Scholarlink

<p>Defects in transmission line components pose serious threats to the safety and reliability of power systems. However, accurate detection remains challenging due to large-scale variations, complex outdoor backgrounds, and the coexistence of subtle and prominent defect patterns. To address these challenges, we propose TLDRT-DETR, an improved real-time detection framework based on RT-DETR. Specifically, we design an Adaptive Attention Dynamic Upsampling (AADU) module to replace conventional upsampling in cross-scale feature fusion, enabling defect-aware cross-scale feature reconstruction under complex background interference and improved cross-scale feature interaction. In addition, a Dual-activation Spatial and Channel Synergistic Attention (DualActSCSA) module is introduced into high-level feature fusion to enhance defect feature discriminability and suppress background interference. Experimental results show that the proposed method achieves 90.4% precision, 85.4% mAP@50, and 55.5% mAP@50:95, outperforming the RT-DETR baseline by 2.1%, 2.1%, and 1.7%, respectively. Meanwhile, TLDRT-DETR maintains real-time inference performance with 52.8 FPS. The proposed framework achieves reliable detection performance for transmission line inspection in complex outdoor environments.</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

TLDRT-DETR: adaptive upsampling and dual-activation attention for real-time transmission line defect detection

  • 期刊论文

  • 发表日期：

    2026年6月3日

查看全文
  • Bing Su,
  • Yi Lu,
  • Yifeng Lin

摘要

Defects in transmission line components pose serious threats to the safety and reliability of power systems. However, accurate detection remains challenging due to large-scale variations, complex outdoor backgrounds, and the coexistence of subtle and prominent defect patterns. To address these challenges, we propose TLDRT-DETR, an improved real-time detection framework based on RT-DETR. Specifically, we design an Adaptive Attention Dynamic Upsampling (AADU) module to replace conventional upsampling in cross-scale feature fusion, enabling defect-aware cross-scale feature reconstruction under complex background interference and improved cross-scale feature interaction. In addition, a Dual-activation Spatial and Channel Synergistic Attention (DualActSCSA) module is introduced into high-level feature fusion to enhance defect feature discriminability and suppress background interference. Experimental results show that the proposed method achieves 90.4% precision, 85.4% mAP@50, and 55.5% mAP@50:95, outperforming the RT-DETR baseline by 2.1%, 2.1%, and 1.7%, respectively. Meanwhile, TLDRT-DETR maintains real-time inference performance with 52.8 FPS. The proposed framework achieves reliable detection performance for transmission line inspection in complex outdoor environments.