基于多尺度特征融合的无人机影像旋转不变性匹配方法  

Unmanned Aerial Vehicle Image Rotation Invariant Matching Based on Multi-scale Feature Fusion

作　　者：刘云 李梓谦 板岩洼门 陈维泰 陈珊 LIU Yun;LI Ziqian;BAN Yanwamen;CHEN Weitai;CHEN Shan(Surveying and Mapping Engineering Institute of Yunnan Province,Kunming 650000 China;Kunming University of Science and Technology,Kunming 650000 China)

机构地区：[1]云南省测绘工程院,昆明650000 [2]昆明理工大学,昆明650000

出　　处：《电光与控制》2025年第2期73-78,102,共7页Electronics Optics & Control

基　　金：云南省科技厅基础研究计划面上项目(202301AT070463)。

摘　　要：无人机影像匹配在无人机影像处理中占据核心位置,而方向估计是进行旋转不变性匹配的重要一环。然而,由于无法明确无人机影像特征点的标准主方向,目前的匹配方法仍然会有较大的方向估计误差,导致匹配精度低。提出一种基于多尺度特征融合的无人机影像旋转不变性匹配(RIMN)方法,其中的多尺度特征提取模块可以融合丰富的影像语义特征,并采用Transformer自注意力模块在影像的弱纹理区域中提取鲁棒稳健的特征,同时设计了双重损失函数来提升特征点的方向估计精度用于完成旋转不变性匹配。设置了不同旋转角度下的影像匹配对比实验,定性及定量结果表明,所提方法具有更为优秀的旋转不变匹配性能。UAV image matching occupies a central position in UAV image processing and orientation estimation is an important part of performing rotation invariant matching.However due to the inability to specify the standard orientations of the UAV image feature points the current matching method still suffers from large orientation estimation errors,resulting in low matching accuracy.A Rotation Invariant Matching Network(RIMN)based on multi-scale feature fusion is proposed for UAV images in which the multi-scale feature extraction module is used to aggregate rich semantic features of the images and the Transformer self-attention block is used to extract robust features in the weakly textured regions of the image.Meanwhile a double constrained loss function is designed to improve the orientation estimation accuracy of the feature points.Finally image matching comparison experiments under different rotation angles is set up.The qualitative and quantitative results show that this method has better rotation invariant matching performance.

关 键 词：无人机影像匹配 方向估计 旋转不变性匹配 注意力机制 

分 类 号：TP715[自动化与计算机技术—检测技术与自动化装置]