Hi all, I'm working on a "killing time" project to detect human using background substraction + classifier, and now the project has been completed. But my application shows some false objects detection are caused by the tree branch shaking, moving bushes, etc.. And now I wanna reduce them using this algorithms:
Utilize the color histogram of object to check whether all the pixels of the object are of one similar color. Because the false object is a part of tree or other background, their pixels have the similar color (Green). If the object is false, the pixel values should be centered by one pixel with maximum probability in color histogram.
Use the technique of the region growing to check whether the object is one part of background. Use the average color as a seed to grow the pixels on vertical direction to form a larger region. If the number of pixels covered by extended region is more than the number of original object, then this object is false.
But I'm still confuse how to convert the algorithms into OpenCV + C++. Are there simple way to do region growing? or any library can help me on region growing?
I'll apreciate any help here. Thanks. :)