面向群车协同感知的车载视频压缩算法

doi:10.11896/jsjkx.250400103

计算机科学 ›› 2026, Vol. 53 ›› Issue (4): 308-317.doi: 10.11896/jsjkx.250400103

• 计算机图形学&多媒体 • 上一篇下一篇

面向群车协同感知的车载视频压缩算法

江子贤¹, 喻赛萱², 黄瑞雪¹, 沈鑫³, 黄河清⁴

1 重庆大学计算机学院重庆 400044
2 四川财经职业学院信息学院成都 610101
3 联勤保障部队工程大学勤务指挥系重庆 401331
4 重庆开放大学重庆工商职业学院重庆 400053

收稿日期:2025-04-22 修回日期:2025-07-25 出版日期:2026-04-15 发布日期:2026-04-08
通讯作者: 沈鑫(sxfrank0216@163.com)
作者简介:(202314131102T@stu.cqu.edu.cn)
基金资助:
重庆市教委重点科技项目(KJZD-K202404002);合川区科技项目(HCKJ-2024-112)

Vehicle-mounted Video Compression Algorithm for Collaborative Vehicle Crowdsensing

JIANG Zixian¹, YU Saixuan², HUANG Ruixue¹, SHEN Xin³, HUANG Heqing⁴

1 College of Computer Science, Chongqing University, Chongqing 400044, China
2 College of Information, Sichuan Vocational College of Finance and Economics, Chengdu 610101, China
3 Department of Logistics Command, Engineering University of the Joint Logistics Support Force, Chongqing 401331, China
4 College of Chongqing Technology and Business, Chongqing Open University, Chongqing 400053, China

Received:2025-04-22 Revised:2025-07-25 Published:2026-04-15 Online:2026-04-08
About author:JIANG Zixian,born in 2001,master.His main research interests include vehicular crowdsensing and urban computing.
SHEN Xin,born in 1983,master.His main research interests include big data intelligence,service computing and AI.
Supported by:
Chongqing Municipal Education Commission(KJZD-K202404002) and Hechuan District Science and Technology Bureau(HCKJ-2024-112).

摘要/Abstract

摘要： 群车协同感知通过大幅度拓展汽车的感知范围,能够极大地提升自动驾驶和辅助驾驶的安全性。但在传输高精度、大容量车载视频感知数据时,其仍面临时延大的问题。为了解决该问题,一些研究通过去除车载视频中包含无效信息的冗余帧,来有效降低数据传输时延。然而,由于车载视频中关键信息动态变化且特征复杂,存在表征帧间关键与冗余信息难、平衡关键信息保留率与压缩率难两个挑战。对此,提出面向群车协同感知的车载视频压缩算法,旨在兼顾信息保真与压缩效率。首先,利用目标检测和多目标追踪算法,跨视频帧提取关键信息的连续特征。然后,基于提取特征的低秩特性,将复杂的关键与冗余信息表征转化为低秩稀疏矩阵分解问题,并通过非精确增广拉格朗日法进行迭代优化,以准确提取视频的关键部分。最后,基于重庆市真实道路数据集和公共数据集BDD100K的部分数据对所提算法进行性能评估。实验结果表明,相比4种对比算法,所提算法在不同交通状况下的关键信息保留率平均提高12.99%,且传输时间平均缩短61.24%。

关键词: 视频压缩, 群车协同感知, 低秩稀疏分解, 多目标追踪, 增广拉格朗日法

Abstract: Collaborative vehicle crowdsensing significantly extends the perception range of individual cars,thereby greatly enhancing the safety of autonomous and assisted driving.However,it also faces the challenge of high transmission latency when dealing with high-precision,large-volume sensory data such as vehicle-mounted video.To solve this problem,the data transmission delay can be effectively reduced by removing redundant frames with invalid information from vehicle-mounted video.However,the dynamics and complexity of key information in vehicle-mounted video pose significant challenges in representing key and redundant information between frames and balancing the key information retention rate and compression rate.To solve the above challenges,this paper proposes a vehicle-mounted video compression algorithm for collaborative vehicle crowdsensing,aiming to balance information fidelity and compression efficiency.Specifically,it first employs target detection and multi-target tracking algorithms to extract continuous features of key information across video frames.Then,based on the low-rank property of video features,it converts the complex key and redundant information representation into a low-rank sparse matrix decomposition problem.Furthermore,it leverages the inexact augmented Lagrangian method to solve the problem.Finally,it evaluates the performance of the proposed algorithm using the real road dataset in Chongqing city and selected data from the public dataset BDD100K.Experimental results show that the proposed algorithm achieves an average 12.99% improvement in key information retention over four baseline methods under different traffic conditions,while reducing the transmission delay by 61.24% on average compared to the original video transmission.

