Multi-Scale Spatiotemporal Feature Enhancement and Recursive Motion Compensation for Satellite Video Geographic Registration

TL;DR

This paper introduces a new method for aligning satellite video with geographic data using enhanced feature matching and motion compensation, improving accuracy for applications like tracking and 3D scene construction.

Contribution

A novel method combining multi-scale feature enhancement and recursive motion compensation for improved satellite video geographic registration.

Findings

The method achieves inter-frame matching accuracy of 0.8 pixels.

Georeferencing accuracy error is reduced to 3 meters.

The approach outperforms traditional single-frame methods significantly.

Abstract

Satellite video geographic alignment can be applied to target detection and tracking, true 3D scene construction, image geometry measurement, etc., which is a necessary preprocessing step for satellite video applications. In this paper, a multi-scale spatiotemporal feature enhancement and recursive motion compensation method for satellite video geographic alignment is proposed. Based on the SuperGlue matching algorithm, the method achieves automatic matching of inter-frame image points by introducing the multi-scale dilated attention (MSDA) to enhance the feature extraction and adopting a joint multi-frame optimization strategy (MFMO), designing a recursive motion compensation model (RMCM) to eliminate the cumulative effect of the orbit error and improve the accuracy of the inter-frame image point matching, and using a rational function model to establish the geometrical mapping between the video and the ground points to realize the georeferencing of satellite video. The geometric mapping between video and ground points is established by using the rational function model to realize the geographic alignment of satellite video. The experimental results show that the method achieves the inter-frame matching accuracy of 0.8 pixel level, and the georeferencing accuracy error is 3 m, which is a significant improvement compared with the traditional single-frame method, and the method in this paper can provide a certain reference for the subsequent related research.

Figures