IDEAS home Printed from https://ideas.repec.org/a/ids/ijetpo/v21y2026i3p258-274.html

Study on large vision model for key feature recognition in power equipment

Author

Listed:
  • Huaqing Cao

Abstract

In this paper, a key feature recognition algorithm for power equipment based on visual large model is proposed. Firstly, collecting multi-source image data from devices through a multidimensional perception network, using an improved side window guided filtering method for image enhancement, and combining OTSU threshold segmentation to achieve target area extraction; then, use the DINOv2 visual big model for self supervised feature extraction; finally, the optimised whale swarm algorithm is introduced for key feature selection, which improves the accuracy of identifying key features of power equipment while reducing feature dimensions. The experimental results show that the proposed algorithm has a maximum signal-to-noise ratio of 48.75 dB for power equipment images, a maximum accuracy of 97.5% for key feature recognition, and a minimum recognition time of only 3.16 s.

Suggested Citation

  • Huaqing Cao, 2026. "Study on large vision model for key feature recognition in power equipment," International Journal of Energy Technology and Policy, Inderscience Enterprises Ltd, vol. 21(3), pages 258-274.
    • Handle: RePEc:ids:ijetpo:v:21:y:2026:i:3:p:258-274
    as

    Download full text from publisher

    File URL: https://www.inderscience.com/link.php?id=155346
    Download Restriction: Access to full text is restricted to subscribers.
    ---><---

    As the access to this document is restricted, you may want to

    for a different version of it.

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;
    ;
    ;

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:ids:ijetpo:v:21:y:2026:i:3:p:258-274. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Sarah Parker (email available below). General contact details of provider: http://www.inderscience.com/browse/index.php?journalID=12 .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.