TY - JOUR

T1 - Automating concrete production control with computer vision-based aggregate characterisation

AU - Coenen, Max

AU - Beyer, Dries

AU - Mohammadi, Sahar

AU - Meyer, Max

AU - Heipke, Christian

AU - Haist, Michael

N1 - Publisher Copyright: © 2025 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license. http://creativecommons.org/licenses/by/4.0/

PY - 2026/2

Y1 - 2026/2

N2 - Concrete production is increasingly affected by fluctuations in the properties of natural and especially recycled aggregates. This paper investigates whether particle size distribution and material composition can be automatically determined from conveyor-belt image data during production. A backbone-agnostic deep-learning framework based on CNNs and Vision Transformers is applied to predict these properties and is extended with an additional branch that estimates aleatoric uncertainty directly from data via an uncertainty-aware loss formulation. The approach is evaluated on more than 80,000 real-world images collected using a camera-based sensor system installed on an operational concrete mixing plant. The results show accurate prediction of both grading curves and recycled material composition, providing a reliable basis for improved quality control for concrete producers and aggregate suppliers. The publicly available dataset enables further research and supports future progress towards fully automated, real-time quality assessment in concrete production.

AB - Concrete production is increasingly affected by fluctuations in the properties of natural and especially recycled aggregates. This paper investigates whether particle size distribution and material composition can be automatically determined from conveyor-belt image data during production. A backbone-agnostic deep-learning framework based on CNNs and Vision Transformers is applied to predict these properties and is extended with an additional branch that estimates aleatoric uncertainty directly from data via an uncertainty-aware loss formulation. The approach is evaluated on more than 80,000 real-world images collected using a camera-based sensor system installed on an operational concrete mixing plant. The results show accurate prediction of both grading curves and recycled material composition, providing a reliable basis for improved quality control for concrete producers and aggregate suppliers. The publicly available dataset enables further research and supports future progress towards fully automated, real-time quality assessment in concrete production.

KW - Granulometry

KW - Recycled concrete aggregate

KW - Particle size distribution

KW - Deep learning

KW - CNN

KW - ViT

KW - Computer vision

UR - http://www.scopus.com/inward/record.url?scp=105029731781&partnerID=8YFLogxK

U2 - 10.1016/j.autcon.2025.106716

DO - 10.1016/j.autcon.2025.106716

M3 - Article

VL - 182

SP - 106716

JO - Automation in construction

JF - Automation in construction

SN - 0926-5805

M1 - 106716

ER -