A robust framework for object tracking based on corrected background-weighted histogram mean shift and unscented Kalman filter
Eman Fathi Ahmed, Ali Ahmad, Mohie Mohamed Hadhoud · 2014
Tracking objects under the presence of noise, objects with partial and full occlusions in complex environments is a challenge for classical mean shift and unscented Kalman filter algorithms. In this paper we propose a new algorithm combining mean shift algorithm with corrected background-weighted histogram (CBWH) and unscented Kalman filter (UKF). The CBWH scheme can effectively reduce background's interference in target localization. So CBWH can guarantee accurate localization of the target. Then UKF algorithm has the ability to estimate the coming state. So the proposed algorithm is used to enhance the solution of object tracking problems. The experimental results show that the proposed method is superior to the traditional tracking methods.