基于深度学习的转弯车流量检测方法  

Turning Traffic Flow Detection Method Based on Deep Learning

作　　者：张韡 李永 刘涛 哈敏捷 ZHANG Wei;LI Yong;LIU Tao;HA Min-jie(Key Laboratory of Transportation Industry of Automobile Transportation Safety and Security Technology,Chang an University,Xi'an 710018,China;Xi'an BYD Auto Co.,Ltd.,Xi'an 710018,China)

机构地区：[1]长安大学汽车运输安全保障技术交通行业重点实验室,西安710018 [2]西安比亚迪汽车有限公司,西安710018

出　　处：《科学技术与工程》2025年第4期1701-1710,共10页Science Technology and Engineering

基　　金：国家自然科学基金面上项目(51978075)。

摘　　要：为方便统计转弯车流量,并提升交叉口转弯车流量的检测速度与精度,提出基于深度学习的方法对城市交叉口转弯车流量进行检测、跟踪和计数。首先,通过对比分析选用轻量高效的YOLOv5s作为目标检测框架,并采用无人机(unmanned aerial vehicle,UAV)航拍方式获取城市交叉口交通流视频,自建车辆航拍图像数据集;利用预训练权重及最新权重文件完成自建数据集的训练与推理;模型评估表明,基于YOLOv5的车辆检测模型具有较高的检测速度与精度:其中模型的box_loss值迅速下降并稳定在0.038,mAP_0.5值迅速上升并保持在0.91附近;之后,对接DeepSORT模型作为后端多车辆跟踪算法,通过坐标转换以简化车辆轨迹提取,并对行驶轨迹线展开有效性判断;针对检测框角点跃变现象,提出角点-质心点坐标变换以强化轨迹点的坐标信息鲁棒性,且采用六次多项式拟合车辆轨迹线,将不满足函数映射要求的轨迹线进行旋转优化,以正常拟合全部轨迹;最后根据预设的转弯角度判定阈值,实现转弯车辆的检测与计数。为验证所提出的转弯车流量检测方法的有效性,以某一城市交叉口为例进行车辆检测实验,对比分析人工计数值和本方法检测结果。结果表明:4个流向平均检测精度为92.9%,最高可达95.7%,能够满足实际交叉口场景转弯车流量的常规检测要求。In order to facilitate the counting of turning traffic flow and to enhance the detection speed and accuracy of turning traffic flow at intersections,a deep learning-based method was suggested for detecting,tracking,and counting turning traffic flow at urban crossings.Initially,the YOLOv5s,which was lightweight and efficient,was chosen as the target detection framework after conducting a comparative analysis.Unmanned aerial vehicle(UAV)aerial photography was utilized to record video footage of traffic movement at urban intersections,resulting in the development of a dataset of vehicle aerial photography photos.The pre-training weights and the most recent weight files were utilized to conduct training and testing on the self-constructed dataset.The model evaluation shows that the vehicle detection model using YOLOv5 exhibits great detection speed and accuracy.The model s box_loss value declines rapidly and stabilizes at 0.038,while the mAP_0.5 value climbs swiftly and stays near 0.91.After that,the DeepSORT model was used as the backend multi-vehicle tracking technique,and a corner-to-centroid coordinate transformation was used to simplify the extraction of vehicle trajectories.The precision of the driving trajectory line was evaluated thereafter.To improve the robustness of trajectory points coordinate information,a corner-point-center-of-mass point coordinate transformation was suggested to tackle the issue of corner points in the detection frame.A sixth-degree polynomial was used to model the vehicle trajectory.Unsuitable trajectory lines were rotated and optimized to meet the function mapping requirements and ensure good fitting of all trajectories.Turning vehicles were detected and counted by using a predetermined threshold to determine the turning angle.Ultimately,to validate the performance of the proposed turning vehicle flow detection method,vehicle detection experiments were conducted at a city intersection as an illustration.The manual counting values were compared and analyzed against the detection resu

关 键 词：交通信息工程 交通流检测 深度学习 转弯车辆 目标检测 车辆跟踪 

分 类 号：U495[交通运输工程—交通运输规划与管理]