| 108 | 0 | 74 |
| 下载次数 | 被引频次 | 阅读次数 |
【目的】随着我国引调水工程数量的逐渐增多，构建高效率的智慧巡检体系对引调水工程的长期安全运维具有重要意义。水工隧洞内的精确定位是ROV实现自主化巡检的关键和难题，而现有ROV水下定位方法主要面向海洋环境，常规定位方法在水工隧洞内难以发挥作用。【方法】提出一种基于视觉增强-惯性SLAM的水下定位技术。针对隧洞图像特征区域受限且特征模糊等问题，构建了基于DE-MFET的水下图像增强网络，融合深度信息和多尺度特征强化模块增强图像重要区域特征的通道响应，突出水下图像边缘局部细节特征，提高SLAM关键帧之间的特征匹配数量和效率；针对水工隧洞内特征弱及特征一致性强等导致视觉里程计易失效的问题，将增强的视觉里程计与惯性导航数据进行融合，进一步校正ROV瞬时位姿，提高ROV在水工隧洞中的定位精度。【结果】通过自制的水工隧洞数据集、LSUI和UIEB公开水下数据集验证提出的图像增强方法使水下图像质量显著提高，在UCIQE、UIQM评分值和ORB特征匹配数量方面均优于其他图像增强方法。并在湖北省鄂北水资源配置工程中进行ROV水下定位试验，结果表明视觉增强-惯性SLAM定位方法有效提升了ROV在水工隧洞内的定位精度。【结论】该定位方法在水工隧洞环境下具有一定的优越性和鲁棒性，为引调水工程智慧巡检方案提供重要研究基础。
Abstract：[Objective]With the increasing number of water transfer projects in China, establishing an efficient intelligent inspection system is crucial for the long-term safe operation and maintenance of water transfer projects. Precise positioning within hydraulic tunnels is key and challenging for ROVs to achieve autonomous inspection, while existing ROV underwater positioning method primarily target marine environments, making conventional positioning approaches difficult to apply effectively in hydraulic tunnels.[Methods]An underwater positioning technology based on enhanced visual-inertial SLAM is proposed. Aiming at the problems of limited feature regions and blurred features in tunnel images, an underwater image enhancement network based on DE-MFET is constructed. This network fuses depth information and multi-scale feature enhancement modules to enhance the channel response of important image features, highlight the local edge details of underwater images, and improve the quantity and efficiency of feature matching between SLAM keyframes. To counteract frequent visual odometry failures caused by weak features and strong feature homogeneity in hydraulic tunnels, enhanced visual odometry is fused with inertial navigation data to further correct the ROVs instantaneous pose, improving positioning accuracy in hydraulic tunnels.[Results]Validation using a self-developed hydraulic tunnel dataset, the LSUI and the UIEB public underwater dataset demonstrates that the proposed image enhancement method significantly improves underwater image quality, outperforming other enhancement method in UCIQE, UIQM scores, and ORB feature matching quantity. ROV underwater positioning experiments in Hubei's Ebei Water Resources Allocation Project confirm that the enhanced visual-inertial SLAM method effectively improves positioning accuracy within hydraulic tunnels.[Conclusion]This positioning method exhibits notable superiority and robustness in hydraulic tunnel environments, providing a critical research foundation for intelligent inspection solutions in water transfer projects.
[1] 黄会宝，谢辉，马芳平，等.引水隧洞表观缺陷智能检测与规律分析[J].中国农村水利水电，2023(8):259-264.HUANG H B,XIE H,MA F P,et al.Intelligent detection and law analysis of apparent defects in diversion tunnel[J].China rural water and hydropower,2023(8):259-264.
[2] 孙玉山，张力文，张国成，等.输水隧洞检测机器人发展现状及关键技术研究[J].哈尔滨工程大学学报，2025,46(7):1253-1267.SUN Y S,ZHANG L W,ZHANG G C,et al.Development and key technology research of AUVs in water conveyance tunnel detection[J].Journal of Harbin Engineering University,2025,46(7):1253-1267.
