Guardado en:
Detalles Bibliográficos
Autores principales: Luo, Qiyan, Zhang, Jidan, Xie, Yuzhen, Huang, Xu, Han, Ting
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2405.06246
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914790380666880
author Luo, Qiyan
Zhang, Jidan
Xie, Yuzhen
Huang, Xu
Han, Ting
author_facet Luo, Qiyan
Zhang, Jidan
Xie, Yuzhen
Huang, Xu
Han, Ting
contents Feature matching determines the orientation accuracy for the High Spatial Resolution (HSR) optical satellite stereos, subsequently impacting several significant applications such as 3D reconstruction and change detection. However, the matching of off-track HSR optical satellite stereos often encounters challenging conditions including wide-baseline observation, significant radiometric differences, multi-temporal changes, varying spatial resolutions, inconsistent spectral resolution, and diverse sensors. In this study, we evaluate various advanced feature matching algorithms for HSR optical satellite stereos. Utilizing a specially constructed dataset from five satellites across six challenging scenarios, HSROSS Dataset, we conduct a comparative analysis of four algorithms: the traditional SIFT, and deep-learning based methods including SuperPoint + SuperGlue, SuperPoint + LightGlue, and LoFTR. Our findings highlight overall superior performance of SuperPoint + LightGlue in balancing robustness, accuracy, distribution, and efficiency, showcasing its potential in complex HSR optical satellite scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2405_06246
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Comparative Analysis of Advanced Feature Matching Algorithms in Challenging High Spatial Resolution Optical Satellite Stereo Scenarios
Luo, Qiyan
Zhang, Jidan
Xie, Yuzhen
Huang, Xu
Han, Ting
Computer Vision and Pattern Recognition
Feature matching determines the orientation accuracy for the High Spatial Resolution (HSR) optical satellite stereos, subsequently impacting several significant applications such as 3D reconstruction and change detection. However, the matching of off-track HSR optical satellite stereos often encounters challenging conditions including wide-baseline observation, significant radiometric differences, multi-temporal changes, varying spatial resolutions, inconsistent spectral resolution, and diverse sensors. In this study, we evaluate various advanced feature matching algorithms for HSR optical satellite stereos. Utilizing a specially constructed dataset from five satellites across six challenging scenarios, HSROSS Dataset, we conduct a comparative analysis of four algorithms: the traditional SIFT, and deep-learning based methods including SuperPoint + SuperGlue, SuperPoint + LightGlue, and LoFTR. Our findings highlight overall superior performance of SuperPoint + LightGlue in balancing robustness, accuracy, distribution, and efficiency, showcasing its potential in complex HSR optical satellite scenarios.
title Comparative Analysis of Advanced Feature Matching Algorithms in Challenging High Spatial Resolution Optical Satellite Stereo Scenarios
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.06246