DOI QR코드

DOI QR Code

Moving Object Detection Using Sparse Approximation and Sparse Coding Migration

  • Li, Shufang (School of Information and Engineering, Yanshan University) ;
  • Hu, Zhengping (School of Information and Engineering, Yanshan University) ;
  • Zhao, Mengyao (School of Information and Engineering, Yanshan University)
  • Received : 2019.07.26
  • Accepted : 2020.02.13
  • Published : 2020.05.31

Abstract

In order to meet the requirements of background change, illumination variation, moving shadow interference and high accuracy in object detection of moving camera, and strive for real-time and high efficiency, this paper presents an object detection algorithm based on sparse approximation recursion and sparse coding migration in subspace. First, low-rank sparse decomposition is used to reduce the dimension of the data. Combining with dictionary sparse representation, the computational model is established by the recursive formula of sparse approximation with the video sequences taken as subspace sets. And the moving object is calculated by the background difference method, which effectively reduces the computational complexity and running time. According to the idea of sparse coding migration, the above operations are carried out in the down-sampling space to further reduce the requirements of computational complexity and memory storage, and this will be adapt to multi-scale target objects and overcome the impact of large anomaly areas. Finally, experiments are carried out on VDAO datasets containing 59 sets of videos. The experimental results show that the algorithm can detect moving object effectively in the moving camera with uniform speed, not only in terms of low computational complexity but also in terms of low storage requirements, so that our proposed algorithm is suitable for detection systems with high real-time requirements.

References

  1. E. Bilgazyev, B. Efraty, S. Shah and I.A. Kakadiaris, "Sparse representation-based super resolution for face recognition at a distance," in Proc. of 22nd British Machine Vision Conf., pp.1-11, August 29 - September 2, 2011.
  2. Y. Liu, Q. Zhang, J. Han and L. Wang, "Salient object detection employing robust sparse representation and local consistency," Image and Vision Computing, vol. 69, pp. 155-167, January, 2018. https://doi.org/10.1016/j.imavis.2017.10.002
  3. Z. Cong, X. G. Wang and K. C. Wai, "Background subtraction via robust dictionary learning," EURASIP Journal on Image and Video Processing, vol. 1, pp. 1-12, January, 2011.
  4. N. Oliver, B. Rosario and A. Pentland, "A bayesian computer vision system for modeling human interactions," IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 831-843, August, 2000. https://doi.org/10.1109/34.868684
  5. S. Javed, S. K. Jung, A. Mahmood and T. Bouwmans, "Motion-aware graph regularized RPCA for background modeling of complex scenes," in Proc. of 23rd Int. Conf. on Pattern Recognition, pp. 120-125, December 4-8, 2016.
  6. W. Hu, Y. Yang, W. Zhang and Y. Xie, "Moving object detection using tensor-based low-rank and saliently fused-sparse decomposition," IEEE Transactions on Image Processing, vol. 26, no. 2, pp.724-737, February, 2017. https://doi.org/10.1109/TIP.2016.2627803
  7. L. Thomaz, E. Jardim, A. da Silva, E. da Silva, S. Netto and H. Krim, "Anomaly detection in moving-camera video sequences using principal subspace analysis," IEEE Transactions on Circuits and Systems I: Regular Papers, vol. 65, no. 3, pp. 1003-1015, March, 2018.
  8. X. Qin, G. Yuan, C. Li and X. Zhang, "An approach to fast and robust detecting of moving target in video sequences," Acta Electronica Sinica, vol. 45, no. 10, pp. 2355-2361, October, 2017.
  9. H. K. Galoogahi, A. Fagg, C. Huang, D. Ramanan and S. Lucey, "Need for speed: a benchmark for higher frame rate object tracking," in Proc. of IEEE Int. Conf. on Computer Vision, pp. 1134-1143, October 22-29, 2017.
  10. G. H. F. de Carvalho, L. A. Thomaz, A. F. da Silva, E. A. B. da Silva and S. L. Netto, "Anomaly detection with a moving camera using multiscale video analysis," Multidimensional Systems and Signal Processing, vol. 30, no. 1, pp. 311-342, January, 2019. https://doi.org/10.1007/s11045-018-0558-4
  11. H. Kong, J. Audibert and J. Ponce, "Detecting abandoned objects with a moving camera," IEEE Transactions on Image Processing, vol. 19, no. 8, pp. 2201-2210, August, 2010. https://doi.org/10.1109/TIP.2010.2045714
  12. H. Mukojima, D. Deguchi, Y. Kawanish, I. Ide, H. Murase, M. Ukai, N. Nagamine and R. Nakasone, "Moving camera background-subtraction for obstacle detection on railway tracks," in Proc. of 23rd IEEE Int. Conf. on Image Processing, pp. 3967-3971, September 25-28, 2016.
  13. Y. Zhou and S. Maskell, "Moving object detection using background subtraction for a moving camera with pronounced parallax," in Proc. of 2017 Symposium on Sensor Data Fusion: Trends, Solutions, Applications, pp.1-6, October 10-12, 2017.
  14. L.Gong, M.Yu and T.Gordon, "Online codebook modelling based background subtraction with a moving camera," in Proc. of 3rd Int. Conf. on Frontiers of Signal Processing, pp. 136-140, September 6-8, 2017.
  15. J. C. Yang, J. Wright, T. Huang and Y. Ma, "Image super-resolution as sparse representation of raw image patches," in Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, pp.1-8, June 24-26, 2008.
  16. D. L. Donoho and X. M. Huo, "Uncertainty principles and ideal atomic decomposition," IEEE Transaction on Information Theory, vol.47, no.7, pp. 2845-2862, 2001. https://doi.org/10.1109/18.959265
  17. M. T. Nakahata, L. A. Thomaz, A. F. da Silva, E. A. B. da Silva and S. L. Netto, "Anomaly detection with a moving camera using spatio-temporal codebooks," IEEE Transactions on Circuits and Systems I: Regular Papers, vol. 65, no. 3, pp. 1003-1015, 2018.
  18. H. X. Li, C. H. Shen and Q. F. Shi, "Real-time visual tracking using compressive sensing," in Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, pp. 1305-1312, June 20-25, 2011.
  19. X. Zhou, C. Yang and W. Yu, "Moving object detection by detecting contiguous outliers in the low-rank representation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 3, pp. 597-610, march, 2013. https://doi.org/10.1109/TPAMI.2012.132
  20. X. Bian and H. Krim, "Bi-sparsity pursuit for robust subspace recovery," in Proc. of IEEE Int. Conf. on Image Processing, pp. 3535-3539, September 27-30, 2015.
  21. E. Jardim, X. Bian, E. A. B. da Silva, S. L. Netto and H. Krim, "On the detection of abandoned objects with a moving camera using robust subspace recovery and sparse representation," in Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Process, pp. 1295-1299, April 19-24, 2015.
  22. L. A. Thomaz, A. F. da Silva, E. A. B. da Silva, S. L. Netto and H. Krim, "Detection of abandoned objects using robust subspace recovery with intrinsic video alignment," in Proc. of IEEE Int. Conf. Symposium on Circuits and Systems, pp. 1-4, May 28-31, 2017.
  23. J. Yang, J. Wright, T. S. Huang and Y. Ma, "Image super-resolution via sparse representation," IEEE Transactions on Image Processing, vol. 19, no. 11, pp. 2861-2873, November, 2010. https://doi.org/10.1109/TIP.2010.2050625
  24. VDAO, "Video database of abandoned objects in a cluttered industrial environment," 2016. [Online] http://www.smt.ufrj.br/-tvdigital/database/objects.