Human pose model and block growth combined crowd segmentation

被引：0
|
作者：
Deng Y.-N. [1 ]
Zhu H. [1 ]
Liu W. [1 ]
Zhang X.-D. [1 ]
机构：
[1] College of Automation and Information Engineering, Xi'an University of Technology
来源：
Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology | 2010年 / 32卷 / 03期
关键词：
Bayesian model; Block growth; Object segmentation; Pose model; Watershed algorithm;
D O I：
10.3724/SP.J.1146.2009.00119
中图分类号：
学科分类号：
摘要：
Crowd object segmentation is a key issue of the object tracking and recognition in multiple cameras. Human rough models with position, scale and pose information are constructed and then get the corresponding models by using Bayesian model. Then, the foreground is segmented into blocks of similar color distribution. Then the problem of the seed blocks selection is solved thought of color and position information under human inter-occlusion, and human region is received by seed growth. For blocks with similar color, they are merged into the objects by comparing the edge energy they brought. It can be seen that the method could segment the crowd precisely, and is not sensitive to background noise from the experimental results.
引用
收藏
页码：750 / 754
页数：4
相关论文
共 10 条
  • [1] Yang R., Zheng Q.-F., Multi-moving people detection from binocular sequences, Proceedings of International Conference on Acoustic, Speech and Signal Processing, 2, pp. 297-300, (2003)
  • [2] Brostow G.J., Cipolla R., Unsupervised Bayesian detection of independent motion in crowds, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1, pp. 594-601, (2006)
  • [3] Elgammal A.M., Davis L.S., Probabilistic framework for segmenting people under Occlusion, Proceedings of 8th IEEE Conference on Computer Vision, 2, pp. 145-152, (2001)
  • [4] Ramanan D., Forsyth D.A., Finding and tracking people from the bottom up, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2, pp. 467-474, (2003)
  • [5] Zhe L., Davis L.S., Doermann D., Et al., An interactive approach to pose-assisted and appearance-based segmentation of humans, Proceedings of IEEE 11th International Conference on Computer Vision, pp. 1-8, (2007)
  • [6] Wu B., Nevatia R., Detection and tracking of multiple, partially occluded humans by Bayesian combination of edgelet based part detectors, International Journal of Computer Vision, 27, 2, pp. 247-266, (2007)
  • [7] Zhao T., Ram N., Bayesian human segmentation in crowded situations, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2, pp. 459-466, (2003)
  • [8] Zhe L., Davis L.S., Doermann D., Dementhon D., Hierarchical part-template matching for human detection and segmentation, Proceedings of IEEE 11th International Conference on Computer Vision, pp. 1-8, (2007)
  • [9] Yang L., Yang X., Multi-object segmentation based on curve evolving and region division, Chinese Journal of Computers, 27, 3, pp. 420-425, (2004)
  • [10] Jacky S.C., Yuk K.K., Wong R., Et al., Real-time multiple head shape detection and tracking system with decentralized trackers, Proceedings of 6th IEEE International Conference on Intelligent System Design and Applications, 2, pp. 384-389, (2006)
1