Aiming at the problems of variable scales, strong background interference and high miss rate of small objects in transmission line foreign object detection, an improved YOLOv11 algorithm fusing the multi-branch feature extraction network MB-FEN and the CBAM attention mechanism is proposed. The algorithm replaces the original Neck structure with MB-FEN to enhance multi-scale feature extraction. The CBAM module is embedded to focus on key features of foreign objects and suppress background interference. Experimental results show that the detection accuracy of the proposed algorithm is significantly better than that of YOLOv5, YOLOv8 and the baseline YOLOv11. It can meet the actual requirements of UAV inspection and provide reliable technical support for transmission line foreign object detection.
Junjie Sang, Yu-Jie Sheng, Liutao Lu· Digital Signal and Computer...· 0 citations
Insulators and their accessories are core components ensuring the safe operation of transmission lines. Defect detection for them is confronted with challenges such as small targets, complex backgrounds and difficulty in fitting the irregular boundaries of defects, while traditional lightweight algorithms suffer from insufficient detection performance. To tackle these challenges, this work presents a lightweight detection algorithm built upon the improved YOLOv11n: the DCNv3 (Deformable Convolution v3) is embedded into the backbone network to replace the traditional convolutional layers, enhancing the ability to extract features of irregular defects; the Inner-WIoU(Inner-Weighted Intersection over Union) loss function is employed to refine the bounding box regression. All experiments are conducted on a self-built dataset with 7,972 images and 7 defect categories. The proposed method achieves a mAP@50 of 86.4%, 3.2 percentage points higher than the baseline YOLOv11n, and outperforms mainstream lightweight detectors and small-object-oriented detectors. Meanwhile, the algorithm retains the lightweight advantage and meets the needs of on-site real-time inspection. The model maintains a lightweight structure with only 2.6 M parameters and achieves an inference speed of 38 FPS on NVIDIA RTX 4080 Super, meeting real-time inspection requirements. Meanwhile, the algorithm retains the lightweight advantage and can meet the requirements of on-site real-time inspection. Since validation is limited to a self-constructed dataset, cross-scene testing and public benchmark evaluation will be conducted in future work to further verify the model’s robustness and generalization in real transmission-line inspection scenarios.
Yu-Jie Sheng, Junjie Sang, Liutao Lu· Digital Signal and Computer...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
