Comparative Analysis of Advanced Feature Matching Algorithms in Challenging High Spatial Resolution Optical Satellite Stereo Scenarios

TL;DR

This paper compares advanced feature matching algorithms for high-resolution satellite stereo images, highlighting SuperPoint + LightGlue as the most effective in challenging scenarios involving diverse conditions and sensors.

Contribution

It provides a comprehensive evaluation of traditional and deep-learning feature matching algorithms on a new challenging satellite stereo dataset, identifying the most robust method.

Findings

SuperPoint + LightGlue outperforms other algorithms in robustness and accuracy.

Deep-learning methods show significant advantages over traditional SIFT.

The HSROSS dataset enables realistic evaluation of feature matching in complex satellite scenarios.

Abstract

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.