Vehicle speed detection method in single-camera videos in close-range photogrammetry

doi:10.13474/j.cnki.11-2246.2024.0304

Abstract

Abstract: Speed detection plays a crucial role in ensuring the safe operation of vehicles in urban transportation systems, making it essential for maintaining traffic safety. However, existing methods for measuring vehicle speed suffer from high costs, susceptibility to external conditions, and limitations in installation areas. To address these issues, this paper proposes a low-cost and flexible vehicle recognition and speed measurement method based on video imagery. The approach utilizes deep learning techniques to construct the YOLOv4 framework and train it on the COCO dataset for vehicle identification. The recognition method is improved by extracting the pixel coordinates of the midpoint of the lower boundary of the maximum bounding rectangle encompassing the recognized vehicles. Additionally, a close-range photogrammetry method is introduced, and improvements are made to the collinearity equations to enable vehicle recognition in a single-camera setup. The displacement of vehicles is computed within a fixed time interval, and a velocity curve of vehicles within the monitoring area is plotted. Experimental validation is conducted to assess the feasibility and accuracy of the proposed method.

Key words: YOLOv4, close-range photogrammetry, single lens, vehicle speed detection

CLC Number:

ZHANG Shaobin, ZHANG Zhihua. Vehicle speed detection method in single-camera videos in close-range photogrammetry[J]. Bulletin of Surveying and Mapping, 2024, 0(3): 19-24.

