一种基于复合框架的城市道路场景车辆轨迹提取方法

doi:10.16088/j.issn.1001-6600.2025032504

摘要/Abstract

摘要： 城市道路车辆轨迹提取对智能交通监管至关重要,但现有技术存在检测精度低、身份跳变导致轨迹断裂等问题。为了解决这些问题,本文提出融合改进YOLOv7-tiny检测、StrongSORT跟踪与Savitzky-Golay滤波优化的复合框架(integrated framework of improved YOLOv7-tiny detection, StrongSORT tracking, and Savitzky-Golay filtering optimization, IYSSG)。该框架能够利用交通监控设备采集的城市道路监控视频数据,高效提取不同车辆目标的轨迹。经过实验评估,IYSSG框架在3个主要任务中表现出色。在车辆检测方面,改进后的YOLOv7-tiny算法在保障检测速度的同时,精度、召回率和mAP@0.5相较于原始YOLOv7-tiny算法分别提升2.5、8.5和3.7个百分点;在车辆跟踪方面,StrongSORT算法相比于DeepSORT算法,MOTA(multiple object tracking accuracy)和MOTP(multiple object tracking precision)指标分别取得4.92和2.7个百分点的提升;在车辆轨迹提取与优化方面,Savitzky-Golay滤波算法有效解决因视频抖动和算法误差等客观因素导致的轨迹点缺失和轨迹不平滑问题,有助于研究人员从交通监控视频中提取精确的车辆轨迹,从而更好地分析定位交通问题。

关键词: YOLOv7-tiny, 目标检测, 深度学习, 多目标跟踪, 轨迹提取, 城市道路, 车辆轨迹

Abstract: Vehicle trajectory extraction on urban roads is crucial for intelligent transportation supervision, but existing techniques suffer from low detection accuracy and broken trajectories due to identity hopping. In this paper, a composite framework that fuses improved YOLOv7-tiny detection, StrongSORT tracking and Savitzky-Golay filter optimization is proposed. The framework is capable of efficiently extracting the trajectories of different vehicle targets using urban road surveillance video data collected by traffic monitoring devices. Based on experimental evaluation, the IYSSG framework performs well in three main tasks. In vehicle detection, the improved YOLOv7-tiny algorithm ensures the detection speed, while precision, recall rate and mAP@0.5 increase by 2.5%, 8.5%, and 3.7%, respectively, compared with the original YOLOv7-tiny algorithm. In terms of vehicle tracking, the StrongSORT algorithm achieves a 4.92% and 2.7% improvement in MOTA and MOTP metrics, respectively, compared with the DeepSORT algorithm. In terms of vehicle trajectory extraction and optimization, the Savitzky-Golay filtering algorithm effectively solves the problems of missing trajectory points and unsmooth trajectory due to objective factors such as video jitter and algorithmic errors, which helps the researchers to extract accurate vehicle trajectories from the traffic surveillance video for better analysis and localization of traffic problems.

Key words: YOLOv7-tiny, target detection, deep learning, multi-target tracking, trajectory extraction, urban road, vehicle track

中图分类号: U495;TP391.41

田晟, 冯帅涛, 李嘉. 一种基于复合框架的城市道路场景车辆轨迹提取方法[J]. 广西师范大学学报（自然科学版）, 2026, 44(2): 31-51.

TIAN Sheng, FENG Shuaitao, LI Jia. A Framework for Enhanced Vehicle Trajectory Extraction in Urban Road Scenes[J]. Journal of Guangxi Normal University(Natural Science Edition), 2026, 44(2): 31-51.

