Object detection and tracking is an important task within the ﬁeld of computer vision, because of its promising application in many areas, such as video surveillance. The need for automated video analysis has generated a great deal of interest in the area of motion tracking. A new technique is proposed for online object tracking-by-detection capable of achieving high detection and tracking rates, using a stationary camera, in a particle filtering framework. The fundamental innovation is that the detection technique integrates the local binary pattern texture feature, the red green blue (RGB) colour feature and the Sobel edge feature, using ‘Choquet’ fuzzy integral to avoid uncertainty in the classification. This is performed by extracting the colour and edge grey scale confidence maps and introducing the texture confidence map. Then, the tracking technique makes use of the continuous confidence detectors, extracted from those confidence maps, along with another three introduced classifier confidence maps, extracted from an online boosting classifier. Finally, both the confidence detectors and the classifier maps are integrated in the particle filtering framework, using the Choquet integral. Experimental results for both indoor and outdoor dataset sequences confirmed the robustness of the proposed technique against illumination variation and scene motion.

References

1. 1)
  - 25. Mei, X., Ling, H.: ‘Robust visual tracking using l1 minimization’. Proc. 12th Int. Conf. on Computer Vision, IEEE, Kyoto, 2009, pp. 1436–1443.
2. 2)
  - 2. Yao, J., Odobez, J.M.: ‘Multi-layer background subtraction based on color and texture’. Proc. Conf. on Computer Vision and Pattern Recognition (CVPR'07), Minneapolis, MN, 2007, pp. 1–8.
3. 3)
  - 36. El Baf, F., Bouwmans, T., Vachon, B.: ‘Foreground detection using the Choquet integral’. Proc. 9th Int. WIAMIS, IEEE, Klagenfurt, 2008, pp. 187–190.
4. 4)
  - 11. Ndiour, I.J., Vela, P.A.: ‘Towards a local Kalman filter for visual tracking’. Proc. Conf. on Decision and Control, IEEE, Shanghai, 2009, pp. 2420–2426.
5. 5)
  - 40. Stalder, S., Grabner, H., Gool, L.V.: ‘Beyond semi-supervised tracking: tracking should be as simple as detection, but not simpler than recognition’. Proc. 12th Int. Conf. on Computer Vision Workshop (ICCV), IEEE, Kyoto, 2009, pp. 1409–1416.
6. 6)
  - L. Li , W. Huang , I.Y.-H. Gu , Q. Tian . Statistical modeling of complex backgrounds for foreground object detection. IEEE Trans. Signal Process. , 11 , 1459 - 1472
7. 7)
  - 26. Kwon, J., Lee, K.: ‘Visual tracking decomposition’. Proc. Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE, San Francisco, CA, 2010, pp. 1269–1276.
8. 8)
  - 23. Yang, J.: ‘An improved particle filter algorithm for target tracking’. Proc. Int. Conf. on ICADE, IEEE, Beijing, 2012, pp. 103–107.
9. 9)
  - 1. Zhu, M., Zhang, C., Chen, Z.: ‘Biologically inspired particle filter for robust visual tracking’, Int. J. Inf. Process. Manage., 2012, 3, (1), pp. 50–60.
10. 10)
  - 18. Karaman, M., Goldmann, L., Yu, D., Sikora, T.: ‘Comparison of static background segmentation methods’. Proc. Visual Communications and Image Processing, SPIE, Beijing, China, 2005, pp. 2140–2151.
11. 11)
