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
Foreground object detection from videos containing complex background
MULTIMEDIA '03 Proceedings of the eleventh ACM international conference on Multimedia
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
Region covariance: a fast descriptor for detection and classification
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
Estimation of number of people in crowded scenes using perspective transformation
IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
Hi-index | 0.00 |
The paper describes an approach to detect abnormal events principally from unidirectional flow of crowd (e.g., escalators). The video frames are labeled normal or abnormal based on the distance measure between covariance matrices of the distributions of the optical flow vectors computed on consecutive frames. These flow vectors are the result of tracking a set of features points discovered by the Harris corner detector applied on each frame considering a region of interest. This region is produced by background subtraction to form a two dimensional histogram of motion called motion heat map. The approach is tested against a single camera data-set placed in the escalator exits in an airport.