Scholarlink

<p>Real-time and accurate detection of overhead cables violating street-level regulations is crucial for smart city management. Existing methods face challenges like slender target nature, occlusion, multi-scale variability, and high inter-class similarity. This paper presents the IOA-YOLO model. It incorporates a Line-Target Enhancement Module (LTEM) for better slender object feature extraction, a Global–Local Dual Perception Module (GDPM) to boost robustness against occlusion, and a Hybrid Iterative Detection Head (HIDH) for multi-scale feature extraction using intra-and inter-layer information. An uncertainty-aware loss function (UAL) is introduced to suppress background interference and reduce inter-class similarity impact. Experiments on a custom dataset show IOA-YOLO outperforms existing methods, achieving 93.94% <i>precision</i> and 88.17% <i>recall</i>, with a good balance between accuracy and efficiency. It also adapts well to various urban environments and lighting conditions, demonstrating robust stability and great real-world deployment potential.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

IOA-YOLO: detection of illegal overhead cables based on linear enhancement and dual perception

  • 期刊论文

  • 发表日期：

    2025年5月28日

查看全文
  • Yujie Wu,
  • Jiguang Dai,
  • Tengda Zhang,
  • Zheng Ma

摘要

Real-time and accurate detection of overhead cables violating street-level regulations is crucial for smart city management. Existing methods face challenges like slender target nature, occlusion, multi-scale variability, and high inter-class similarity. This paper presents the IOA-YOLO model. It incorporates a Line-Target Enhancement Module (LTEM) for better slender object feature extraction, a Global–Local Dual Perception Module (GDPM) to boost robustness against occlusion, and a Hybrid Iterative Detection Head (HIDH) for multi-scale feature extraction using intra-and inter-layer information. An uncertainty-aware loss function (UAL) is introduced to suppress background interference and reduce inter-class similarity impact. Experiments on a custom dataset show IOA-YOLO outperforms existing methods, achieving 93.94% precision and 88.17% recall, with a good balance between accuracy and efficiency. It also adapts well to various urban environments and lighting conditions, demonstrating robust stability and great real-world deployment potential.