International Journal of Computer Vision

, Volume 82, Issue 2, pp 185–204

Detection and Segmentation of Multiple, Partially Occluded Objects by Grouping, Merging, Assigning Part Detection Responses

Article

Abstract

We propose a method that detects and segments multiple, partially occluded objects in images. A part hierarchy is defined for the object class. Both the segmentation and detection tasks are formulated as binary classification problem. A whole-object segmentor and several part detectors are learned by boosting local shape feature based weak classifiers. Given a new image, the part detectors are applied to obtain a number of part responses. All the edge pixels in the image that positively contribute to the part responses are extracted. A joint likelihood of multiple objects is defined based on the part detection responses and the object edges. Computation of the joint likelihood includes an inter-object occlusion reasoning that is based on the object silhouettes extracted with the whole-object segmentor. By maximizing the joint likelihood, part detection responses are grouped, merged, and assigned to multiple object hypotheses. The proposed approach is demonstrated with the class of pedestrians. The experimental results show that our method outperforms the previous ones.

Keywords

Object detection Object segmentation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Bray, M., Kohli, P., & Torr, P. (2006). POSECUT: Simultaneous segmentation and 3D pose estimation of humans using dynamic graph-cuts. In ECCV. Google Scholar
  2. Chan, A. B., Liang, Z. S. J., & Vasconcelos, N. (2008). Privacy preserving crowd monitoring: counting people without people models or tracking. In CVPR. Google Scholar
  3. Dalal, N., Triggs, B., & Schmid, C. (2006). Human detection using oriented histograms of flow and appearance. In ECCV. Google Scholar
  4. Dalal, N., & Triggs, B. (2005). Histograms of oriented gradients for human detection. In CVPR. Google Scholar
  5. Ess, A., Leibe, B., & Gool, L. V. (2007). Depth and appearance for mobile scene analysis. In ICCV. Google Scholar
  6. Gavrila, D. M. (2000). Pedestrian detection from a moving vehicle. In ECCV. Google Scholar
  7. Gavrila, D. M. (2007). A Bayesian, exemplar-based approach to hierarchical shape matching. PAMI, 29(8), 1408–1421. Google Scholar
  8. Gavrila, D. M., & Philomin, V. (1999). Real-time object detection for smart vehicles. In ICCV. Google Scholar
  9. Huang, C., Ai, H., Li, Y., & Lao, S. (2005). Vector boosting for rotation invariant multi-view face detection. In ICCV. Google Scholar
  10. Huang, C., Ai, H., Li, Y., & Lao, S. (2006). Learning sparse features in granular space for multi-view face detection. In FG. Google Scholar
  11. Huang, C., Ai, H., Li, Y., & Lao, S. (2007). High performance rotation invariant multi-view face detection. PAMI, 29(4), 671–686. Google Scholar
  12. Kapoor, A., & Winn, J. (2006). Located hidden random fields: learning discriminative parts for object detection. In ECCV. Google Scholar
  13. Kong, D., Gray, D., & Tao, H. (2006). A viewpoint invariant approach for crowd counting. In ICPR. Google Scholar
  14. Kuhn, H. W. (1955). The Hungarian method for the assignment problem. Naval Research Logistics Quarterly, 2, 83–87. CrossRefMathSciNetGoogle Scholar
  15. Leibe, B., Leonardis, A., & Schiele, B. (2004). Combined object categorization and segmentation with an implicit shape model. In Workshop on statistical learning in computer vision, in conjunction with ECCV. Google Scholar
  16. Leibe, B., Seemann, E., & Schiele, B. (2005). Pedestrian detection in crowded scenes. In CVPR. Google Scholar
  17. Lin, Y.-Y., Liu, T.-L., & Fuh, C.-S. (2004). Fast object detection with occlusion. In ECCV. Google Scholar
  18. Lin, Z., Davis, L. S., Doermann, D., & DeMenthon, D. (2007). Hierarchical part-template matching for human detection and segmentation. In ICCV. Google Scholar
  19. Medioni, G., Lee, M. S., & Tang, C. K. (2000). A computational framework for segmentation and grouping. Amsterdam: Elsevier. MATHGoogle Scholar
  20. Mikolajczyk, C., Schmid, C., & Zisserman, A. (2004). Human detection based on a probabilistic assembly of robust part detectors. In ECCV. Google Scholar
  21. Mohan, A., Papageorgiou, C., & Poggio, T. (2001). Example-based object detection in images by components. IEEE Transactions on PAMI, 23(4), 349–361. Google Scholar
