南方电网技术2026，Vol.20Issue(5)：123-135,13.DOI:10.13648/j.cnki.issn1674-0629.2026.05.013
基于改进YOLOv8的轻量化输电线路异物检测模型
Lightweight Foreign Object Detection Model for Power Transmission Lines Based on Improved YOLOv8
摘要
Abstract
In response to the issues of low accuracy and poor real-time performance caused by the large scale of foreign objects and complex backgrounds in existing transmission line foreign object detection algorithms,a lightweight model based on improved YOLOv8 is proposed.Firstly,a modified feature extraction network is designed by integrating a dual-branch architecture with atten-tion mechanisms into MobileNetV2,optimizing the model's parameters and enhancing the feature representation capability.Addition-ally,the CBAM attention mechanism is embedded into the SPPF and PANet modules to enhance the discrimination between foreign objects and the environment,to improve the model's detection capability in complex backgrounds and consequently enhance the detection accuracy.Furthermore,the WIoU loss function is introduced to properly allocate gradient gains,enhancing the model's generalization ability and detection box localization accuracy.Experimental results demonstrate that the improved YOLOv8 achieves a detection accuracy of 96.12%mAP and an inference speed of 60 frames per second.It outperforms YOLOv8 and five other mainstream object detection models in terms of overall performance.Moreover,it exhibits high stability and robustness under differ-ent lighting conditions,proving its practicality in complex environments.Further testing on embedded devices confirms that even under limited computational resources,the improved YOLOv8 can still achieve accurate detection.关键词
分布式光伏/超短期功率预测/相关性信息/数据隐私性/联邦学习/深度学习Key words
transmission line/ultra short term power forecasting/relevant information/data privacy/federated learning/deep learning分类
信息技术与安全科学引用本文复制引用
李旭阳,王文峰,李凌云,殷跃,孙争,葛贤军..基于改进YOLOv8的轻量化输电线路异物检测模型[J].南方电网技术,2026,20(5):123-135,13.基金项目
国家自然科学基金资助项目(52007095). Supported by the National Natural Science Foundation of China(52007095). （52007095）
