A Survey on Image-Based Automation of CCTV and SSET Sewer Inspections

摘要

This survey presents an in-depth overview of the last 25 years of research within the field of image-based automation of Closed-Circuit Television (CCTV) and Sewer Scanner and Evaluation Technology (SSET) sewer inspection. The survey investigates both the algorithmic pipeline, and the datasets and corresponding evaluation protocols. As a result of the in-depth survey, several trends within the research field are revealed, discussed, and future research directions are proposed. Based on the conducted survey, we put forth a set of three recommendations, which we believe will further improve and open the research field, as well as make the future research more reproducible: 1) The introduction of free and public benchmark datasets, 2) Standardized evaluation metrics, and 3) Open-sourcing the associated code.