A multiple moving targets edge detection algorithm based on sparse matrix block operation

Abstract

A multiple moving targets edge detection algorithm based on sparse matrix block operation is proposed in this paper. The algorithm uses background subtraction algorithm to obtain the foreground image contains multiple moving targets. After getting the ideal foreground image, active contour model is used for edge detection. Here, we improved the active contour model by introducing the sparse matrix block operation. Through the quad-tree decomposition of the foreground image, the proposed algorithm uses the sparse matrix block operation to calculate the corresponding regional seed position of multiple moving targets. Finally, it executes the active contour model in parallel to complete the edge detection. Experimental results show that edge detection of the algorithm similar to the human visual judgment, and the introduction of sparse matrix block operation to calculate regional seed for active contour model reduces the time, improves the convergence of the profile curve and edge detection accuracy.