A Pedestrian Tracking Algorithm Based on Camshift and Kalman Filtering

Yan Zhang, Lijie Li

Abstract: The traditional MeanShift algorithm, for video target tracking, is prone to color interference, loss of target occlusion, and the speed and degree of convergence of the algorithm. The Camshift algorithm is used to improve the Camshift algorithm by Kalman filter, which can predict the position of the target in the next frame image and determine the Camshift algorithm in the pedestrian tracking search area to overcome the target block and noise interference. Experiments show that the method has well pedestrian tracking effect and application prospect.

Keywords: Camshift, Kalman filter, pedestrian tracking