Insulator Defect Detection

Submission Dates:
08/11/2021 to 10/30/2021
Citation Author(s):
Dexter
Lewis
Pratik
Kulkarni
Submitted by:
Dexter Lewis
Last updated:
Tue, 09/21/2021 - 17:59
DOI:
10.21227/vkdw-x769
License:
Creative Commons Attribution

Abstract 

 

Electric utilities collect imagery and video to inspect transmission and distribution infrastructure.  Utilities use this information to identify infrastructure defects and prioritize maintenance decisions.  The ability to collect these data is quickly outpacing the ability to analyze it.   Today’s data interpretation solutions rely on human-in-the-loop workflows.  This is time consuming, costly, and inspection quality can be subjective.  It’s likely some of these inspection tasks can be automated by leveraging machine learning techniques and artificial intelligence.

    

Instructions: 

 

Data description: 

The Insulator Defect Image Dataset (IDID) consists of labeled high quality images of transmission line insulators. The images have insulator string as the primary subject and parent class. These images contain 3 sub-classes:

1. Flashover damage insulator shell

2. Broken insulator shell

3. Good insulator shell.

Submission Requirements:

The submission should be a csv file with format (imageid, PredictionString)

Here, the image_id is the image name and PredictionString consists of (Class ID, confidence_score, xmin, ymin, xmax, ymax)

The Class IDs are as follows - 0:broken , 1:flashed, 2:good, 3:insulator.

Example:

(xyz_imgname1, 2 0.89 232 224 322 512)

(xyz_imgname2, 1 0.94 134 143 458 565)

 Evaluation Metrics:

 The evaluation metrics used will be mAp@0.5.

 

 

 

   

Please provide a link to the fill license.
Please provide a brief explanation of your need for this alternate license.

Competition Dataset Files

AttachmentSize
File Train_IDID_V1.2.zip2.26 GB
File Test_IDID.zip697.6 MB
    ACCESS ON AWS

    Documentation

    AttachmentSize
    File ReadMe -V1.2 for IDID.pdf238.16 KB