Detecting and segmenting humans in crowded scenes

ABSTRACT

We describe an approach for detecting and segmenting humans with extensive posture articulations in crowded video sequences. In our method we learn a set of mean posture clusters, and a codebook of local shape distributions for humans in various postures. Detection proceeds in two stages: first instances of the codebook entries cast votes for locations of humans in the video and their respective postures. Subsequently, consistent hypotheses are found as maxima within a voting space. The segmentation of humans in the scene is initialized by the corresponding posture clusters and contours are evolved to obtain precise and consistent segmentations.

Our experimental results indicate that the framework provides a simple yet effective means for aggregating local and global shape-based cues. The proposed method is capable of detecting and segmenting humans in crowded scenes as they perform a diverse set of activities and undergo a wide range of articulations within different contexts.

REFERENCES

• 1: S. Belongie , J. Malik , J. Puzicha, Shape Matching and Object Recognition Using Shape Contexts, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.24 n.4, p.509-522, April 2002 [doi>10.1109/34.993558]
• 2: Navneet Dalal , Bill Triggs, Histograms of Oriented Gradients for Human Detection, Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1, p.886-893, June 20-26, 2005 [doi>10.1109/CVPR.2005.177]
• 3: Dariu Gavrila, Pedestrian Detection from a Moving Vehicle, Proceedings of the 6th European Conference on Computer Vision-Part II, p.37-49, June 26-July 01, 2000
• 4: Bastian Leibe , Edgar Seemann , Bernt Schiele, Pedestrian Detection in Crowded Scenes, Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1, p.878-885, June 20-26, 2005 [doi>10.1109/CVPR.2005.272]
• 5: A. Micilotta, E. Ong, and R. Bowden. Detection and Tracking of Humans by Probabilistic Body Part Assembly. BMVC, 2005.
• 6: K. Mikolajczyk, C. Schmid, and A. Zisserman. Human detection based on a probabilistic assembly of robust part detectors. ECCV, 1:69--81, 2004.
• 7: Deva Ramanan , D. A. Forsyth , Andrew Zisserman, Strike a Pose: Tracking People by Finding Stylized Poses, Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1, p.271-278, June 20-26, 2005 [doi>10.1109/CVPR.2005.335]
• 8: T. Roberts, S. McKenna, and I. Ricketts. Human pose estimation using learnt probabilistic region similarities and partial configurations. ECCV, 4:291--303, 2004.
• 9: Rémi Ronfard , Cordelia Schmid , Bill Triggs, Learning to Parse Pictures of People, Proceedings of the 7th European Conference on Computer Vision-Part IV, p.700-714, May 28-31, 2002
• 10: P. Viola and M. Jones. Rapid object detection using a boosted cascade of simple features. CVPR, 1:511--518, 2001.
• 11: Paul Viola , Michael J. Jones , Daniel Snow, Detecting Pedestrians Using Patterns of Motion and Appearance, International Journal of Computer Vision, v.63 n.2, p.153-161, July 2005 [doi>10.1007/s11263-005-6644-8]
• 12: Ying Wu , Ting Yu, A Field Model for Human Detection and Tracking, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.28 n.5, p.753-765, May 2006 [doi>10.1109/TPAMI.2006.87]
• 13: Alper Yilmaz , Xin Li , Mubarak Shah, Contour-Based Object Tracking with Occlusion Handling in Video Acquired Using Mobile Cameras, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.26 n.11, p.1531-1536, November 2004 [doi>10.1109/TPAMI.2004.96]
• 14: V. Zatsiorsky. Kinetics of Human Motion. Human Kinetics, 2002.
• 15: Liang Zhao , Larry S. Davis, Closely Coupled Object Detection and Segmentation, Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1, p.454-461, October 17-20, 2005 [doi>10.1109/ICCV.2005.55]
• 16: L. Zhao and C. Thorpe. Stereo-and neural network-based pedestrian detection. ITS, IEEE Transactions on, 1(3):148--154, 2000.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.8 Scene Analysis
          Subjects: Object recognition

Additional Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.6 Segmentation

General Terms:
Algorithms

Keywords:
human detection, object recognition, segmentation