计算机与现代化 ›› 2025, Vol. 0 ›› Issue (11): 41-48.doi: 10.3969/j.issn.1006-2475.2025.11.005

• 人工智能 • 上一篇    下一篇

基于LightGlue网络改进的输电线路巡检无人机V-SLAM方法

  


  1. (1.广西电网有限责任公司电力科学研究院,广西 南宁 530000; 2.广西百色市供电局,广西 百色 533000;
    3.南方电网科学研究院,广东 广州 510000)
  • 出版日期:2025-11-20 发布日期:2025-11-24
  • 作者简介:作者简介:祝文姬(1983—),女,广西南宁人,高级工程师,博士,研究方向:视觉SLAM,E-mail: 1359325829@qq.com; 班卫华(1979—),男,广西百色人,助理工程师,硕士,研究方向:智能电网,E-mail: 2524177365@qq.com; 邹林(1978—),女,广西南宁人,助理工程师,硕士,研究方向:视觉SLAM,E-mail: 331094871@qq.com; 刘旭(1982—),女,广西南宁人,助理工程师,硕士,研究方向:智能电网,E-mail: 673180294@qq.com。
  • 基金资助:

Improved V-SLAM Method for Transmission Line Inspection UAV Based on LightGlue Network


  1. (1. Electric Power Research Institute of Guangxi Power Grid, Nanning 530000, China; 2. Guangxi Baise Power Supply Bureau, Baise 533000, China; 3. CSG Electric Power Research Institute, Guangzhou 510000, China)
  • Online:2025-11-20 Published:2025-11-24

摘要: 摘要:针对巡检无人机在输电线路环境中进行视觉同时定位与建图(Visual Simultaneous Localization And Mapping, V-SLAM)时,定位精度受视角以及光照变化影响的问题,提出一种基于LightGlue网络改进的双目V-SLAM方法。首先,采用轻量级的SuperPoint网络提取对光照和视角变换更鲁棒的特征点;接着,通过LightGlue网络结合并行优化的图像金字塔模型改进特征匹配模块,提高图像特征匹配的准确率和算法运行的实时性能;最后,将点云地图转化为八叉树地图以节省内存空间。实验结果表明,论文所提算法对光照和视角变化的适应性更强;在EuRoc数据集测试中,定位精度与OpenVSLAM相比提升了约28.34%,实时性较改进前的SL-ORB-SLAM2提升了约33.30%;在现场实验中,定位精度提升明显,构建的八叉树地图与点云地图相比内存占用减少了约47.28%。综上所述,本文提出的LG-SLAM算法能适应输电线路环境,完成精准的实时定位并构建八叉树地图,具有良好的工程应用前景。


关键词: 关键词:视觉同时定位与建图, 注意力机制, 特征匹配, 图像金字塔

Abstract: Abstract: To address the problem that the localization accuracy of inspection UAVs is affected by the change of illumination and view angle when they perform visual simultaneous localization and mapping (V-SLAM) in the transmission line environment,an improved Stereo V-SLAM method based on LightGlue network is proposed. Firstly, a SuperPoint feature extraction network is used to extract feature points that are more robust to changes in illumination and viewing angle. Then, the feature matching module is improved by LightGlue network combined with optimized parallel image pyramid model to improve the precision of image feature matching and the real-time performance of algorithm operation. Finally, the point cloud map is converted to an octree map to reduce the memory overhead. The experimental results show that the proposed algorithm is more adaptable to changes in illumination and viewing angle; in the EuRoc dataset test, the localization accuracy is improved by about 28.34% compared with OpenVSLAM, and the real-time performance is improved by 33.30% compared with SL-ORB-SLAM2. In the field experiment, the localization accuracy is improved significantly,and the octree map reduces the memory footprint by about 47.28% compared to the point cloud map. In summary, the algorithm proposed can adapt to the transmission line environment, complete accurate localization in real-time and construct octree maps, which has good engineering application prospect.

Key words: Key words: visual simultaneous localization and mapping, attention mechanism, feature matching, image pyramid

中图分类号: