Sewer Status Detection : Perspectives with Innovative 3D Image Data and with Artificial Intelligence in 2D and 3D Image Analysis Based on the Example of the BMBF Project AUZUKA

The AUZUKA research project, supported by the German Federal Ministry for Education and Research (BMBF), enables to map the status of sewer systems in an automated and more standardised manner by developing modern sensor and image processing technology. This technology is based on mapping sewer damage using artificial intelligence (AI) for both traditional fish-eye technology (2D) and for new 3D image capture technology. Recognition rate results averaging over 80 per cent have been achieved to date by combining AI with existing image analysis algorithms and the heuristics developed here. The software that has been developed assists in detecting the status of sewer systems with efficient ways to determine damage and take stock, including information about their characterisation and identifying the extent. This software and 3D sensor technology can be used as a complete solution or as a component to quickly identify priority areas for action for sewer renovations and thus guide investments in an optimised manner. Automated damage detection and surveying of the extent of damage using an assistance system significantly reduces the high level of subjectivity that has existed to date.