Title :
A neural vision based approach for intelligent transportation system
Author_Institution :
Sch. of Electr. & Electron. Eng., Nanyang Technol. Univ., Singapore, Singapore
Abstract :
There is a growing demand for road traffic data of all kinds. These data are required by local and central governments for traffic surveillance, control and management. Vehicle detection and monitoring through video image processing is now considered as an attractive and flexible technique. Previous methods proposed by researchers for detecting and monitoring road vehicles are based on traditional image processing algorithms. The method proposed here is based on the combination of edge detection and neural network algorithms. The edge detection technique is used to detect vehicles while neural network is used to monitor vehicle movements. The neural network is trained for various road traffic conditions and is able to provide better results than the traditional image processing algorithms. The results show that the proposed vision approach can detect and monitor vehicles in real-time.
Keywords :
computer vision; computerised monitoring; edge detection; learning (artificial intelligence); neural nets; road traffic; traffic control; traffic engineering computing; computer vision; edge detection; image processing; learning; neural network; real-time system; road vehicle monitoring; traffic control; transportation; Centralized control; Image edge detection; Image processing; Intelligent transportation systems; Local government; Monitoring; Neural networks; Roads; Surveillance; Vehicle detection;
Conference_Titel :
Industrial Technology, 2002. IEEE ICIT '02. 2002 IEEE International Conference on
Print_ISBN :
0-7803-7657-9
DOI :
10.1109/ICIT.2002.1189939