Automated system for road extraction and traffic volume estimation for traffic jam detection. (10th December 2020)

• Record Type: Journal Article
• Authors: Parsola, Jyoti; Gangodkar, Durgaprasad; Mittal, Ankush
• Is Part Of: International journal of computational vision and robotics. Volume 11:Number 2(2021)
• Page Start: 127
• Page End: 150
• Publication Date: 2020-12-10
• Subjects: intelligent transportation system -- traffic density estimation -- congestion detection; Computer vision -- Periodicals; Robotics -- Periodicals; Artificial intelligence -- Periodicals; 006.3705
• Languages: English
• ISSNs: 1752-9131

Abstract

Vehicle detection and traffic density estimation is one of the essential tasks for traffic congestion estimation and is solved up to some extent. We also propose an automated surveillance system for vehicle detection from a traffic scene which perform functions like path followed by vehicle, traffic volume estimation, traffic analysis and reports traffic jam. Our system directly extracts road region from traffic scene by segmentation of moving vehicle. Further based on the movement of vehicle, path is plotted. Vehicular density is computed with respect to the corresponding road of moving vehicle. A traffic jam alert is generated based on the intensity of traffic density and density is categorised in heavy, medium or low based on the flow of the traffic. Performance of our system is evaluated using various benchmark datasets which, shows the ability of proposed method to work in any road conditions and thus makes it suitable for deployment.