A small sample multi-scale spatial fragment target detection method based on illumination transfer

An illumination transfer method based on multi-scale feature extraction and gated residual mechanism solves the detection challenges caused by illumination variations and diversity in space debris detection, achieving efficient and accurate space debris detection while reducing computational complexity and power consumption.

CN122199901APending Publication Date: 2026-06-12PLA PEOPLES LIBERATION ARMY OF CHINA STRATEGIC SUPPORT FORCE AEROSPACE ENG UNIV
0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
PLA PEOPLES LIBERATION ARMY OF CHINA STRATEGIC SUPPORT FORCE AEROSPACE ENG UNIV
Filing Date
2025-06-30
Publication Date
2026-06-12

AI Technical Summary

⚠Technical Problem

The diversity of space debris and the variation in lighting conditions increase the difficulty of detection, leading to a decrease in the accuracy of deep learning models in space debris detection. Furthermore, high-precision detection requires a large amount of computation, increasing the power consumption and complexity of the equipment.

⚗Method used

A small-sample, multi-scale space debris target detection method based on illumination migration is adopted. This method strengthens the association between features and background through multi-scale feature extraction, global average pooling, and attention mechanisms. It also combines a gated residual mechanism to identify illumination components and dynamically adjusts the detection threshold to achieve feature fusion for identifying space debris.

🎯Benefits of technology

The model's robustness and adaptability under complex lighting conditions have been improved, enabling accurate detection of space debris while reducing computational complexity and power consumption.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
Patent Text Reader

Abstract

The embodiment of the application provides a small sample multi-scale space debris target detection method based on illumination migration, which comprises the following steps: collecting an image to be processed; identifying space debris in the image to be processed based on a preset space debris detection model; the space debris detection model is used for multiple feature extraction, in each feature extraction, multi-scale features are extracted first, and then based on global average pooling and attention mechanism, the correlation between the features and the background of the image to be processed is strengthened to obtain first features; based on a gating residual mechanism, the illumination component in the first features is identified; according to the illumination component, the detection threshold of the gating unit is adjusted; according to the detection threshold, second features are obtained; based on the first features and the second features, feature fusion is performed to identify the space debris. The technical scheme provided by the application is used to solve the problems of high detection difficulty, low detection precision and large calculation amount in the prior art.
Need to check novelty before this filing date? Find Prior Art