计算机科学

计算机科学 ›› 2026, Vol. 53 ›› Issue (9): 180-187.doi: 10.11896/jsjkx.260300040

• 计算机图形学&多媒体 • 上一篇    下一篇

基于分散式多目视觉基线的移动目标协同测距方法研究

刘馨琳1, 吴克强1, 徐畅2, 李骁2   

  1. 1 浙江大学软件学院 浙江 宁波 315100
    2 河海大学信息科学与工程学院 江苏 常州 213251
  • 收稿日期:2026-03-09 修回日期:2026-06-14 出版日期:2026-09-15 发布日期:2026-09-10
  • 通讯作者: 吴克强(wkq@zju.edu.cn)
  • 作者简介:(liuxinlin6@126.com)
  • 基金资助:
    国网江苏省电力有限公司面向生产一线科技项目(B310B0244T2P-002)

Research on Collaborative Ranging Method for Moving Targets Based on Decentralized Multi-view Visual Baseline

LIU Xinlin1, WU Keqiang1, XU Chang2, LI Xiao2   

  1. 1 School of Software Technology,Zhejiang University,Ningbo,Zhejiang 315000,China
    2 School of Information Science and Engineering,Hohai University,Changzhou,Jiangsu 213251,China
  • Received:2026-03-09 Revised:2026-06-14 Published:2026-09-15 Online:2026-09-10
  • About author:LIU Xinlin,born in 2002,postgraduate.Her main research interest is artificial intelligence technology.
    WU Keqiang,born in 1982,Ph.D,researcher.His main research interests include artificial intelligence and cloud computing performance optimization.
  • Supported by:
    Science and Technology Project of State Grid Jiangsu Electric Power Co., Ltd. for Frontline Production(B310B0244T2P-002).

PDF (PC)

290

摘要： 摄像机广泛使用于公共场合及专业场景,但仅限于视频图像的捕捉,当有测距需求时,需要安装双目摄像机或其他测距设备。以变电站已安装的分散式摄像机为例,提出一种基于分散式多目视觉基线的协同测距方法,通过构建多组虚拟双目摄像机,实现对移动目标的测距。该方法利用变电站已有分散部署的高清摄像机,在已知位姿参数与基准目标的前提下,动态构建多组双目视觉测距基线,结合多视角图像的时间与空间一致性,实现移动目标的实时定位与安全距离测量。研究内容包括:多摄像机位姿参数的自标定与基线优选机制、基于双目几何约束的移动目标深度估计、融合语义分割的目标关键点匹配策略,以及多基线协同测距的加权融合算法。在实验室与真实变电站场景下的实验结果表明,所提方法能够在低算力边缘设备上实现厘米级测距精度,显著优于传统单基线双目系统,具有良好的工程适用性与推广价值。

关键词: 分散式摄像机, 双目测距, 多基线协同, 移动目标定位

Abstract: Cameras are widely deployed in public and professional environments,but their functionality is limited to capturing video images.When ranging is required,binocular cameras or other ranging devices need to be installed.Taking the decentralized cameras already installed in substations as an example,this paper proposes a collaborative ranging method based on decentralized multi-view visual baselines.By dynamically constructing multiple sets of virtual binocular pairs,the method enables ranging for moving targets without additional hardware.Utilizing existing high-definition cameras with known pose parameters and reference objects,the proposed approach dynamically establishes binocular baselines and integrates spatiotemporal consistency across multiple views to achieve real-time target localization and safety ranging.The research content includes:self-calibration and baseline optimization mechanism for multi-camera pose parameters,depth estimation of moving targets based on binocular geometric constraints,target keypoint matching strategy integrating semantic segmentation,and weighted fusion algorithm for multi-baseline collaborative ranging.Experimental results in laboratory and real substation scenarios show that the proposed method can achieve centimeter-level ranging accuracy on low-computing-power edge devices,significantly out performing traditional single-baseline binocular systems.It offers high engineering applicability and promotional value.

