GPU accelerated foreground segmentation using CodeBook model and shadow removal using CUDA

摘要

Background Subtraction is the major important step in many image processing applications which can be applied in much of video surveillances. The major result of this method is accuracy as well as processing time. So we mainly focused on these two challenges. We parallelized the Two Layered CodeBook Model on Graphical Processing Unit (GPU) for increasing the processing speed and the accuracy of the object is increased by using Shadow Removal technique in this proposed method. This algorithm uses CUDA programming language on GPU for making the computation faster when compared with the existing Two Layered CodeBook Model on CPU.