Key words: Vedio compression, Collaborative vehicle crowdsensing, Low rank and sparse decomposition, Multiple targets tra-cking, Augmented Lagrangian method

中图分类号:

TP393

江子贤, 喻赛萱, 黄瑞雪, 沈鑫, 黄河清. 面向群车协同感知的车载视频压缩算法[J]. 计算机科学, 2026, 53(4): 308-317. https://doi.org/10.11896/jsjkx.250400103

JIANG Zixian, YU Saixuan, HUANG Ruixue, SHEN Xin, HUANG Heqing. Vehicle-mounted Video Compression Algorithm for Collaborative Vehicle Crowdsensing[J]. Computer Science, 2026, 53(4): 308-317. https://doi.org/10.11896/jsjkx.250400103

参考文献

[1]人民网.公安机关已累计发放自动驾驶汽车测试号牌1.6万张[EB/OL].(2024-08-27)[2024-12-17].https://www.gov.cn/lianbo/bumen/202408/content_6970854.htm.
[2]澎湃新闻.蔚来31岁车主车祸身亡背后的自动驾驶盲区[EB/OL].(2021-08-18)[2024-12-17].https://www.thepaper.cn/newsDetail_forward_14087952.
[3]NTSB.Collision Between Vehicle Controlled by Developmental Automated Driving System and Pedestrian[EB/OL].(2018-03-18)[2024-12-17].https://www.ntsb.gov/investigations/AccidentReports/Reports/HAR1903.pdf.
[4]ZHANG Q,ZHANG X,ZHU R,et al.Robust Real-Time Multi-Vehicle Collaboration on Asynchronous Sensors[C]//Procee-dings of the International Conference on Mobile Computing and Networking.ACM,2023:1-15.
[5]智能汽车资源网.自动驾驶传感器能“看”多远[EB/OL].(2021-08-24)[2024-12-20].https://www.smartautoclub.com/p/10250/.
[6]XIAO Z,SHU J,JIANG H,et al.Toward Collaborative Occlusion-Free Perception in Connected Autonomous Vehicles[J].IEEE Transactions on Mobile Computing,2024,23(5):4918-4929.
[7]CHAN Q,TANG S,YANG Q,et al.Cooper:Cooperative Per-ception for Connected Autonomous Vehicles Based on 3D Point Clouds[C]//Proceedings of the IEEE International Conference on Distributed Computing Systems.IEEE,2019:514-524.
[8]JIANG X,YU F R,SONG T,et al.Intelligent Resource Allocation for Video Analytics in Blockchain-Enabled Internet of Autonomous Vehicles With Edge Computing[J].IEEE Transactions on Network Science and Engineering,2020,7(4):2205-2218.
[9]XIANG C,ZHANG Z,QU Y,et al.Edge Computing-Empowe-red Large-Scale Traffic Data Recovery Leveraging Low-Rank Theory[J].IEEE Transactions on Network Science and Engineering,2020,7(4):2205-2218.
[10]ZHOU E,LI Z,LIU D,et al.Balancing Electric Scooter Battery Swapping Network by Spatio-Temporal Recommendation[J].IEEE Transactions on Intelligent Transportation Systems,2024,25(12):21315-21326.
[11]HAN Y,ZHANG H,LI H,et al.Collaborative Perception inAutonomous Driving:Methods,Datasets,and Challenges[J].IEEE Intelligent Transportation Systems Magazine,2023,15(6):131-151.
[12]DUAN X,JIANG H,TIAN D,et al.V2I Based Environment Perception for Autonomous Vehicles at Intersections[J].China Communications,2021,18(7):1-12.
[13]ZHANG K,LIU Y,ZHANG W,et al.π-Learner:A Lifelong Roadside Learning Framework for Infrastructure Augmented Autonomous Driving[J].Computer,2022,55(6):30-39.
[14]XIANG C,CHENG W,LIN C,et al.LSTAloc:A Driver-Oriented Incentive Mechanism for Mobility-on-Demand Vehicular Crowdsensing Market[J].IEEE Transactions on Mobile Computing,2023,23(4):3106-3122.
[15]ZHANG Y,LIU K,BAO H,et al.PMPF:Point-Cloud Multiple-Pixel Fusion-Based 3D Object Detection for Autonomous Driving[J].Remote Sensing,2023,15(6):1580-1603.
[16]DANAPAL G,SANTOS G A,DA COSTA J P C L,et al.Sensor Fusion of Camera and LiDAR Raw Data for Vehicle Detection[C]//Proceedings of Workshop on Communication Networks and Power Systems.IEEE,2020:1-6.
[17]XIANG C,LI Y,ZHOU Y,et al.A Comparative Approach to Resurrecting the Market of MOD Vehicular Crowdsensing[C]//Proceedings of IEEE Conference on Computer Communications.IEEE,2022:1479-1488.
[18]XIANG C,ZHOU Y,DAI H,et al.Reusing Delivery Drones for Urban Crowdsensing[J].IEEE Transactions on Mobile Computing,2021,22(5):2972-2988.
