Scholarlink

<p>In intelligent transportation and safety monitoring, infrared road object detection technology holds significant value due to its low-light environmental advantages. However, inherent limitations such as low image resolution and blurred textures cause severe feature information loss and insufficient small object detection accuracy in existing algorithms. This study proposes an infrared road small object detection model integrating super-resolution reconstruction with improved YOLOv10n called SOG-YOLO. The Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) is employed to reconstruct image details. A Dynamic Generalized Efficient Layer Aggregation Network (D-GELAN) enhances feature fusion, combined with Omni-Dimensional Dynamic Convolution (OD-Conv) for adaptive feature extraction. A neck structure (DD-PAN) that combines D-GELAN and DySample has been designed to capture weak small object features with low computational cost. Experiments on two infrared road datasets demonstrate that SOG-YOLO achieves recall improvements of 7.4% and 10.4%, respectively, compared to baseline models, with <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="11227_2025_7692_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="50" /> </InlineMediaObject> <EquationSource Format="TEX">\(\text {mAP}_\text {50}\)</EquationSource> <EquationSource Format="MATHML"><math> <msub> <mtext>mAP</mtext> <mtext>50</mtext> </msub> </math></EquationSource> </InlineEquation> increasing by 7.4% and 10.3% correspondingly. This provides a high-performance solution for infrared road object detection.</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

SOG-YOLO: an infrared road scene small object detection model

  • 期刊论文

  • 发表日期：

    2025年8月4日

查看全文
  • Ende Peng,
  • Qing Ai,
  • Ziqiang Li,
  • Shaoyu Mao,
  • Tao Han

摘要

In intelligent transportation and safety monitoring, infrared road object detection technology holds significant value due to its low-light environmental advantages. However, inherent limitations such as low image resolution and blurred textures cause severe feature information loss and insufficient small object detection accuracy in existing algorithms. This study proposes an infrared road small object detection model integrating super-resolution reconstruction with improved YOLOv10n called SOG-YOLO. The Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) is employed to reconstruct image details. A Dynamic Generalized Efficient Layer Aggregation Network (D-GELAN) enhances feature fusion, combined with Omni-Dimensional Dynamic Convolution (OD-Conv) for adaptive feature extraction. A neck structure (DD-PAN) that combines D-GELAN and DySample has been designed to capture weak small object features with low computational cost. Experiments on two infrared road datasets demonstrate that SOG-YOLO achieves recall improvements of 7.4% and 10.4%, respectively, compared to baseline models, with \(\text {mAP}_\text {50}\) mAP 50 increasing by 7.4% and 10.3% correspondingly. This provides a high-performance solution for infrared road object detection.