AI & Sewer Defect Analysis

AI & Sewer Defect Analysis

Amount awarded: £189,315

Led by: United Utilities

Partners: Dŵr Cymru (Welsh Water), Scottish Water, Severn Trent Water plc, Thames Water Utilities Limited, Water Research Centre, and Yorkshire Water Services Ltd

Using artificial intelligence and machine learning to automatically recognise features in CCTV inspection of sewers, the AI & Sewer Defect Analysis project will give a better understanding of sewer deterioration and reduce the cost of inspections.

—

Update from the project (July 2024)

This project is now complete.

—

Resources:

For more information on AI & Sewer Defect Analysis, take a look at the following resources:

• Read the case study from December 2022 and December 2023
• The foreground IPR developed by this project is as below, which can be accessed in the Spring Knowledge Transfer Library. 

• • Dataset of common defects and features of sewers / library of images 
  • A new dataset containing validated images of sewers and various defect types, suitable for uploading to Artificial Intelligence models