Electronics Optics & Control, Volume. 32, Issue 2, 73(2025)

Unmanned Aerial Vehicle Image Rotation Invariant Matching Based on Multi-scale Feature Fusion

LIU Yun1... LI Ziqian1, BAN Yanwamen1,2, CHEN Weitai1 and CHEN Shan1 |Show fewer author(s)
Author Affiliations
  • 1Surveying and Mapping Engineering Institute of Yunnan Province, Kunming 650000, China
  • 2Kunming University of Science and Technology, Kunming 650000, China
  • show less

    UAV image matching occupies a central position in UAV image processing, and orientation estimation is an important part of performing rotation invariant matching. However, due to the inability to specify the standard orientations of the UAV image feature points, the current matching method still suffers from large orientation estimation errors, resulting in low matching accuracy. A Rotation Invariant Matching Network (RIMN) based on multi-scale feature fusion is proposed for UAV images, in which the multi-scale featureextraction module is used to aggregate rich semantic features of the images and the Transformer self-attention block is used to extract robust features in the weakly textured regions of the image. Meanwhile, a double constrained loss function is designed to improve the orientation estimation accuracy of the feature points. Finally, image matching comparison experiments under different rotation angles is set up. The qualitative and quantitative results show that this method has better rotation invariant matching performance.

    Tools

    Get Citation

    Copy Citation Text

    LIU Yun, LI Ziqian, BAN Yanwamen, CHEN Weitai, CHEN Shan. Unmanned Aerial Vehicle Image Rotation Invariant Matching Based on Multi-scale Feature Fusion[J]. Electronics Optics & Control, 2025, 32(2): 73

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category:

    Received: Jan. 10, 2024

    Accepted: Feb. 20, 2025

    Published Online: Feb. 20, 2025

    The Author Email:

    DOI:10.3969/j.issn.1671-637x.2025.02.012

    Topics