Fast Background Subtraction Based on GPU
In this paper, a fast background subtraction algorithm using codebook model is presented to extract moving objects from surveillance videos. The time for stopped objects being absorbed into the background can be controlled to deal with different applications and have nothing to do with the complexity of the scene. We implement the algorithm on GPU using CUDA, and optimize the implementation using pinned memory and asynchronous execution techniques. Experimental results are provided to demonstrate the accuracy, effectiveness, and efficiency of the proposed algorithm.
J. P. Han et al., "Fast Background Subtraction Based on GPU", Advanced Materials Research, Vols. 341-342, pp. 737-742, 2012