No full text
Paper published in a journal (Scientific congresses and symposiums)
Adaptive Video-Based Algorithm for Accident detection on Highways
Maaloul, Boutheina; Taleb Ahmed, Abdelmalik; Niar, Smail et al.
2017
 

Files


Full Text
No document available.

Send to



Details



Abstract :
[en] For the past few decades, automatic accident detection, especially using video analysis, has become a very important subject. It is important not only for traffic management but also, for Intelligent Transportation Systems (ITS) through its contribution to avoid the escalation of accidents especially on highways. In this paper a novel vision based road accident detection algorithm on highways and expressways is proposed. This algorithm is based on an adaptive traffic motion flow modeling technique, using Farneback Optical Flow for motions detection and a statistic heuristic method for accident detection. The algorithm was applied on different collected videos of traffic and accidents on highways and results prove the efficiency and practicability of the proposed algorithm using only 240 frames for traffic motion modeling. This method avoids the recurring to a large database while adequate and common accidents videos benchmarks do not exist.
Disciplines :
Electrical & electronics engineering
Author, co-author :
Maaloul, Boutheina ;  Université de Mons > Faculté Polytechnique > Electronique et Microélectronique
Taleb Ahmed, Abdelmalik
Niar, Smail
Harb, Naim ;  Université de Mons > Faculté Polytechnique > Electronique et Microélectronique
Valderrama, Carlos  ;  Université de Mons > Faculté Polytechnique > Service d'Electronique et Microélectronique
Language :
English
Title :
Adaptive Video-Based Algorithm for Accident detection on Highways
Publication date :
14 June 2017
Event name :
International Symposium on Industrial Embedded Systems
Event place :
Thoulouse, France
Event date :
2017
Research unit :
F109 - Electronique et Microélectronique
Available on ORBi UMONS :
since 20 April 2017

Statistics


Number of views
0 (0 by UMONS)
Number of downloads
0 (0 by UMONS)

Scopus citations®
 
38
Scopus citations®
without self-citations
38

Bibliography


Similar publications



Contact ORBi UMONS