Key words: Decentralized cameras, Binocular ranging, Multi-baseline coordination, Moving target localization

中图分类号: 

  • TP391.41
[1] LI X S,LI Z L.Fast Distance Measurement Algorithm for Objects Based on Binocular Vision [J].Computer Applications and Software,2024,41(1):219-223,260.
[2] GODARD C,MAC AODHA O,FIRMAN M,et al.Digging into self-supervised monocular depth estimation[C] //Proceedings of the IEEE/CVF International Conference on Computer Vision.2019:3828-3838.
[3] YAO Y,LUO Z,LI S,et al.MVSNet:Depth inference for unstructured multi-view stereo[C] //Proceedings of the European Conference on Computer Vision.2018:767-783.
[4] LI H F,CHEN Q,HUANG Y H,et al.Research on Substation Camera Inspection Task Scheduling Method Based on Improved Discrete Black-Winged Kite Algorithm [J].Computer Science,2025,52(S2):219-228.
[5] WANG F,GALLIANI S,VOGEL C,et al.Iterative multi-view depth estimation with adaptive cost aggregation[C] //Procee-dings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2024:3210-3219.
[6] XU H,ZHANG J,CAI J,et al.Revisiting multi-view stereo:A robustified baseline for accuracy evaluation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2024,46(5):2788-2805.
[7] TIAN W J,MIN Y Z,WANG X.Safety distance detection for10 kV uninterrupted operation[J].Measurement,2025,254:117801.
[8] YUAN Z K,TANG J Q,WEI Z X.Semantic-driven spatial fusion for noise-resilient distance measurement in autonomous inspection of insulators[J].Advanced Engineering Informatics,2025,69(A):103823.
[9] DING Y,ZHU Q,LIU X,et al.TransMVSNet:Global context-aware multi-view stereo network with transformers[C] //Proceedings of the IEEE/CVF International Conference on Computer Vision.2023:12345-12354.
[10] CAO C H,ZHANG B,LI W H.Research on Geometric Con-straint Solving Technology Based on Trust Region Method [J].Computer Science,2007,5:208-209,221.
[11] KONG W J,SUN J,WANG C Y,et al.VINS-MultiCam:An ASLfeat-Based MultiCam Visual-Inertial Odometry Framework[C] //IEEE Conference on Robotics and Automation.2025.
[12] DIAZ-RAMIREZ V H,GONZALEZ-RUIZ M,JUAREZ-SALA-ZAR R,et al.Reliable Disparity Estimation Using Multiocular Vision with Adjustable Baseline[J].Sensors,2025,25(1):21.
[13] ZHANG Y,WANG Z,XU Y,et al.Dual supporting matching for multi-view target association[J].Advanced Engineering Informatics,2025,67:103485.
[14] CHEN S,LI Y,WANG G.Semantic-aware multi-view object association for crowded scenes[C] //Proceedings of the European Conference on Computer Vision.2024:567-583.
[15] SCHONBERGER J L,FRAHM J M.Structure-from-motion revisited[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:4104-4113.
[16] FISCHLER M A,BOLLES R C.Random sample consensus:aparadigm for model fitting with applications to image analysis and automated cartography[J].Communications of the ACM,1981,24(6):381-395.
[17] HU A L,QIN Y S.Improved adaptive weighted distance mea-surement and tracking of maritime targets [J].Electronic Technology Application,2024,50(7):20-28.
[18] WANG Q,WU B,ZHU P,et al.ECA-Net:Efficient channel attention for deep convolutional neural networks[C] //Procee-dings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:11534-11542.
[19] SUN L J,ZENG T F,WANG W J.Multi-modal Dual Attention Mechanism for Point Cloud Semantic Segmentation [J].Microelectronics and Computer,2025,42(8):58-66.
[20] ZHANG Z.A flexible new technique for camera calibration[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(11):1330-1334.
[21] LOWE D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[22] HUBERP J.Robust estimation of a location parameter[J].Annals of Mathematical Statistics,1964,35(1):73 101.
[23] HE K,ZHANG X,REN S,et al.Deep residual learning forimage recognition[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:770-778.
[24] CHEN L C,PAPANDREOU G,KOKKINOS I,et al.DeepLab:Semantic image segmentation with deep convolutional nets,atrous convolution,and fully connected CRFs[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,40(4):834-848.
[25] RONNEBERGER O,FISCHER P,BROX T.U-Net:Convolu-tional networks for biomedical image segmentation[C] //International Conference on Medical Image Computing and Compu-ter-Assisted Intervention.Springer,2015:234-241.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市两江新区洪湖西路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