© The Institution of Engineering and Technology
In this study, the authors focus on the performance improvements of multi-human tracking from sparse detection responses. Many previous detection-based data association tracking methods used dense detection responses as input, but they did not take into account in the case of sparse detection responses. Dense detection responses are difficult to obtain in complex environments all the time. In order to achieve this goal, they propose a particle-filter-based triple threshold method to build reliable trajectories. Here, they apply topic model to represent human appearance. The appearance of each person can be considered as topic distribution. Then a cost function algorithm is used to associate these trajectories in a time sliding window for final tracking results. The cost function is composed of four parts: appearance cost, motion direction cost, object size cost and distance cost. These four parts are integrated into a unified formula to build this cost function. Finally, they use three challenging datasets to evaluate the performance of the author's approach in the case of dense and sparse detection responses, respectively, and compare with state-of-the-art approaches. The results show that their approach can obtain better tracking performance than that of previous methods in both cases.
References
-
-
1)
-
Li, Y., Ai, H., Yamashita, T., Lao, S., Kawade, M.: `Tracking in low frame rate video: a cascade particle filter with discriminative observers of different lifespans', IEEE Computer Society Conf. Computer Vision and Pattern Recognition (CVPR), June 2007, Minneapolis, USA, p. 1–8.
-
2)
-
Zhang, L., Li, Y., Nevatia, R.: `Global data association for multi-object tracking using network flows', IEEE Computer Society Conf. Computer Vision and Pattern Recognition (CVPR), June 2008, Anchorage, Alaska, USA, p. 1–8.
-
3)
-
Yilmaz, A.: `Object tracking by asymmetric kernel mean shift with automatic scale and orientation selection', IEEE Computer Society Conf. Computer Vision and Pattern Recognition (CVPR), June 2007, Minneapolis, USA, p. 1–6.
-
4)
-
Hofmann, T.: `Probabilistic latent semantic indexing', 22ndAnnual Int. ACM SIGIR Conf. Research and Development in Information Retrieval, 1999, p. 50–57.
-
5)
-
D. Reid
.
An algorithm for tracking multiple targets.
IEEE Trans. Autom. Control
,
6 ,
843 -
854
-
6)
-
M. Isard ,
A. Blake
.
Condensation-conditional density propagation for visual tracking.
Int. J. Comput. Vis.
,
1 ,
5 -
28
-
7)
-
C.L. Morefield
.
Application of 0-1 integer programming to multitarget tracking problems.
IEEE Trans. Autom. Control
,
3 ,
302 -
312
-
8)
-
L. Bretzner ,
T. Lindeberg
.
Feature tracking with automatic selection of spatial scales.
Comput. Vis. Image Underst.
,
385 -
392
-
9)
-
Kuo, C., Huang, C., Nevatia, R.: `Multi-target tracking by on-line learned discriminative appearance models', IEEE Computer Society Conf. Computer Vision and Pattern Recognition (CVPR), June 2010, San Francisco, p. 685–692.
-
10)
-
Uchida, S., Fujimura, I., Kawano, H., Feng, Y.: `Analytical dynamic programming tracker', Asian Conf. Computer vision (ACCV), 2010, Queenstown, New Zealand, p. 296–309.
-
11)
-
Okuma, K., Taleghani, A., Freitas, N.D., Little, J., Lowe, D.: `A boosted particle filter: multitarget detection and tracking', European Conf. Computer Vision (ECCV), 2004, Prague, p. 28–39.
-
12)
-
H. Jiang ,
S. Fels ,
J.J. Little
.
Optimizing multiple object tracking and best view video synthesis.
IEEE Trans. Multimedia
,
6 ,
997 -
1012
-
13)
-
Bar-shalom, Y., Fortmann, T., Scheffe, M.: `Joint probabilistic data association for multiple targets in clutter', Conf. Information Sciences and Systems, 1980.
-
14)
-
Maggio, E., Cavallaro, A.: `Multi-part target representation for color tracking', IEEE Int. Conf. Image Processing (ICIP), September 2005, Genoa, Italy, p. 729–732.
-
15)
-
Breitenstein, M.D., Reichlin, F., Leibe, B., Meier, E.K., Gool, L.V.: `Robust tracking-by-detection using a detector confidence particle filter', IEEE Int. Conf. Computer Vision (ICCV), September 2009, Kyoto, Japan, p. 1515–1522.
-
16)
-
D.M. Blei ,
J.D. Lafferty ,
Y. Weiss ,
B. Schölkopt ,
J. Platt
.