References

[1] ZHANG Junping,WANG Feiyue,WANG Kunfeng,et al. Data-driven intelligent transportation systems:a survey[J]. IEEE Transactions on Intelligent Transportation Systems,2011,12(4):1624-1639.
[2] WANG Guolin,XIAO Deyun,GU J. Review on vehicle detection based on video for traffic surveillance[C]//Proceedings of 2008 IEEE International Conference on Automation and Logistics. Qingdao:IEEE,2008:2961-2966.
[3] HU L L,ZHANG Z W,ZHOU M Z,et al. Crushing behaviors and failure of packed batteries[J]. International Journal of Impact Engineering,2020,143:103618.
[4] SONG Huansheng,LIANG Haoxiang,LI Huaiyu,et al. Vision-based vehicle detection and counting system using deep learning in highway scenes[J]. European Transport Research Review,2019,11(1):51.
[5] CHEN Leiyu,LI Shaobo,BAI Qiang,et al. Review of image classification algorithms based on convolutional neural networks[J]. Remote Sensing,2021,13(22):4712.
[6] WU Jianping,LIU Zhaobin,LI Jinxiang,et al. An algorithm for automatic vehicle speed detection using video camera[C]//Proceedings of 2009 International Conference on Computer Science & Education.Nanning:IEEE,2009:193-196.
[7] ADNAN M A,SULAIMAN N,ZAINUDDIN N I,et al. Vehicle speed measurement technique using various speed detection instrumentation[C]//Proceedings of 2013 IEEE Business Engineering and Industrial Applications Colloquium. Langkawi:IEEE,2013:668-672.
[8] 靳慧云,李苑,谢贤能,等. 监控视频中目标车辆速度被动式测量方法研究[J]. 测绘通报,2012(8):47-50.
[9] 梁建术,贾汇沦,张琳琳. 基于监控视频图像车辆测速的研究[J]. 农业装备与车辆工程,2022,60(6):87-89.
[10] SANG Jun,WU Zhongyuan,GUO Pei,et al. An improved YOLOv2 for vehicle detection[J]. Sensors,2018,18(12):4272.
[11] LIN Chengjian,JENG S Y,LIOA H W. A real-time vehicle counting,speed estimation,and classification system based on virtual detection zone and YOLO[J]. Mathematical Problems in Engineering,2021,2021:1577614.
[12] 赵丽丽,唐阳山. 基于固定式视频的车速鉴定方法研究[J]. 山东交通科技,2022(2):111-113.
[13] YILMAZ H M,YAKAR M,GULEC S A,et al. Importance of digital close-range photogrammetry in documentation of cultural heritage[J]. Journal of Cultural Heritage,2007,8(4):428-433.
[14] JIANG Ruinian,JÁUREGUI D V,WHITE K R.Close-range photogrammetry applications in bridge measurement:literature review[J]. Measurement,2008,41(8):823-834.
[15] LUHMANN T. Close range photogrammetry for industrial applications[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2010,65(6):558-569.
[16] MOKROý M,LIANG Xinlian,SUROVŠ P,et al. Evaluation of close-range photogrammetry image collection methods for estimating tree diameters[J]. ISPRS International Journal of Geo-Information,2018,7(3):93.
[17] DU Xinguang,JIN Xianlong,ZHANG Xiaoyun,et al. Geometry features measurement of traffic accident for reconstruction based on close-range photogrammetry[J]. Advances in Engineering Software,2009,40(7):497-505.
[18] HAMZAH N B,SETAN H,MAJID Z. Reconstruction of traffic accident scene using close-range photogrammetrytechnique[J].Environmental Science,2010:129589944.
[19] EPSTEIN B,WESTLAKE B G. Determination of vehicle speed from recorded video using reverse projection photogrammetry and file metadata[J]. Journal of Forensic Sciences,2019,64(5):1523-1529.
[20] ABDEL-AZIZ Y I,KARARA H M,HAUCK M. Direct linear transformation from comparator coordinates into object space coordinates in close-range photogrammetry[J]. Photogrammetric Engineering & Remote Sensing,2015,81(2):103-107.
[21] EL-DIN FAWZY H. Study the accuracy of digital close range photogrammetry technique software as a measuring tool[J]. Alexandria Engineering Journal,2019,58(1):171-179.
[22] ROOM M M,AHMAD A. Mapping of a river using close range photogrammetry technique and unmanned aerial vehicle system[J]. IOP Conference Series:Earth and Environmental Science,2014,18:012061.
[23] ZAKRIA Z,DENG Jianhua,KUMAR R,et al. Multiscale and direction target detecting in remote sensing images via modified YOLO-v4[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2022,15:1039-1048.
[24] NEPAL U,ESLAMIAT H. Comparing YOLOv3,YOLOv4 and YOLOv5 for autonomous landing spot detection in faulty UAVs[J]. Sensors,2022,22(2):464.
[25] BOCHKOVSKIY A,WANG C Y,LIAO H. YOLOv4:optimal speed and accuracy of object detection[J].Computer Science,2020:216080778.
[26] KIM J A,SUNG J Y,PARK S H. Comparison of faster-RCNN,YOLO,and SSD for real-time vehicle type recognition[C]//Proceedings of 2020 IEEE International Conference on Consumer Electronics-Asia. Seoul:IEEE,2020:1-4.
[27] KUMAR B C,PUNITHA R,MOHANA. YOLOv3 and YOLOv4:multiple object detection for surveillance applications[C]//Proceedings of 2020 Third International Conference on Smart Systems and Inventive Technology. Tirunelveli:IEEE,2020:1316-1321.
[28] CAI Yingfeng,LUAN Tianyu,GAO Hongbo,et al. YOLOv4-5D:an effective and efficient object detector for autonomous driving[J]. IEEE Transactions on Instrumentation Measurement,2021,70:3065438.
[29] DU Shuangjiang,ZHANG Pin,ZHANG Baofu,et al. Weak and occluded vehicle detection in complex infrared environment based on improved YOLOv4[J]. IEEE Access,2021,9:25671-25680.
[30] NI Zhenhao,LIU Tingna,LI Ke,et al. Real-time vehicle detection and computer intelligent recognition through improved YOLOv4[J]. Journal of Physics:Conference Series,2021,2083(4):042006.
[31] WANG C Y,MARK LIAO H Y,WU Y H,et al. CSPNet:a new backbone that can enhance learning capability of CNN[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Seattle:IEEE,2020:390-391.
[32] HE Kaiming,ZHANG Xiangyu,REN Shaoqing,et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1904-1916.
[33] LIN T Y,MAIRE M,BELONGIE S,et al. Microsoft COCO:common objects in context[M]//Computer Vision-ECCV 2014. Cham:Springer International Publishing,2014:740-755.