Self-Supervised Learning for Identifying Defects in Sewer Footage
This addresses the problem of costly manual sewer inspections for municipalities and infrastructure managers, offering a scalable solution, though it is incremental as it applies an existing method to a new domain.
The study tackled automated defect detection in sewer footage without needing large labeled datasets by applying Self-Supervised Learning, achieving competitive results with a model at least 5 times smaller than other approaches and using only 10% of the data.
Sewerage infrastructure is among the most expensive modern investments requiring time-intensive manual inspections by qualified personnel. Our study addresses the need for automated solutions without relying on large amounts of labeled data. We propose a novel application of Self-Supervised Learning (SSL) for sewer inspection that offers a scalable and cost-effective solution for defect detection. We achieve competitive results with a model that is at least 5 times smaller than other approaches found in the literature and obtain competitive performance with 10\% of the available data when training with a larger architecture. Our findings highlight the potential of SSL to revolutionize sewer maintenance in resource-limited settings.