Foreground target detection algorithm (FTDA) is a fundamental preprocessing step in computer vision and video processing. A\nuniversal background subtraction algorithm for video sequences (ViBe) is a fast, simple, efficient and with optimal sample\nattenuation FTDA based on background modeling. However, the traditional ViBe has three limitations: (1) the noise problem\nunder dynamic background; (2) the ghost problem; and (3) the target adhesion problem. In order to solve the three problems\nabove, ant colony clustering is introduced and Ant_ViBe is proposed in this paper to improve the background modeling\nmechanism of the traditional ViBe, from the aspects of initial sample modeling, pheromone and ant colony update mechanism,\nand foreground segmentation criterion. Experimental results show that the Ant_ViBe greatly improved the noise resistance under\ndynamic background, eased the ghost and targets adhesion problem, and surpassed the typical algorithms and their fusion\nalgorithms in most evaluation indexes.
Loading....