[3] 崔金良，张俊文，万雷，等.基于全景影像的引水隧洞结构缝检测方法及应用[J].人民长江，2022,53(7):135-141.CUI J L,ZHANG J W,WAN L,et al.Application of detection method of structural seams for water conveyance tunnel based on panoramic image[J].Yangtze River,2022,53(7):135-141.
[4] 陈松林，王立川，胡恒千，等.北江引水工程新型敞开式TBM断层破碎带塌方整治技术研究[J].隧道建设(中英文),2023,43(12):2122-2132.CHEN Songlin,WANG Lichuan,HU Hengqian,et al Research on collapse treatment technology of new open type TBM fault fracture zone in Beijiang water diversion project [J].Tunnel Construction,2023,43 (12):2122-2132.
[5] 王吉亮，向家菠，颜慧明，等.引江补汉工程输水线路工程地质选线研究[J].长江科学院院报，2023,40(5):100-105.WANG J L,XIANG J B,YAN H M,et al.Route selection for water diversion project from Three Gorges Reservoir to Hanjiang River based on engineering geology[J].Journal of Changjiang River Scientific Research Institute,2023,40(5):100-105.
[6] 陈亮，孙晨，王雷雨，等.水工隧洞超前预处理灌浆材料研究与应用进展[J].南水北调与水利科技(中英文),2024,22(6):1181-1188.CHEN L,SUN C,WANG L Y,et al.Research and application progress of grouting materials for advance pretreatment of headrace tunnel[J].South-to-North Water Transfers and Water Science &Technology,2024,22(6):1181-1188.
[7] 邓旭方，徐轶，阿依胡兰·阿山，等.基于多任务约束深度学习的水工隧洞缺陷检测方法研究[J].水利水电快报，2024,45(7):64-69.DENG X F,XU T,AYIHULAN A,et al.Research on hydraulic tunnel defect detection method based on deep learning model with multi-task constraint[J].Express Water Resources & Hydropower Information,2024,45(7):64-69.
[8] 朱轲涵，黄博伦，杨启.引水隧洞检测水下机器人运动控制研究[J].海洋工程装备与技术，2023,10(1):32-39.ZHU K H,HUANG B L,YANG Q,et al.Research on motion control of underwater vehicle for diversion tunnel detection[J].Ocean Engineering Equipment and Technology,2023,10(1):32-39.
[9] 陈永灿，陈嘉杰，王皓冉，等.大直径长引水隧洞水下检测机器人系统关键技术[J].清华大学学报(自然科学版),2023,63(7):1015-1031.CHEN Y C,CHEN J J,WANG H R,et al.Key technology of underwater inspection robot system for large diameter and long headrace tunnel[J].Journal of Tsinghua University(science and technology),2023,63(7):1015-1031.
[10] QI Z L,LIU D H,ZHANG J Y,et al.Micro-concrete crack detection of underwater structures based on convolutional neural network [J].Machine Vision and Applications,2022,33(5):74.
[11] 张世童，张宏伟，王延辉，等.自主水下航行器导航技术发展现状与分析[J].导航定位学报，2020,8(2):1-7.ZHANG S T,ZHANG H W,WANG Y H,et al.Development status and analysis of navigation technology for autonomous underwater vehicles[J].Journal of Navigation and Positioning,2020,8(2):1-7.
[12] 范刚，张亚，赵河明，等.水下机器人定位导航技术发展现状与分析[J].兵器装备工程学报，2022,43(3):22-29.FAN G,ZHANG Y,ZHAO H M,et al.Underwater robot positioning and navigation technology development status and analysis[J].Journal of Ordnance Equipment Engineering,2022,43(3):22-29.
[13] 王英志，范文涛.水下导航定位技术研究进展[J].数字海洋与水下攻防，2020,3(5):372-381.WANG Y Z,FAN W T.Research progress of underwater navigation and positioning technology[J].Digital Ocean & Underwater Warfare,2020,3(5):372-381.
[14] ZHANG Y,ZHOU L,LI H,et al.Marine application evaluation of monocular SLAM for underwater robots[J].Sensors 2022,22,4657-4663.
