基于改进SuperPoint的空天异源图像匹配算法

刘庚辰; 姜梁; 吴国强; 黄坤

doi:10.12263/DZXB.20240724

您当前的位置：

首页 >

文章列表页 >

基于改进SuperPoint的空天异源图像匹配算法

学术论文 | 更新时间：2025-07-24

- 基于改进SuperPoint的空天异源图像匹配算法
- Aerospace Heterogeneous Image Matching Algorithm Based on Improved SuperPoint
- 电子学报 2025年53卷第4期页码：1201-1211
- 作者机构：
  
  1.航天时代飞鸿技术有限公司，北京 100094
  2.中国航天科技集团有限公司智能无人系统总体技术研发中心，北京 100094
  3.中国航天科技集团有限公司第九研究院，北京 100094
  4.北京理工大学机电学院，北京 100081
- 作者简介：
  
  [ "刘庚辰男，2000年2月出生.现为中国空间技术研究院研究生.主要研究方向为无人系统信息融合.E-mail: 1259012790@qq.com" ]
  [ "姜梁男，1976年12月出生.现在中国航天科技集团有限公司任职.主要研究方向为无人系统总体技术、人工智能." ]
  [ "吴国强男，1984年9月出生.现在中国航天科技集团有限公司任职.主要研究方向为无人系统指挥控制、人工智能." ]
  [ "黄坤男，1990年8月出生.现在中国航天科技集团有限公司任职.主要研究方向为无人系统情报处理." ]
- 基金信息：
- DOI：10.12263/DZXB.20240724
  中图分类号： TN91;
- 收稿：2024-08-01，
  
  修回：2025-04-30，
  
  纸质出版：2025-04-25
- 稿件说明：
移动端阅览
刘庚辰, 姜梁, 吴国强, 等. 基于改进SuperPoint的空天异源图像匹配算法[J]. 电子学报, 2025, 53(04): 1201-1211.

LIU Geng-chen, JIANG Liang, WU Guo-qiang, et al. Aerospace Heterogeneous Image Matching Algorithm Based on Improved SuperPoint[J]. Acta Electronica Sinica, 2025, 53(04): 1201-1211.
刘庚辰, 姜梁, 吴国强, 等. 基于改进SuperPoint的空天异源图像匹配算法[J]. 电子学报, 2025, 53(04): 1201-1211. DOI：10.12263/DZXB.20240724

LIU Geng-chen, JIANG Liang, WU Guo-qiang, et al. Aerospace Heterogeneous Image Matching Algorithm Based on Improved SuperPoint[J]. Acta Electronica Sinica, 2025, 53(04): 1201-1211. DOI：10.12263/DZXB.20240724

摘要

空天异源图像特征提取难度较大，图像匹配精度较低，给无人机精确目标定位带来了不利影响.SuperPoint-SuperGlue算法由于其自监督，易训练，精度高等特性，近年来在图像匹配领域应用较为广泛，但针对空天异源图像匹配领域，SuperPoint特征提取能力仍有待提高.为提高空天异源图像匹配精度，本文提出基于改进SuperPoint的空天异源图像匹配算法.首先，将群智能增强模块（Spatial Group-wise Enhance，SGE）与全局注意力机制（Global Attention Mechanism，GAM）引入到SuperPoint编码器中构成补充编码器，一定程度上解决了图像特征分布不均匀以及弱纹理图像特征提取较难的问题；其次，为进一步增强算法特征提取能力，将补充编码器与原SuperPoint编码器进行并联构成组合编码器，结合二者优势，提取差异性更大的图像特征，减少对相似区域的特征点误匹配，提高空天异源图像的匹配精度；最后，通过实验验证，在UAV-VisLoc 数据集上80像素误差区间以内可匹配图像数量可达82.14%，与原SuperPoint算法相比，80像素误差区间以内可匹配图像数量提高了6.05%，与其他先进算法相比，在各像素误差区间以内可匹配图像数量均有提高.实验表明，本文提出的算法可以有效地解决空天异源图像匹配中特征提取能力较弱，特征分布不均匀等问题.

Abstract

It is quite difficult to extract features from heterogeneous aerospace images

and the image matching accuracy is relatively low

which has a negative impact on the precise target positioning of unmanned aerial vehicles (UAVs). The SuperPoint-SuperGlue algorithm has been widely applied in the field of image matching in recent years due to its characteristics such as self-supervision

easy training

and high accuracy. However

in the field of heterogeneous aerospace image matching

the feature extraction ability of SuperPoint still needs to be improved. In order to improve the matching accuracy of heterogeneous aerospace images

this paper proposes a heterogeneous aerospace image matching algorithm based on the improved SuperPoint. Firstly

the spatial group-wise enhance (SGE) module and the global attention mechanism (GAM) are introduced into the SuperPoint encoder to form a supplementary encoder