参考文献

[1] 胡昭华, 王长富.改进Faster R-CNN的遥感图像小目标检测算法[J].计算机工程与科学, 2024, 46(6):1063-1071.
[2] 邵延华, 张铎, 楚红雨, 等.基于深度学习的YOLO目标检测综述[J].电子与信息学报, 2022,44(10):3697-3708.
[3] YIN Q J, YANG W Z, RAN M Y, et al.FD-SSD:an improved SSD object detection algorithm based on feature fusion and dilated convolution[J].Signal Processing:Image Communication, 2021, 98:116402.DOI:10.1016/j.image.2021.116402.
[4] QIU M L, HUANG L, TANG B H.ASFF-YOLOv5:multielement detection method for road traffic in UAV images based on multiscale feature fusion[J].Remote Sensing, 2022, 14(14):3498.DOI:10.3390/rs14143498.
[5] HU S M, ZHAO F, LU H Z, et al.Improving YOLOv7-tiny for infrared and visible light image object detection on drones[J].Remote Sensing, 2023, 15(13):3214.DOI:10.3390/rs15133214.
[6] 范谦, 姚利德, 赵宇, 等.基于改进YOLOv7-Tiny的交通车辆与行人轻量级目标检测算法[J].扬州大学学报(自然科学版), 2024, 27(6):34-42.DOI:10.19411/j.1007-824x.2024.06.005.
[7] 火久元, 苏泓瑞, 武泽宇, 等.基于改进YOLOv8的道路交通小目标车辆检测算法[J].计算机工程, 2025, 51(1):246-257.DOI:10.19678/j.issn.1000-3428.0069825.
[8] 王国帅, 黄贻望, 刘建晓, 等.Transformer结构与注意力机制融合的无人机图像小目标识别方法[J].南京大学学报(自然科学), 2025, 61(2):214-222.DOI:10.13232/j.cnki.jnju.2025.02.003.
[9] BEWLEY A, GE Z Y, OTT L, et al.Simple online and realtime tracking[C]//2016 IEEE International Conference on Image Processing (ICIP).Piscataway,NJ:IEEE, 2016:3464-3468.DOI:10.1109/ICIP.2016.7533003.
[10] WOJKE N, BEWLEY A, PAULUS D.Simple online and realtime tracking with a deep association metric[C]//2017 IEEE International Conference on Image Processing (ICIP).New York, NY:ACM, 2017:3645-3649.DOI:10.1109/ICIP.2017.8296962.
[11] DU Y H, ZHAO Z C, SONG Y, et al.StrongSORT:make DeepSORT great again[J].IEEE Transactions on Multimedia, 2023, 25:8725-8737.DOI:10.1109/TMM.2023.3240881.
[12] LUO H, JIANG W, GU Y Z, et al.A strong baseline and batch normalization neck for deep person re-identification[J].IEEE Transactions on Multimedia, 2020, 22(10):2597-2609.DOI:10.1109/TMM.2019.2958756.
[13] SHENG W S, SHEN J H, HUANG Q M, et al.Multi-objective pedestrian tracking method based on YOLOv8 and improved DeepSORT[J].Mathematical Biosciences and Engineering, 2024, 21(2):1791-1805.DOI:10.3934/mbe.2024077.
[14] ZHANG Y N, ZHANG T, HUANG Z C.Multiple vehicle detection and tracking using improved YOLOv5 and strong SORT[C]//International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2022).Bellingham, WA:SPIE, 2023:66.DOI:10.1117/12.2674583.
[15] DHATBALE R, CHILUKURI B R.Deep learning techniques for vehicle trajectory extraction in mixed traffic[J].Journal of Big Data Analytics in Transportation, 2021, 3(2):141-157.DOI:10.1007/s42421-021-00042-3.
[16] 周雄峰.基于深度学习的多目标车辆轨迹自动采集方法[J].交通科技, 2021(4):135-140, 144.DOI:10.3963/j.issn.1671-7570.2021.04.030.
[17] 李俊彦, 宋焕生, 张朝阳, 等.基于视频的多目标车辆跟踪及轨迹优化[J].计算机工程与应用, 2020, 56(5):194-199.DOI:10.3778/j.issn.1002-8331.1904-0191.
[18] ZHU L, WANG X J, KE Z H, et al.BiFormer:vision transformer with bi-level routing attention[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Piscataway,NJ:IEEE, 2023:10323-10333.DOI:10.1109/CVPR52729.2023.00995.
[19] OUYANG D L, HE S, ZHANG G Z, et al.Efficient multi-scale attention module with cross-spatial learning[C]//2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).Piscataway,NJ:IEEE, 2023:1-5.DOI:10.1109/ICASSP49357.2023.10096516.
[20] DONG Z, WU Y W, PEI M T, et al.Vehicle type classification using a semisupervised convolutional neural network[J].IEEE Transactions on Intelligent Transportation Systems, 2015, 16(4):2247-2256.DOI:10.1109/TITS.2015.2402438.
[21] WEN L Y, DU D W, CAI Z W, et al.UA-DETRAC:a new benchmark and protocol for multi-object detection and tracking[J].Computer Vision and Image Understanding, 2020, 193:102907.DOI:10.1016/j.cviu.2020.102907.
[22] TIAN S, LI J, ZHANG J M, et al.STLRF-Stack:a fault prediction model for pure electric vehicles based on a high dimensional imbalanced dataset[J].IET Intelligent Transport Systems, 2023, 17(2):400-417.DOI:10.1049/itr2.12267.
[23] ZHANG L H, XIONG N, PAN X H, et al.Improved object detection method utilizing YOLOv7-tiny for unmanned aerial vehicle photographic imagery[J].Algorithms, 2023, 16(11):520.DOI:10.3390/a16110520.
[24] 刘浩翰, 樊一鸣, 贺怀清, 等.改进YOLOv7-tiny的目标检测轻量化模型[J].计算机工程与应用, 2023, 59(14):166-175.DOI:10.3778/j.issn.1002-8331.2302-0115.
[25] 李永上, 马荣贵, 张美月.改进YOLOv5s+DeepSORT的监控视频车流量统计[J].计算机工程与应用, 2022, 58(5):271-279.DOI:10.3778/j.issn.1002-8331.2108-0346.
[26] LI F F, CHEN Y, HU M, et al.Helmet-wearing tracking detection based on StrongSORT[J].Sensors, 2023, 23(3):1682.DOI:10.3390/s23031682.
[27] 李俊彦.交通场景中多目标车辆检测跟踪技术研究[D].西安:长安大学, 2020.DOI:10.26976/d.cnki.gchau.2020.000980.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed