Scholarlink

<p>Multi-category Personal Protective Equipment (PPE) non-compliance monitoring on construction sites remains challenging because visual cues for missing PPE often appear at multiple scales, particularly as small objects. To address these challenges, an enhanced YOLOv10-based detector is developed that incorporates Omni-Dimensional Dynamic Convolution (ODConv) to strengthen fine-grained feature representation, an Efficient Multi-scale Attention–guided Bidirectional Feature Pyramid Network (EMA-BiFPN) to improve cross-scale fusion, a four-scale prediction strategy to increase sensitivity to extremely small instances, and the Minimum Points Distance IoU (MPDIoU) loss to stabilize bounding-box regression. Experiments are conducted on a dataset of 4060 images annotated for five violation categories (No-helmet, No-mask, No-vest, No-glove, and No-shoes), using stratified splits and a controlled hyperparameter search (243 configurations). On the test set, the proposed method achieves 92.49 mAP@50 and 70.04 mAP@50:95 while maintaining 57.28 FPS, outperforming representative two-stage, one-stage, and transformer-based baselines. The largest gains are observed in small-object regimes, reaching <InlineEquation ID="IEq1"><EquationSource Format="TEX">\({\text{A}\text{P}}_{ES}\)</EquationSource></InlineEquation> = 82.74 and <InlineEquation ID="IEq2"><EquationSource Format="TEX">\({\text{A}\text{P}}_{S}\)</EquationSource></InlineEquation> = 88.96, indicating improved robustness to distant and tiny PPE cues. Robustness analyses further show that performance is less sensitive to weight initialization than to dataset partitioning, and condition-based evaluation confirms that far-field views and worker overlap remain the dominant failure cases due to the difficulty of localizing extremely small instances.</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

YOLOv10-based multi-scale variant object detection for multi-category PPE non-compliance monitoring on construction sites

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月29日

查看全文
  • Seunghyeon Wang,
  • Hyuna Kim,
  • Jiyoung Yeo,
  • Juhyung Kim

摘要

Multi-category Personal Protective Equipment (PPE) non-compliance monitoring on construction sites remains challenging because visual cues for missing PPE often appear at multiple scales, particularly as small objects. To address these challenges, an enhanced YOLOv10-based detector is developed that incorporates Omni-Dimensional Dynamic Convolution (ODConv) to strengthen fine-grained feature representation, an Efficient Multi-scale Attention–guided Bidirectional Feature Pyramid Network (EMA-BiFPN) to improve cross-scale fusion, a four-scale prediction strategy to increase sensitivity to extremely small instances, and the Minimum Points Distance IoU (MPDIoU) loss to stabilize bounding-box regression. Experiments are conducted on a dataset of 4060 images annotated for five violation categories (No-helmet, No-mask, No-vest, No-glove, and No-shoes), using stratified splits and a controlled hyperparameter search (243 configurations). On the test set, the proposed method achieves 92.49 mAP@50 and 70.04 mAP@50:95 while maintaining 57.28 FPS, outperforming representative two-stage, one-stage, and transformer-based baselines. The largest gains are observed in small-object regimes, reaching \({\text{A}\text{P}}_{ES}\) = 82.74 and \({\text{A}\text{P}}_{S}\) = 88.96, indicating improved robustness to distant and tiny PPE cues. Robustness analyses further show that performance is less sensitive to weight initialization than to dataset partitioning, and condition-based evaluation confirms that far-field views and worker overlap remain the dominant failure cases due to the difficulty of localizing extremely small instances.