Context-based global multi-class semantic image segmentation by wireless multimedia sensor networks

详细信息    查看全文

• 作者：Chen Wei (1) (2)
  Xiaorong Jiang (1)
  Zhibo Tang (1)
  Wang Qian (3)
  Na Fan (4)
  
  1. College of Computer Science and Technology ; China University of Mining and Technology ; Xuzhou ; 221116 ; Jiangsu ; China
  2. State Key Laboratory of Coal Resources and Safe Mining ; China University of Mining and Technology ; Xuzhou ; 221116 ; Jiangsu ; China
  3. Information Science and Engineering Department ; Southeast University ; Nanjing ; 210096 ; Jiangsu ; China
  4. Eduasean Consulting Co. Ltd. ; 238 Shinmunro Bldg. ; Shinmunro-1ga ; Jongno-gu ; Seoul ; 110820 ; Korea
  
• 关键词：Context ; based ; Multi ; class ; Segmentation
• 刊名：Artificial Intelligence Review
• 出版年：2015
• 出版时间：April 2015
• 年：2015
• 卷：43
• 期：4
• 页码：579-591
• 全文大小：1,053 KB
• 参考文献：1. Boros, E, Hammer, PL (2002) Pseudo-Boolean optimization. Discret Appl Math 123: pp. 155-225 CrossRef
  2. Boros E, Hammer PL, Sun X (May 1991) Network flows and minimization of quadratic pseudo-Boolean functions. Technical Report RRR 17鈥?991, RUTCOR Research Report
  3. Boros E, Hammer PL, Tavares G (April 2006) Preprocessing of unconstrained quadratic binary optimization. Technical Report RRR 10鈥?006, RUTCOR Research Report
  4. Boykov, Y, Veksler, O, Zabih, R (2001) Fast approximate energy minimization via graph cuts. IEEE TPAMI 23: pp. 1222-1239 CrossRef
  5. Boykov, Y, Kolmogorov, V (2004) An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. IEEE TPAMI 26: pp. 1124-1137 CrossRef
  6. Boykov Y, Jolly MP (2001) Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images. In ICCV
  7. Delong A, Boykov Y (2009) Globally optimal segmentation of multi-region objects. In ICCV
  8. Desai C, Ramanan D, Fowlkes C (2009) Discriminative models for multi-class object layout. In ICCV
  9. Fulkerson B, Vedaldi A, Soatto S (2009) Class segmentation and object localization with superpixel neighborhoods. In ICCV
  10. Galleguillos C, Rabinovich A, Belongie S (2008) Object categorization using co-occurrence, location and appearance. In CVPR
  11. Gould, S, Rodgers, J, Cohen, D, Elidan, G, Koller, D (2008) Multi-class segmentation with relative location prior. IJCV 80: pp. 300-316 CrossRef
  12. He X, Zemel RS, Carreira-Perpinnan MA (2004) Multiscale conditional random fields for image labeling. In CVPR
  13. He X, Zemel RS, Ray D (2006) Learning and incorporating top-down cues in image segmentation. In ECCV
  14. Hoiem D, Efros AA, Hebert M (2006) Putting objects in perspective. In CVPR
  15. Ishikawa, H (2003) Exact optimization for Markov random fields with convex priors. IEEE TPAMI 25: pp. 1333-1336 CrossRef
  16. Kohli P, Ladicky L, Torr PHS (2008) Robust higher order potentials for enforcing label consistency. In CVPR
  17. Kolmogorov, V, Zabih, R (2004) What energy functions can be minimized via graph cuts. IEEE TPAMI 26: pp. 65-81 CrossRef
  18. Kolmogorov, V, Rother, C (2007) Minimizing non-submodular functions with graph cuts鈥揳 review. IEEE TPAMI 28: pp. 1274-1279 CrossRef
  19. Kumar S, Hebert M (2005) A hierarchical field framework for unified context-based classification. In ICCV
  20. Ladicky L, Russell C, Kohli P (2009) Associative hierarchical CRFs for object class image segmentation. In ICCV
  21. Li Y, Huttenlocher DP (2008) Sparse long-range random field and its application to image denoising. In ECCV
  22. Long YJ, Huang YZ (2006) Image based source camera identification using demosaicking. IEEE 8th workshop on multimedia signal processing, pp 419鈥?24
  23. Rabinovich A, Vedaldi A, Galleguillos C, Wiewiora E, Belongie S (2007) Objects in context. In ICCV
  24. Ramalingam S, Kohli P, Alahari K, Torr PHS (2008) Exact inference in multi-label CRFs with higher order cliques. In CVPR
  25. Rother C, Kohli P, Feng W, Jia J (2009) Minimizing sparse higher order energy functions of discrete variables. In CVPR
  26. Rother C, Kolmogorov V, Lempitsky V, Szummer M (2007) Optimizing binary MRFs via extended roof duality. In CVPR
  27. Schroff F, Criminisi A, Zisserman A (2008) Object class segmentation using random forests. In BMVC
  28. Shotton, J, Winn, J, Rother, C, Criminisi, A (2009) Textonboost for image understanding: multi-class object recognition and segmentation by jointly modeling texture, layout, and context. IJCV 81: pp. 2-23 CrossRef
  29. Torralba, A (2003) Contextual priming for object detection. IJCV 53: pp. 169-191 CrossRef
  30. Torralba A, Murphy KP, Freeman WT (2004) Sharing features: efficient boosting procedures for multiclass object detection. In CVPR
  31. Verbeek J, Triggs B (2007) Region classification with Markov field aspect models. In CVPR
  32. Verbeek J, Triggs B (2007) Scene segmentation with CRFs learned from partially labeled images. In NIPS
  33. Winn J, Criminisi A, Minka T (2005) Object categorization by learned universal visual dictionary. In ICCV
  34. Yang L, Meer P, Foran DJ (2007) Multiple class segmentation using a unified framework over mean-shift patches. In CVPR
  
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Science, general
  Complexity
  
• 出版者：Springer Netherlands
• ISSN：1573-7462

文摘

Using context to aid object detection is becoming more popular among computer vision researchers. Our physical world is structured, and our perception as human beings does not neglect contextual information. In this paper, we propose a framework that is able to simultaneously detect and segment objects of different classes under context. Context is incorporated into our model as long-range pairwise interactions between pixels, which impose a prior on the labeling. Long-range interactions have seen seldom use in the computer vision literature, and we show how to use them to encode contextual information in our segmentation. Our framework formulates the multi-class image segmentation task as an energy minimization problem and finds a globally optimal solution under certain conditions using a single graph cut. We experimentally evaluate performance of our model on two publicly available datasets: the MSRC-1 and the CorelB datasets. Our results show the applicability of our model to the multi-class segmentation problem.