Rethinking Infrastructure Inspection as Image Difference Classification: A Traffic Sign Case Study
For infrastructure inspection practitioners with limited annotated data, this work proposes a new task formulation that reduces data requirements.
The paper reformulates image-based defect detection as image difference classification (IDC) to reduce data reliance in infrastructure inspection, showing that an instruction-based classifier outperforms encoder-based ones in a traffic sign case study.
Digital twins (DTs) allow the digitalization of road infrastructure inspection, though this is hindered by limited annotated data. This work exploits the relational nature of continuous asset condition monitoring to reformulate image-based defect detection as image difference classification (IDC) to reduce data reliance. This was evaluated in a case study on low-resource traffic sign inspection with different IDC classifiers using a newly-curated, high quality dataset. Results indicate that the instruction-based classifier outperforms encoder-based ones and gains from comparison with reference images. This shows that IDC can be an effective task modeling for tackling data constraints in infrastructure inspection and DT asset condition updating.