A lightweight method, device and medium for small target recognition in infrared remote sensing images

By constructing a lightweight backbone network HLNet and a multi-scale feature fusion network LSF, the computational complexity and accuracy problems of small target recognition in infrared remote sensing images are solved, achieving efficient and real-time recognition in complex backgrounds, which is particularly suitable for nighttime monitoring and infrared remote sensing observation under low light conditions.

CN122090041AActive Publication Date: 2026-05-26BEIJING INSTITUTE OF TECHNOLOGY (ZHUHAI)
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202610525323.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-04-21
Publication Date
2026-05-26
Estimated Expiration
2046-04-21

Smart Images

  • Figure CN122090041A_ABST
    Figure CN122090041A_ABST
Patent Text Reader

Abstract

This invention discloses a lightweight method, device, and medium for small target recognition in infrared remote sensing images. The method includes the following steps: Step S1: Constructing and preprocessing an infrared remote sensing image dataset; Step S2: Constructing a lightweight backbone network HLNet, training the HLNet based on the infrared remote sensing image dataset, and obtaining a trained HLNet network; Step S3: Constructing a lightweight multi-scale feature fusion network LSF, inputting the feature map output by the trained HLNet network into the LSF for multi-scale feature fusion, and obtaining an enhanced multi-scale feature map; Step S4: Inputting the enhanced multi-scale feature map into a detection head module for small target recognition, and obtaining the recognition result. This invention can effectively recognize small infrared targets in complex backgrounds while reducing model complexity.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Transform-based automatic driving target detection method and system

    CN114627446A

  • Remote sensing image small target detection method and system based on improved Swin Transform

    CN121214245A