Multiple instance learning tracking method with local sparse representation

Chengjun Xie; Jieqing Tan; Peng Chen; Jie Zhang; Lei He

Multiple instance learning tracking method with local sparse representation

View Fulltext

Author(s): Chengjun Xie ^{1, 2} ; Jieqing Tan ¹ ; Peng Chen ^{2, 3} ; Jie Zhang ² ; Lei He ¹
- Affiliations: 1: School of Computer and Information, Hefei University of Technology, Hefei 230009, People's Republic of China;
  2: Laboratory of Intelligent Decision, Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei 230031, People's Republic of China;
  3: Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal 23955-6900, Saudi Arabia
Source: Volume 7, Issue 5, October 2013, p. 320 – 334
DOI: 10.1049/iet-cvi.2012.0228 , Print ISSN 1751-9632, Online ISSN 1751-9640

Received 11/10/2012, Accepted 13/05/2013, Revised 06/04/2013, Published

When objects undergo large pose change, illumination variation or partial occlusion, most existed visual tracking algorithms tend to drift away from targets and even fail in tracking them. To address this issue, in this study, the authors propose an online algorithm by combining multiple instance learning (MIL) and local sparse representation for tracking an object in a video system. The key idea in our method is to model the appearance of an object by local sparse codes that can be formed as training data for the MIL framework. First, local image patches of a target object are represented as sparse codes with an overcomplete dictionary, where the adaptive representation can be helpful in overcoming partial occlusion in object tracking. Then MIL learns the sparse codes by a classifier to discriminate the target from the background. Finally, results from the trained classifier are input into a particle filter framework to sequentially estimate the target state over time in visual tracking. In addition, to decrease the visual drift because of the accumulative errors when updating the dictionary and classifier, a two-step object tracking method combining a static MIL classifier with a dynamical MIL classifier is proposed. Experiments on some publicly available benchmarks of video sequences show that our proposed tracker is more robust and effective than others.

