Image‐based quality control of fresh concrete based on semantic segmentation algorithms

Abstract In practice, various empirical methods such as the flow table test or the slump test are in use worldwide for assessing the workability of fresh concrete on the construction site. The majority of these tests has in common, that fresh concrete is subjected to some kind of defined flow process on a standardized table‐like platform and that the geometrical properties of the material after the flow has ceased is determined by simple means such as measuring the flow cake diameter or its sag. The paper at hand proposes a novel image‐based approach for an automatic derivation of concrete properties as part of the flow table test. The image‐based method enables a digital evaluation of concrete properties. By combining digital image analysis and deep learning methods, not only the consistency but also an abundance of additional concrete properties can be derived from image data. In this way, the quality control of the fresh concrete can be expanded to include a large number of additional parameters, currently not available to the producer nor to the construction site. This data can be integrated into a digital control loop, with which communication between the concrete producer and the construction site can be automated using highly precise real‐time data.