Journal of Multimedia, Vol 7, No 5 (2012), 364-371, Oct 2012
doi:10.4304/jmm.7.5.364-371

An Adaptive Motion Model and Multi-feature Cues Based on Particle Filter for Object Tracking

Ming Li, Liuqing Yuan, Wenxia Du

Abstract


If there is an occlusion, the target state model would not match motion model anymore and measurement model also would get worse. To solve these problems, an improved particle filtering algorithm based on adaptive motion model and multiple-cue fusion is presented. Under the theory framework of particle filters, the weighted color histogram and LBP texture feature entropy are used to describe features. And the algorithm adjusts features distribution coefficient  automatically by calculating the Bhattacharyya distance between the object reference distribution and object sample distribution, thus the color and texture features can intelligently be fused to develop the observation model. The simple second order auto regressive model is chosen as the state transition model, and the system noise variance is adaptively determined by the minimum noise variance of every feature in object tracking. For the occlusion problem, the system maximum noise variance can be selected, along with particle random motion intensified and disseminating coverage amplified. The posterior distribution of the object is approximated by a set of weighted samples, while object tracking is implemented by the Bayesian propagation of the sample set. The analyses and experiments show that the performance of the proposed method is more effective and robust to target maneuver and occlusion and has good performances under complex background.



Keywords


Target tracking; Particle Filter; Bhattacharyya coefficient; Occlusion; system model

References


Yardim C., Gerstoft P., Hodgkiss W.S., “Tracking Refractivity from Clutter Using Kalman and Particle Filters,” Antennas and Propagation, vol.56, pp. 1058–1017, April 2008.

B. Ristic, S. Arulampalam, and N. Gordon, Beyond the Kalman filter: Particle filters for tracking applications, Artech House, 2004.

R. Venkatesh Babu, Patrick Pérez and Patrick Bouthemy, “Robust tracking with motion estimation and local Kernel-based color modeling,” Image and Vision Computing, Vol. 25, pp. 1205-1216, August 2007.

G. Hager, P. Belhumeur, “Efficient region tracking with parametric models of geometry and illumination,” IEEE Trans. Pattern Anal. Mach. Intell. vol.20, pp.1025–1039, 1998.

Feng Tang, Hai Tao, “Object tracking with dynamic feature graph,” Visual Surveillance and Performance Evaluation of Tracking and Surveillance, pp. 25–32, Oct. 2006.

D. Comaniciu, V. Ramesh, P. Meer, “Kernel-based object tracking,” IEEE Trans. Pattern Anal. Mach. Intell. Vol.25, pp.564–577, 2003.

G. Bradski, “Computer vision face tracking as a component of aperceptual user interface,” Workshop on Application of Computer Vision, Princeton, NJ, pp. 214–219, 1998.

G. Cheung, S. Baker, T. Kanade, “Shape-from silhouette of articulated objects and its use for human body kinematics estimation and motion capture,” IEEE Conf. on Computer Vision and Pattern Recognition, vol. 1, pp. 77–84, 2003.

M.J. Black, A.D. Jepson, “Eigentracking: robust matching and tracking of articulated objects using a view-based representation,” Int. J. Comput. Vis. Vol.26, pp.63–84, 1998.

O. Williams, A. Blake, R. Cipolla, “Sparse bayesian learning forefficient visual tracking,” IEEE Trans. Pattern Anal. Mach. Intell. Vol.27, pp.1292–1304, 2005.

P. Perez, C. Hue, J. Vermaak, and M. Gangnet, “Color-based probabilistic tracking,” Proc. of the European Conference on Computer Vision, vol. 1, Copenhagen, Denmark, pp. 661–675 , May-June 2002.

BIAN Zhi-guo, JIN Li-zuo, FEI Shu-min, “Likelihood map fusion for visual object tracking,” Application Research of Computers. vol. 27, pp.1537-1539, Apr. 2010.

LIU Yun-hai, QUAN Xiao-chen, “Adaptive multiple-cue fusion based anti-occlusions algorithm for object tracking,” Journal of Zhejiang University (Engineering Science). vol.43, pp.1208-1213, Jul.2009.

Jacek Czyz, Branko Ristic and Benoit Macq, “A particle filter for joint detection and tracking of color objects” Image and Vision Computing, Vol. 25, pp. 1271-1281, August 2007.

Jacek Czyz, Branko Ristic and Benoit Macq, “A COLOR-BASED PARTICLE FILTER FOR JOINT DETECTION AND TRACKING OF MULTIPLE OBJECTS,” International Conference on Pattern Recognition, 2005.

A. Doucet, N. de Freitas, and N. Gordon, Eds., Sequential Monte Carlo Methods in Practice, Springer, New York, NY, USA, 2001.

NIU Chang-feng, LIU Yu-shu, “Particle filter targets tracking by fusing multiple features,” J. Huazhong Univ. of Sci. & Tech. (Natural Science Edition). vol.38, pp.18-21, 2010.

Cheng Jian. “Research on Visual Tracking Algorithms Based on Particle Filtering and Their Applications in Infrared Imaging Guidance,” Shanghai Jiao Tong University, Shanghai, 2006

A. Blake and M. Isard, Active Contour, Spinger-Verlag, 1998.

Blake, A., Isard, M., and Reynard, Learning to track the visual motion of contours , vol.78, Artificial Intelligence, pp. 101–134, 1995.

Reynard, D., Wildenberg, A., Blake, A., and Marchant, “Learning dynamics of complex motions from image sequences,” Proc. 4th European Conf. on Computer Vision, Cambridge,England, pp. 357–368 , 1996.

Triesch, J., von der Malsburg, “Democratic integration: Self-organized integration of adaptive cues,” Neural Computation. pp. 2049–2074, 2001.

Md. Zahidul Islam, Chi-Min Oh and Chil-Woo Lee, “New Integrated Framework for Video Based Moving Object Tracking”. Human Computer Interaction, part III, HCII2009, LNCS5612, pp.423 – 432, 2009.

Manesh Kokare P K, Biswas B N, Chatterji. “Texture image retrieval using new rotated complex wavelet filters,” IEEE Transactions on Systems, Man and Cyber-netics, vol.35, pp.1168 - 1178, 2005.

Katja Nummiaro,Esther Koller-Meier and Luc Van Gool. “An Adaptive Color-Based Particle Filter,” Preprint submitted to Elsevier Science, vol.21, pp.99-110, January 2003.

Ojala T, Pietikinen M, Harwood D, “Comparative study of texture measures with classification based on feature distributions,” Pattern Recognition. vol.29, pp.51-59, 1996.

T. Ojala, M. Pietikainen, and T. Maenpaa, “Multiresolution gray-scale and rotation invariant texture classification with local binary patterns,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol.24, pp.971-987, 2002.

SUN Hui-xian, ZHANG Yu-hua, LUO Fei-lu, “Wire Rope Image Segmentation Method Based on Texture Features,” Opto-Electronic Engineering. Vol.36, pp.123-127, 2009.


Full Text: PDF


Journal of Multimedia (JMM, ISSN 1796-2048)

Copyright @ 2006-2014 by ACADEMY PUBLISHER – All rights reserved.