计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (12): 190-198.doi: 10.11896/jsjkx.231100096

• 计算机图形学&多媒体 • 上一篇    下一篇

适于高动态视频场景下的城市道路违停检测算法

程梁华1,2, 黄瑞雪1,2, 沈鑫3   

  1. 1 重庆大学计算机学院 重庆 400044
    2 信息物理社会可信服务计算教育部重点实验室(重庆大学) 重庆 400044
    3 解放军陆军勤务学院勤务指挥系 重庆 401331
  • 收稿日期:2023-11-16 修回日期:2024-10-25 出版日期:2024-12-15 发布日期:2024-12-10
  • 通讯作者: 沈鑫(5912829@qq.com)
  • 作者简介:(asus378773285@163.com)
  • 基金资助:
    国家自然科学基金(62172063)

Urban Illegal On-road Parking Detection Algorithm for High Dynamic Video Scenarios

CHENG Lianghua1,2, HUANG Ruixue1,2, SHEN Xin3   

  1. 1 College of Computer Science, Chongqing University, Chongqing 400044, China
    2 Key Laboratory of Dependable Service Computing in Cyber Physical Society(Chongqing University), Ministry of Education, Chongqing 400044, China
    3 Department of Logistics Command, Army Logistics University, Chongqing 401331, China
  • Received:2023-11-16 Revised:2024-10-25 Online:2024-12-15 Published:2024-12-10
  • About author:CHENG Lianghua,born in 1998,master.His main research interests include vehicular crowdsensing,urban computing and deep learning.
    SHEN Xin,born in 1983,Ph.D.His main research interests include big data intelligence,service computing and AI.
  • Supported by:
    National Natural Science Foundation of China(62172063).

PDF (PC)

175

摘要： 日益突出的停车矛盾导致城市道路违停现象严重,给城市交通带来巨大安全隐患。因此,及时有效地监测并处理违停事件对于保障城市交通安全至关重要。然而,现有基于人工巡检和固定摄像头的违停监测方式存在效率低、监测范围受限等缺点,难以满足大规模城市违停监管的需求。群车感知作为一种新兴感知范式,通过激励用户在行车过程中采集道路视频并上传至云端进行监测,能为大规模、低成本的城市违停监管提供重要手段。然而车载视频场景十分复杂,这导致了车辆追踪目标的高丢失性和违停判断的高复杂性,给实现精准违停检测提出了严峻挑战。为应对上述挑战,提出适于高动态视频场景下的城市道路违停检测算法。具体地,首先通过对车载视频进行多车辆目标追踪,以跨视频帧追踪获取车辆图像信息;然后通过动态视觉测距将目标车辆图像信息转换为真实场景中的相对距离变化,并结合车间相互运动实现违停判断;最后,基于重庆市道路数据集对所提算法进行性能评估。实验结果表明,所提算法的违停车辆检测精度为87.1%,相比3种对比算法平均提高21.9%,且在不同违停场景下均表现出优异检测性能。

关键词: 违章停车检测, 群车感知, 车载视频, 多目标追踪, 动态视觉测距

Abstract: The increasing parking conflicts have led to serious parking violations on urban roads,posing a huge safety hazard to urban traffic.Therefore,timely and effective monitoring and handling of illegal parking events is essential to ensure urban traffic safety.However,existing illegal parking monitoring methods based on manual patrolling and fixed-point surveillance cameras have disadvantages such as low efficiency and limited monitoring range,which makes it difficult to meet the demand for large-scale urban monitoring.As an emerging sensing paradigm,vehicular crowdsensing can provide promising opportunities for large-scale and low-cost urban parking monitoring by motivating users to collect road videos while driving and upload them to the cloud.However,the complexity of in-vehicle video scenes,which leads to a high loss of vehicle target tracking and high complexity of parking judgment,poses a serious challenge to achieving accurate illegal on-road parking detection.To solve the above challenges,we propose an urban illegal on-road parking detection algorithm for high dynamic video scenarios.Specifically,first,we obtain vehicle image information across video frames through multi-vehicle target tracking on in-vehicle videos,Then,we convert the target vehicle image information into relative distance changes in real scenes through dynamic visual ranging and integrate it with the inter-vehicle movement to achieve the judgment of illegal parking.Finally,the performance of the proposed algorithm is evaluated based on the road dataset in Chongqing City.Experimental results show that the proposed algorithm achieves a detection accuracy of 87.1% for illegal parking vehicles,which is 21.9% higher than three baselines on average,and it shows excellent detection performance in different illegal parking scenarios.

