite image into specific classes, such as water, forest, urban areas, or different crop types. It works by leveraging human knowledge to "train" the computer to recognize these classes. B. Unsupervised Classification: It is the process of automatic identification of natural groups or structures within a remote sensing data. Unsupervised image classification takes a different approach to categorizing pixels in satellite images. Instead of relying on pre-defined classes and labelled training data, it allows the computer to discover inherent groupings (clusters) within the data itself.

7. Image Classification Techniques in Remote A. Supervised Classification: It is the process of identification of classes within a remote sensing data with inputs from and as directed by the user in the form of training data. Supervised image classification is a powerful technique used to categorize pixels in a satellite image into specific classes, such as water, forest, urban areas, or different crop types. It works by leveraging human knowledge to "train" the computer to recognize these classes. B. Unsupervised Classification: It is the process of automatic identification of natural groups or structures within a remote sensing data. Unsupervised image classification takes a different approach to categorizing pixels in satellite images. Instead of relying on pre-defined classes and labelled training data, it allows the computer to discover inherent groupings (clusters) within the data itself.