[15] 陈嘉辉.基于双目视觉的水下机器人同时定位建图方法研究[D].哈尔滨：哈尔滨工程大学，2024.CHEN J H.Research on Simultaneous Localization and Mapping of Underwater Robot Based on Stereo Carmera[D].Harbin:Harbin Engineering University,2020.
[16] DRUPT J,CLAIRE D,ANDREW I C,et al.Qualitative evaluation of state-of-the-art DSO and ORB-SLAM-based monocular visual SLAM algorithms for underwater applications[J].IEEE Oceans,2023:1-7.
[17] 王富民.自主水下机器人同时定位和地图构建方法研究[D].沈阳：沈阳工业大学，2020.WANG F M.Research on Simultaneous Localization and Map Construction of Autonomous Underwater Vehicle[D].Shenyang:Shenyang University of Technology,2020.
[18] 谢勇.隧洞检测机器人里程计与激光雷达融合定位[D].杭州：中国计量大学，2019.XIE Y.Detection Robot Localization with Odometry and Lidar Fusion in Tunnel[D].Hangzhou:China University of Metrology,2019.
[19] 胡祺林.有压输水隧洞检测AUV的实时定位与在线构图[D].哈尔滨：哈尔滨工程大学，2020.HU Q L.Research on Real-Time Localization and Online Mapping of an Autonomous Underwater Vehicle for Water Tunnel inspection[D].Harbin:Harbin Engineering University,2020.
[20] 周辉奎，章立，胡素娟.改进直方图匹配和自适应均衡的水下图像增强[J].红外技术，2024,46(5):532-538.ZHOU H K,ZHANG L,HU S J.Underwater image enhancement based on improved histogram matching and adaptive equalization [J].Infrared Technology,2024,46(5):532-538.
[21] IZA S I,SITI N S,MUZAIMI M,et al.Automatic contrast enhancement of brain MR images using Average Intensity Replacement based on Adaptive Histogram Equalization (AIR-AHE)[J].Biocybernetics and Biomedical Engineering,2017,37(1):24-34.
[22] 弭永发，迟明善，张强，等.基于颜色校正与改进的CLAHE多尺度融合水下图像增强[J].无线电工程，2024,54(6):1470-1480.MI Y F,CHI M S,ZHANG Q,et al.Underwater image enhancement based on color correction and improved CLAHE multi-scale fusion[J].Radio Engineering,2024,54(6):1470-1480.
[23] 胡瀚文，王猛，程卫平，等.水下视觉SLAM的图像滤波除尘与特征增强算法[J].机器人，2023,45(2):197-206.HU H W,WANG M,CHENG W P,et al.An image dust-filtering and feature enhancement aalgorithm for underwater visual SLAM[J].Robot,2023,45(2):197-206.
[24] 梅杰，覃嘉锐，陈定方，等.基于视觉同时定位与地图构建的水下图像增强式视觉三维重建方法[J].中国机械工程，2024,35(2):268-279.MEI J,QIN J R,CHEN D F,et al.SLAM-based underwater image enhanced visual 3D reconstruction method[J].China Mechanical Engineering,2024,35(2):268-279.
[25] 纪勋，冷娜，郭慧.水下图像增强与复原技术进展与展望[J].计算机辅助设计与图形学学报，2024,36(6):805-830.JI X,LENG N,GUO H.Underwater image enhancement and restoration techniques:State-of-the-art methods and prospects[J].Journal of Computer Aided Design &Computer Graphics,2024,36(6):805-830.
[26] LI C,ANWAR S,HOU J,et al.Underwater image enhancement via medium transmission-guided multi-color space embedding[J].IEEE Transactions on Image Processing,2021,30:4985-5000.
[27] ZHANG W,ZHOU L,ZHUANG P,et al.Underwater image enhancement via weighted wavelet visual perception fusion[J].IEEE Transactions on Circuits and Systems for Video Technology,2024,34(4):2469-2483.
[28] 刘佳玮，曹江涛，姬晓飞.基于Swin Transformer和YOLOv5的无纺布瑕疵检测[J].辽宁石油化工大学学报，2024,44(3):80-88.LIU Jiawei,CAO Jiangtao,JI Xiaofei.Non-woven fabric defect detection based on the combination of Swin Transformer and YOLOv5[J].Journal of Liaoning Petrochemical University,2024,44(3):80-88.
