Insulator-Defect Detection is a dataset for an object detection task. It is used in the energy industry.

The dataset consists of 1600 images with 5373 labeled objects belonging to 3 different classes including insulator, pollution-flashover, and broken.

Images in the Insulator-Defect Detection dataset have bounding box annotations. All images are labeled (i.e. with annotations). There are 3 splits in the dataset: train (1296 images), test (160 images), and val (144 images). The dataset was released in 2022 by the Changzhou University and Chinese Academy of Sciences.

Here is the visualized example grid with annotations:

Insulator-Defect Detection is under CC BY 4.0 license.

Source

If you make use of the Insulator-Defect Detection data, please cite the following reference:

@Article{s22228801,
    AUTHOR = {Zheng, Jianfeng and Wu, Hang and Zhang, Han and Wang, Zhaoqi and Xu, Weiyue},
    TITLE = {Insulator-Defect Detection Algorithm Based on Improved YOLOv7},
    JOURNAL = {Sensors},
    VOLUME = {22},
    YEAR = {2022},
    NUMBER = {22},
    ARTICLE-NUMBER = {8801},
    URL = {https://www.mdpi.com/1424-8220/22/22/8801},
    PubMedID = {36433397},
    ISSN = {1424-8220},
    ABSTRACT = {Existing detection methods face a huge challenge in identifying insulators with minor defects when targeting transmission line images with complex backgrounds. To ensure the safe operation of transmission lines, an improved YOLOv7 model is proposed to improve detection results. Firstly, the target boxes of the insulator dataset are clustered based on K-means++ to generate more suitable anchor boxes for detecting insulator-defect targets. Secondly, the Coordinate Attention (CoordAtt) module and HorBlock module are added to the network. Then, in the channel and spatial domains, the network can enhance the effective features of the feature-extraction process and weaken the ineffective features. Finally, the SCYLLA-IoU (SIoU) and focal loss functions are used to accelerate the convergence of the model and solve the imbalance of positive and negative samples. Furthermore, to optimize the overall performance of the model, the method of non-maximum suppression (NMS) is improved to reduce accidental deletion and false detection of defect targets. The experimental results show that the mean average precision of our model is 93.8%, higher than the Faster R-CNN model, the YOLOv7 model, and YOLOv5s model by 7.6%, 3.7%, and 4%, respectively. The proposed YOLOv7 model can effectively realize the accurate detection of small objects in complex backgrounds.},
    DOI = {10.3390/s22228801}
}

Source

Dataset Insulator-Defect Detection can be downloaded in Supervisely format:

As an alternative, it can be downloaded with dataset-tools package:

pip install --upgrade dataset-tools

… using following python code:

import dataset_tools as dtools

dtools.download(dataset='Insulator-Defect Detection', dst_dir='~/dataset-ninja/')

Make sure not to overlook the python code example available on the Supervisely Developer Portal. It will give you a clear idea of how to effortlessly work with the downloaded dataset.

The data in original format can be downloaded here.