which to a certain extent solves the problems of uneven distribution of image features and the difficulty in extracting features from weakly textured images. Secondly

to further enhance the feature extraction ability of the algorithm

the supplementary encoder is connected in parallel with the original SuperPoint encoder to form a combined encoder. By combining the advantages of the two

it can extract image features with greater differences

reduce the false matching of feature points in similar regions

and improve the matching accuracy of heterogeneous aerospace images. Finally

through experimental verification

within the error range of 80 pixels on the UAV-VisLoc dataset

the number of matchable images can reach 82.14%. Compared with the original SuperPoint algorithm

the number of matchable images within the error range of 80 pixels has increased by 6.05%. Compared with other advanced algorithms

the number of matchable images within each pixel error range has increased. The experiments show that the algorithm proposed in this paper can effectively solve the problems such as weak feature extraction ability and uneven feature distribution in the matching of heterogeneous aerospace images.

关键词

Keywords

references

XU S B , CHEN S P , XU R T , et al . Local feature matching using deep learning: A survey [J ] . Information Fusion , 2024 , 107 : 102344 .

刘畅 , 李嘉杰 , 眭海刚 , 等 . 基于FLoFTR算法的无人机实时在线地理定位 [J ] . 航空科学技术 , 2023 , 34 ( 5 ): 87 - 94 .

LIU C , LI J J , SUI H G , et al . Real-time geolocation on UAV based on FLoFTR algorithm [J ] . Aeronautical Science & Technology , 2023 , 34 ( 5 ): 87 - 94 . (in Chinese)

任艳 , 刘胜男 , 陈新禹 , 等 . 不同季节下无人机航拍图像与卫星图像匹配方法研究 [J ] . 弹箭与制导学报 , 2023 , 43 ( 5 ): 16 - 24 .

REN Y , LIU S N , CHEN X Y , et al . An image matching method for season-changing UAV aerial images and satellite images [J ] . Journal of Projectiles, Rockets, Missiles and Guidance , 2023 , 43 ( 5 ): 16 - 24 . (in Chinese)

DETONE D , MALISIEWICZ T , RABINOVICH A . SuperPoint : Self-supervised interest point detection and description [C ] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) . Piscataway : IEEE , 2018: 337 - 33712 .

LI X , HU X L , YANG J . Spatial group-wise enhance: Improving semantic feature learning in convolutional networks [EB/OL ] . ( 2019-05-25 )[ 2024-07-20 ] . https://arxiv.org/abs/1905.09646v2 https://arxiv.org/abs/1905.09646v2 .

LIU Y C , SHAO Z R , HOFFMANN N . Global attention mechanism: Retain information to enhance channel-spatial interactions [EB/OL ] . ( 2021-11-10 )[ 2024-07-20 ] . https://arxiv.org/abs/2112.05561v1 https://arxiv.org/abs/2112.05561v1 .

XU W J , YAO Y X , CAO J Q , et al . UAV-VisLoc: A large-scale dataset for UAV visual localization [EB/OL ] . ( 2024-05-20 )[ 2024-07-20 ] . https://arxiv.org/abs/2405.11936v1 https://arxiv.org/abs/2405.11936v1 .

SARLIN P E , DETONE D , MALISIEWICZ T , et al . SuperGlue : Learning feature matching with graph neural networks [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020: 4938 - 4947 .

LI T Q , PANG G S , BAI X , et al . Learning adversarial semantic embeddings for zero-shot recognition in open worlds [J ] . Pattern Recognition , 2024 , 149 : 110258 .

ZHANG J , HUANG L , BAI X , et al . Exploring the usage of pre-trained features for stereo matching [J ] . International Journal of Computer Vision , 2024 , 132 ( 10 ): 1 .

BAI X , ZHANG P , YU X , et al . Learning from human attention for attribute-assisted visual recognition [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2025 , 46 : 10.1109/TPAMI.2024.3458921 .

WU Y C , ZHANG P C , GU M Y , et al . Embodied navigation with multi-modal information: A survey from tasks to methodology [J ] . Information Fusion , 2024 , 112 : 102532 .

赵克龙 . 基于改进ORB和改进SURF的影像匹配算法研究 [D ] . 西安 : 西安科技大学 , 2022 .

ZHAO K L . Research on Image Matching Algorithm Based on Improved ORB and Improved SURF [D ] . Xi’an : Xi’an University of Science and Technology , 2022 . (in Chinese)

RUBLEE E , RABAUD V , KONOLIGE K , et al . ORB: An efficient alternative to SIFT or SURF [C ] // 2011 International Conference on Computer Vision . Piscataway : IEEE , 2011 : 2564 - 2571 .

温育杜 , 郭士增 , 刘晟 , 等 . 基于尺度配准的航拍图像与卫星影像匹配方法 [J ] . 哈尔滨工业大学学报 , 2023 , 55 ( 10 ): 19 - 26 .

