Scholarlink

<p>Real-time object detection in adverse weather and low-light conditions is crucial for applications such as autonomous driving and intelligent surveillance. This paper presents MDAT-YOLO, a novel object detection framework designed to balance accuracy and efficiency in challenging environments. The model integrates multi-dimensional attention mechanisms and transformer-based enhancements to strengthen feature extraction and adaptability. It introduces two core modules: DWConv_O, an optimized depthwise separable convolution layer, and ODConv++, an omni-dimensional dynamic convolution module that enhances spatial, channel, and kernel-level interactions for improved feature selectivity and dynamic response. A lightweight C3 Transformer (C3TR) block further reduces computational overhead while maintaining strong representational capacity. MDAT-YOLO is evaluated on four benchmark datasets, including RTTS, VOC-Foggy, ExDark, and a custom foggy VOC-PASCAL subset, achieving accuracy improvements of 70.50%, 65.14%, 77.40%, and 49.00%, respectively. The model sustains real-time speeds up to 145 FPS, demonstrating robustness and practicality for real-world deployment under diverse environmental conditions.</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

Multi-dimensional attention transformer for vehicle and pedestrian detection in adverse weather

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月8日

查看全文
  • Soumen Biswas,
  • Jayendra Kumar,
  • Abhishek Mitra,
  • Ananth Ganesh,
  • Priyanka Singh

摘要

Real-time object detection in adverse weather and low-light conditions is crucial for applications such as autonomous driving and intelligent surveillance. This paper presents MDAT-YOLO, a novel object detection framework designed to balance accuracy and efficiency in challenging environments. The model integrates multi-dimensional attention mechanisms and transformer-based enhancements to strengthen feature extraction and adaptability. It introduces two core modules: DWConv_O, an optimized depthwise separable convolution layer, and ODConv++, an omni-dimensional dynamic convolution module that enhances spatial, channel, and kernel-level interactions for improved feature selectivity and dynamic response. A lightweight C3 Transformer (C3TR) block further reduces computational overhead while maintaining strong representational capacity. MDAT-YOLO is evaluated on four benchmark datasets, including RTTS, VOC-Foggy, ExDark, and a custom foggy VOC-PASCAL subset, achieving accuracy improvements of 70.50%, 65.14%, 77.40%, and 49.00%, respectively. The model sustains real-time speeds up to 145 FPS, demonstrating robustness and practicality for real-world deployment under diverse environmental conditions.