An Improved Algorithm for Foreign Objects Detection on Power Transmission Lines

Da-Ming Zou,Yangkai Liu,Hang Lin, Zhen Qiu

International Conference on Systems and Informatics (ICSAI)（2023）

被引用1|浏览5

摘要

Foreign objects threaten transmission line reliability and can cause cascading blackouts. Manual inspection of thousands of miles is inadequate. This paper presents an optimized deep learning model for real-time foreign object detection. We enhance YOLOv4 with GhostNet, CBAM, and BiFPN to to simplify the model structure and improve efficiency and accuracy. GhostNet enables lightweight detection through efficient convolutions. CBAM and BiFPN refine representations. Experiments show state-of-the-art accuracy while using 4.4x fewer parameters than YOLOv4. Our model operates in real-time on edge devices, advancing automated inspection to monitor critical infrastructure. Precise and timely foreign object detection enables proactive maintenance to prevent faults and failures.

查看译文

关键词

Object Detection,Foreign Body,Transmission Line,Transmission Power,Power Line,Deep Learning Models,Fewer Parameters,Critical Infrastructure,Edge Devices,Object Detection Model,Automatic Inspection,Real-time Object Detection,Convolutional Neural Network,Convolutional Layers,Feature Maps,Convolution Operation,Bounding Box,Class Probabilities,Small Objects,Spatial Attention,You Only Look Once,Feature Pyramid,Feature Pyramid Network,Standard Convolution,Backbone Network,Top-down And Bottom-up,Real-time Inference,Faster R-CNN,Egg Collection,One-stage Object Detection

上传PDF