Abstract
In this paper, a deep learning-based traffic state discrimination method is proposed to detect traffic congestion at urban intersections. The detection algorithm includes two parts, global speed detection and a traffic state discrimination algorithm. Firstly, the region of interest (ROI) is selected as the road intersection from the input image of the You Only Look Once (YOLO) v3 object detection algorithm for vehicle target detection. The Lucas-Kanade (LK) optical flow method is employed to calculate the vehicle speed. Then, the corresponding intersection state can be obtained based on the vehicle speed and the discrimination algorithm. The detection of the vehicle takes the position information obtained by YOLOv3 as the input of the LK optical flow algorithm and forms an optical flow vector to complete the vehicle speed detection. Experimental results show that the detection algorithm can detect the vehicle speed and traffic state discrimination method can judge the traffic state accurately, which has a strong anti-interference ability and meets the practical application requirements.
Highlights
With the significant increase of motor vehicles, traffic congestion is recognized as a serious problem globally
The main contributions of this study are as follows: (1) The LK optical flow method is improved by combining with the YOLOv3 algorithm to determine the exact position of the current vehicle and calculate the vehicle speed, which reduces the calculation of the optical flow value and achieves the real time performance without accuracy loss
Wu proposed a feature-matching vehicle speed measurement based on single shot multibox detector (SSD) in [32], where SSD is first used as the target detection algorithm to get the target vehicle position and the optical flow method is employed to calculate the vehicle speed
Summary
With the significant increase of motor vehicles, traffic congestion is recognized as a serious problem globally. [9] proposed a method on the basis of multisource global positioning system (GPS) data, which takes the k-means algorithm to cluster the data, obtain the average speed within the cluster, and determine the traffic congestion state. This study proposes a new method that utilizes the four vertices of the vehicle target frame detected by YOLOv3 in [18] as the tracking points of the LK optical flow method [19], which greatly simplifies the calculation. (1) The LK optical flow method is improved by combining with the YOLOv3 algorithm to determine the exact position of the current vehicle and calculate the vehicle speed, which reduces the calculation of the optical flow value and achieves the real time performance without accuracy loss.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