(2006)
Correlated topic models, Advances in Neural Informantion Processing Systems 18.
-
17)
-
Wu, B., Nevatia, R.: `Tracking of multiple, partially occluded humans based on static body part detection', IEEE Computer Society Conf. Computer Vision and Pattern Recognition (CVPR), June 2006, New York, USA, p. 951–959.
-
18)
-
Cai, Y., Freitas, N.d., Little, J.J.: `Robust visual tracking for multiple targets', European Conf. Computer Vision (ECCV), 2006, Graz, Austria, p. 107–118.
-
19)
-
Ess, A., Leibe, B., Gool, L.V.: `Depth and appearance for mobile scene analysis', IEEE Int. Conf. Computer Vision (ICCV), Rio de Janeiro, October 2007, Brazil, p. 1–8.
-
20)
-
Zhu, Q., Avidan, S., Yeh, M.C., Cheng, K.T.: `Fast human detection using a cascade of histograms of oriented gradients', IEEE Computer Society Conf. Computer Vision and Pattern Recognition (CVPR), New York, June 2006, USA, 2, p. 1491–1498.
-
21)
-
Qi, S., Huang, X.: `Hand tracking and gesture recognition by anisotropic kernel mean shift', IEEE Int. Conf. Neural Networks and Signal Processing, June 2008, Zhenjiang, China, p. 581–585.
-
22)
-
http://www.groups.inf.ed.ac.uk/vision/CAVIAR/CAVIARDATA1/, accessed July 2011.
-
23)
-
Maggio, E., Cavallaro, A.: `Hybrid particle filter and mean shift tracker with adaptive transition model', IEEE Int. Conf. Acoustics Speech and Signal Process (ICASSP), March 2005, Philadelphia, USA, 2, p. 221–224.
-
24)
-
Y. Bar-Shalom ,
T.E. Fortmann
.
(1988)
Tracking and data association.
-
25)
-
Vermaak, J., Doucet, A., Perez, P.: `Maintaining multimodality through mixture tracking', IEEE Int. Conf. Computer Vision (ICCV), October 2003, Nice, France, 2, p. 1110–1116.
-
26)
-
Li, Y., Huang, C., Nevatia, R.: `Learning to associate: hybridboost multi-target tracker for crowded scene', IEEE Computer Society Conf. Computer Vision and Pattern Recognition (CVPR), June 2009, Miami Beach, Florida, p. 2953–2960.
-
27)
-
D.M. Blei ,
A.Y. Ng ,
M.I. Jordan
.
Latent Dirichlet allocation.
J. Mach. Learn. Res.
,
993 -
1022
-
28)
-
Berclaz, J., Fleuret, F., Fua, P.: `Robust people tracking with global trajectory optimization', IEEE Computer Society Conf. Computer Vision and Pattern Recognition (CVPR), June 2006, New York, USA, 1, p. 17–22.
-
29)
-
D. Comaniciu ,
V. Ramesh ,
P. Meer
.
Kernel-based object tracking.
IEEE Trans. Pattern Anal. Mach. Intell.
,
564 -
577
-
30)
-
http://www.eecs.qmul.ac.uk/~andrea/avss2007_d.html, accessed July 2011.
-
31)
-
Huang, C., Wu, B., Nevatia, R.: `Robust object tracking by hierarchical association of detection responses', European Conf. Computer Vision (ECCV), October 2008, Marseille, France, p. 788–801.
-
32)
-
Khan, Z., Balch, T., Dellaert, F.: `An MCMC-based particle filter for tracking multiple interacting targets', European Conf. Computer Vision (ECCV), 2004, Prague, p. 279–290.
-
33)
-
Shen, Y., Miao, Z., Wang, Z.: `A cost function approach for multi-human tracking', IEEE Int. Conf. Image Processing (ICIP), September 2011, Brussels, Belguim, p. 481–484.
-
34)
-
Collins, R.T.: `Mean-shift blob tracking through scale space', IEEE Computer Society Conf. Computer Vision and Pattern Recognition (CVPR), June 2003, Madison, USA, 2, p. 234–240.
-
35)
-
Parameswaran, V., Ramesh, V., Zoghlami, I.: `Tunable kernels for tracking', IEEE Computer Society Conf. Computer Vision and Pattern Recognition (CVPR), June 2006, New York, USA, 2, p. 2179–2186.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2011.0198
Related content
content/journals/10.1049/iet-cvi.2011.0198
pub_keyword,iet_inspecKeyword,pub_concept
6
6