jskye
commented
8 years ago if the image is a color image, color can be used to determine the sky. if not, then texture density based method might work. or perhaps other features like sun,clouds, trees can be used to signal that the sky is present in the scene. of course there is a tradeoff of computation, workers here, but depends on requirements of application, how precise car detector needs to be.
if we can see the sky, or some significant portion of it, then we shouldn't need to look for cars in say the top third of the image. of course, if we have a very good trained classifier wed assume this shouldnt be the case. but cascade classifiers are very sensitive to the training data so having post-hypothesis methods to screen out bad hypotheses is still often necessary.