Research on Embedded System with Implementation of a Moving Object Tracking Algorithm Based on Improved Meanshift on DM6437
Yan Fei Liu, Qi Li, Hao Fang, Hua Xu · Advanced materials research · 2014
To improve the real-time performance of the meanshift algorithm in the embedded system, an improved meanshift algorithm for tracking moving target is proposed in this paper. In order to reduce the influence of background pixel in a target model, the target model is build by using the target model of continuous frames; to reduce the times of iteration, a kalman filter is used to predict the position of moving object in the current frame; to improve the accuracy of the target model, it is updated in real-time. At last, the improved algorithm is realized on a DM6437 platform and the experimental results show that the improved algorithm can track moving objects effectively.