Video Tracking Based on Election Campaign Algorithm
Qinghua Xie, Xiangwei Zhang, Wenge Lv, Siyuan Cheng · Advances in intelligent systems research/Advances in Intelligent Systems Research · 2016
Grey scale feature is not sensitive to the deformation and rotation in the image, and has good stability to detect similarity of image sequence.Using grey scale feature as object function, Election Campaign Algorithm considers the tracking windows as the effect ranges and focus center, the problem of video tracking converges to the optimal evaluation function to the central point.The focus center gets the feature different to the background and can be tracking the movement of the target.Random points around the focus center are generated to test the range of tracking window and determine the start point of focus center in the next image of the sequence.The simulation results show that the presented algorithm of video tracking is able to apply in real time, and the tracking performance is superior to conventional algorithms.