Municipalities conduct routine inspections to assess the condition of sewer pipelines and determine the optimal choice and timing of maintenance operations. For many municipalities, closed-circuit television (CCTV) is the primary method of inspecting sewers. The manual process of identifying defects has a propensity for errors and inconsistencies, since it relies on a subjective interpretation of images. Furthermore, this process tends to be slow and labor intensive since it frequently involves re-watching the video recordings. Automated defect identification could improve the speed, consistency, and accuracy of CCTV inspections. This project will leverage recent advances in artificial intelligence to develop an automated system for interpreting CCTV sewer inspection videos.
Originally funded as WERF project WRF-17-24.