Abstract
Accurate localization of traffic participants is very important and useful in Intelligent Transportation System(ITS). The most frequent discussed method for accurate vehicle localization in literature is based on Global Navigation Satellite System(GNSS) or Radio Frequency Identification(RFID). However, GNSS-based methods are vulnerable to signal loss when obscured and RFID-based methods have requirements for road construction. In this paper, a low-cost method which only uses the computer vision of a roadside camera to locate traffic participants including car, bus, pedestrian and cyclists precisely is proposed. The final localization result is represented by a center point for vehicle and a quadrilateral region for all targets, which also contain the information of object size. The proposal is consist of three main part: traffic participant detection and classification, contact point determination for vehicle and location area calculation for each kind of traffic participants. Experiment shows the average localization accuracy for car is 0.107 meter.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