  22. Munder, S., & Gavrila, D. M. (2006). An experimental study on pedestrian classification. IEEE Transactions on PAMI, 28(11), 1863–1868. Google Scholar
  23. Mutch, J., & Lowe, D. (2006). Multiclass object recognition with sparse, localized features. In CVPR. Google Scholar
  24. Opelt, A., Pinz, A., & Zisserman, A. (2006). A boundary-fragment-model for object detection. In ECCV. Google Scholar
  25. Papageorgiou, C., Evgeniou, T., & Poggio, T. (1998). A trainable pedestrian detection system. In Proceedings of intelligent vehicles. Google Scholar
  26. Pawan Kumar, M., Torr, P., & Zisserman, A. (2005). OBJ CUT. In CVPR. Google Scholar
  27. Rowley, H., Baluja, S., & Kanade, T. (1998). Neural network-based face detection. PAMI, 20(1), 23–38. Google Scholar
  28. Sabzmeydani, P., & Mori, G. (2007). Detecting pedestrians by learning shapelet features. In CVPR. Google Scholar
  29. Schapire, R. E., & Singer, Y. (1999). Improved boosting algorithms using confidence-rated predictions. Machine Learning, 37, 297–336. MATHCrossRefGoogle Scholar
  30. Schneiderman, H., & Kanade, T. (2000). A statistical method for 3D object detection applied to faces and cars. In CVPR. Google Scholar
  31. Sharma, V., & Davis, J. W. (2007). Integrating appearance and motion cues for simultaneous detection and segmentation of pedestrians. In ICCV. Google Scholar
  32. Shashua, A., Gdalyahu, Y., & Hayun, G. (2004). Pedestrian detection for driving assistance systems: single-frame classification and system level performance. In IEEE intelligent vehicles symposium. Google Scholar
  33. Shet, V. D., Neumann, J., Ramesh, V., & Davis, L. S. (2007). Bilattice-based logical reasoning for human detection. In CVPR. Google Scholar
  34. Shotton, J., Blake, A., & Cipolla, R. (2005). Contour-based learning for object detection. In ICCV. Google Scholar
  35. Shotton, J., Winn, J., Rother, C., & Criminisi, A. (2006). TextonBoost: joint appearance, shape and context modeling for multi-class object recognition and segmentation. In ECCV. Google Scholar
  36. Todorovic, S., & Ahuja, N. (2006). Extracting subimages of an unknown category from a set of images. In CVPR. Google Scholar
  37. Tu, Z., Zhu, S.-C., & Shum, H.-Y. (2001). Image segmentation by data driven Markov chain Monte Carlo. In ICCV. Google Scholar
  38. Tuzel, O., Porikli, F., & Meer, P. (2007). Human detection via classification on Riemannian manifolds. In CVPR. Google Scholar
  39. Viola, P., & Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In CVPR. Google Scholar
  40. Viola, P., Jones, M., & Snow, D. (2003). Detecting pedestrians using patterns of motion and appearance. In ICCV. Google Scholar
  41. Winn, J., & Jojic, N. (2005). LOCUS: Learning object class with unsupervised segmentation. In ICCV. Google Scholar
  42. Winn, J., & Shotton, J. (2006). The layout consistent random field for recognition and segmentation partially occluded objects. In CVPR. Google Scholar
  43. Wu, B., & Nevatia, R. (2005). Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors. In ICCV. Google Scholar
  44. Wu, B., & Nevatia, R. (2007a). Cluster boosted tree classifier for multi-view, multi-pose object detection. In ICCV. Google Scholar
  45. Wu, B., & Nevatia, R. (2007b). Simultaneous object detection and segmentation by boosting local shape feature based classifier. In CVPR. Google Scholar
  46. Wu, B., & Nevatia, R. (2007c). Detection and tracking of multiple, partially occluded humans by Bayesian combination of edgelet based part detectors. International Journal of Computer Vision, 75(2), 247–266. CrossRefGoogle Scholar
  47. Wu, B., Nevatia, R., & Li, Y. (2008). Segmentation of multiple, partially occluded objects by grouping, merging, assigning part detection responses. In CVPR. Google Scholar
  48. Zhao, L., & Davis, L. (2005). Closely coupled object detection and segmentation. In ICCV. Google Scholar
  49. Zhu, Q., Avidan, S., Yeh, M.-C., & Cheng, K.-T. (2006). Fast human detection using a cascade of histograms of oriented gradients. In CVPR. Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2008

Authors and Affiliations

  1. 1.Institute for Robotics and Intelligent SystemsUniversity of Southern CaliforniaLos AngelesUSA

Personalised recommendations