Bilderkennungsmethoden für eine teilautomatisierte Inspektion von Brandschutzanlagen: Eine Studie unter Berücksichtigung von maschinellen Lernverfahren und der Integration von Expertenwissen.

Image recognition methods for the partial inspection of fire safety equipment – a study considering machine learning techniques and the integration of expert knowledge This paper explores the potential application of artificial intelligence (AI) and computer vision in the context of Building Information Modeling (BIM) for documenting fire safety equipment. Detection algorithms, particularly current You Only Look Once (YOLO) models, are utilized to automatically identify fire safety equipment such as fire extinguishers, fire blankets, smoke detectors, and fire alarms in images. The results demonstrate high detection accuracy in both images. Future work aims to expand automated detection by directly integrating it into BIM models. In addition, the importance of expert knowledge in determining the extinguishing agent type of a fire extinguisher is addressed to verify and, if necessary, correct the prediction of an AI‐based fire safety inspection. The developed AI applications aim to increase the level of automation in fire safety inspections to improve the safety of buildings in the operational phase. [ABSTRACT FROM AUTHOR]