Object Tracking across Non-Overlapping Cameras Based on Improved TLD and Multi-Feathers Object Matching

Abstract:

Object tracking across non-overlapping views is a hot and important research topic in compute vision. In this paper, a novel method to track the interested object continuously across non-overlapping cameras is presented. This challenging task is taken as two sub-problems: single camera object tracking and object matching across disjoint cameras. An object tracking algorithm which improves Tracking-Learning-Detection (TLD) algorithm by adding background extraction and Kalman filter is presented to deal with the first problem. A new object matching algorithm based on the fusion of global features and local features at the assistance of 3D GIS is also introduced for object matching across disjoint cameras. The proposed approach does not need a training phase and inter-camera calibration. Experiments are carried out on real world videos to validate the proposed approach.

• Periodical: Applied Mechanics and Materials (Volumes 602-605)
• Pages: 1713-1717
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.602-605.1713
• Online since: August 2014
• Authors: Rui Peng Lv, Hai Gang Sui*, Ji Hui Tu, Xiao Yu Cai, Liang Dong
• Keywords: Non-Overlapping Cameras, Object Tracking, Opponent Color LBP, Spatiograms

References

[1] Stauffer, C. and Tieu, K., Automated multi-camera planar tracking correspondence modeling, CVPR(2003), vol. 1, p. I-259.

DOI: 10.1109/cvpr.2003.1211362

[2] Hu, W., et al. Principal axis-based correspondence between multiple cameras for people tracking, Pattern Analysis and Machine Intelligence(2006), vol. 28, no. 4, pp.663-671.

DOI: 10.1109/tpami.2006.80

[3] Chen, X., et al. Object tracking across non-overlapping cameras using adaptive models, Computer Vision-ACCV 2012 Workshops, pp.464-477.

DOI: 10.1007/978-3-642-37484-5_38

[4] Kalal, Z., Mikolajczyk, K., and Matas, J., Tracking-learning-detection, Pattern Analysis and Machine Intelligence(2012), vol. 34, no. 7, pp.1409-1422.

DOI: 10.1109/tpami.2011.239

[5] Fang C., et al. Person re-identification based on multi-features, Journal of Image and Graphics(2013), vol. 18, no. 6, pp.711-717.

[6] Birchfield, S. T. and Rangarajan, S., Spatiograms versus histograms for region-based tracking, Computer Vision and Pattern Recognition(2005) , vol. 2, pp.1158-1163.

DOI: 10.1109/cvpr.2005.330

[7] Maenpaa, T., Pietikainen, M., and Viertola, J., Separating color and pattern information for color texture discrimination, ICPR(2002), vol. 1, pp.668-671.

DOI: 10.1109/icpr.2002.1044840

[8] Barnich, O. and Van Droogenbroeck, M., ViBe: A universal background subtraction algorithm for video sequences, IEEE Transactions on Image Processing(2011), vol. 20, no. 6, pp.1709-1724.

DOI: 10.1109/tip.2010.2101613

[9] Hofmann, M., Tiefenbacher, P. and Rigoll, G., Background segmentation with feedback: The pixel-based adaptive segmenter, Computer Vision and Pattern Recognition Workshops (CVPRW2012), pp.38-43.

DOI: 10.1109/cvprw.2012.6238925

[10] Wang J., Yang J., Object Tracking Based on Kalman-Mean Shift in Occlusions, Journal of System Simulation(2007), vol. 19, no. 18, pp.4216-4220.

[11] Ojala, T., Pietikäinen, M. and Mäenpää, T., Gray scale and rotation invariant texture classification with local binary patterns, ECCV(2000), pp.404-420.

DOI: 10.1007/3-540-45054-8_27

[12] Ning, J., Zhang, L., Zhang, D. and Wu, C., Robust object tracking using joint color-texture histogram, International Journal of Pattern Recognition and Artificial Intelligence, vol. 23, no. 7, pp.1245-1263.

DOI: 10.1142/s0218001409007624