Abstract
We propose a novel method for the segmentation of deformable objects and the extraction of motion features for tracking objects in video data. The method adopts an algorithm called two-dimensional continuous dynamic programming (2DCDP) for extracting pixel-wise trajectories. A clustering algorithm is applied to a set of pixel trajectories to determine a shape of deformable objects each of which corresponds to a trajectory cluster. We conduct experiments to compare our method with conventional methods such as KLT tracker and SIFT. The experiment shows that our method is more powerful than the conventional methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Yilmaz, A., Javed, O., Shah, M.: Object tracking: A survey. ACM Computing Surveys (CSUR) 38(4) (2006)
Viola, P.: Rapid object detection using a boosted cascade of simple features. In: Proc. of IEEE CVPR 2001, pp. 511–518 (2001)
Mochiki, R., Katto, J.: Human tracking by particle filter using haar-like feature. In: Proc. of the IEICE General Conference 2007, vol. 2, p. 121 (2007)
Nakagawa, H., Habe, H., Kidode, M.: Efficient prior acquisition of human existence by using past human trajectories and color of image. Technical report of IEICE. PRMU 108(484), 305–312 (2009)
Takeuchi, D., Ito, Y., Yamashita, A., Kaneko, T.: Multi-viewpoint person tracking based on face detection of arbitrary pose and mean-shift algorithm. ITE Technical Report 33(11), 69–72 (2009)
Dan, M., Kazuhiro, O., Junji, Y.: Memory-based particle filter for face pose tracking robust under complex dynamics. In: Proc. of IEEE CVPR 2009, pp. 999–1006 (2009)
Takayoshi, Y., Hironobu, F., Shihong, L., Masato, K.: Human tracking based on soft decision feature and online real boosting. In: Proc. of MIRU 2008, pp. 12–19 (2008)
Rabaud, V., Belongie, S.: Counting Crowded Moving Objects. In: Proc. of IEEE CVPR 2006, vol. 1, pp. 705–711 (2006)
Shi, J., Tomasi, C.: Good features to track. In: Proc. of IEEE Conference on CVPR 1994, pp. 593–600 (1994)
Sugimura, D., Kitani, K.M., Okabe, T., Sato, Y., Sugimoto, A.: Tracking people in crowds based on clustering feature trajectories using gait features and local appearances. In: Proc. of MIRU 2009, pp. 135–142 (2009)
Tsuduki, Y., Fujiyoshi, H., Kanade, T.: Mean shift-based point feature tracking using sift. IPSJ SIG Technical Reports 49(6), 101–108 (2007)
Yuji, T., Hironobu, F.: A method for visualizing pedestrian traffic flow using sift feature point tracking. In: Proc. of IEEE PSIVT 2009 (2009)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. Journal of Computer Vision 60(2), 91–110 (2004)
Yaguchi, Y., Iseki, K., Oka, R.: Optimal Pixel Matching between Images. In: Wada, T., Huang, F., Lin, S. (eds.) PSIVT 2009. LNCS, vol. 5414, pp. 597–610. Springer, Heidelberg (2009)
Oka, R.: Spotting method for classification of real world data. The Computer Journal 41(8), 559–565 (1998)
Gonzalez, R.C., Woods, R.E.: Digital Image Processing, 2nd edn. Prentice-Hall International (2001)
Stan, B.: KLT: an implementation of the kanade lucas tomasi feature tracker, http://www.ces.clemson.edu/stb/klt/index.html
Hess, R.: Sift feature detector, http://web.engr.oregonstate.edu/~hess/
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Aota, H., Ota, K., Yaguchi, Y., Oka, R. (2012). Deformable Multi-object Tracking Using Full Pixel Matching of Image. In: Obaidat, M.S., Tsihrintzis, G.A., Filipe, J. (eds) e-Business and Telecommunications. ICETE 2010. Communications in Computer and Information Science, vol 222. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-25206-8_22
Download citation
DOI: https://doi.org/10.1007/978-3-642-25206-8_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-25205-1
Online ISBN: 978-3-642-25206-8
eBook Packages: Computer ScienceComputer Science (R0)