ProgramsView all programs
From the news
- Chancellor Amma Addresses the Parliament of World’s Religions
- Amrita Students Qualify for the European Mars Rover Challenge
Publication Type : Conference Proceedings
Publisher : 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI), IEEE, Bangalore, India.
Source : 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI), IEEE, Bangalore, India (2018)
Keywords : ADAS, advanced driver assistance system, Autonomous Vehicles, Blob detection, bright lights, Cameras, clustered points, Computer vision, driver information systems, dual tail-light functional case, forward facing optical camera, HSV color space, Image color analysis, Image processing, Mobile robots, night-time vehicle detection, non divergent optical flow, Object Detection, Optical flow, Optical imaging, Optical saturation, pattern clustering, road traffic, Road vehicles, space vehicles, Street lighting, street lights, Tail-light detection, Vehicle detection.
Campus : Coimbatore
School : School of Engineering
Department : Electronics and Communication
Year : 2018
Abstract : Autonomous vehicles are mainly dependent on Advanced Driver Assistance System (ADAS). One of the most important feature in ADAS is vehicle detection. There are many methods for vehicle detection at day time. However, during night-time vehicle detection, ADAS has to depend solely on tail-light of the vehicles ahead. Street lights and other bright lights are of major concern in this scenario. In developing countries like India, vehicles with only one functional tail-light are also allowed on road. In this paper, we propose two improvised methods for nighttime vehicle detection using forward facing optical camera. First method is for improving accuracy in dual tail-light functional case and the other for improving accuracy in single tail-light scenario. Vehicle with only one functional tail-light were detected using non-divergent optical flow points clustered with the functional tail-light. The proposed algorithm has been tested in actual traffic scenarios.
Cite this Research Publication : C. S. Pradeep and Ramanathan, R., “An improved technique for Night-time Vehicle detection”, in 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI), Bangalore, India, 2018.