Scholarlink

<p>UAV object detection under hazy conditions is challenging because atmospheric scattering reduces image contrast, weakens object boundaries, and suppresses fine-grained details that are important for small-object recognition. To address these issues, this paper proposes GRFW-YOLOv11, a YOLOv11-based detection framework with a moderate model size for hazy UAV scenes. The proposed framework incorporates detection-oriented haze-interference suppression, frequency–spatial feature recalibration, content-aware cross-scale feature fusion, and localization-oriented regression optimization. These components are designed to improve the representation and localization of small or degraded targets under haze-related visual degradation. Experiments are conducted on VisDrone2019, Foggy VisDrone2019, RTTS, and HazyDet. On VisDrone2019, GRFW-YOLOv11n achieves 41.3% <InlineEquation ID="IEq1"><EquationSource Format="TEX">\(mAP_{50}\)</EquationSource><EquationSource Format="MATHML"><math><mrow><mi>m</mi><mi>A</mi><msub><mi>P</mi><mn>50</mn></msub></mrow></math></EquationSource></InlineEquation> and 24.8% <InlineEquation ID="IEq2"><EquationSource Format="TEX">\(mAP_{50:95}\)</EquationSource><EquationSource Format="MATHML"><math><mrow><mi>m</mi><mi>A</mi><msub><mi>P</mi><mrow><mn>50</mn><mo>:</mo><mn>95</mn></mrow></msub></mrow></math></EquationSource></InlineEquation> with 4.09 M parameters, improving YOLOv11n by 9.1 and 6.2 percentage points, respectively. On HazyDet, GRFW-YOLOv11n improves <InlineEquation ID="IEq3"><EquationSource Format="TEX">\(mAP_{50}\)</EquationSource><EquationSource Format="MATHML"><math><mrow><mi>m</mi><mi>A</mi><msub><mi>P</mi><mn>50</mn></msub></mrow></math></EquationSource></InlineEquation> from 65.8% to 72.3% and <InlineEquation ID="IEq4"><EquationSource Format="TEX">\(mAP_{50:95}\)</EquationSource><EquationSource Format="MATHML"><math><mrow><mi>m</mi><mi>A</mi><msub><mi>P</mi><mrow><mn>50</mn><mo>:</mo><mn>95</mn></mrow></msub></mrow></math></EquationSource></InlineEquation> from 46.0% to 53.3%. The results indicate that the proposed design improves detection accuracy under hazy UAV scenarios, while the increased computational cost suggests that further efficiency optimization is still needed for resource-constrained deployment.</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

A detection-oriented cross-scale fusion YOLOv11 for UAV object detection in hazy environments

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月19日

查看全文
  • Weiguo Yi,
  • Guoqing Liu,
  • Wei Zheng

摘要

UAV object detection under hazy conditions is challenging because atmospheric scattering reduces image contrast, weakens object boundaries, and suppresses fine-grained details that are important for small-object recognition. To address these issues, this paper proposes GRFW-YOLOv11, a YOLOv11-based detection framework with a moderate model size for hazy UAV scenes. The proposed framework incorporates detection-oriented haze-interference suppression, frequency–spatial feature recalibration, content-aware cross-scale feature fusion, and localization-oriented regression optimization. These components are designed to improve the representation and localization of small or degraded targets under haze-related visual degradation. Experiments are conducted on VisDrone2019, Foggy VisDrone2019, RTTS, and HazyDet. On VisDrone2019, GRFW-YOLOv11n achieves 41.3% \(mAP_{50}\)mAP50 and 24.8% \(mAP_{50:95}\)mAP50:95 with 4.09 M parameters, improving YOLOv11n by 9.1 and 6.2 percentage points, respectively. On HazyDet, GRFW-YOLOv11n improves \(mAP_{50}\)mAP50 from 65.8% to 72.3% and \(mAP_{50:95}\)mAP50:95 from 46.0% to 53.3%. The results indicate that the proposed design improves detection accuracy under hazy UAV scenarios, while the increased computational cost suggests that further efficiency optimization is still needed for resource-constrained deployment.