I will first provide links to Baidu.com discs for some of the datasets. More specific datasets involve confidential information from Tianjin Grid, and I need to discuss with them whether they can be made public. However, the datasets I provided are sufficient for code debugging and model training. The links to the datasets are below:
Link: https://pan.baidu.com/s/1inULMZcnibOsfjXvJQiFjQ
Extraction code: 8kdy
This is our PyTorch implementation of the paper "A Lightweight Insulator Defect Detection Model Based on Drone Images" published in Drones.
Install
First, clone the project and configure the environment. Python>=3.7.0, PyTorch>=1.7.
git clone https://github.com/LuYang-2023/Insulator-Defect-Detection-YOLO.git # clone
cd Insulator-Defect-Detection-YOLO
pip install -r requirements.txt # installTrain
python train.py --cfg models/IDD-YOLO.yaml --data data/mydata.yamlTest
python val.py --data data/mydata.yaml --weights best.pt --task test
3.1 Edge Platform Deployment
If you use this code or article in your research, please cite it using the following BibTeX entry:
@Article{drones8090431,
AUTHOR = {Lu, Yang and Li, Dahua and Li, Dong and Li, Xuan and Gao, Qiang and Yu, Xiao},
TITLE = {A Lightweight Insulator Defect Detection Model Based on Drone Images},
JOURNAL = {Drones},
VOLUME = {8},
YEAR = {2024},
NUMBER = {9},
ARTICLE-NUMBER = {431},
URL = {https://www.mdpi.com/2504-446X/8/9/431},
ISSN = {2504-446X},
DOI = {10.3390/drones8090431}
}