Urban scene recognition by graphical model and 3D geometry

doi:10.1016/S1005-8885(10)60072-6

Acta Metallurgica Sinica(English letters) ›› 2011, Vol. 18 ›› Issue (3): 110-119.doi: 10.1016/S1005-8885(10)60072-6

Urban scene recognition by graphical model and 3D geometry

任柯燕¹,孙汉旭²,贾庆轩³,Weiyu Zhang⁴

1. 北京邮电大学自动化学院
2.
3. Automation school,bupt
4. University of Pennsylvania

收稿日期:2010-10-11 修回日期:2011-02-25 出版日期:2011-06-30 发布日期:2011-06-13
通讯作者: 任柯燕 E-mail:aizi625@qq.com
基金资助:
This work was supported by the National Natural Science Foundation of China (60803103), Research Found For Doctoral Program of Higher Education of China (200800131026), Fundamental Research Funds for the Central Universities (2009RC0603, 2009RC0601).

Urban scene recognition by graphical model and 3D geometry

Received:2010-10-11 Revised:2011-02-25 Online:2011-06-30 Published:2011-06-13
Supported by:
This work was supported by the National Natural Science Foundation of China (60803103), Research Found For Doctoral Program of Higher Education of China (200800131026), Fundamental Research Funds for the Central Universities (2009RC0603, 2009RC0601).

摘要/Abstract

摘要：

This paper proposes a simple and discriminative framework, using graphical model and 3D geometry to understand the diversity of urban scenes with varying viewpoints. Our algorithm constructs a conditional random field (CRF) network using over-segmented superpixels and learns the appearance model from different set of features for specific classes of our interest. Also, we introduce a training algorithm to learn a model for edge potential among these superpixel areas based on their feature difference. The proposed algorithm gives competitive and visually pleasing results for urban scene segmentation. We show the inference from our trained network improves the class labeling performance compared to the result when using the appearance model solely.

关键词:

scene recognition, CRF, graphical model, 3D geometry

Abstract:

Key words:

scene recognition, CRF, graphical model, 3D geometry

参考文献

1. Liu C, Yuen J, Torralba A. Nonparametric scene parsing: label transfer via dense scene alignment. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR’09), Jun 20-25, 2009, Miami, FL, USA. Los Alamitos, CA, USA: IEEE Computer Society, 2009: 1972-1979

2. Oliva A, Torralba A B. Modeling the shape of the scene: a holistic representation of the spatial envelope. International Journal of Computer Vision, 2001, 42(3): 145-175

3. Barrow H G, Tenebaum J M. Recovering intrinsec scene characteristics from images. Computer Vision Systems. Proceedings of the Workshop on Computer Vision Systems, Jun 1-3, 1977, Amherst, MA USA. New York, NY, USA : Academic Press, 1978: 3-26.

4. Henderson J M, Hollingworth A. High level scene perception. Annual Review of Psychology, 1999, 50(1): 243-271

5. Russell B C, Torralba A, Liu C, et al. Object recognition by scene alignment. Advances in Neural Information Processing Systems. Proceedings of the 21st Annual Conference on Neural Information Processing Systems (NIPS’07), Dec 7-8, 2007, Vancouver, Canada. Cambridge, MA, USA: MIT Press, 2007

6. Carbonetto P, De Freitas N, Barnard K. A statistical model for general contextual object recognition. Proceedings of the 8th European Conference on Computer Vision (ECCV’04), May 11-14, 2004, Prague, Czech. LNCS 3021. Berlin, Germany: Springer-Verlag, 2004: 350-362.

7. Winn J, Shotton J. The layout consistent random field for recognizing and segmenting partially occluded objects. Proceedings of the 2006 IEEE Conference on Computer Vision and Pattern Recognition (CVPR’06), Jun 17-22, 2006, Washington, DC, USA. Los Alamitos, CA, USA: IEEE Computer Society, 2006: 37-44

8. Yang L, Meer P, Foran D J. Multiple class segmentation using a unified framework over mean-shift patches. Proceedings of the 2007 IEEE Conference on Computer Vision and Pattern Recognition (CVPR’07), Jun 17-22, 2007, Minneapolis, MN, USA. Los Alamitos, CA, USA: IEEE Computer Society, 2007: 8p

9. Savarese S, Winn J, Criminisi A. Discriminative object class models of appearance and shape by correlatons. Proceedings of the 2006 IEEE Conference on Computer Vision and Pattern Recognition (CVPR’06), Jun 17-22, 2006, Washington, DC, USA. Los Alamitos, CA, USA: IEEE Computer Society, 2006: 2033-2040

