Skip to Main content Skip to Navigation
Journal articles

Abnormal event detection via covariance matrix for optical flow based feature

Abstract : Abnormal event detection is one of the most important objectives in security surveillance for public scenes. In this paper, a new high-performance algorithm based on spatio-temporal motion information is proposed to detect global abnormal events from the video stream as well as the local abnormal event. We firstly propose a feature descriptor to represent the movement by adopting the covariance matrix coding optical flow and the corresponding partial derivatives of multiple connective frames or the patches of the frames. The covariance matrix of multi-RoI (region of interest) which consists of frames or patches can represent the movement in high accuracy. For public surveillance video, the normal samples are abundant while there are few abnormal samples. Thus the one-class classification method is suitable for handling this problem inherently. The nonlinear one-class support vector machine based on a proposed kernel for Lie group element is applied to detect abnormal events by merely training the normal samples. The computational complexity and time performance of the proposed method is analyzed. The PETS, UMN and UCSD benchmark datasets are employed to verify the advantages of the proposed method for both global abnormal and local abnormal event detection. This method can be used for event detection for a surveillance video and outperforms the state-of-the-art algorithms. Thus it can be adopted to detect the abnormal event in the monitoring video.
Document type :
Journal articles
Complete list of metadata
Contributor : Jean-Baptiste Vu Van Connect in order to contact the contributor
Submitted on : Monday, August 16, 2021 - 11:06:39 AM
Last modification on : Wednesday, October 13, 2021 - 7:16:03 PM





Tian Wang, Meina Qiao, Aichun Zhu, Yida Niu, Ce Li, et al.. Abnormal event detection via covariance matrix for optical flow based feature. Multimedia Tools and Applications, Springer Verlag, 2018, 77 (13), pp.17375-17395. ⟨10.1007/s11042-017-5309-2⟩. ⟨hal-03320616⟩



Record views