Visual information fusion for object-based video image segmentation using unsupervised Bayesian online learning

Author(s): Z. Jia ; A. Balasuriya ; S. Challa
DOI: 10.1049/iet-ipr:20050346

For access to this article, please select a purchase option:

Buy article PDF

Buy Knowledge Pack

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership

Recommend Title Publication to library

IET Image Processing — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

Author(s): Z. Jia ¹ ; A. Balasuriya ² ; S. Challa ³
- Affiliations: 1: United Technologies Research Center, Shanghai, People's Republic of China
  2: Marine Robotics Laboratory, Massachusetts Institute of Technology, USA
  3: Faculty of Engineering, The University of Technology, Sydney, Australia
Source: Volume 1, Issue 2, June 2007, p. 168 – 181
DOI: 10.1049/iet-ipr:20050346 , Print ISSN 1751-9659, Online ISSN 1751-9667

An algorithm using the unsupervised Bayesian online learning process is proposed for the segmentation of object-based video images. The video image segmentation is solved using a classification method. First, different visual features (the spatial location, colour and optical-flow vectors) are fused in a probability framework for image pixel clustering. The appropriate modelling of the probability distribution function (PDF) for each feature-cluster is obtained through a Gaussian distribution. The image pixel is then assigned a cluster number in a maximum a posteriori probability framework. Different from the previous segmentation methods, the unsupervised Bayesian online learning algorithm has been developed to understand a cluster's PDF parameters through the image sequence. This online learning process uses the pixels of the previous clustered image and information from the feature-cluster to update the PDF parameters for segmentation of the current image. The unsupervised Bayesian online learning algorithm has shown satisfactory experimental results on different video sequences.