[19]HE Z,WANG L,YE H,et al.Resource Allocation based on Graph Neural Networks in Vehicular Communications[C]//Proceedings of the IEEE Global Communications Conference.IEEE,2020:1-5.
[20]AOKI S,HIGUCHI T,ALTINTAS O.Cooperative Perception with Deep Reinforcement Learning for Connected Vehicles[C]//Proceedings of the IEEE Intelligent Vehicles Symposium.IEEE,2020:328-334.
[21]LU G,ZHANG X,OUYANG W,et al.An End-to-End Learning Framework for Video Compression[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2021,43(10):3292-3308.
[22]COHEN R A,CHOI H,BAJIC I V.Lightweight Compression of Neural Network Feature Tensors for Collaborative Intelligence[C]//Proceedings of the IEEE International Conference on Multimedia and Expo.IEEE,2020:1-6.
[23]TAN T,CAO G.Deep Learning on Mobile Devices Through Neural Processing Units and Edge Computing[C]//Proceedings of the IEEE Conference on Computer Communications.IEEE,2022:1209-1218.
[24]ZHANG X,WU X.Attention-Guided Image Compression byDeep Reconstruction of Compressive Sensed Saliency Skeleton[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.IEEE,2021:13354-13364.
[25]SHAHAM T R,MICHAELI T.Deformation Aware ImageCompression[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.IEEE,2018:2453-2462.
[26]CHEN D,CHEN Q,ZHU F.Pixel-Level Texture Segmentation Based AV1 Video Compression[C]//Proceedings of the IEEE International Conference on Acoustics,Speech and Signal Processing.IEEE,2019:1622-1626.
[27]SENGAR S S,MUKHOPADHYAY S.Motion Segmentation-Based Surveillance Video Compression Using Adaptive Particle Swarm Optimization[J].Neural Computing and Applications,2020,32(15):11443-11457.
[28]GUO G,ZHAO S.3D Multi-Object Tracking With Adaptive Cubature Kalman Filter for Autonomous Driving[J].IEEE Transactions on Intelligent Vehicles,2022,8(1):512-519.
[29]MA H,WEI X,WANG P,et al.Multi-Arm Global CooperativeCoal Gangue Sorting Method Based on Improved Hungarian Algorithm[J].Sensors,2022,22(20):7987-8007.
[30]STRANG G.Introduction to Linear Algebra,Sixth Edition[M].Wellesley-Cambridge Press,2022:1-12.
[31]ZHANG X,LIN W,XIONG R,et al.Low-Rank Decomposition-Based Restoration of Compressed Images via Adaptive Noise Estimation[J].IEEE Transactions on Image Processing,2016,25(9):4158-4171.
[32]NIE F,YUAN J,HUANG H.Optimal Mean Robust PrincipalComponent Analysis[C]//Proceedings of the International Conference on Machine Learning.JMLR,2014:1062-1070.
[33]XIA Y,ZHANG D,KIM J,et al.Predicting Driver Attention in Critical Situations[C]//Proceedings of the Computer Vision.Springer,2018:658-674.
[34]SURESH M,SAM I S.Exponential Fractional Cat Swarm Optimization for Video Steganography[J].Multimedia Tools and Applications,2021,80(9):13253-13270.
[35]MU H,LI J,SU J,et al.Fast Detection Method for Pedestrian Video Abnormal Behavior Based on Keyframe Extraction and Multi-Task Mixed Model[C]//Proceedings of the IEEE International Symposium on Parallel and Distributed Processing with Applications.IEEE,2024:1925-1930.
[36]BAO G,LI D,MEI Y.Key Frames Extraction Based on Optical-Flow and Mutual Information Entropy[C]//Proceedings of the Journal of Physics:Conference Series.IOP,2020:1646-1652.
[37]WANG Y,CHAN P H,DONZELLA V.Semantic-Aware Video Compression for Automotive Cameras[J].IEEE Transactions on Intelligent Vehicles,2023,8(6):3712-3722.
[38]SHI Y,YANG Y,WU Y.Federated Edge Learning With Differential Privacy:An Active Reconfigurable Intelligent Surface Approach[J].IEEE Transactions on Wireless Communications,2024,23(11):17368-17383.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