Key words: Illegal on-road parking detection, Vehicular crowdsensing, In-vehicle video, Multiple targets tracking, Dynamic visual ranging

中图分类号: 

  • TP393
[1]人民网.2021年全国机动车保有量达3.95亿 新能源汽车同比增59.25%[EB/OL].(2022-01-12)[2023-10-28].http://www.gov.cn/xinwen/2022-01/12/content_5667715.htm.
[2]人民网.高德地图联合清华大学交通研究所发布全国停车场分析报告[EB/OL].(2022-01-07)[2023-10-28].http://finance.people.com.cn/n1/2022/0107/c1004-32326295.html.
[3]找法网.城市乱停车问题分析及对策[EB/OL].(2019-09-23)[2023-10-28].https://china.findlaw.cn/xfwq/xiaofeiweiquanlunwen/49875.html.
[4]九江频道.浅析乱停车现象的成因、影响及对策[EB/OL].(2013-07-05)[2023-10-28].https://jj.jxnews.com.cn/system/2013/07/05/012501843.shtml.
[5]BBC N.CCTV:Too many cameras useless,warns surveillance watchdog Tony Porter[EB/OL].(2019-01-26)[2023-11-01].https://www.bbc.com/news/uk-30978995.
[6]TELECOMTV.IDC releases China video surveillance equipment tracker report ai & 5g bring video surveillance to a new era[EB/OL].(2019-09-23)[2023-11-01].https://www.telecomtv.com/content/video-technology/idc-releases-china-video-surveillance-equipment-tracker-report-ai-5g-bring-video-surveillance-to-a-new-era-36395/.
[7]XIANG C,LI Y,ZHOU Y,et al.A comparative approach to re-surrecting the market of mod vehicular crowdsensing[C]//Proceedings of IEEE INFOCOM 2022-IEEE Conference on Computer Communications.IEEE,2022:1479-1488.
[8]XIANG C,CHENG W,LIN C,et al.LSTAloc:A driver-oriented incentive mechanism for mobility-on-demand vehicular crowd-sensing market[J].IEEE Transactions on Mobile Computing,2023,23(4):3106-3122.
[9]XIE X,WANG C,CHEN S,et al.Real-time illegal parking detection system based on deep learning[C]//Proceedings of the 2017 International Conference on Deep Learning Technologies.ACM,2017:23-27.
[10]TONG P,LI M,LI M,et al.Large-scale vehicle trajectory reconstruction with camera sensing network[C]//Proceedings of the 27th Annual International Conference on Mobile Computing and Networking.ACM,2021:188-200.
[11]HE T,BAO J,LI R,et al.Detecting vehicle illegal parkingevents using sharing bikes’ trajectories[C]//Proceedings of ACM SIGKDD International Conference on Knowledge Disco-very and Data Mining.ACM,2018:340-349.
[12]XU S,CHEN X,PI X,et al.ilocus:Incentivizing vehicle mobility to optimize sensing distribution in crowd sensing[J].IEEE Transactions on Mobile Computing,2019,19(8):1831-1847.
[13]XU T,ZHU H,ZHAO X,et al.Taxi driving behavior analysis in latent vehicle-to-vehicle networks:A social influence perspective[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,2016:1285-1294.
[14]XIANG C C,LI Y Y,FENG L,et al.Near-optimal vehicularcrowdsensing task allocation empowered by deep reinforcement learning[J].Chinese Journal of Computers,2022,45(5):918-934.
[15]PENG X,SONG R,CAO Q,et al.Real-time illegal parking detection algorithm in urban environments[J].IEEE Transactions on Intelligent Transportation Systems,2022,23(11):20572-20587.
[16]MATSUDA A,MATSUI T,MATSUDA Y,et al.A system for real-time on-street parking detection and visualization on an edge device[C]//Proceedings of 2021 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events.IEEE,2021:227-232.
[17]MARVASTI-ZADEH S M,CHENG L,GHANEI-YAKHDAN H,et al.Deep learning for visual tracking:A comprehensive survey[J].IEEE Transactions on Intelligent Transportation Systems,2021,23(5):3943-3968.
[18]FORTMANN T,BAR-SHALOM Y,SCHEFFE M.Sonartracking of multiple targets using joint probabilistic data association[J].IEEE Journal of Oceanic Engineering,1983,8(3):173-184.
[19]WANG Z,ZHENG L,LIU Y,et al.Towards real-time multi-object tracking[C]//Proceedings of European Conference on Computer Vision.Springer,2020:107-122.
[20]KHALKHALI M B,VAHEDIAN A,YAZDI H S.Situation assessment-augmented interactive Kalman filter for multi-vehicle tracking[J].IEEE Transactions on Intelligent Transportation Systems,2021,23(4):3766-3776.
[21]TONG P,LI M,LI M,et al.Large-scale vehicle trajectory reconstruction with camera sensing network[C]//Proceedings of the 27th Annual International Conference on Mobile Computing and Networking.ACM,2021:188-200.
