[1] Lu Hong, Fei Shumin, Zheng Jianyong, et al. Multi-object tracking based on behaviour and partial observation [J]. Journal of Southeast University (English Edition), 2008, 24 (4): 468-472. [doi:10.3969/j.issn.1003-7985.2008.04.014]

Copy

Multi-object tracking based on behaviour and partial observation()

Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:

24

Issue:

2008 4

Page:

468-472

Research Field:

Computer Science and Engineering

Publishing date:

2008-12-30

Info

Title:

Multi-object tracking based on behaviour and partial observation

Author(s):

Lu Hong¹;  2;  Fei Shumin¹;  Zheng Jianyong³;  Zhang Tao¹

¹ School of Automation, Southeast University, Nanjing 210096, China
²School of Automation, Nanjing Institute of Technology, Nanjing 211167, China
³School of Electrical Engineering, Southeast University, Nanjing 210096, China

Keywords:

multi-object tracking;  projection ratio;  occlusion ratio;  behaviour;  partial observation;  Kalman filter

PACS:

TP391.41

DOI:

10.3969/j.issn.1003-7985.2008.04.014

Abstract:

To cope with multi-object tracking under real-world complex situations, a new video-based method is proposed.In the detecting step, the moving objects are segmented with the third level DWT(discrete wavelet transform)and background difference.In the tracking step, the Kalman filter and scale parameter are used first to estimate the object position and bounding box.Then, the center-association-based projection ratio and region-association-based occlusion ratio are defined and combined to judge object behaviours.Finally, the tracking scheme and Kalman parameters are adaptively adjusted according to object behaviour.Under occlusion, partial observability is utilized to obtain the object measurements and optimum box dimensions.This method is robust in tracking mobile objects under such situations as occlusion, new appearing and stablization, etc.Experimental results show that the proposed method is efficient.

References:

[1] Cheng F H, Chen Y L.Real time multiple objects tracking and identification based on discretewavelet transform [J].Pattern Recognition, 2006, 39(6):1126-1139.
[2] Jang D S, Choi H I.Active models for tracking moving objects [J].Pattern Recognition, 2000, 33(7):1135-1146.
[3] Letang J M, Rebuffel V, Bouthemy P.Motion detection robust to perturbations:a statistical regularization and temporal integration framework[C]//Proceedings of the International Conference on Computer Vision.Berlin, Germany, 1993:21-30.
[4] Weng S K, Kuo C M, Tu S K.Video object tracking using adaptive Kalman filter [J].Journal of Visual Communication and Image Representation, 2006, 17(6):1190-1208.
[5] Xu M, Ellis T.Tracking occluded objects using partial observation [J].Acta Automatica Sinica, 2003, 29(3):370-380.
[6] Ge Jiaqi, Li Bo, Chen Qimei.A region-based vehicle tracking algorithm under occlusion [J].Journal of Nanjing University:Natural Sciences, 2007, 43(1):66-72.(in Chinese)
[7] Chang Faliang, Liu Xue, Wang Huajie.Target tracking algorithm based on meanshift and Kalman filter [J].Computer Engineering and Applications, 2007, 43(12):50-52.(in Chinese)
[8] Sun Zhongsen, Sun Junxi, Song Jianzhong, et.al.Anti-occlusion arithmetic for moving object tracking [J].Optics and Precision Engineering, 2007, 15(2):267-271.(in Chinese)
[9] Chang Faliang, Ma Li, Qiao Yizheng.Human oriented multi-target tracking algorithm in video sequence [J].Control and Decision, 2007, 22(4):418-422.(in Chinese)
[10] Lu Hong, Fei Shumin, Zheng Jianyong, et al.An occlusion tolerant method for multi-object tracking [C]//Proceedings of the 7th World Congress on Intelligent Control and Automation.Chongqing, China, 2008:5105-5110.

Memo

Memo:

Biographies: Lu Hong(1973—), female, graduate;Fei Shumin(corresponding author), male, doctor, professor, smfei@seu.edu.cn.
Foundation item: The National Natural Science Foundation of China(No.60574006, 60804017).
Citation: Lu Hong, Fei Shumin, Zheng Jianyong, et al.Multi-object tracking based on behaviour and partial observation[J].Journal of Southeast University(English Edition), 2008, 24(4):468-472.

Common functions