Title :
Real time traffic congestion detection system
Author :
Nidhal, Ahmed ; Ngah, Umi Kalthum ; Ismail, Widad
Author_Institution :
Imaging & Comput. Intell. (ICI) Group, Univ. Sains Malaysia, Nibong Tebal, Malaysia
Abstract :
In recent years, vehicle management systems have been expanded to include more fields and features. One important system which requires attention is the traffic congestion alert. All previous works on traffic congestion detection either need prior knowledge or lengthy time to detect and recognize the presence of congestion. Some other methods involve huge infrastructure in order to implement. The proposed system in this paper offers a novel method to detect congestion in real-time without any human supervision or any prior knowledge. The designed system counts the vehicles on road by detecting and paring the vehicles backlights from a real time captured image, whereas the system consumes shorter time and maybe feasible to be implemented at any highway premise. The experimental results show that the system has very high detection accuracy (99-100) %.
Keywords :
object detection; traffic engineering computing; real time traffic congestion detection system; real-time captured image; vehicle management systems; vehicles backlights; Accuracy; Image color analysis; Real-time systems; Roads; Robustness; Vehicles;
Conference_Titel :
Intelligent and Advanced Systems (ICIAS), 2014 5th International Conference on
Conference_Location :
Kuala Lumpur
Print_ISBN :
978-1-4799-4654-9
DOI :
10.1109/ICIAS.2014.6869538