10. Shotton J, Winn J, Rother C, et al. TextonBoost: joint appearance, shape and context modeling for multi-class object recognition and segmentation. Proceedings of the 9th European Conference on Computer Vision (ECCV’06), May 7-13, 2006, Graz, Austria. LNCS 3951. Berlin, Germany: Springer-Verlag, 2006: 1-15

11. Shotton J, Winn J, Rother C, et al. TextonBoost for image understanding: Multi-class object recognition and segmentation by jointly modeling texture, layout and context. International Journal of Computer Vision, 2009, 81(1): 2-23

12. Shotton J, Johnson M, Cipolla R. Semantic texton forests for image categorization and segmentation. Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition (CVPR’08), Jun 23-28, 2008, Anchorage, AK, USA. Los Alamitos, CA, USA: IEEE Computer Society, 2008: 8p

13. Lazebnik S, Schmid C, Ponce J. Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. Proceedings of the 2006 IEEE Conference on Computer Vision and Pattern Recognition (CVPR’06), Jun 17-22, 2006, Washington, DC, USA. Los Alamitos, CA, USA: IEEE Computer Society, 2006: 2169-2178

14. Murphy K, Torralba A, Freeman W T. Using the forest to see the tree: a graphical model relating features, objects and the scenes. Proceedings of the 17th Annual Conference on Neural Information Processing Systems (NIPS’03), Dec 8-13, 2003, Vancouver, Canada. Cambridge, MA, USA: MIT Press, 2003

15. He X, Zemel R S, Ray D. Learning and incorporating top-down cues in image segmentation. Proceedings of the 9th European Conference on Computer Vision (ECCV’06), May 7-13, 2006, Graz, Austria. LNCS 3951. Berlin, Germany: Springer-Verlag, 2006: 338-351

16. He X, Zemel R, Perpinan C M. Multiscale conditional random fields for image labelling. Proceedings of the 2004 IEEE Conference on Computer Vision and Pattern Recognition (CVPR’04): Jun 27-Jul 2, 2004, Washington, DC, USA. Los Alamitos, CA, USA: IEEE Computer Society, 2004: 695-702

17. Gould S, Rodgers J, Cohen D, et al. Multi-class segmentation with relative location prior. International Journal of Computer Vision, 2008, 80(3): 300-316

18. Felzenszwalb P, Huttenlocher D. Efficient graph-based image segmentation. International Journal of Computer Vision, 2004, 70(2): 109-131

19. Ren X, Malik J. Learning a classification model for segmentation. Proceedings of the 9th IEEE International Conference on Computer Vision (ICCV’03): Vol 1, Oct 11-12, 2003, Nice, France. Piscataway, NJ, USA: IEEE, 2003: 10-17

20. Leung T K, Malik J. Representing and recognizing the visual appearance of materials using three-dimensional textons. International Journal of Computer Vision, 2001, 43(1): 29-44

21. Kosecka J, Zhang W. Video compass. Proceedings of the 7th European Conference on Computer Vision (ECCV’02), May 28-Jun 2, 2002, Copenhagen, Denmark. LNCS 2353. Berlin, Germany: Springer-Verlag, 2002: 476-490

22. Wang L, Zhang X, Guo L. Review of incremental learning. Journal of Chongqing University of Posts and Telecommunications (Natural Science), 2007, 19 (Suppl.): 99-102 (in Chinese)

23. Felzenszwalb P, McAllester D, Ramanan D. A discriminatively trained, multiscale, deformable part model. Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition (CVPR’08), Jun 23-28, 2008, Anchorage, AK, USA. Los Alamitos, CA, USA: IEEE Computer Society, 2008: 8p

24. Marcotte P, Savard G. Novel approaches to the discrimination problem. Mathematical Methods of Operations Research, 1992, 36(6): 517-545

25. Sutton C, McCallum A. Piecewise training for structured prediction. Machine Learning Journal, 2009, 77(2/3): 165-194

26. Brostow G, Shotton J, Fauqueur J, et al. Segmentation and recognition using structure from motion point clouds. Proceedings of the 10th European Conference on Computer Vision (ECCV’08), Oct 12-18, 2008, Marseille, France. LNCS 5305. Berlin, Germany: Springer-Verlag, 2008: 44-57

Urban scene recognition by graphical model and 3D geometry

Urban scene recognition by graphical model and 3D geometry

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价