Space target autonomous recognition method based on transfer learning, electronic equipment and storage medium

Abstract

The invention discloses a space target autonomous identification method based on transfer learning, electronic equipment and a storage medium. The method comprises the steps of obtaining a plurality of frames of image data of an unknown space target in real time; performing feature compensation on the image data of the unknown space target at the current moment according to the image data of the unknown space target at a plurality of frames of preorder moments to obtain an unknown space target feature map at the current moment after feature compensation; and recognizing the unknown space target feature map subjected to feature compensation at the current moment by adopting a pre-trained neural network to obtain a recognition result. According to the method, the problem that the number andtypes of samples are not rich enough due to loss of priori information of a non-cooperative space target is solved.

Description

technical field [0001] The invention relates to the field of space technology, in particular to a transfer learning-based autonomous recognition method for space targets, electronic equipment and storage media. Background technique [0002] Space target spacecraft can be divided into cooperative targets and non-cooperative targets. A cooperative target refers to a target aircraft that has a known target image library or a 3D model library, or is capable of communicating with a tracking aircraft; a non-cooperative target refers to a target spacecraft that does not have a special docking interface or identification marker. During its tracking and manipulation, it will not actively provide relevant information for the serving spacecraft. At present, the on-orbit control technology for space cooperation targets has been relatively mature. However, for non-cooperative targets in space, cognition of their on-orbit status, capture and docking, and service operations are all diffi...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a method for autonomous recognition of space targets based on transfer learning, electronic equipment and storage media, which can effectively solve the problems of scarce samples of non-cooperative targets, excessive cost of on-orbit verification, and difficulty in completely simulating the actual space environment on the ground. , improve the adaptability of the space target recognition model for different task scenarios, and significantly improve the recognition accuracy and success rate for space unknown targets

Images