Paper
25 May 2023 Intelligent detection and recognition of high voltage tower bird's nest based on improved neural network
Qunyuan Li, Daili Liang, Nan Chen, Wentong Zhang, Lixuan Ye, Yumeng Wang, Zhijian Shao, Yiming Peng, Jiayi Huo
Author Affiliations +
Proceedings Volume 12636, Third International Conference on Machine Learning and Computer Application (ICMLCA 2022); 126361G (2023) https://doi.org/10.1117/12.2675372
Event: Third International Conference on Machine Learning and Computer Application (ICMLCA 2022), 2022, Shenyang, China
Abstract
The YOLOv5 used in this paper is a single-segment target detection algorithm that improves the speed and precision performance based on YOLOv4. The original anchor frame of YOLOv5 is difficult to cope with the uneven distribution of detection targets in different training sets. In this paper, the dynamic anchor frame mechanism is used to improve YOLOv5. After improvement, the accuracy of the model was 93.5 %, increased by 4.2 %, the recall rate was 92.31 %, increased by 3.64 %. Through the actual data detection, the YOLOv5s model with dynamic anchor frame mechanism can better detect the bird's nest on the high voltage tower.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Qunyuan Li, Daili Liang, Nan Chen, Wentong Zhang, Lixuan Ye, Yumeng Wang, Zhijian Shao, Yiming Peng, and Jiayi Huo "Intelligent detection and recognition of high voltage tower bird's nest based on improved neural network", Proc. SPIE 12636, Third International Conference on Machine Learning and Computer Application (ICMLCA 2022), 126361G (25 May 2023); https://doi.org/10.1117/12.2675372
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Education and training

Target detection

Detection and tracking algorithms

Neural networks

Data modeling

Sampling rates

Image processing

RELATED CONTENT

Post-segmentation processing based on image morphology
Proceedings of SPIE (December 20 2021)
Research on parking detection algorithm based on yolov8
Proceedings of SPIE (October 11 2023)
Object detection for traffic management based on YOLO
Proceedings of SPIE (February 14 2024)

Back to Top