Abstract

Features of images are often used for cast shadow removal. A technique based on using only a single feature cannot universally distinguish an object pixel from a shadow pixel of a video frame. On the other hand, the use of multiple features increases the computational cost of a shadow removal technique considerably. In this paper, an efficient yet simple method for cast shadow removal from video sequences with static background using multiple features isdeveloped. The basic idea of the proposed technique is that a simultaneous use of a small number of multiple features, if chosen judiciously, can reduce the similarity between object and shadow pixels without an excessive increase in the computational cost. Using the features of gray levels, color composition and gradients of foreground and background pixels, a method is devised to create a complete object mask. First, based on each of the three features, three individual shadow masks are constructed, from which three corresponding object masks are obtained through a simple subtraction operation. The object masks are then merged together to generate a single object mask. Each of the three shadow masks is created so as to cover as many shadow pixels as possible, even if it results in falsely including in them some of the object pixels. As a result, the subsequent object masks may lose some of these pixels. However, the object pixels missed by one of the object masks should be able to be recovered by at least one of the other two, since they are generated based on features complementary to the one used to construct the first one. The final object mask obtained through a logical OR operation of the three individual masks can, therefore, be expected to include most of the object pixels. The proposed method is applied to a number of video sequences. The simulation results demonstrate that the proposed method provides a mechanism for shadow removal that is superior to some of the recently proposed techniques without imparting an excessive computational cost.