References

1. 1)
  - 19. Dalal, N., Triggs, B.: ‘Histograms of oriented gradients for human detection’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, June 2005, pp. 886–893.
2. 2)
  - 5. Babenko, B., Ming-Hsuan, Y., Belongie, S.: ‘Robust object tracking with online multiple instance learning’, IEEE Trans. Pattern Anal. Mach. Intell., 2011, 33, (8), pp. 1619–1632 (doi: 10.1109/TPAMI.2010.226).
3. 3)
  - 29. Avidan, S.: ‘Support vector tracking’, IEEE Trans. Pattern Anal. Mach. Intell. , 2004, 26, (8), pp. 1064–1072 (doi: 10.1109/TPAMI.2004.53).
4. 4)
  - 11. Wang, J.Q., Yagi, Y.S.: ‘Integrating color and shape-texture features for adaptive real-time object tracking’, IEEE Trans. Image Process., 2008, 17, (2), pp. 235–240 (doi: 10.1109/TIP.2007.914150).
5. 5)
  - 45. http://vision.ucsd.edu/~bbabenko/project_miltrack.shtml.
6. 6)
  - 36. Grabner, H., Bischof, H.: ‘On-line boosting and vision’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, June 2006, pp. 260–267.
7. 7)
  - 28. Liu, B., Yang, L., Huang, J., Meer, P., Gong, L., Kulikowski, C.: ‘Robust and fast collaborative tracking with two stage sparse optimization’. Proc. ECCV, 2010, no. 4, pp. 624–637.
8. 8)
  - 49. Santner, J., Leistner, C., Saffari, A., Pock, T., Bischof, H.: ‘Prost: parallel robust online simple tracking’. June 2010, pp. 723–730.
9. 9)
  - 10. Han, Z.J., Ye, Q.X., Jiao, J.B.: ‘Feature evaluation by particle filter for adaptive object tracking’. Proc. SPIE Visual Communication and Image Processing, 2009.
10. 10)
  - 17. Ning, J., Zhang, L., Zhang, D., Wu, C.: ‘Robust mean shift tracking with corrected background-weighted histogram’, IET Comput. Vis., 2012, 6, (1), pp. 62–69 (doi: 10.1049/iet-cvi.2009.0075).
11. 11)
  - 25. Lin, H.X., Shen, C.H., Shi, Q.F.: ‘Real-time visual tracking using compressive sensing’. IEEE Conf. on CVPR, June 2011, pp. 1305–1312.
12. 12)
  - 32. Kalal, Z., Matas, J., Mikolajczyk, K.: ‘P-N learning: bootstrapping binary classifiers by structural constraints’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 2010, pp. 49–56.
13. 13)
  - 34. Avidan, S.: ‘Ensemble tracking’, IEEE Trans. Pattern Anal. Mach. Intell., 2007, 29, (2), pp. 261–271 (doi: 10.1109/TPAMI.2007.35).
14. 14)
  - 39. Andrews, S., Tsochantaridis, I., Hofmann, T.: ‘Support vector machines for multiple-instance learning’. Proc. NIPS, 2002, pp. 561–568.
15. 15)
  - 24. Wright, J., Yang, A., Ganesh, A., Sastry, S., Ma, Y.: ‘Robust face recognition via sparse representation’, IEEE Trans. Pattern Anal. Mach. Intell., 2009, 31, (2), pp. 210–227 (doi: 10.1109/TPAMI.2008.79).
16. 16)
  - 26. Han, Z., Jiao, J., Zhang, B., Ye, Q., Liu, J.: ‘Visual object tracking via sample-based adaptive sparse representation (AdaSR)’, Pattern Recognit., 2011, 44, (9), pp. 2170–2183 (doi: 10.1016/j.patcog.2011.03.002).
17. 17)
  - 14. Comaniciu, D., Ramesh, V., Meer, P.: ‘Kernel-based object tracking’, IEEE Trans. Pattern Anal. Mach. Intell., 2003, 25, (5), pp. 564–575 (doi: 10.1109/TPAMI.2003.1195991).
18. 18)
  - 21. Wright, J., Ma, Y., Mairal, J., Sapiro, G., Huang, T., Yan, S.: ‘Sparse representation for computer vision and pattern recognition’, Proc. IEEE, 2010, 98, (6), pp. 1031–1044 (doi: 10.1109/JPROC.2010.2044470).
19. 19)
  - 8. Wang, J., Chen, X., Gao, W.: ‘Online selecting discriminative tracking features using particle filter’. Proc. IEEE Conf. on CVPR, June 2005, pp. 1037–1042.
20. 20)
  - 15. Jepson, A.D., Fleet, D.J., El-Maraghi, T.F.: ‘Robust online appearance models for visual tracking’, IEEE Trans. Pattern Anal. Mach. Intell. (PAMI), 2003, 25, (10), pp. 1296–1311 (doi: 10.1109/TPAMI.2003.1233903).
21. 21)
  - 22. Candès, E., Romberg, J., Tao, T.: ‘Stable signal recovery from incomplete and inaccurate measurements’, Commun. Pure Appl. Math., 2006, 59, (8), pp. 1207–1223 (doi: 10.1002/cpa.20124).
22. 22)
  - 23. Donoho, D.: ‘Compressed sensing’, IEEE Trans. Inf. Theory, 2006, 52, (4), pp. 1289–1306 (doi: 10.1109/TIT.2006.871582).
23. 23)
  - 37. Parag, T., Porikli, F., Elgammal, A.: ‘Boosting adaptive linear weak classifiers for online learning and tracking’ (CVPR, 2008), pp. 1–8.
24. 24)
  - 3. Dietterich, T.G., Lathrop, R.H., Perez, L.T.: ‘Solving the multiple-instance problem with axis parallel rectangles’, Artif. Intell., 1997, 88, (1–2), pp. 31–71 (doi: 10.1016/S0004-3702(96)00034-3).
25. 25)
  - 43. Arulampalam, M.S., Maskell, S., Gordon, N., Clapp, T.: ‘A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking’, IEEE Trans. Signal Process., 2002, 50, (2), pp. 174–188 (doi: 10.1109/78.978374).