References

1. 1)
  - Sista, S., Kashyap, R.L.: `Bayesian estimation for multiscale image segmentation', Proc. 1999 IEEE Int. Conf. Acoustics, Speech, and Signal Processing, March 1999, Phoenix, AZ, USA, 6, p. 3493–3496.
2. 2)
  - Yang, M.H.: `Hand gesture recognition and face detection in image', 2002, PhD, University of Illinois at Urbana-Champagne.
3. 3)
  - Y. Wang , E. Adelson . Representing moving images with layers. IEEE Trans. Image Process. , 5
4. 4)
  - R.O. Duda , P.E. Hart , D.G. Stork . Pattern classification.
5. 5)
  - Ray, S., Turi, R.H.: `Determination of number of clusters in ', Proc. 4th Int. Conf. Advances in Pattern Recognition and Digital Techniques (ICAPRDT'99), December 1999, Calcutta, India, p. 137–143.
6. 6)
  - Csurka, G., Bouthemy, P.: `Direct identification of moving objects and background from 2D motion models', Proc. Int. Conf. Computer Vision, September 1999, Kerkyra, Corfu, Greece, 1, p. 566–571.
7. 7)
  - Jia, Z., Balasuriya, A.: `Motion based image segmentation with unsupervised Bayesian learning', Proc. IEEE Workshop Motion and Video Computing (WACV/MOTION'05), January 2005, CO, USA, 2, p. 2–7.
8. 8)
  - T. Mitchell . (1997) Machine learning.
9. 9)
  - Y. Altunbasak , P.E. Eren , A.M. Tekalp . Region based parametric motion segmentation using color information. Graph. Models Image Process. , 13 - 23
10. 10)
  - Khan, S., Shah, M.: `Object based segmentation of video using color, motion and spatial information', Proc. 2001 IEEE Computer Society Conf. Computer Vision and Pattern Recognition, December 2001, Kauai Marriott, HI, USA, 2, p. 746–751.
11. 11)
  - G.N. DeSouza , A.C. Kak . Vision for mobile robot navigation: a survey. IEEE Trans. Pattern Anal. Mach. Intell. , 2 , 237 - 267
12. 12)
  - J.Q. Chen , T.N. Pappas , A. Mojsilovic , B.E. Rogowitz . Adaptive perceptual color-texture image segmentation. IEEE Trans. Image Process. , 1524 - 1536
13. 13)
  - Jia, Z., Balasuriya, A., Challa, S.: `Visual information and camera motion fusion for 3D target tracking', Proc. 8th Int. Conf. Control, Automation, Robotics and Vision, December 2004, Kunming, China, p. 2296–2301.
14. 14)
  - L. Amsaleg , P. Gros . Content-based retrieval using local descriptors: problems and issues from a database perspective. Pattern Anal. Appl. , 108 - 124
15. 15)
  - M.M. Chang , A.M. Tekalp , M.I. Sezan . Simultaneous motion estimation and segmentation. IEEE Trans. Image Process , 9 , 1326 - 1333
16. 16)
  - P. Smith , T. Drummond , R. Cipolla . Layered motion segmentation and depth ordering by tracking edges. IEEE Trans. Pattern Anal. Mach. Intell. , 4 , 479 - 494
17. 17)
  - K. Li , X.D. Wu , D.Z. Chen , M. Sonka . Optimal surface segmentation in volumetric images – a graph-theoretic approach. IEEE Trans. Pattern Anal. Mach. Intell. , 119 - 134
18. 18)
  - Y. Keselman , S. Dickinson . Generic model abstraction from examples. IEEE Trans. Pattern Anal. Mach. Intell. , 7 , 1141 - 1156
19. 19)
  - Wang, Y., Tan, T.L., Loe, K.-F.: `Video segmentation based on graphical models', Proc. 2003 IEEE Computer Society Conf. Computer Vision and Pattern Recognition, June 2003, Madison, WI, USA, 2, p. 335–342.
20. 20)
  - A. Tremeau , P. Colantoni . Regions adjacency graph applied to color image segmentation. IEEE Trans. Image Process. , 4 , 735 - 744
21. 21)
  - H.Y. Liu , R. Chellappa , A. Rosenfeld . Accurate dense optical flow estimation using adaptive structure tensors and a parametric model. IEEE Trans. Image Process. , 10 , 1170 - 1180
22. 22)
  - D. Ross , R. Zemel . (2003) Multiple-cause vector quantization, Advances in neural information processing systems 15.
23. 23)
  - Li, M.K., Sethi, I.K., Li, D.G., Dimitrova, N.: `Region growing using online learning', Proc. Int. Conf. Imaging Science, Systems and Technology, CISST'03, June 2003, Las Vegas, NV, USA, p. 73–76.
24. 24)
  - Jojic, N., Frey, B.J.: `Learning flexible sprites in video layers', Proc. 2001 IEEE Computer Society Conf. Computer Vision and Pattern Recognition, December 2001, Kauai Marriott, HI, USA, 1, p. 199–206.
25. 25)
  - Chen, S.-C., Shyu, M.-L., Zhang, C.-C., Kashyap, R.L.: `Video scene change detection method using unsupervised segmentation and object tracking', Proc. 2001 IEEE Int. Conf. Multimedia and Expo, August 2001, p. 56–59.
26. 26)
  - Kashyap, R.L., Sista, S.: `Bayesian framework for unsupervised classification with application to target tracking', Proc. 1999 IEEE Int. Conf. Acoustics, Speech, and Signal Processing, March 1999, Phoenix, AZ, USA, 3, p. 1745–1748.
27. 27)
  - Bergen, L., Meyer, F.: `A novel approach to depth ordering in monocular image sequences', Proc. IEEE Computer Society Conf. Computer Vision and Pattern Recognition, June 2000, Hilton Head Island, SC, USA, 2, p. 536–541.
28. 28)
  - Kalitzin, S.N., Staal, J.J., Romeny, B.M.terH., Viergever, M.A.: `Image segmentation and object recognition by Bayesian grouping', Proc. 2000 IEEE Int. Conf. Image Processing, September 2000, Vancouver, BC, Canada, 3, p. 580–583.
29. 29)
  - Huang, S.S., Fu, L.C., Hsiao, P.Y.: `A region-level motion-based background modelling and subtraction using MRFs', Proc. 2005 IEEE Int. Conf. Robotics and Automation, April 2005, Barcelona, Spain, p. 2179–2184.

Visual information fusion for object-based video image segmentation using unsupervised Bayesian online learning

Visual information fusion for object-based video image segmentation using unsupervised Bayesian online learning

Buy article PDF

Buy Knowledge Pack

Thank you

References

Related content