Browse > Article
http://dx.doi.org/10.5302/J.ICROS.2010.16.10.982

A Study of Image Target Detection and Tracking for Robust Tracking in an Occluded Environment  

Kim, Yong (Hanyang University)
Song, Taek-Lyul (Hanyang University)
Publication Information
Journal of Institute of Control, Robotics and Systems / v.16, no.10, 2010 , pp. 982-990 More about this Journal
Abstract
In a target tracking system using image information from a CCD (Charged Couple Device) or an IIR (Imaging Infra-red) sensor, occluded targets can result in track losses. If the target is occlued by background objects such as buildings or trees, probability of track existence will be reduced sharply and track will be terminated due to track maintenance algorithms. This paper proposes data association algorithm based on target existence for the robust tracking performance. we suggest the HPDA (Highest Probability Data Association) algorithm based on target existence and the tracking performance is compared with the established method based on target perceivability. Image tracking simulation that utilizes virtual 3D images and real IR images is employed to evaluate the robustness of the proposed tracking algorithm.
Keywords
target perceivability; target existence; HPDAF (Highest Probability Data Association Filter); EB-HPDA (HPDA based target existence); IIR (Imaging Infra-red) seeker; data association;
Citations & Related Records
연도 인용수 순위
  • Reference
1 D. Musicki, R. Evans, and S. Stankovic, "Integrated probabilistic data association," IEEE Trnasactions on Automatic Control, vol. 39, no. 6, June 1994.
2 Y. Bar-Shalom, Tracking and data association, Academic Press Professional, Inc., 1987.
3 X. R. Li and Y. Bar-Shalmo, "Theoritical analysis and performance prediction of tracking in clutter with strongest neighbor filters," Proc. of the 34th conference on Decision and Control, New Orleans, pp. 2758-2763, Dec. 1995.
4 T. L. Song and D. G. Lee, "A probabilistic nearest neighbor filter algorithm for m validated measurements," IEEE Trans. Signal Processing, vol. 54, no. 7, July 2006.
5 T. L. Song, Y. T. Lim, and D. G. Lee, "A probabilistic strongest neighbor filter algorithm for m validated measurements," IEEE Trans. on AES, in review process.
6 Thiagalingam Kirubarajan and Yaakov Bar-Shalom, "Probabilistic data association techniques for target tracking in clutter," Proc. of the IEEE, vol. 32, no. 3, pp. 536-557 March 2004.
7 T. L. Song and D. S. Kim, "Highest probability data association for active sonar tracking," Information Fusion, 2006 9th International Conf., pp. 1-8, July 2006.
8 D. Musicki, R. Evans, and S. Stankovic, "IPDA (Integrated Probabilistic Data Association)," Proc. of the 31st Conference on Decision and Control, Tucson, Artzone, Dec. 1992.
9 D. Musicki and R. Evans, "Integrated probabilistic data association in clutter with finite resolution sensor," Proc. of the 32nd Conference on Decision and Control, San Astonlo, Texas, Dec. 1993.