An Optical Flow-Based PIG Method for Active Contour Tracking Initialization

Abstract:

In this paper, we propose a new optical flow-based Poisson inverse gradient (OFPIG) initialization method for active contour tracking. This method can automatically initialize the contour of moving target for consequent tracking. First, an optical flow based motion detection method is adopted to remove background information, and then a Poisson inverse gradient (PIG) initialization is applied to locate the target region. Finally, parametric active contour is used to evolve the correct target contour depending on the initialization precision. Experimental results have demonstrated its effectiveness and robustness.

• Periodical: Advanced Materials Research (Volumes 760-762)
• Pages: 1311-1316
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.760-762.1311
• Online since: September 2013
• Authors: Jun Ru Wang, Xiao Feng Lu, Yu Chen Wang, Tian Xiang Fan
• Keywords: Contour Tracking, Optical Flow, Parametric Active Contour Model, Pig

References

[1] Kass, Michael, Andrew Witkin, and Demetri Terzopoulos. Snakes: Active contour models., International journal of computer vision 1. 4 (1988): 321-331.

DOI: 10.1007/bf00133570

[2] Paragios, Nikos, and Rachid Deriche. Geodesic active regions for motion estimation and tracking., Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on. Vol. 1. IEEE, (1999).

DOI: 10.1109/iccv.1999.791292

[3] Xingfei, Ge, and Tian Jie. An automatic active contour model for multiple objects., Pattern Recognition, 2002. Proceedings. 16th International Conference on. Vol. 2. IEEE, (2002).

DOI: 10.1109/icpr.2002.1048444

[4] Li, Chunming, Jundong Liu, and Martin D. Fox. Segmentation of external force field for automatic initialization and splitting of snakes., Pattern Recognition 38. 11 (2005): 1947-(1960).

DOI: 10.1016/j.patcog.2004.12.015

[5] Chung, Chih-Yuan, and Homer H. Chen. Video object extraction via MRF-based contour tracking., Circuits and Systems for Video Technology, IEEE Transactions on 20. 1 (2010): 149-155.

DOI: 10.1109/tcsvt.2009.2026823

[6] Chen, Qiang, et al. Two-stage object tracking method based on kernel and active contour., Circuits and Systems for Video Technology, IEEE Transactions on 20. 4 (2010): 605-609.

DOI: 10.1109/tcsvt.2010.2041819

[7] Javed, Omar, Saad Ali, and Mubarak Shah. Online detection and classification of moving objects using progressively improving detectors., Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on. Vol. 1. IEEE, (2005).

DOI: 10.1109/cvpr.2005.259

[8] Heikkila, Marko, and Matti Pietikainen. A texture-based method for modeling the background and detecting moving objects., Pattern Analysis and Machine Intelligence, IEEE Transactions on 28. 4 (2006): 657-662.

DOI: 10.1109/tpami.2006.68

[9] Panin, Giorgio, Alexander Ladikos, and Alois Knoll. An efficient and robust real-time contour tracking system. " Computer Vision Systems, 2006 ICVS, 06. IEEE International Conference on. IEEE, (2006).

DOI: 10.1109/icvs.2006.13

[10] Li, Bing, and Scott T. Acton. Automatic active model initialization via Poisson inverse gradient., Image Processing, IEEE Transactions on 17. 8 (2008): 1406-1420.

DOI: 10.1109/tip.2008.925375

[11] Horn B, Schunck B. Determining optical flow. Artificial Intelligence 1981; 17(1–3): 185–203.

DOI: 10.1016/0004-3702(81)90024-2

[12] Shin, Jeongho, et al. Optical flow-based real-time object tracking using non-prior training active feature model., Real-Time Imaging 11. 3 (2005): 204-218.

DOI: 10.1016/j.rti.2005.03.006

[13] http: /www. anc. ed. ac. uk/demos/tracker/pets2001. html.