Detecting contextual anomalies of crowd motion in surveillance video. Jiang, F., Wu, Y., Katsaggelos, A. K., Fan Jiang, Ying Wu, & Katsaggelos, A. K. In 2009 16th IEEE International Conference on Image Processing (ICIP), pages 1117–1120, nov, 2009. IEEE, IEEE.
Detecting contextual anomalies of crowd motion in surveillance video [link]Paper  doi  abstract   bibtex   
Many works have been proposed on detecting individual anomalies in crowd scenes, i.e., human behaviors anomalous with respect to the rest of the behaviors. In this paper, we introduce a new concept of contextual anomaly into the field of crowd analysis, i.e., the behaviors themselves are normal but they are anomalous in a specific context. Our system follows an unsupervised approach. It automatically discovers important contextual information from the crowd video and detects the blobs corresponding to contextually anomalous behaviors. Our experiments show that the approach works well in detecting contextual anomalies from crowd video with different motion contexts. ©2009 IEEE.
@inproceedings{jiang2009detecting,
abstract = {Many works have been proposed on detecting individual anomalies in crowd scenes, i.e., human behaviors anomalous with respect to the rest of the behaviors. In this paper, we introduce a new concept of contextual anomaly into the field of crowd analysis, i.e., the behaviors themselves are normal but they are anomalous in a specific context. Our system follows an unsupervised approach. It automatically discovers important contextual information from the crowd video and detects the blobs corresponding to contextually anomalous behaviors. Our experiments show that the approach works well in detecting contextual anomalies from crowd video with different motion contexts. {\textcopyright}2009 IEEE.},
author = {Jiang, Fan and Wu, Ying and Katsaggelos, Aggelos K. and {Fan Jiang} and {Ying Wu} and Katsaggelos, Aggelos K.},
booktitle = {2009 16th IEEE International Conference on Image Processing (ICIP)},
doi = {10.1109/ICIP.2009.5414535},
isbn = {978-1-4244-5653-6},
issn = {15224880},
keywords = {Anomaly detection,Clustering,Crowd analysis},
month = {nov},
organization = {IEEE},
pages = {1117--1120},
publisher = {IEEE},
title = {{Detecting contextual anomalies of crowd motion in surveillance video}},
url = {http://ieeexplore.ieee.org/document/5414535/},
year = {2009}
}

Downloads: 0