面向群车协同感知的车载视频压缩算法

Vehicle-mounted Video Compression Algorithm for Collaborative Vehicle Crowdsensing

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	唐心亮, 潘晓润, 王建超, 苏鹤. 融合ByteTrack的EAP-YOLOv8无人机Marker点检测与追踪 Integrate ByteTrack’s EAP-YOLOv8 UAV Marker Point Detection and Tracking 计算机科学, 2026, 53(3): 266-276. https://doi.org/10.11896/jsjkx.241100115
[2]	马一心, 曾军皓, 杨鑫岩, 梁刚. 基于多目标追踪的视频无关人员自动识别 Automatic Recognition of Irrelevant Individuals in Videos Based on Multi-object Tracking 计算机科学, 2025, 52(11A): 241100155-8. https://doi.org/10.11896/jsjkx.241100155
[3]	程梁华, 黄瑞雪, 沈鑫. 适于高动态视频场景下的城市道路违停检测算法 Urban Illegal On-road Parking Detection Algorithm for High Dynamic Video Scenarios 计算机科学, 2024, 51(12): 190-198. https://doi.org/10.11896/jsjkx.231100096
[4]	赵敏, 刘惊雷. 基于高斯场和自适应图正则的半监督聚类 Semi-supervised Clustering Based on Gaussian Fields and Adaptive Graph Regularization 计算机科学, 2021, 48(7): 137-144. https://doi.org/10.11896/jsjkx.200800190
[5]	王海燕,殷俊,潘显萌. 基于Surfacelet变换和SPIHT算法的视频压缩 Video Compression Based on Surfacelet Transform and SPIHT Algorithm 计算机科学, 2016, 43(Z11): 237-239. https://doi.org/10.11896/j.issn.1002-137X.2016.11A.054
[6]	张旭,蒋建国,洪日昌,杜跃. 基于低秩稀疏分解与协作表示的图像分类算法 Image Classification Algorithm Based on Low Rank and Sparse Decomposition and Collaborative Representation 计算机科学, 2016, 43(7): 83-88. https://doi.org/10.11896/j.issn.1002-137X.2016.07.014
[7]	朱光喜戴声奎李霄刘文予张江山. 一种低码率下的新型码率控制策略计算机科学, 2006, 33(1): 60-63.
[8]	董海燕张其善. 基于最小匹配误差方向预测的快速半像素运动估计计算机科学, 2005, 32(9): 218-220.
[9]	胡旭刘晓明杨士中仲元红陈涛. 基于红外视频的变电站监控系统的实现计算机科学, 2005, 32(8): 241-244.
[10]	张剑郑心炜. 基于对象的编码模式优化选择算法计算机科学, 2005, 32(7): 125-127.
[11]	郭建军戴葵成运王志英. H．264中块分割模式选择算法研究计算机科学, 2005, 32(11): 25-26.
[12]	曾玮薛向阳. 基于运动特征的视频信息检索综述计算机科学, 2004, 31(2): 135-138.
[13]	张剑. H．264标准量化的16位算法计算机科学, 2004, 31(11): 60-62.
[14]	陈蜀宇杨茂斌. 基于Internet传输的视频压缩编码技术现状与发展计算机科学, 2003, 30(9): 111-116.
[15]	许平谈宁韡郭胜陆桑璐谢立. 基于MPEG－4的视频检索技术研究计算机科学, 2003, 30(7): 60-63.