Parallel algorithm implementation for multi-object tracking and surveillance

Mohamed Elbahri; Nasreddine Taleb; Kidiyo Kpalma; Joseph Ronsin

Parallel algorithm implementation for multi-object tracking and surveillance

View Fulltext

Author(s): Mohamed Elbahri ¹ ; Nasreddine Taleb ² ; Kidiyo Kpalma ³ ; Joseph Ronsin ³
- Affiliations: 1: Department of Computer Science, Djillali Liabes University, Sidi Bel-Abbes, Algeria ;
  2: RCAM Laboratory, Department of Electronics, Djillali Liabes University, Sidi Bel-Abbes, Algeria ;
  3: Département Image et Automatique, UEB INSA IETR, 35708 Rennes, France
Source: Volume 10, Issue 3, April 2016, p. 202 – 211
DOI: 10.1049/iet-cvi.2015.0115 , Print ISSN 1751-9632, Online ISSN 1751-9640

Received 24/04/2015, Accepted 27/08/2015, Revised 19/08/2015, Published 01/04/2016

A recently developed sparse representation algorithm, has been proved to be useful for multi-object tracking and this study is a proposal for developing its parallelisation. An online dictionary learning is used for object recognition. After detection, each moving object is represented by a descriptor containing its appearance features and its position feature. Any detected object is classified and indexed according to the sparse solution obtained by an orthogonal matching pursuit (OMP) algorithm. For a real-time tracking, the visual information needs to be processed very fast without reducing the results accuracy. However, both the large size of the descriptor and the growth of the dictionary after each detection, slow down the system process. In this work, a novel accelerating OMP algorithm implementation on a graphics processing unit is proposed. Experimental results demonstrate the efficiency of the parallel implementation of the used algorithm by significantly reducing the computation time.

