The paper proposes an abnormal event detection approach based on intelligent video content analysis, and applies it to ATM video forensics analysis. It aims at the surveillance video of payee's abnormal behaviors, based on the advantage combined the weighted geometric characterization with the PCA method, and discusses a new algorithm, namely improved PCA algorithm. This algorithm in the ATM can detect abnormal event under the influence of obstruction, such as hat, and the light. Experimental results show that the above approach is proved to be effective and robust in real videos event analysis. © 2011 Springer-Verlag.
CITATION STYLE
Yi, M. (2011). Abnormal event detection method for ATM video and its application. In Communications in Computer and Information Science (Vol. 176 CCIS, pp. 186–192). https://doi.org/10.1007/978-3-642-21802-6_30
Mendeley helps you to discover research relevant for your work.