红外技术2026，Vol.48Issue(5)：589-596,8.
基于改进SuperPoint-LightGlue的可见光红外图像匹配算法
A Visible Light Infrared Image Matching Algorithm Based on Improved SuperPoint-LightGlue
杨波 1张洋 1蔡富杰 1刘长发 1万鹏伟 1裴冬1
作者信息
- 1. 四川阿坝金川华电新能源有限公司,四川 阿坝藏族羌族自治州 624000
- 折叠
摘要
Abstract
A visible light and infrared image-matching algorithm based on improved SuperPoint and LightGlue was proposed to address the difficulty and high mismatch rate of image matching in regions with significant lighting differences and deformation in photovoltaic power station inspection robots.First,owing to the shortcomings of the native SuperPoint feature point extraction network with a large number of parameters and weak global feature extraction ability,a lightweight SuperPoint encoder based on the Conv2Former structure with a self-attention mechanism was adopted,and a strong global feature expression ability was obtained.Second,owing to the inability of native SuperPoint to maintain the spatial invariance of input data,STN modules were alternately inserted into the SuperPoint encoder to provide spatial invariance for the improved SuperPoint.Finally,in the feature-matching module,LightGlue was used to match the feature points extracted by the improved SuperPoint.Experimental results show that,compared with existing algorithms,the proposed algorithm achieves better matching performance,higher matching efficiency,and stronger robustness to lighting variations and deformation.关键词
巡检机器人/轻量化/全局特征表达/空间不变性/LightGlueKey words
inspection robot/lightweight/global feature representation/space invariance/LightGlue分类
信息技术与安全科学引用本文复制引用
杨波,张洋,蔡富杰,刘长发,万鹏伟,裴冬..基于改进SuperPoint-LightGlue的可见光红外图像匹配算法[J].红外技术,2026,48(5):589-596,8.