References

1. 1)
  - 9. Efron, B., Hastie, T., Johnstone, I., Tibshirani, R.: ‘Least angle regression’, Ann. Statist. (With Discussion), 2004, 32, pp. 407–499 (doi: 10.1214/009053604000000067).
2. 2)
  - 15. Shen, Y., Miao, Z.: ‘Multi-human tracking from sparse detection responses’, IET Comput. Vis., 2012, 6, (6), pp. 590–602 (doi: 10.1049/iet-cvi.2011.0198).
3. 3)
  - 18. Wang, Q., Chen, F., Xu, W., et al: ‘Online discriminative object tracking with local sparse representation’. IEEE Workshop on Applications of Computer Vision (WACV), January 2012, pp. 425–432.
4. 4)
  - 41. Swirszcz, G., Abe, N., Lozano, A.C.: ‘Grouped orthogonal matching pursuit for variable selection and prediction’. Advances in Neural Information Processing Systems, 2009, pp. 1150–1158.
5. 5)
  - 22. Mei, X., Ling, H.: ‘Robust visual tracking and vehicle classification via sparse representation’, IEEE Trans. Pattern Anal. Mach. Intell., 2011, 33, (11), pp. 2259–2272 (doi: 10.1109/TPAMI.2011.66).
6. 6)
  - 26. Berclaz, J., Fleuret, F., Türetken, E., et al: ‘Multiple object tracking using k- shortest paths optimization’, IEEE Trans. Pattern Anal. Mach. Intell., 2011, 33, (9), pp. 1806–1819 (doi: 10.1109/TPAMI.2011.21).
7. 7)
  - 37. Breitenstein, M.D., Reichlin, F., Leibe, B., Koller-Meier, E., Gool, L.V.: ‘Online multi-person tracking-by-detection from a single, uncalibrated camera’, IEEE Trans. Pattern Anal. Mach. Intell., 2010, 33, (9), pp. 1820–1833 (doi: 10.1109/TPAMI.2010.232).
8. 8)
  - 3. Bercla, J., Fleuret, F., Fua, P.: ‘Robust people tracking with global trajectory optimization’. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, 2006, vol. 1, pp. 744–750.
9. 9)
  - 42. Lindholm, E., Nickolls, J., Oberman, S., et al: ‘NVIDIA Tesla: a unified graphics and computing architecture’, IEEE Micro, 2008, (2), pp. 39–55 (doi: 10.1109/MM.2008.31).
10. 10)
  - 25. Possegger, H., Mauthner, T., Roth, P.M., et al: ‘Occlusion geodesics for online multi-object tracking’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2014, pp. 1306–1313.
11. 11)
  - 5. Leibe, B., Schindler, K., Cornelis, N., et al: ‘Coupled object detection and tracking from static cameras and moving vehicles’, IEEE Trans. Pattern Anal. Mach. Intell., 2008, 30, (10), pp. 1683–1698 (doi: 10.1109/TPAMI.2008.170).
12. 12)
  - 35. Fang, Y., Chen, L., Wu, J., et al: ‘Gpu implementation of orthogonal matching pursuit for compressive sensing’. Parallel and Distributed Systems (ICPADS), December 2011, pp. 1044–1047.
13. 13)
  - 24. Lu, W., Bai, C., Kpalma, K., et al: ‘Multi-object tracking using sparse representation’. IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), May 2013, pp. 2312–2316.
14. 14)
  - 15. 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).
15. 15)
  - 37. Amato, A., Mozerov, M.G., Roca, F.X., et al: ‘Robust real-time background subtraction based on local neighborhood patterns’, EURASIP Adv. Signal Proc, 2010, 34, pp. 1–7.
16. 16)
  - 36. Dai, Y., He, D., Fang, Y., et al: ‘Accelerating 2D orthogonal matching pursuit algorithm on GPU’, J. Supercomput., 2014, 69, (3), pp. 1363–1381 (doi: 10.1007/s11227-014-1188-8).
17. 17)
  - 30. He, W., Yamashita, T., Lu, H., et al: ‘Surf tracking’. IEEE 12th Int. Conf. on Computer Vision, September 2009, pp. 1586–1592.
18. 18)
  - 19. Wang, L., Yan, H., Lv, K., et al: ‘Visual tracking via kernel sparse representation with multikernel fusion’, IEEE Trans. Circuits Syst. Video Technol., 2014, 24, (7), pp. 1132–1141 (doi: 10.1109/TCSVT.2014.2302496).
19. 19)
  - 27. Wu, Z., Zhang, J., Betke, M.: ‘Online motion agreement tracking’. Proc. BMVC, 2013.
20. 20)
  - 38. Babu, J.J.J., Sudha, G.F.: ‘Non-subsampled contourlet transform based image denoising in ultrasound thyroid images using adaptive binary morphological operations’, IET Comput. Vis., 2014, 8, (6), pp. 718–728 (doi: 10.1049/iet-cvi.2014.0008).
21. 21)
  - 11. Yan, Q., Li, L.: ‘Kernel sparse tracking with compressive sensing’, IET Comput. Vis., 2014, 8, (4), pp. 305–315 (doi: 10.1049/iet-cvi.2013.0095).
22. 22)
  - 20. Lowe, D.G.: ‘Distinctive image features from scale-invariant keypoints’, Int. J. Comput. Vis., 2004, 60, pp. 91–110 (doi: 10.1023/B:VISI.0000029664.99615.94).
23. 23)
  - 17. Han, Z., Jiao, J., Zhang, B., et al: ‘Visual object tracking via sample-based Adaptive Sparse Representation (AdaSR)’, Pattern Recogn., 2011, 44, (9), pp. 2170–2183 (doi: 10.1016/j.patcog.2011.03.002).
24. 24)
