Image processing system for determining satellite configuration and attributes

CN120808184APending Publication Date: 2025-10-17THE BOEING CO
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202510432777.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2024-04-10
Filing Date
2025-04-08
Publication Date
2025-10-17

AI Technical Summary

Technical Problem

Existing technologies have difficulty accurately classifying satellites with unknown hardware configurations, especially in scenarios of newly launched or unidentified satellites. The lack of prior knowledge limits the effectiveness of image segmentation technology.

Method used

A deep neural network (DNN) is used as the satellite classification model. By receiving test images and training based on multiple training satellite images, it generates an output image segmentation map, identifies different hardware components of the satellite, and outputs position and attitude parameters to achieve satellite classification.

Benefits of technology

It can generate accurate image segmentation maps under unknown hardware configurations, identify satellite hardware components and determine their position and attitude. It is suitable for various application scenarios such as satellite navigation and monitoring, and enhances the analysis capability in the absence of prior knowledge.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120808184A_ABST
    Figure CN120808184A_ABST
Patent Text Reader

Abstract

The invention relates to an image processing system for determining satellite configuration and attributes. A method (600) for satellite component classification includes receiving, at a satellite classification system (100), a test image (104) depicting a satellite (108) having a hardware component configuration (110) unknown to the satellite classification system (100). The test image (104) is input to a satellite classification model (102) trained based at least in part on the plurality of training satellite images (402) to generate an output image segmentation map for the input satellite image. The satellite classification model (102) outputs an output image segmentation map (112) of the test image (104), one or more position parameters (118) of the satellite (108), and one or more attitude parameters (116) of the satellite (108). The output segmentation map (112) includes a plurality of image pixels (114) corresponding to the plurality of image pixels (106) in the test image (104), where pixel values of the plurality of image pixels (114) classify corresponding image pixels (106) of the test image (104) as different hardware components depicting the satellite (108).
Need to check novelty before this filing date? Find Prior Art