[22]BEWLEY A,GE Z,OTT L,et al.Simple online and realtime tracking[C]//Proceedings of 2016 IEEE International Confe-rence on Image Processing.IEEE,2016:3464-3468.
[23]WOJKE N,BEWLEY A,PAULUS D.Simple online and realtime tracking with a deep association metric[C]//Proceedings of 2017 IEEE International Conference on Image Processing.IEEE,2017:3645-3649.
[24]REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:Unified,real-time object detection[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2016:779-788.
[25]ZAIDI Z R,MARK B L.Real-time mobility tracking algorithms for cellular networks based on Kalman filtering[J].IEEE Transactions on Mobile Computing,2005,4(2):195-208.
[26]MUNKRES J.Algorithms for the assignment and transportation problems[J].Journal of the Society for Industrial and Applied Mathematics,1957,5(1):32-38.
[27]YE M,SHEN J,LIN G,et al.Deep learning for person re-identification:A survey and outlook[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2021,44(6):2872-2893.
[28]ZHANG Z.A flexible new technique for camera calibration[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(11):1330-1334.
[29]CREATIVECOMMONS.Android camera api[EB/OL].(2012-8-11)[2023-11-01].https://www.android-doc.com/guide/to-pics/media/index.html.
[30]EVERINGHAM M,ESLAMI S A,VAN GOOL L,et al.Thepascal visual object classes challenge:A retrospective[J].International Journal of Computer Vision,2015,111(1):98-136.
[31]LIU X,LIU W,MEI T,et al.A deep learning-based approach to progressive vehicle re-identification for urban surveillance[C]//Proceedings of European Conference on Computer Vision.Springer,2016:869-884.
[32]REN S,HE K,GIRSHICK R,et al.Faster r-cnn:Towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
[33]LIU W,ANGUELOV D,ERHAN D,et al.SSD:Single shotmultiBox detector[C]//Proceedings of European Conference on Computer Vision.Springer,2016:21-37.
[34]GRASSI G,JAMIESON K,BAHL P,et al.Parkmaster:An in-vehicle,edge-based video analytics service for detecting open parking spaces in urban environments[C]//Proceedings of the Second ACM/IEEE Symposium on Edge Computing.ACM,2017:1-14.
[35]刘丹萍,汪珺,葛文祥.面向园区场景的车道线局部定位检测方法研究[J].重庆工商大学学报(自然科学版),2022,39(4):19-25.
[36]XIANG C C,CHENG W H,ZHANG Z,et al.Large-scale traffic data adaptive recovery empowered by edge computing[J].Journal of Computer Research and Development,2023,60(3):619-634.
[37]XIANG C,CHENG W,ZHENG X,et al.Enabling cost-effective wireless data collection by piggybacking on delivery drones in agriculture[J/OL].https://dl.acm.org/doi/pdf/10.1145/3595296.
[38]CHEN D,SHIN K G.Turnsmap:Enhancing driving safety at intersections with mobile crowdsensing and deep learning[J].Proceedings of the ACM on Interactive,Mobile,Wearable and Ubiquitous Technologies,2019,3(3):1-22.
[39]XIANG C,YANG P,TIAN C,et al.CARM:Crowd-sensing accurate outdoor RSS maps with error-prone smartphone measurements[J].IEEE Transactions on Mobile Computing,2015,15(11):2669-2681.
[40]XIANG C,HE S,SHIN K G,et al.Incentivizing platform-user interactions for crowdsensing[J].IEEE Internet of Things Journal,2020,8(10):8314-8327.
[41]WU X G,CHU Z B,ZHENG X,et al.Sparse random projection compressive data gathering in lossy wireless sensor networks[J].Chinese Journal of Computers,2019,42(2):158-172.
[42]PANG X,WANG Z,LIU D,et al.Towards personalized privacy-preserving truth discovery over crowdsourced data streams[J].IEEE/ACM Transactions on Networking,2021,30(1):327-340.
[43]WANG Z,LIU K,HU J,et al.Attrleaks on the edge:Exploiting information leakage from privacy-preserving co-inference[J].Chinese Journal of Electronics,2023,32(1):1-12.
[44]WANG Z,CHEN Y,ZHENG H,et al.Body RFID skeleton-based human activity recognition using graph convolution neural network[J].IEEE Transactions on Mobile Computing,2023,23(6):7301-7317.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发