Online Pedestrian Tracking with Kalman Filter and Random Ferns

Abstract:

Object tracking is one of the most important components in numerous applications of computer vision. Much progress has been made in recent years. The Tracking-Learning-Detection (TLD) algorithm achieves excellent performance on a set of challenging video sequences. However, classical TLD algorithm fails to track non-rigid pedestrian as complicated appearance, varying viewpoints, shape changes and occlusions. In this paper, we follow the TLD and propose a robust KMD framework which consists of the Kalman filter tracker, random ferns pedestrian detector and the pedestrian model. During the tracking process the tracker and detector are complementary: the Kalman filter tracker predicts the motion, the pedestrian detector searches the best-match appearance and the pedestrian model combines performance of both to determine final result and generate new samples for learning. Experimental results show our framework comparatively improves performance for pedestrian tracking in surveillance videos.

• Periodical: Applied Mechanics and Materials (Volumes 536-537)
• Pages: 205-212
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.536-537.205
• Online since: April 2014
• Authors: Zhi Qiang Qu*, Dan Tu, Jun Lei
• Keywords: Kalman Filter, Online Learning, Pedestrian Tracking, TLD, Tracking-by-Detection

References

[1] S. Stalder, H. Grabner and L. V. Gool: Beyond Semi-Supervised Tracking: Tracking Should Be as Simple as Detection, but not Simpler than Recognition, ICCV(2009), pp.1409-1416.

DOI: 10.1109/iccvw.2009.5457445

[2] J. Santner, C. Leistner, A. Saffari, T. Pock, H. Bischof: PROST: Parallel Robust Online Simple Tracking, CVPR(2010), pp.723-730.

DOI: 10.1109/cvpr.2010.5540145

[3] Y. Aloer, J. Omar and S. MuBarak: Object tracking: a survey, ACM Journal of Computing Surveys(2006), vol. 38, no. 4, pp.1-45.

[4] F. A. Faruqi and R. C. Davis: Kalman Filter Design for Target Tracking, IEEE Transactions on Aerospace and Electronic Systems(1980), vol. 16, no. 4, pp.500-508.

DOI: 10.1109/taes.1980.308980

[5] N. Dalal and B. Triggs: Histograms of oriented gradients for human detection, CVPR(2005), pp.886-893.

[6] Z. Kalal, J. Matas and K. Mikolajczyk: P-N Learning: Bootstrapping Binary Classifiers by Structural Constraints, CVPR(2010), pp.49-56.

DOI: 10.1109/cvpr.2010.5540231

[7] Z. Kalal, K. Mikolajczyk and J. Matas: Forward-Backward Error: Autonomous Detection of Tracking Failures, ICPR(2010), pp.23-26.

DOI: 10.1109/icpr.2010.675

[8] Z. Kalal, K. Mikolajczyk and J. Matas: Tracking-Learning-Detection, IEEE TPAMI(2010), vol. 6, no. 1, pp.1-14.

[9] Y. Wu, J. Lim and M. H. Yang: Online Object Tracking: A Benchmark, CVPR(2013), pp.2411-2418.

[10] Fatih Porikli: Multi-Camera Surveillance: Object-Based Summarization Approach, Mitsubishi Electric Research Laboratories(2004).

[11] P. F. Felzenszwalb, R. B. Girshick, D. McAllester and D. Ramanan: Object detection with discriminatively trained part based models, IEEE TPAMI(2010), vol. 32, no. 9, pp.1627-1645.

DOI: 10.1109/tpami.2009.167

[12] P. F. Felzenszwalb and D. Huttenlocher: Pictorial Structures for Object Recognition, IEEE IJCV( 2005), vol. 61, no. 1, pp.1-42.

[13] R. B. Girshick, P. F. Felzenszwalb and D. McAllester: Object Detection with Grammar Model, IEEE TPAMI(2011), vol. 24, no. 3, pp.22-25.

[14] D. Tu, J. Lei and Y. Yang: A Robust Approach for Congested Vehicles Tracking Based on Tracking-Model-Detection Framework, ICSP(2012), pp.820-824.

DOI: 10.1109/icosp.2012.6491707