[29] PENG L,ZHU C,BIAN L,et al.U-Shape transformer for underwater image enhancement[J].IEEE Transactions on Image Processing,2023,32:3066-3079.
[30] 王宁，贾薇，陈延政，等.基于深度估计和梯度下降的水下图像恢复与增强[J].大连海事大学学报，2024,50(3):1-12.WANG N,JIA W,CHEN Y,et al.Underwater image restoration and enhancement using depth estimation and gradient descent[J].Journal of Dalian Maritime University,2024,50(3):1-12.
[31] 王曦，陈心怡.一种基于时序卷积网络-Transformer的海上风电功率预测方法[J].发电技术，2025,46(6):1123-1132.WANG X,CHEN X Y.Power prediction method for offshore wind farms based on temporal convolutional network-Transformer[J].Power Generation Technology,2025,46(6):1123-1132.
[32] 李伟杰，祁军，潘斌 .基于通道注意力和时序改进多摄像头的鸟瞰视角目标检测[J].辽宁石油化工大学学报，2024,44(6):89-96.LI W J,QI J,PAN B.Optimizing bird’s-eye-view object detection from multi-camera images via channel attention and temporal Transformers[J].Journal of Liaoning Petrochemical University,2024,44(6):89-96.
[33] JOHNSON J,ALAHI A,LI F F.Lecture Notes in Computer Science[M].Cham:Springer,2016.
[34] 曾庆化，王守一，李方东，等.基于交互式多模型因子图的自适应组合导航算法[J].中国惯性技术学报，2024,32(4):346-353.ZENG Q H,WANG S Y,LI F D,et al.Adaptive integrated navigation algorithm based on interacting multiple model factor graph optimization[J].Journal of Chinese Inertial Technology,2024,32(4):346-353.
[35] 白克强，朱亚兰，杨秀清，等.融合动态目标跟踪的视觉SLAM算法.信息与控制，2024(5):574-584.BAI K Q,ZHU Y L,YANG X Q,et al.Visual SLAM algorithm of integrating dynamic target tracking[J].Information and Control,2024(5):574-584.
[36] LIAO J,LI X X,WANG X B,et al.Enhancing navigation performance through visual-inertial odometry in GNSS-degraded environment[J].GPS Solutions,2021,25(2):50.
[37] 东旭，刘鑫宇，朱杰辉，等.基于因子图优化的水下机器人SLAM算法[J].现代制造技术与装备，2024,60(12):205-208.DONG X,LIU X Y,ZHU J H,et al.SLAM algorithm of underwater robot based on factor map optimization[J].Modern Manufacturing Technology and Equipment,2024,60(12):205-208.
[38] PENG L T,ZHU C L,BIAN L H.U-shape transformer forunder water image enhancement[J].IEEE Transactions on Image Processing,2023,32:3066-3079.
[39] LI C,GUO C,REN W,et al.An underwater image enhancement benchmark dataset and beyond[J].IEEE Transactions on Image Processing,2020,29:4376-4389.
[40] YANG M,SOWMYAA A.Underwater color image quality evaluation metric[J].IEEE Transactions on Image Processing,2015,24(12):6062-6071.
[41] PANETTA K,GAO C,AGAIAN S.Human-visual-system-inspired underwater image quality measures[J].IEEE Journal of Oceanic Engineering,2015,41(3):541-551.
基本信息:
DOI：10.13928/j.cnki.wrahe.2026.07.017
中图分类号:TV698.1;TP391.41
引用信息:
[1]王小波,殷浤益,万刚,等.水工隧洞环境下基于视觉增强-惯性SLAM的ROV水下定位技术研究[J].水利水电技术(中英文),2026,57(07):227-240.DOI:10.13928/j.cnki.wrahe.2026.07.017.
基金信息:
国家自然科学基金项目(42302337); 湖北省智慧水电技术创新中心2023年度开放研究基金资助项目(SDCXZX-JJ-2023-09); 湖北省教育厅科学研究计划重点项目(D20231304); 深地国家科技重大专项(2024ZD1001003)
2026-06-02
2026-06-02
2026-06-02