A method for estimating satellite target attitude in ISAR images based on geometric feature constraints

By employing a geometrically constrained ISAR image satellite target attitude estimation method, and utilizing techniques such as Conv-LSTM and PCA, the problem of low accuracy of traditional methods under different climatic conditions is solved, achieving high-precision estimation and stable monitoring of satellite attitude.

CN121921674BActive Publication Date: 2026-06-30SOUTHEAST UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SOUTHEAST UNIV
Filing Date
2026-03-27
Publication Date
2026-06-30

AI Technical Summary

Technical Problem

Traditional satellite attitude estimation methods are not accurate under different climatic conditions, making it difficult to meet the requirements of stable monitoring in all weather and all time. Furthermore, ISAR technology has difficulty eliminating the influence of target attitude changes on image projection geometry during image acquisition, which makes satellite target attitude estimation difficult.

Method used

A geometrically constrained ISAR image satellite target attitude estimation method is adopted. The sequential ISAR images are processed by a convolutional long short-term memory network (Conv-LSTM), and the satellite main axis is estimated by combining the attribute scattering center model and principal component analysis (PCA). The solar panel axis features are extracted by density clustering and L-shaped rectangle search algorithm, and the radar line-of-sight projection matrix is ​​constructed for attitude estimation.

Benefits of technology

It achieves high-precision estimation of satellite target attitude under complex conditions, improves the accuracy of target component extraction, has strong anti-interference capability, and can accurately estimate satellite attitude in multiple frames of images.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121921674B_ABST
    Figure CN121921674B_ABST
Patent Text Reader

Abstract

This invention discloses a satellite target attitude estimation method based on geometric feature constraints in ISAR images, comprising the following steps: segmenting typical satellite components in sequential ISAR images using a Conv-LSTM network and extracting component scattering centers using an attribute scattering center model; estimating the direction and length of the satellite's main axis using Principal Component Analysis (PCA); extracting the axis features of the solar panels using DBSCAN clustering and L-shaped rectangle search algorithms; and finally, constructing a projection geometric model of the target from a 3D to a 2D ISAR imaging plane by combining radar line-of-sight information, establishing an optimization objective function, and solving for the satellite attitude angles using a particle swarm optimization algorithm. This invention fully integrates the spatiotemporal information of sequential images with the geometric constraints of the target, effectively overcoming the projection variation problem caused by target motion in ISAR imaging, achieving high-precision satellite attitude estimation, and possessing strong anti-interference capabilities and practical application value.
Need to check novelty before this filing date? Find Prior Art