Introduction to statistical pattern recognition (2nd ed.)
Introduction to statistical pattern recognition (2nd ed.)
Evaluation of Interest Point Detectors
International Journal of Computer Vision - Special issue on a special section on visual surveillance
Learning Patterns of Activity Using Real-Time Tracking
IEEE Transactions on Pattern Analysis and Machine Intelligence
Pattern Classification (2nd Edition)
Pattern Classification (2nd Edition)
Improved Adaptive Gaussian Mixture Model for Background Subtraction
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2 - Volume 02
Multi Feature Path Modeling for Video Surveillance
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2 - Volume 02
Video Behaviour Profiling and Abnormality Detection without Manual Labelling
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
A System for Learning Statistical Motion Patterns
IEEE Transactions on Pattern Analysis and Machine Intelligence
Hidden Markov Models for Optical Flow Analysis in Crowds
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 01
Modelling Crowd Scenes for Event Detection
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 01
Detecting Irregularities in Images and in Video
International Journal of Computer Vision
An iterative image registration technique with an application to stereo vision
IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2
Learning semantic scene models from observing activity in visual surveillance
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Hi-index | 0.00 |
The paper presents a simple but effective method to detect abnormal crowd behaviors from real crowd videos. The method does not depend on person detection or segmentation, instead it takes the advantages of the use of cluster analysis such as robustness against variable numbers of people in the scenes. It lies in the use of the Bhattacharyya distance to measure differences in properties of clusters over time between frames. The normalized Bhattacharyya distance measure provides the knowledge of the state of abnormality. Experiments have been conducted on different real crowd videos covering both normal and abnormal activities. The experimental results show that distances between clusters of tracked corners on movers are reasonable ways to characterize abnormal behavior as the distances vary significantly in case of abnormalities.