Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon openaccess Variational Bayesian learning for background subtraction based on local fusion feature

This is an open access article published by the IET under the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0/)
Received 10/03/2016, Accepted 15/06/2016, Revised 15/05/2016, Published 23/06/2016

To resist the adverse effect of shadow interference, illumination changes, indigent texture and scenario jitter in object detection and improve performance, a background modelling method based on local fusion feature and variational Bayesian learning is proposed. First, U-LBSP (uniform-local binary similarity patterns) texture feature, lab colour and location feature are used to construct local fusion feature. U-LBSP is modified from local binary patterns in order to reduce computational complexity and better resist the influence of shadow and illumination changes. Joint colour and location feature are introduced to deal with the problem of indigent texture and scenario jitter. Then, LFGMM (Gaussian mixture model based on local fusion feature) is updated and learned by variational Bayes. In order to adapt to dynamic changing scenarios, the variational expectation maximisation algorithm is applied for distribution parameters optimisation. In this way, the optimal number of Gaussian components as well as their parameters can be automatically estimated with less time expended. Experimental results show that the authors’ method achieves outstanding detection performance especially under conditions of shadow disturbances, illumination changes, indigent texture and scenario jitter. Strong robustness and high accuracy have been achieved.

Inspec keywords: image texture; optimisation; image fusion; expectation-maximisation algorithm; computational complexity; object detection; learning (artificial intelligence); image colour analysis; jitter; Bayes methods; variational techniques

Other keywords: U-LBSP texture feature; background subtraction; variational Bayesian learning; illumination changes; object detection; LFGMM; distribution parameter optimisation; indigent texture; lab colour; shadow interference effect; location feature; Gaussian components; variational expectation maximisation algorithm; shadow disturbances; Gaussian mixture model based on local fusion feature; scenario jitter; computational complexity; background modelling method; uniform-local binary similarity pattern texture feature

Subjects: Other topics in statistics; Computational complexity; Optimisation techniques; Optimisation techniques; Optical, image and video signal processing; Computer vision and image processing techniques; Sensor fusion; Knowledge engineering techniques; Other topics in statistics

References

    1. 1)
      • 16. Shen, Y., Cornford, D., Opper, M., et al: ‘Variational Markov chain Monte Carlo for Bayesian smoothing of non-linear diffusions’, Comput. Stat., 2012, 27, (1), pp. 149–176.
    2. 2)
      • 7. Li, L., Huang, W., Gu, I.Y.H., et al: ‘Statistical modeling of complex backgrounds for foreground object detection’, IEEE Trans. Image Process., 2004, 13, (11), pp. 1459–1472.
    3. 3)
      • 22. ‘CDNET: A video database for testing change detection algorithms’. Available at http://www.changedetection.net, accessed 22 April 2016.
    4. 4)
      • 19. Attias, H.: ‘A variational Bayesian framework for graphical models’, Adv. Neural Inf. Process. Syst., 2000, 12, pp. 209–215.
    5. 5)
      • 1. Piccardi, M.: ‘Background subtraction techniques: a review’. IEEE Int. Conf. on Systems, Man and Cybernetics, Holland, Netherlands, October 2004, pp. 3099–3104.
    6. 6)
      • 18. Covoes, T.F., Hruschka, E.R.: ‘Unsupervised learning of Gaussian mixture models: evolutionary create and eliminate for expectation maximization algorithm’. IEEE Congress on Evolutionary Computation, Cancun, Mexico, June 2013, pp. 3206–3213.
    7. 7)
      • 15. Gorur, D., Rasmussen, C.E.: ‘Dirichlet process Gaussian mixture models: choice of the base distribution’, J. Comput. Sci. Technol., 2010, 25, (4), pp. 653–664.
    8. 8)
      • 5. Hernandez-Lopez, J.J., Quintanilla-Olvera, A.L., Lopez-Ramirez, J.L., et al: ‘Detecting objects using color and depth segmentation with Kinect sensor’, Procedia Technol., 2012, 3, (1), pp. 196–204.
    9. 9)
      • 17. Guo, C., Fu, H., Luk, W.: ‘A fully-pipelined expectation-maximization engine for Gaussian mixture models’. Proc. Int. Conf. on Field-Programmable Technology (FPT), Seoul, South Korea, December 2012, vol. 45, pp. 182–189.
    10. 10)
      • 13. Ari, C., Aksoy, S.: ‘Maximum likelihood estimation of Gaussian mixture models using particle swarm optimization’. Proc. 20th Int. conf. on Pattern Recognition, Istanbul, Turkey, August 2010, pp. 746–749.
    11. 11)
      • 21. Wang, Y., Jodoin, P.M., Porikli, F., et al: ‘CDnet 2014: an expanded change detection benchmark dataset’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition Workshops (CVPRW), Columbus, Ohio, USA, June 2014, pp. 393–400.
    12. 12)
      • 3. Oliver, A., Llado, X., Freixenet, J., et al: ‘False positive reduction in mammographic mass detection using local binary patterns’. Medical Image Computing and Computer-Assisted Intervention (MICCAI), Brisbane, Australia, 2007, pp. 286–293.
    13. 13)
      • 2. Heikkila, M., Pietikainen, M.: ‘A texture-based method for modeling the background and detecting moving objects’, IEEE Trans. PAMI, 2006, 28, (4), pp. 657–662.
    14. 14)
      • 4. Stcharles, P.L., Bilodeau, G.A.: ‘Improving background subtraction using local binary similarity patterns’. IEEE Winter Conf. on Applications of Computer Vision (WACV), Steamboat Springs, Co., USA, March 2014, pp. 509–515.
    15. 15)
      • 9. Bianco, S., Ciocca, G., Schettini, R.: ‘How far can you get by combining change detection algorithms?’, arXiv preprint, 2015, arXiv: 1505.02921.
    16. 16)
      • 14. Çaglar, A., Aksoy, S., Arikan, O.: ‘Maximum likelihood estimation of Gaussian mixture models using stochastic search’, Pattern Recognit., 2012, 45, (45), pp. 2804–2816.
    17. 17)
      • 20. Boyd, S., Vandenberghe, L.: ‘Convex optimization’, IEEE Trans. Autom. Control, 2006, 51, (11), pp. 1859–1859.
    18. 18)
      • 6. Wang, B., Liu, Y., Xu, W., et al: ‘Background subtraction using spatiotemporal condition information’, Opt.-Int. J. Light Electron. Opt., 2014, 125, (3), pp. 1406–1411.
    19. 19)
      • 8. Mikic, I., Cosman, P.C., Kogut, G.T., et al: ‘Moving shadow and object detection in traffic scenes’. Proc. 15th Int. Conf. on Pattern Recognition, Barcelona, Spain, September 2000, vol. 1, pp. 321–324.
    20. 20)
      • 11. Stauffer, C., Grimson, W.E.L.: ‘Adaptive background mixture models for real-time tracking’. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition (CVPR), Fort Collins, CO, USA, June 1999, vol. 2.
    21. 21)
      • 12. Zivkovic, Z.: ‘Improved adaptive Gaussian mixture model for background subtraction’. Proc. 17th Int. Conf. on Pattern Recognition, Cambridge, UK, August 2004, vol. 2, pp. 28–31.
    22. 22)
      • 10. Wang, R., Bunyak, F., Seetharaman, G., et al: ‘Static and moving object detection using flux tensor with split Gaussian models’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition Workshops (CVPRW), Columbus, Ohio, USA, June 2014, pp. 420–424.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2016.0075
Loading

Related content

content/journals/10.1049/iet-cvi.2016.0075
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address