Copyright © 2007 The Institute of Electronics, Information and Communication Engineers
Regular Section -- Papers -- Image Recognition, Computer Vision |
Object Tracking with Target and Background Samples
1 The authors are with the Faculty of System Engineering, Wakayama University, Wakayama-shi, 640–8510 Japan. E-mail: wuhy{at}sys.wakayama-u.ac.jp
In this paper, we present a general object tracking method based on a newly proposed pixel-wise clustering algorithm. To track an object in a cluttered environment is a challenging issue because a target object may be in concave shape or have apertures (e.g. a hand or a comb). In those cases, it is difficult to separate the target from the background completely by simply modifying the shape of the search area. Our algorithm solves the problem by 1) describing the target object by a set of pixels; 2) using a K-means based algorithm to detect all target pixels. To realize stable and reliable detection of target pixels, we firstly use a 5D feature vector to describe both the color ("Y, U, V") and the position ("x, y") of each pixel uniformly. This enables the simultaneous adaptation to both the color and geometric features during tracking. Secondly, we use a variable ellipse model to describe the shape of the search area and to model the surrounding background. This guarantees the stable object tracking under various geometric transformations. The robust tracking is realized by classifying the pixels within the search area into "target" and "background" groups with a K-means clustering based algorithm that uses the "positive" and "negative" samples. We also propose a method that can detect the tracking failure and recover from it during tracking by making use of both the "positive" and "negative" samples. This feature makes our method become a more reliable tracking algorithm because it can discover the target once again when the target has become lost. Through the extensive experiments under various environments and conditions, the effectiveness and efficiency of the proposed algorithm is confirmed.
Key Words: object tracking, K-means clustering, tracking failure detection and recovery, background interfusion
Manuscript received April 14, 2006. Manuscript revised August 11, 2006.
References
[1] C. Hua, H. Wu, T. Wada, and Q. Chen, "K-means tracking with variable ellipse model," IPSJ Trans. CVIM, vol.46, no.Sig 15 (CVIM12), pp.59–68, 2005.
[2] C. Stauffer and W.E.L. Grimson, "Adaptive background mixture model for real-time tracking," CVPR, pp.246–252, 1999.
[3] H.T. Nguyen and A. Semeulders, "Tracking aspects of the foreground against the background," ECCV, vol.2, pp.446–456, 2004.
[4] H.D. Crane and C.M. Steele, "Translation-tolerant mask matching using noncoherent reflective optics," Pattern Recognit., vol.1, no.2, pp.129–136, 1968.
[5] C. Gräßl, T. Zinßer, and H. Niemann, "Illumination insensitive template matching with hyperplanes," DAGM, pp.273–280, 2003.
[6] D. Comaniciu, V. Ramesh, and P. Meer, "Real-time tracking of non-rigid objects using mean shift," CVPR, vol.2, pp.142–149, 2000.
[7] D. Comaniciu, V. Ramesh, and P. Meer, "Kernel-based object tracking," IEEE Trans. Pattern Anal. Mach. Intell., vol.25, no.5, pp.564–577, 2003.
[8] M. Isard and A. Blake, "Condensation-conditional density propagation for visual tracking," IJCV, vol.29, no.1, pp.5–28, 1998.
[9] J. Deutscher, B. North, B. Bascle, and A. Blake, "Tracking through singularities and discontinuities by random sampling," ICCV, pp.1144–1149, 1999.
[10] K. Smith and D. Gatica-Perez, "Order matters: A distributed sampling method for multi-object tracking," BMVC, pp.25–32, London, Sept. 2004.
[11] F.C. Schweppe, "State space evaluation of the Bhattacharyya distance between two Gaussian processes," Information and Control, vol.11, no.3, pp.352–372, Sept. 1967.
[12] H.Z. Rafi and H. Soltanianzadeh, "Mutual information restoration of multispectral images," IWSSIP, 2003.
[13] M. Kass, A. Witkin, and D. Terzopoulos, "Snakes: Active contour models," IJCV, vol.1, pp.321–332, 1988.
[14] T. Zhao and R. Nevatia, "Tracking multiple humans in crowded environment," CVPR, vol.2, pp.406–413, 2004.
[15] Y. Wu, G. Hua, and T. Yu, "Switching observation models for contour tracking in clutter," CVPR, vol.1, pp.295–302, 2003.
[16] N.T. Siebel and S. Maybank, "Fusion of multiple tracking algorithms for robust people tracking," ECCV, vol.4, pp.373–387, 2002.
[17] J. Vermaak, P. Pérez, M. Gangnet, and A. Blake, "Towards improved observation models for visual tracking: Selective adaptation," ECCV, vol.1, pp.645–660, 2002.
[18] H. Tao, H.S. Sawhney, and R. Kumar, "Object tracking with Bayesian estimation of dynamic layer representations," IEEE Trans. Pattern Anal. Mach. Intell., vol.24, no.1, pp.75–89, 2002.
[19] B. Heisele, U, Kreßel, and W. Ritter, "Tracking non-rigid moving objects based on color cluster flow," CVPR, pp.253–257, 1997.
[20] A. Agarwal and B. Triggs, "Tracking articulated motion using a mixture of autoregressive models," ECCV, vol.3, pp.54–65, 2004.
[21] J. Hartigan and M. Wong, "Algorithm AS136: A K-means clustering algorithm," Applied Statistics, vol.28, pp.100–108, 1979.
[22] M. Isard and A. Blake, "Contour tracking by stochastic propagation of conditional density," ECCV, vol.1, pp.343–356, 1996.
[23] T. Wada, T. Hamatsuka, and T. Kato, "K-means tracking: A robust target tracking against background involution," MIRU2004, vol.2, pp.7–12, 2004.
CiteULike 
Connotea 
Del.icio.us What's this?
| ||||||||||||||||||||||||||||||||||||||||||||||||||