A survey of the existing shadow detection techniques

Abstract

Shadows are formed when light from the source is obstructed by an object. Shadows hide the information of the underlying objects which will lead to wrong interpretations during image processing. Hence shadow detection has become a vital pre-processing step in digital image processing as most of the images acquired are contaminated with shadows. The shadows are found more in urban images where the surface elevation changes dramatically thus increasing the complexity of the scenes. In this paper we discuss the various techniques that have been used for shadow detection for both still images and moving objects.