Crowd Segmentation from a Static Camera

Authors:
Bin Lai;Deng Yi Zhang;Zhi Yong Yuan;Jian Hui Zhao
Affiliations:
Department of Computer Science, Wuhan University, Wuhan, Hubei, China 430079;Department of Computer Science, Wuhan University, Wuhan, Hubei, China 430079;Department of Computer Science, Wuhan University, Wuhan, Hubei, China 430079;Department of Computer Science, Wuhan University, Wuhan, Hubei, China 430079
Venue:
ICIC '08 Proceedings of the 4th international conference on Intelligent Computing: Advanced Intelligent Computing Theories and Applications - with Aspects of Theoretical and Methodological Issues
Year:
2008

Citing 9
Cited 0

W4: Real-Time Surveillance of People and Their Activities

IEEE Transactions on Pattern Analysis and Machine Intelligence
Example-Based Object Detection in Images by Components

IEEE Transactions on Pattern Analysis and Machine Intelligence
Active Appearance Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
Introduction to the Special Section on Video Surveillance

IEEE Transactions on Pattern Analysis and Machine Intelligence
Fusion of Multiple Tracking Algorithms for Robust People Tracking

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
Pedestrian Detection in Crowded Scenes

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Detection of Multiple, Partially Occluded Humans in a Single Image by Bayesian Combination of Edgelet Part Detectors

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Modification of the AdaBoost-based Detector for Partially Occluded Faces

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 02
Image change detection algorithms: a systematic survey

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a more enhanced and efficient method for crowd segmentation from background subtracted images using active basis model associated detection cascade. Firstly, the problem is significant because the case of inter-human occlusion usually appears in the image which may disturb the result of tracking and recognition, consequently debases the effect of the whole surveillance system. Secondly, the problem is challenging because the state space formed by the number, positions, and articulations of people is large, and the noisy may confluence the achievement of the shape of the crowd of background subtracted. We combine some effective methods into one system for improving the hit rate in crowded scene, such as the head position estimation, active basis model, etc. Especially, using the active basis model to verify the result from detection cascade, the system gives the excellent performance for detecting human in crowded scene.