  - 17. Zhang, L., Li, Y., Nevatia, R.: ‘Global data association for multi-object tracking using network flows’. Proc. Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE, Anchorage, AK, 2008, pp. 1–8.
12. 12)
  - M. Isard , A. Blake . Condensation-conditional density propagation for visual tracking. Int. J. Comput. Vis. , 1 , 5 - 28
13. 13)
  - 37. El Baf, F., Bouwmans, T., Vachon, B.: ‘A fuzzy approach for background subtraction’. Proc. 15th Int. Conf. on Image Processing (ICIP), IEEE, San Diego, CA, 2008, pp. 2648–2651.
14. 14)
  - 3. Wang, Q., Chen, F., Xu, W., Yang, M.H.: ‘An experimental comparison of online object tracking algorithms’. Proc. SPIE Wavelets and Sparsity XIV, San Diego, CA, USA, 2011, pp. 81381A.
15. 15)
  - Z. Khan , T.R. Balch , F. Dellaert . MCMC-based particle filtering for tracking a variable number of interacting targets. IEEE Trans. Pattern Anal. Mach. Intell. , 11 , 1805 - 1918
16. 16)
  - 38. Toyama, K., Krumm, J., Brumitt, B., Meyers, B.: ‘Wallflower: principles and practice of background maintenance’. Proc. Seventh Int. Conf. on Computer Vision, IEEE, 1999, pp. 255–261.
17. 17)
  - 6. Zhong, W., Lu, H., Yang, M.: ‘Robust object tracking via sparsity-based collaborative model’. Proc. Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE, Providence, RI, 2012, pp. 1838–1845.
18. 18)
  - 42. Oza, N.C., Russell, S.: ‘Online bagging and boosting’. Proc. Int. Conf. on Systems, Man and Cybernetics, IEEE, 2005, pp. 2340–2345.
19. 19)
  - 28. Babenko, B., Yang, M.H., Belongie, S.: ‘Visual tracking with online multiple instance learning’. Proc. Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE, Miami, FL, 2009, pp. 983–990.
20. 20)
  - 15. Andriluka, M., Roth, S., Schiele, B.: ‘People-tracking-by-detection and people-detection-by-tracking’. Proc. Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE, Anchorage, AK, 2008, pp. 1–8.
21. 21)
  - 27. Grabner, H., Bischof, H.: ‘On-line boosting and vision’. Proc. Conf. on Computer Vision and Pattern Recognition, IEEE, 2006, pp. 260–267.
22. 22)
  - 8. Liang, K.H., Tjahjadi, T.: ‘Multiresolution segmentation of optical flow fields for object tracking’, Appl. Signal Process., 1998, 4, (3), pp. 179–187.
23. 23)
  - 14. Jin, L., Cheng, J., Huang, H.: ‘Human tracking in the complicated background by particle filter using color-histogram and HOG’. Proc. Int. Symp. on ISPACS, Chengdu, 2010, pp. 1–4.
24. 24)
  - 24. Adam, A., Rivlin, E., Shimshoni, I.: ‘Robust fragments-based tracking using the integral histogram’. Proc. Conf. on Computer Vision and Pattern Recognition, IEEE, June 2006, pp. 798–805.
25. 25)
  - 31. Santner, J., Leistner, C., Saffari, A., Pock, T., Bischof, H.: ‘PROST: parallel robust online simple tracking’. Proc. Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE, 2010, pp. 723–730.
26. 26)
  - 19. Jabri, S., Duric, Z., Wechsler, H., Rosenfeld, A.: ‘Detection and location of people in video images using adaptive fusion of color and edge information’. Proc. 15th Int. Conf. on Pattern Recognition, Barcelona, 2000, pp. 627–630.
27. 27)
  - 30. Liu, R., Cheng, J., Lu, H.: ‘A robust boosting tracker with minimum error bound in a co-training framework’. Proc. 12th Int. Conf. on Computer Vision, IEEE, Kyoto, 2009, pp. 1459–1466.
28. 28)
  - 39. Grabner, H., Leistner, C., Bischof, H.: ‘Semi-supervised on-line boosting for robust tracking’. Proc. 1th European Conf. on Computer Vision, Marseille, 2008, pp. 234–247.