WEN Y D , GUO S Z , LIU S , et al . Matching method between UAV images and satellite images based on scale registration [J ] . Journal of Harbin Institute of Technology , 2023 , 55 ( 10 ): 19 - 26 . (in Chinese)

罗卿莉 , 张书缤 , 陈相 , 等 . 无人机与卫星影像匹配的相似性逼近算法 [J ] . 测绘通报 , 2023 ( 9 ): 64 - 69 .

LUO Q L , ZHANG S B , CHEN X , et al . A similarity approximation algorithm for matching UAV and satellite image [J ] . Bulletin of Surveying and Mapping , 2023 ( 9 ): 64 - 69 . (in Chinese)

SUN J M , SHEN Z H , WANG Y A , et al . LoFTR: Detector-free local feature matching with transformers [C ] // 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2021 : 8918 - 8927 .

WANG Y F , HE X Y , PENG S D , et al . Efficient LoFTR: Semi-dense local feature matching with sparse-like speed [C ] // 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2024 : 21666 - 21675 .

CHEN H K , LUO Z X , ZHOU L , et al . ASpanFormer: Detector-free image matching with adaptive span transformer [M ] // Computer Vision - ECCV 2022 . Cham : Springer Nature Switzerland , 2022 : 20 - 36 .

LINDENBERGER P , SARLIN P E , POLLEFEYS M . LightGlue: Local feature matching at light speed [C ] // 2023 IEEE/CVF International Conference on Computer Vision (ICCV) . Piscataway : IEEE , 2023 : 17581 - 17592 .

眭海刚 , 李嘉杰 , 苟国华 . 基于异源影像匹配的无人机在线快速定位方法 [J ] . 系统工程与电子技术 , 2023 , 45 ( 10 ): 3008 - 3015 .

SUI H G , LI J J , GOU G H . Online fast localization method of UAVs based on heterologous image matching [J ] . Systems Engineering and Electronics , 2023 , 45 ( 10 ): 3008 - 3015 . (in Chinese)

黄振家 . 不同季节景象的无人机航拍图像与卫星影像匹配技术研究 [D ] . 沈阳 : 沈阳航空航天大学 , 2023 .

HUANG Z J . Research on Matching Technology of UAV aerial Images and Satellite Images in Different Seasons [D ] . Shenyang : Shenyang Aerospace University , 2023 . (in Chinese)

SIMONYAN K , ZISSERMAN A . Very deep convolutional networks for large-scale image recognition [EB/OL ] . ( 2015-08-10 )[ 2024-07-20 ] . https://arxiv.org/abs/1409.1556v6 https://arxiv.org/abs/1409.1556v6 .

WOO S , PARK J , LEE J Y , et al . CBAM: Convolutional Block attention module [C ] // Computer Vision - ECCV 2018 . Cham : Springer International Publishing , 2018 : 3 - 19 .

XIA G S , HU J , HU F , et al . AID: A benchmark dataset for performance evaluation of aerial scene classification .[EB/OL ] . ( 2016-08-18 )[ 2024-07-20 ] . https://arxiv.org/abs/1608.05167 https://arxiv.org/abs/1608.05167 .

CHENG G , HAN J W , LU X Q . Remote sensing image scene classification: Benchmark and state of the art [J ] . Proceedings of the IEEE , 2017 , 105 ( 10 ): 1865 - 1883 .

ZOU Q , NI L H , ZHANG T , et al . Deep learning based feature selection for remote sensing scene classification [J ] . IEEE Geoscience and Remote Sensing Letters , 2015 , 12 ( 11 ): 2321 - 2325 .

DAI D X , YANG W . Satellite image classification via two-layer sparse coding with biased image representation [J ] . IEEE Geoscience and Remote Sensing Letters , 2011 , 8 ( 1 ): 173 - 176 .

ZHAO B , ZHONG Y F , XIA G S , et al . Dirichlet-derived multiple topic scene classification model for high spatial resolution remote sensing imagery [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2016 , 54 ( 4 ): 2108 - 2123 .

ZHENG Z D , WEI Y C , YANG Y . University-1652: A multi-view multi-source benchmark for drone-based geo-localization [EB/OL ] . ( 2020-08-16 )[ 2024-07-20 ] . https://arxiv.org/abs/2002.12186 https://arxiv.org/abs/2002.12186 .

MAO R Y , BAI C , AN Y T , et al . 3DG-STFM: 3D geometric guided student-teacher feature matching [M ] // Computer Vision - ECCV 2022 . Cham : Springer Nature Switzerland , 2022 : 125 - 142 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于深度压缩感知的联合信源信道编码方法研究

基于视觉的无人机定位与导航方法研究综述

一种适用于H.264标准的高度并行双层流水线结构CAVLC编码器