Scholarlink

<p>Automatic detection of safety helmets and harnesses is crucial for industrial safety supervision. Existing methods face challenges in detecting small objects, handling complex environments, and capturing fine-grained features. This paper presents a deep learning-based approach that incorporates a fine-grained feature extraction (FFE) branch for fusing low-level details with high-level semantics, and a dynamic label assignment (DLA) strategy to optimize positive sample selection during training. A comprehensive real-world dataset, GDUT-HHD, is created for model development and evaluation. Experiments demonstrate robust detection performance, achieving an mAP@50 of 92.2% at <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(320\times 320\)</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mn>320</mn> <mo>×</mo> <mn>320</mn> </mrow> </math></EquationSource> </InlineEquation>, confirming its effectiveness and practical applicability for on-site safety monitoring.</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

Safety helmet and harness detection on construction sites based on deep learning

  • 期刊论文

  • 发表日期：

    2026年1月16日

查看全文
  • Yuxuan Mo,
  • Shaoqiu Xu,
  • Shuai Ao,
  • Nian Cai,
  • Shaona Zhou,
  • Yinghong Zhou

摘要

Automatic detection of safety helmets and harnesses is crucial for industrial safety supervision. Existing methods face challenges in detecting small objects, handling complex environments, and capturing fine-grained features. This paper presents a deep learning-based approach that incorporates a fine-grained feature extraction (FFE) branch for fusing low-level details with high-level semantics, and a dynamic label assignment (DLA) strategy to optimize positive sample selection during training. A comprehensive real-world dataset, GDUT-HHD, is created for model development and evaluation. Experiments demonstrate robust detection performance, achieving an mAP@50 of 92.2% at \(320\times 320\) 320 × 320 , confirming its effectiveness and practical applicability for on-site safety monitoring.