Comprehensive Learning Particle Swarm Optimizer for Intelligent Visual Tracking

摘要

Visual object tracking remains an accessible and demanding challenge in computer vision, despite recent breakthroughs in the area. Modern applications need trackers, even on embedded systems, to be accurate and very fast. This paper proposed a robust solution based on object tracking derived from the Bhattacharyya coefficient as a measure of similarity dependent on Comprehensive learning particle swarm optimization (CLPSO). To reveal the performance of proposed algorithm’s capacity, existing Mean-Shift based object tracking system is compared with the proposed system.