3D Building models were generated by using Google Sketchup Pro and Google Earth.
Then shadow casted 2D orthographic raster models were exported as TIFF or JPEG format.
For further analysis with respect to shadow casted roof top areas, exported 2D raster models have to be classified or segmented. This process wanted to be executed for extraction of shadow polygons which casted over building roof tops and roof-tops open to sun light as well.
- To achieving this objective unsupervised classification was done. But unfortunately shadows which casted over rooftops and ground area were being merged into one single class. Rooftop area shadow could not be extracted separately.
- Supervised classification could not be done, because of unable to get training samples. (RGB values of training samples were same for shadow areas and open areas)
- Therefore I figured out Matlab Application for image feature extraction.
- I used some sort of extraction techniques such as Color threshold, RGB value extraction
- But unfortunately they all were with lack of satisfaction.
- Even though using Matlab with different approach may be result reliable output for this purpose. But up to now, I could not find out appropriate codes.