融合双域特征的绝缘子缺陷检测算法
CSTR:
作者:
作者单位:

(1.陕西科技大学 电气与控制工程学院,西安 710021; 2.陕西科技大学 电子信息与人工智能学院,西安 710021)

作者简介:

党宏社(1962—),男,陕西省咸阳市人,博士,教授,主要研究方向为数字图像处理、模式识别;张代言(2002—),男,陕西省宝鸡市人,硕士研究生,主要研究方向为深度学习、图像处理。

通讯作者:

中图分类号:

TP391. 41

基金项目:


Insulator Defect Detection Algorithm Based on Dual-Domain Feature Fusion
Author:
Affiliation:

(1. School of Electrical and Control EngineeringXi’an 710021,CHN;2. School of Electrical Information and Artificial Intelligence, Shaanxi University of Science and Technology,Xi’an 710021,CHN)

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    在无人机航拍输电线路巡检场景中,针对复杂环境干扰导致的绝缘子缺陷检测精度不高、误检、漏检等问题,文章基于实时端到端目标检测模型(RT-DETR)算法,提出一种融合双域特征的绝缘子缺陷检测算法。在主干网络中设计空频特征融合(FreqSF)模块,通过融合空间域与频率域信息,增强了绝缘子缺陷细节纹理特征的表达能力;引入高低频注意力(HiLo)机制替换多头自注意力(MHSA)机制,将特征图中的高频与低频特征分开处理,以强化对局部细节特征的提取;采用三重特征编码器(TFE)与尺度序列特征融合(SSFF)模块,将深层语义信息与浅层细节信息进行深度融合。实验结果表明,所提算法相较于主流算法取得了较好的检测效果,其 mAP@

    Abstract:

    To address the issues of low detection accuracy and frequent false positives and false negatives caused by complex environmental interferences during unmanned aerial vehicle inspections of power transmission lines,this study proposes a dual-domain feature fusion algorithm for insulator defect detection based on Real-Time Detection Transformer(RT-DETR). First, a Spatial-Frequency Feature Fusion module is designed within the backbone network. By integrating spatial-and frequency-domain information, this module significantly enhances the feature-representation capability for fine textures of insulator defects. Second,a High-Low-Frequency Attention mechanism is introduced to replace the conventional Multi-Head Self-Attention mechanism. Processing the high-and low-frequency features separately strengthens the extraction of local-detail features. Finally,a Triple Feature Encoder and a Scale Sequence Feature Fusion module are employed to achieve the deep fusion of high-level semantic information and low-level detail information. Experimental results demonstrate that the proposed algorithm outperforms mainstream detection models. Specifically,it achieves a mAP@0. 5 of 0. 974,which is 1. 5% higher than that of the baseline algorithm,as well as improved precision and recall by 1. 2% and 1. 1%,respectively.

    参考文献
    相似文献
    引证文献
引用本文

党宏社,张代言,张兰馨,魏赵恺,张选德.融合双域特征的绝缘子缺陷检测算法[J].半导体光电,2026,47(5):953-960. DANG Hongshe, ZHANG Daiyan, ZHANG Lanxin, WEI Zhaokai, ZHANG Xuande. Insulator Defect Detection Algorithm Based on Dual-Domain Feature Fusion[J].,2026,47(5):953-960.

复制
分享
相关视频

文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2026-04-12
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2026-10-23
  • 出版日期:
文章二维码