A Novel 24 h × 7 Days Broken Wire Detection and Segmentation Framework Based on Dynamic Multi-Window Attention and Meta-Transfer Learning

A Novel 24 h × 7 Days Broken Wire Detection and Segmentation Framework Based on Dynamic Multi-Window Attention and Meta-Transfer Learning

Detecting and segmenting damaged wires in substations is challenging due to varying lighting conditions and limited annotated data, which degrade model accuracy and robustness. In this paper, a novel 24 h × 7 days broken wire detection and segmentation framework based on dynamic multi-window attenti...

Full description

Saved in:
Bibliographic Details
Main Authors: Han Wu, Shiyu Xiong, Yunhan Lin
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Sensors
Subjects:
Yolov11
segmentation
detection
attention mechanism
transfer learning
Online Access:https://www.mdpi.com/1424-8220/25/12/3718
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://www.mdpi.com/1424-8220/25/12/3718

Similar Items