Urban transportation is an essential part of modern urban development. With the rapid development of China's economy, the number of private vehicles is increasing year by year, and traffic congestion is becoming more and more frequent. However, as existing map software determines the congestion judgment method based on the number of navigation software installed in users' vehicles or cell phones, there is a defect of inaccurate prediction results. This paper compares and analyzes the object detection methods based on deep learning by studying and analyzing the current mainstream object detection frameworks and finally selects YOLOv3 as the object detection tool. We combine the driving recorder video and GPS navigation tracking to judge the congestion situation in real-time. It feeds the congestion status to the map, effectively making up for the shortcomings of mapping software in judging congestion, facilitating car owners and traffic management departments to make more good travel planning and traffic diversions, and improving traffic efficiency.
A research on urban road congestion detection based on YOLOv3
International Conference on Geographic Information and Remote Sensing Technology (GIRST 2022) ; 2022 ; Kunming,China
Proc. SPIE ; 12552
2023-02-10
Conference paper
Electronic Resource
English
Research on Evaluation of Urban Road Congestion
Trans Tech Publications | 2014
|Road Sign Detection and Recognition of Thai Traffic Based on YOLOv3
British Library Conference Proceedings | 2019
|Research on Smart Car Safety Based on YOLOv3 Target Detection Algorithm
Springer Verlag | 2024
|