In view of security issues, this paper studies how to track suspicious human at the metro entrance and exit accurately and quickly. A novel tracking method combining Kalman filter and SURF algorithm embedded in CAMShift target tracking algorithm was proposed. Firstly, the algorithm chooses target template for tracking by hand, then the Bhattacharyya coefficient is calculated by comparing the comprehensive histogram of chromaticity and gradient direction between the candidate target and the template target. If the Bhattacharyya coefficient between the template with the candidate target area is greater than the given threshold for detection, the tracking process will be failed. At this time, the SURF algorithm is used for feature matching on tracking result window in current search window and previous frame, and the size and position of the suspicious person are recalculated. At the same time, in order to avoid the failure of suspicious personnel tracking caused by occlusion, Kalman filter is used to predict and update the moving window so as to determine the central position of the search window in the next frame. Experiments show that the proposed algorithm can stably track the suspicious target personnel even when adverse effects such as color disturbance, partial occlusion, and complex image background occur.
[1]
李英 Li Ying,et al.
Moving Target Fast Tracking Using SURF and Cluster Analysis Method
,
2011
.
[2]
Nancy G. La Vigne.
SAFE TRANSPORT: SECURITY BY DESIGN ON THE WASHINGTON METRO
,
1996
.
[3]
Chih-Hsien Hsia,et al.
Directional Prediction CamShift algorithm based on Adaptive Search Pattern for moving object tracking
,
2013,
Journal of Real-Time Image Processing.
[4]
Chunbo Xiu,et al.
Improved Camshift tracking method based on the edge suppression
,
2017,
2017 29th Chinese Control And Decision Conference (CCDC).
[5]
Kai-Yew Lum,et al.
Automated image tracking based on the CAMSHIFT algorithm with adaboost and target trajectory and size estimation
,
2014,
11th IEEE International Conference on Control & Automation (ICCA).
[6]
Yueming Lu,et al.
Combining SURF with MSER for image matching
,
2013,
2013 IEEE International Conference on Granular Computing (GrC).
[7]
Juhng-Perng Su,et al.
Moving Target Tracking Based on CamShift Approach and Kalman Filter
,
2015
.