Dacl-Challenge: Semantic Segmentation During Visual Bridge Inspections

Johannes Flotzinger, Philipp J. Rösch, Christian Benz, Muneer Ahmad, Murat Cankaya, Helmut Mayer, Volker Rodehorst, Norbert Oswald, Thomas Braml; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops, 2024, pp. 716-725


Civil engineering structures - such as bridges - form an essential component of the transportation infrastructure. A failure of an individual structure can result in enormous damage and costs. The economic costs caused by the closure of a bridge due to congestion can be many times the costs of the bridge itself and its maintenance. Thus, it is mandatory to keep these structures in a safe and operational state. In order to ensure this, they are frequently inspected. However, the current inspection process is error-prone and lengthy. Especially the damage documentation using a hand-drawn sketch causes inconsistencies in the building assessment. On the other hand, recent advancements in hardware enable the deployment of computer vision models for increasing the quality, traceability, and efficiency of structural inspections. Such models are the key element of digitized structural inspections and the basis for automated damage classification, measurement and localization on a pixel-level. Current datasets available for this task suffer from limitations in both size and diversity of classes, raising concerns about their applicability in real-world contexts and their effectiveness as benchmarks. Addressing this problem, we introduced "dacl10k" (damage classification), a diverse dataset designed for multi-label semantic segmentation. Comprising 9,920 images extracted from real-world bridge inspections, "dacl10k" stands out by its comprehensive coverage. It includes 13 damage classes and 6 crucial bridge components pivotal in assessing structures and guiding decisions on restoration, traffic restrictions, and bridge closures. To accelerate progress in baseline development, we organized the "dacl-challenge", inviting enthusiasts in damage recognition to vie for training the best performing model on the "dacl10k" dataset. The competition is at the core of the "1st Workshop on Vision-Based Structural Inspections in Civil Engineering", hosted at WACV 2024.

Related Material

@InProceedings{Flotzinger_2024_WACV, author = {Flotzinger, Johannes and R\"osch, Philipp J. and Benz, Christian and Ahmad, Muneer and Cankaya, Murat and Mayer, Helmut and Rodehorst, Volker and Oswald, Norbert and Braml, Thomas}, title = {Dacl-Challenge: Semantic Segmentation During Visual Bridge Inspections}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {January}, year = {2024}, pages = {716-725} }