计算机科学
电力传输
算法
对象(语法)
人工智能
工程类
电气工程
作者
Shanshan Zhang,Hongxu Li,Yining Song,Chunwang Yan,Jianchao Wang
出处
期刊:
日期:2024-06-13
卷期号:: 40-46
被引量:3
标识
DOI:10.1109/asip63198.2024.00015
摘要
To address the problem of low detection accuracy of foreign objects on transmission lines using the YOLOv5 algorithm, this thesis proposes a transmission line foreign object detection algorithm based on YOLOv5. The CSP-DarkNet53 backbone network is replaced with an improved lightweight Mobilenetv2 structure to reduce the computation of training the network and improve detection speed. The SENet attention mechanism model is integrated, and deeper downsampling is added to the feature extraction module to improve the recognition accuracy of small targets in transmission line foreign objects. The experimental results show that the mAP of the improved model proposed in this paper reaches 91.6%, which is 4.5% higher than that of the original model.
科研通智能强力驱动
Strongly Powered by AbleSci AI