Learning of scene-specific object detectors by classifier co-grids

Proceedings - IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2010

Volumn , Issue , 2010, Pages 408-413

  Sternig, Sabine ^a   Roth, Peter M ^a   Bischof, Horst ^a  

^a GRAZ UNIVERSITY OF TECHNOLOGY   (Austria)

Author keywords

[No Author keywords available]

Indexed keywords

CLASSIFICATION (OF INFORMATION); OBJECT RECOGNITION; SECURITY SYSTEMS;

BENCHMARK DATA; CLASSIFIER GRIDS; CO-TRAINING; ENVIRONMENTAL CONDITIONS; OBJECT DETECTORS; SLIDING WINDOW; SPECIFIC INFORMATION; STATIC CAMERAS;

OBJECT DETECTION;

EID: 78449286710     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/AVSS.2010.10     Document Type: Conference Paper

References (23)

1. S. Abney. Bootstrapping. In Proc. Annual Meeting of the Association for Computational Linguistics, pages 360-367, 2002.
2. B. Babenko, M.-H. Yang, and S. Belongie. Visual tracking with online mulitple instance learning. In Proc. CVPR, 2009.
3. M.-F. Balcan, A. Blum, and K. Yang. Co-training and expansion: Towards bridging theory and practice. In NIPS, pages 89-96, 2004.
4. A. Blum and T. Mitchell. Combining labeled and unlabeled data with co-training. In Proc. COLT, pages 92-100, 1998.
5. N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. In Proc. CVPR, volume I, pages 886-893, 2005.
6. P. Felzenszwalb, D. McAllester, and D. Ramanan. A discriminatively trained, multiscale, deformable part model. In Proc. CVPR, 2008.
7. A. B. Goldberg, M. Li, and X. Zhu. Online manifold regularization: A new learning setting and empirical study. In Proc. European Conf. on Machine Learning and Knowledge Discovery in Databases, volume I, pages 393-407, 2008.
8. H. Grabner, P. M. Roth, and H. Bischof. Is pedestrian detection really a hard task? In Proc. IEEE Workshop on PETS, 2007.
9. D. Hoiem, A. A. Efros, and M. Hebert. Putting objects in perspective. In Proc. CVPR, volume II, pages 2137-2144, 2006.
10. C. Leistner, A. Saffari A. A., P. M. Roth, and H. Bischof. On robustness of on-line boosting - a competitive study. In Proc. IEEE On-line Learning for Computer Vision Workshop, 2009.
11. A. Levin, P. Viola, and Y. Freund. Unsupervised improvement of visual detectors using co-training. In Proc. ICCV, volume I, pages 626-633, 2003.
12. L.-J. Li, G.Wang, and L. Fei-Fei. Optimol: automatic online picture collection via incremental model learning. In Proc. CVPR, pages 1-8, 2007.
13. R. Liu, J. Cheng, and H. Lu. A robust boosting tracker with minimum error bound in a co-training framework. In Proc. ICCV, 2009.
14. N. J. B. McFarlane and C. P. Schofield. Segmentation and tracking of piglets. Machine Vision and Applications, 8(3):187-193, 1995.
15. V. Nair and J. J. Clark. An unsupervised, online learning framework for moving object detection. In Proc. CVPR, volume II, pages 317-324, 2004.
16. P. M. Roth and H. Bischof. Machine Learning Techniques for Multimedia, chapter Conservative Learning for Object Detectors, pages 139-158. Springer, 2008.
17. P. M. Roth, S. Sternig, H. Grabner, and H. Bischof. Classifier grids for robust adaptive object detection. In Proc. CVPR, 2009.
18. S. Stalder, H. Grabner, and L. v. Gool. Exploring context to learn scene specific object detectors. In Proc. IEEE Workshop on PETS, 2009.
19. S. Sternig, M. Godec, P. M. Roth, and H. Bischof. Transient-boost: On-line boosting with transient data. In Proc. IEEE Online Learning for Computer Vision Workshop (CVPR), 2010.
20. W. Wang and Z.-H. Zhou. Analyzing co-training style algorithms. In Proc. European Conf. on Machine Learning, pages 454-465, 2007.
21. B. Wu and R. Nevatia. Detection of multiple, partially occluded humans in a single image by bayesian combination of edgelet part detectors. In Proc. ICCV, volume I, pages 90-97, 2005.
22. B. Wu and R. Nevatia. Simultaneous object detection and segmentation by boosting local shape eature based classifier. In Proc. CVPR, pages 1-8, 2007.
23. Q. Zhu, S. Avidan, and K.-T. Cheng. Learning a sparse, corner-based representation for background modelling. In Proc. ICCV, volume I, pages 678-685, 2005.