  - 1. Huo, F., Hendriks, E.A.: ‘Multiple people tracking and pose estimation with occlusion estimation’, Comput. Vis. Image Underst., 2012, 116, pp. 634–647 (doi: 10.1016/j.cviu.2011.12.006).
25. 25)
  - 16. Bao, C., Wu, Y., Ling, H., et al: ‘Real time robust l1 tracker using accelerated proximal gradient approach’. , IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2012, pp. 1830–1837.
26. 26)
  - 22. Aharon, M., Elad, M., Bruckstein, A.: ‘K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation’, IEEE Trans. Signal Process., 2006, 54, pp. 4311–4322 (doi: 10.1109/TSP.2006.881199).
27. 27)
  - 28. Guo, Y., Chen, Y., Tang, F., et al: ‘Object tracking using learned feature manifolds’, Comput. Vis. Image Underst., 2014, 118, pp. 128–139 (doi: 10.1016/j.cviu.2013.09.007).
28. 28)
  - 33. Abramov, A., Pauwels, K., Papon, J., et al: ‘Real-time segmentation of stereo videos on a portable system with a mobile gpu’, IEEE Trans. Circuits Syst. Video Technol., 2012, 22, (9), pp. 1292–1305 (doi: 10.1109/TCSVT.2012.2199389).
29. 29)
  - 20. Pati, Y.C., Rezaiifar, R., Krishnaprasad, P.S.: ‘Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition’, Signals Syst. Comput., Conf. Record of The Twenty-Seventh Asilomar Conf. on IEEE, November 1993, pp. 40–44 (doi: 10.1109/ACSSC.1993.342465).
30. 30)
  - 14. Shao, J., Dong, N., Tong, M.: ‘Multi-part sparse representation in random crowded scenes tracking’, Pattern Recogn. Lett., 2013, 34, (7), pp. 780–788 (doi: 10.1016/j.patrec.2012.07.008).
31. 31)
  - 40. Cai, T.T., Wang, L.: ‘Orthogonal matching pursuit for sparse signal recovery with noise’, IEEE Trans. Inf. Theory, 2011, 57, (7), pp. 4680–4688 (doi: 10.1109/TIT.2011.2146090).
32. 32)
  - 21. Zhou, H., Yuan, Y., Shi, C.: ‘Object tracking using SIFT features and mean shift’, Comput. Vis. Image Understand., 2009, 113, (3), pp. 345–352 (doi: 10.1016/j.cviu.2008.08.006).
33. 33)
  - 46. Bernardin, K., Stiefelhagen, R.: ‘Evaluating multiple object tracking performance: the CLEAR MOT metrics’, J. Image Video Process., 2008, 1, pp. 1–10 (doi: 10.1155/2008/246309).
34. 34)
  - 4. Huang, C., Wu, B., Nevatia, R.: ‘Robust object tracking by hierarchical association of detection responses’, Proc. European Conf. ‘Computer Vision–ECCV’, 2008, (Springer, Berlin Heidelberg), pp. 788–801.
35. 35)
  - 37. Chen, S.S., Donoho, D.L., Saunders, M.A.: ‘Atomic decomposition by basis pursuit’, SIAMJ. Sci. Comput., 1999, 20, pp. 33–61 (doi: 10.1137/S1064827596304010).
36. 36)
  - 8. Ben Shitrit, H., Berclaz, J., Fleuret, F., et al: ‘Tracking multiple people under global appearance constraints’. IEE Int. Conf. on Computer Vision (ICCV), November 2011, pp. 137–144.
37. 37)
  - 13. Xie, C., Tan, J., Chen, P., et al: ‘Multiple instance learning tracking method with local sparse representation’, IET Comput. Vis., 2013, 7, (5), pp. 320–334 (doi: 10.1049/iet-cvi.2012.0228).
38. 38)
  - 6. Chen, X., Qin, Z., An, L., et al: ‘An online learned elementary grouping model for multi-target tracking’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2014, pp. 1242–1249.
39. 39)
  - 44. Ferryman, J., Ellis, A.L.: ‘Performance evaluation of crowd image analysis using the PETS2009 dataset’, Pattern Recogn. Lett., 2014, 44, pp. 3–15 (doi: 10.1016/j.patrec.2014.01.005).
40. 40)
  - 2. Andriluka, M., Roth, S., Schiele, B.: ‘People-tracking-by-detection and people-detection-by-tracking’. IEEE Conf. on CVPR, 2008, pp. 1–8.
41. 41)
  - 45. Our results: https://www.youtube.com/watch?v=8WX2Rvn36mQ.
42. 42)
  - 43. PETS 2009 Benchmark Data ‘http://cs.binghamton.edu/~mrldata/pets2009’.
43. 43)
  - 6. Bay, H., Ess, A., Tuytelaars, T., et al: ‘SURF: Speeded up robust features’, Comput. Vis. Image Underst., 2008, 110, (3), pp. 346–359 (doi: 10.1016/j.cviu.2007.09.014).
44. 44)
  - 24. Mallat, S., Zhang, Z.: ‘Matching pursuit in a time frequency dictionary’, IEEE Trans. Signal Process., 1993, 41, (12), pp. 3397–3415 (doi: 10.1109/78.258082).
45. 45)
  - 36. 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).
46. 46)
  - 34. Chiang, C.K., Wang, S.F., Chen, Y.L., et al: ‘Fast JND-based video carving with GPU acceleration for real-time video retargeting’, IEEE Trans. Circuits Syst. Video Technol., 2009, 19, (11), pp. 1588–1597 (doi: 10.1109/TCSVT.2009.2031462).

Login

Not registered yet?

Share

Tools

Login to add to favourites

Key

Parallel algorithm implementation for multi-object tracking and surveillance

References

Related content