TY - GEN
T1 - Unsupervised Abnormal Behaviour Detection with Overhead Crowd Video
AU - Shoujiang, Xu
AU - Ho, Edmond
AU - Aslam, Nauman
AU - Shum, Hubert P. H.
PY - 2017/12
Y1 - 2017/12
N2 - Due to the increasing threat of terrorism, it has become more and more important to detect abnormal behaviour in public areas. In this paper, we introduce a system to identify pedestrians with abnormal movement trajectories in a scene using a data-driven approach. Our system includes two parts. The first part is an interactive tool that takes an overhead video as an input and tracks the pedestrians in a semi-automatic manner. The second part is a data-driven abnormal trajectories detection algorithm, which applies iterative k-means clustering to find out possible paths in the scene and thereby identifies those that do not fit well in any paths. Since the system requires only RGB video, it is compatible with most of the closed-circuit television (CCTV) systems used for security monitoring. Furthermore, the training of the abnormal trajectories detection algorithm is unsupervised and fully automatic. It means that the system can be deployed into a new location without manual parameter tuning and training data annotations. The system can be applied in indoor and outdoor environments and is best for automatic security monitoring.
AB - Due to the increasing threat of terrorism, it has become more and more important to detect abnormal behaviour in public areas. In this paper, we introduce a system to identify pedestrians with abnormal movement trajectories in a scene using a data-driven approach. Our system includes two parts. The first part is an interactive tool that takes an overhead video as an input and tracks the pedestrians in a semi-automatic manner. The second part is a data-driven abnormal trajectories detection algorithm, which applies iterative k-means clustering to find out possible paths in the scene and thereby identifies those that do not fit well in any paths. Since the system requires only RGB video, it is compatible with most of the closed-circuit television (CCTV) systems used for security monitoring. Furthermore, the training of the abnormal trajectories detection algorithm is unsupervised and fully automatic. It means that the system can be deployed into a new location without manual parameter tuning and training data annotations. The system can be applied in indoor and outdoor environments and is best for automatic security monitoring.
UR - http://www.scopus.com/inward/record.url?scp=85054271948&partnerID=8YFLogxK
U2 - 10.1109/SKIMA.2017.8294092
DO - 10.1109/SKIMA.2017.8294092
M3 - Conference contribution
AN - SCOPUS:85054271948
SN - 9781538646038
T3 - International Conference on Software, Knowledge Information, Industrial Management and Applications, SKIMA
BT - Proceedings of the 11th International Conference on Software, Knowledge, Information Management and Applications, SKIMA 2017
PB - IEEE
CY - Piscataway, NJ
T2 - 11th International Conference on Software, Knowledge, Information Management and Applications, SKIMA 2017
Y2 - 6 December 2017 through 8 December 2017
ER -