26. 26)
  - 30. Avidan, S.: ‘Ensemble tracking’, IEEE Trans. Pattern Anal. Mach. Intell. , 2007, 29, (2), pp. 261–271 (doi: 10.1109/TPAMI.2007.35).
27. 27)
  - 40. Viola, P., Platt, J.C., Zhang, C.: ‘Multiple instance boosting for object detection’ (NIPS, 2007), pp. 1417–1426.
28. 28)
  - 7. Wang, Q., Chen, F., Xu, W., Yang, M.-H.: ‘Online discriminative object tracking with local sparse representation’. WACV ‘12 Proc. 2012 IEEE Workshop on the Applications of Computer Vision, January 2012, pp. 425–432.
29. 29)
  - 18. Lowe, D.: ‘Distinctive image features from scale-invariant key points’, Int. J. Comput. Vis., 2004, 60, (2), pp. 91–110 (doi: 10.1023/B:VISI.0000029664.99615.94).
30. 30)
  - 9. Han, Z.J., Ye, Q.X., Jiao, J.B.: ‘Online feature evaluation for object tracking using kalman filter’. 19th Int. Conf. on Pattern Recognition, December 2008, pp. 1–4.
31. 31)
  - 13. Pérez, P., Hue, C., Vermaak, J., Gangnet, M.: ‘Color-based probabilistic tracking’. Proc. European Conf. on Computer Vision, 2002, pp. 661–675.
32. 32)
  - 50. Everingham, M., Van Gool, L., Williams, C., Winn, J., Zisserman, A.: ‘The pascal visual object classes (voc) challenge’, Int. J. Comput. Vis., 2010, 88, (2), pp. 303–338 (doi: 10.1007/s11263-009-0275-4).
33. 33)
  - 2. Mei, X., Ling, H.: ‘Robust visual tracking and vehicle classification via sparse representation’, IEEE Trans. Pattern Anal. Mach. Intell. (PAMI), 2011, 33, (11), pp. 2259–2272 (doi: 10.1109/TPAMI.2011.66).
34. 34)
  - 20. Ojala, T., Pietikainen, M., Maenpaa, T.: ‘Multiresolution gray-scale and rotation invariant texture classification with local binary patterns’, IEEE Trans. Pattern Anal. Mach. Intell., 2002, 24, (7), pp. 971–987 (doi: 10.1109/TPAMI.2002.1017623).
35. 35)
  - 38. Grabner, H., Leistner, C., Bischof, H.: ‘Semi-supervised on-line boosting for robust tracking’. Proc. European Conf. on Computer Vision, 2008, pp. 234–247.
36. 36)
  - 33. Yu, Q., Dinh, T.B., Medioni, G.: ‘Online tracking and reacquisition using co-trained generative and discriminative trackers’. Proc. European Conf. on Computer Vision, 2008, pp. 678–691.
37. 37)
  - 48. http://gpu4vision.icg.tugraz.at/index.php?content=subsites/prost/prost.php.
38. 38)
  - 35. Zhou, Q.H., Lu, H.C., Yang, M.-H.: ‘Online multiple support instance tracking’. Proc. IEEE Conf. Automatic Face and Gesture Recognition, March 2011, pp. 545–552.
39. 39)
  - 42. Doucet, A., Freitas, N.de., Gordon, N.: ‘Sequential monte carlo methods in practice’ (Springer, 2001).
40. 40)
  - 6. Matthews, I., Ishikawa, T., Baker, S.: ‘The template update problem’, IEEE Trans. Pattern Anal. Mach. Intell., 2004, 26, (6), pp. 810–815 (doi: 10.1109/TPAMI.2004.16).
41. 41)
  - 27. Bai, T., Li, Y.F.: ‘Robust visual tracking with structured sparse representation appearance model’, Pattern Recognit., 2012, 45, (6), pp. 2390–2404 (doi: 10.1016/j.patcog.2011.12.004).
42. 42)
  - 44. Ross, D., Lim, J., Lin, R.S., Yang, M.-H.: ‘Incremental learning for robust visual tracking’, Int. J. Comput. Vis., 2008, 77, (1), pp. 125–141 (doi: 10.1007/s11263-007-0075-7).
43. 43)
  - 41. Chen, Y., Bi, J., Wang, J.Z.: ‘Miles: multiple-instance learning via embedded instance selection’, IEEE Trans. Pattern Anal. Mach. Intell., 2006, 28, (12), pp. 1931–1947 (doi: 10.1109/TPAMI.2006.248).
44. 44)
  - 16. Ning, J., Zhang, L., Zhang, D., Wu, C.: ‘Scale and orientation adaptive mean shift tracking’, IET Comput. Vis., 2012, 6, (1), pp. 52–61 (doi: 10.1049/iet-cvi.2010.0112).
45. 45)
  - 46. http://www.dabi.temple.edu/~hbling/code_data.htm.
46. 46)
  - 31. Collins, R.T., Liu, Y.: ‘On-line selection of discriminative tracking features’. Proc. IEEE Conf. on Computer Vision, June 2003, pp. 346–352.
47. 47)
  - 4. Babenko, B., Yang, M.-H., Belongie, S.: ‘Visual tracking with online multiple instance learning’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, June 2009, pp. 983–990.
48. 48)
  - 12. Collins, R.T., Liu, Y., Leordeanu, M.: ‘Online selection of discriminative tracking features’, IEEE Trans. Pattern Anal. Mach. Intell., 2005, 27, (10), pp. 1631–1643 (doi: 10.1109/TPAMI.2005.205).
49. 49)
  - 47. http://www.cs.toronto.edu/~dross/ivt/.
50. 50)
  - 1. Yilmaz, A., Javed, O., Shah, M.: ‘Object tracking: a survey’, ACM Comput. Surv., 2006, 38, (4), pp. 1–45 (doi: 10.1145/1177352.1177355).

Login

Not registered yet?

Share

Tools

Login to add to favourites

Key

Multiple instance learning tracking method with local sparse representation

References

Related content