TY - GEN
T1 - Multi-level threat analysis in anomalous crowd videos
AU - Sikdar, Arindam
AU - Chowdhury, Ananda S.
N1 - Publisher Copyright:
© Springer Nature Singapore Pte Ltd 2020.
PY - 2020/3/29
Y1 - 2020/3/29
N2 - Crowd anomaly detection is a challenging problem in the field of computer vision. An abnormal event in a crowd scene can be labeled as threat in a video. Several existing solutions in this area have marked video frames either normal or abnormal event. Such categorization of frames can be referred as two-class threat labeling problem. However, this notion of two-class threat labeling is not well defined in literature. An event can have multiple aspects as it can be treated as anomalous or non-anomalous based on the situation of occurrence. Based on this argument, we propose a new paradigm of extending this two class threat labeling problem to multi-class labeling. As a solution to this multi-class labeling problem, we cluster frames with low, medium and high threat. We also propose a new feature known as pseudo-entropy for better clustering of threats. Our framework consists of two main components, namely, Earth mover distance (EMD) based anomaly detection system and multi-level threat analysis. As an outcome frame-wise and segment-wise threat representation are also presented to facilitate real time video search for relevant events. Exhaustive internal comparison and statistical analysis over benchmark UCSD and UMN dataset clearly indicates the merit of the proposed framework.
AB - Crowd anomaly detection is a challenging problem in the field of computer vision. An abnormal event in a crowd scene can be labeled as threat in a video. Several existing solutions in this area have marked video frames either normal or abnormal event. Such categorization of frames can be referred as two-class threat labeling problem. However, this notion of two-class threat labeling is not well defined in literature. An event can have multiple aspects as it can be treated as anomalous or non-anomalous based on the situation of occurrence. Based on this argument, we propose a new paradigm of extending this two class threat labeling problem to multi-class labeling. As a solution to this multi-class labeling problem, we cluster frames with low, medium and high threat. We also propose a new feature known as pseudo-entropy for better clustering of threats. Our framework consists of two main components, namely, Earth mover distance (EMD) based anomaly detection system and multi-level threat analysis. As an outcome frame-wise and segment-wise threat representation are also presented to facilitate real time video search for relevant events. Exhaustive internal comparison and statistical analysis over benchmark UCSD and UMN dataset clearly indicates the merit of the proposed framework.
KW - Crowd anomaly
KW - Frame-wise pattern
KW - Local motion descriptor
KW - Multi-level threat
KW - Segment-wise pattern
UR - http://www.scopus.com/inward/record.url?scp=85083741008&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85083741008&partnerID=8YFLogxK
U2 - 10.1007/978-981-15-4018-9_44
DO - 10.1007/978-981-15-4018-9_44
M3 - Conference proceeding (ISBN)
AN - SCOPUS:85083741008
SN - 9789811540172
T3 - Communications in Computer and Information Science
SP - 495
EP - 506
BT - Computer Vision and Image Processing - 4th International Conference, CVIP 2019, Revised Selected Papers
A2 - Nain, Neeta
A2 - Vipparthi, Santosh Kumar
A2 - Raman, Balasubramanian
PB - Springer
T2 - 4th International Conference on Computer Vision and Image Processing, CVIP 2019
Y2 - 27 September 2019 through 29 September 2019
ER -