Abstract
Movement information of persons is a very vital feature for abnormality detection in crowded scenes. In this paper, a new method for detection of crowd escape event in video surveillance system is proposed. The proposed method detects abnormalities based on crowd motion pattern, considering both crowd motion magnitude and direction. Motion features are described by weighted-oriented histogram of optical flow magnitude (WOHOFM) and weighted-oriented histogram of optical flow direction (WOHOFD), which describes local motion pattern. The proposed method uses semi-supervised learning approach using combined classifier (KNN and K-Means) framework to detect abnormalities in motion pattern. The authors validate the effectiveness of the proposed approach on publicly available UMN, PETS2009, and Avanue datasets consisting of events like gathering, splitting, and running. The technique reported here has been found to outperform the recent findings reported in the literature.
Highlights
Security is a major concern for everyone at public places and there is an increase in demand of video surveillance systems
Motion features are described by weighted-oriented histogram of optical flow magnitude (WOHOFM) and weighted-oriented histogram of optical flow direction (WOHOFD), which describes local motion pattern
receiver operating characteristic plot (ROC) curve and higher value of Area Under the Curve (AUC) suggest that our proposed method outperforms over other state of the art methods
Summary
Security is a major concern for everyone at public places and there is an increase in demand of video surveillance systems. One cannot solely rely upon human observer because a long time may pass before a suspicious event takes place and human attention may not have remained focus on task in such situations which can lead to an event of interest being missed. To avoid such situations an automated system is needed that can analyze such huge amount of data and trigger alarm in abnormal events. Feature extraction methods are mainly classified into two classes: an object based and pixel based
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Cognitive Informatics and Natural Intelligence
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
