Share Email Print

Proceedings Paper • new

Deep learning architecture for recognition of abnormal activities
Author(s): Marwa Khatrouch; Mariem Gnouma; Ridha Ejbali; Mourad Zaied
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The video surveillance is one of the key areas in computer vision researches. The scientific challenge in this field involves the implementation of automatic systems to obtain detailed information about individuals and groups behaviors. In particular, the detection of abnormal movements of groups or individuals requires a fine analysis of frames in the video stream. In this article, we propose a new method to detect anomalies in crowded scenes. We try to categorize the video in a supervised mode accompanied by unsupervised learning using the principle of the autoencoder. In order to construct an informative concept for the recognition of these behaviors, we use a technique of representation based on the superposition of human silhouettes. The evaluation of the UMN dataset demonstrates the effectiveness of the proposed approach.

Paper Details

Date Published: 13 April 2018
PDF: 7 pages
Proc. SPIE 10696, Tenth International Conference on Machine Vision (ICMV 2017), 106960F (13 April 2018); doi: 10.1117/12.2314834
Show Author Affiliations
Marwa Khatrouch, Univ. of Gabes (Tunisia)
Mariem Gnouma, Research Groups in Intelligent Machines (Tunisia)
Ridha Ejbali, Univ. of Gabes (Tunisia)
Research Groups in Intelligent Machines (Tunisia)
Mourad Zaied, Research Groups in Intelligent Machines (Tunisia)

Published in SPIE Proceedings Vol. 10696:
Tenth International Conference on Machine Vision (ICMV 2017)
Antanas Verikas; Petia Radeva; Dmitry Nikolaev; Jianhong Zhou, Editor(s)

© SPIE. Terms of Use
Back to Top