29. 29)
  - 9. Stolkin, R., Florescu, I., Kamberov, G.: ‘An adaptive background model for CAMSHIFT tracking with a moving camera’. Proc. Sixth Int. Conf. on Advances in Pattern Recognition (ICAPR'07), Kolkata, 2007, pp. 147–151.
30. 30)
  - 13. Zhao, Y., Pei, H.: ‘Object tracking based on particle filter with discriminative features’, J. Control Theory Appl., 2013, 11, (1), pp. 42–53 (doi: 10.1007/s11768-013-1088-0).
31. 31)
  - 22. Rezaei, F., Khalaj, B.H.: ‘Human tracking-by-detection using adaptive particle filter based on HOG and color histogram’. Proc. Third Int. Conf. on CICIS, Zanjan, 2012.
32. 32)
  - 21. Klare, B., Sarkar, S.: ‘Background subtraction in varying illuminations using an ensemble based on an enlarged feature set’. Proc. Conf. on Computer Vision and Pattern Recognition Workshops (CVPR), IEEE, Miami, FL, 2009, pp. 66–73.
33. 33)
  - 43. ‘PETS 2006 Benchmark Data’,http://www.cvg.rdg.ac.uk/PETS2006/data.html.
34. 34)
  - P. Viola , M. Jones . Robust real-time face detection. Int. J. Comput. Vis. , 2 , 137 - 154
35. 35)
  - 32. Vermaak, J., Doucet, A., Perez, P.: ‘Maintaining multimodality through mixture tracking’. Proc. Ninth Int. Conf. on Computer Vision, IEEE, Nice, France, 2003, pp. 1110–1116.
36. 36)
  - 35. Lanz, O.: ‘Approximate Bayesian multibody tracking’, IEEE Trans. PAMI, 2006, 28, (9), pp. 1436–1449 (doi: 10.1109/TPAMI.2006.177).
37. 37)
  - M. Heikkila , M. Pietikainen . A texture-based method for modelling the background and detecting moving objects. IEEE Trans. Pattern Anal. Mach. Intell. , 657 - 662
38. 38)
  - 10. Cheng, Z.Q., Ma, Y.Z., Bu, J.: ‘Mean shifts identification model in bivariate process based on LSSVM pattern recognizer’, Int. J. Digit. Content Technol. Appl., 2010, 4, (3), pp. 154–170 (doi: 10.4156/jdcta.vol4.issue3.16).
39. 39)
  - 33. Schulz, D., Burgard, W., Fox, D., Cremers, A.B.: ‘Tracking multiple moving targets with a mobile robot using particle filters and statistical data association’. Proc. Int. Conf. on Robotics and Automation (ICRA), IEEE, 2001, pp. 1665–1670.
40. 40)
  - 7. Breitenstein, M.D., Reichlin, F., Leibe, B., Koller-Meier, E., Gool, L.V.: ‘Online multiperson tracking-by detection from a single, uncalibrated camera’, IEEE Trans. PAMI, 2011, 33, (9), pp. 1820–1833 (doi: 10.1109/TPAMI.2010.232).
41. 41)
  - C. Wren , A. Azarbayejani , T. Darrell , A. Pentland . Pfinder: real-time tracking of the human body. IEEE Trans. Pattern Anal. Mach. Intell. , 7 , 780 - 785
42. 42)
  - 29. Kalal, Z., Matas, J., Mikolajczyk, K.: ‘P-n learning: bootstrapping binary classifiers by structural constraints’. Proc. Conf. on Computer Vision and Pattern Recognition, IEEE, San Francisco, CA, 2010, pp. 49–56.
43. 43)
  - 16. Huang, C., Wu, B., Nevatia, R.: ‘Robust object tracking by hierarchical association of detection responses’. Proc. Tenth European Conf. on Computer Vision, Marseille, 2008, pp. 788–801.
44. 44)
  - 5. Wang, Z., Xu, H., Sun, L., Yang, S.: ‘Background subtraction in dynamic scenes with adaptive spatial fusing’. Proc. Int. Workshop on Multimedia Signal Processing, IEEE, Rio De Janeiro, 2009, pp. 1–6.

New technique for online object tracking-by-detection in video

References

Related content