An On-Line and Adaptive Method for Detecting Abnormal Events in Videos Using Spatio-Temporal ConvNet

Samir Bouindour 1 Hichem Snoussi 1 Mohamad Hittawe 2 Nacef Tazi 1 Tian Wang 3
1 LM2S - Laboratoire Modélisation et Sûreté des Systèmes
ICD - Institut Charles Delaunay
2 KAUST - King Abdullah University of Science and Technology
3 School of Automation and Electrical Engineering [Beijing] (University of Science and Technology Beijing)
Abstract : We address in this paper the problem of abnormal event detection in video-surveillance. In this context, we use only normal events as training samples. We propose to use a modified version of pretrained 3D residual convolutional network to extract spatio-temporal features, and we develop a robust classifier based on the selection of vectors of interest. It is able to learn the normal behavior model and detect potentially dangerous abnormal events. This unsupervised method prevents the marginalization of normal events that occur rarely during the training phase since it minimizes redundancy information, and adapt to the appearance of new normal events that occur during the testing phase. Experimental results on challenging datasets show the superiority of the proposed method compared to the state of the art in both frame-level and pixel-level in anomaly detection task.
Document type :
Journal articles
Complete list of metadatas
https://hal-utt.archives-ouvertes.fr/hal-02297585
Contributor : Jean-Baptiste Vu Van <>
Submitted on : Thursday, September 26, 2019 - 11:41:14 AM
Last modification on : Friday, September 27, 2019 - 1:27:40 AM

Links full text

openaccess

Identifiers

Collections

ROSAS | UTT

Citation

Samir Bouindour, Hichem Snoussi, Mohamad Hittawe, Nacef Tazi, Tian Wang. An On-Line and Adaptive Method for Detecting Abnormal Events in Videos Using Spatio-Temporal ConvNet. Applied Sciences, MDPI, 2019, 9 (4), pp.757. ⟨10.3390/app9040757⟩. ⟨hal-02297585⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

7

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD