Automated quality control of recycled aggregates via deep learning: A unified framework for instance segmentation and mass estimation

  • Jérôme Lux orcid

    Laboratoire des Sciences de l’Ingénieur pour l’Environnement (LaSIE), UMR CNRS 7356, La Rochelle University, 17000 La Rochelle, France

    Department of Civil Engineering and Sustainable Construction, IUT La Rochelle, La Rochelle University, 17000 La Rochelle, France
  • Pierre-Yves Mahieux

    Laboratoire des Sciences de l’Ingénieur pour l’Environnement (LaSIE), UMR CNRS 7356, La Rochelle University, 17000 La Rochelle, France

    Department of Civil Engineering and Sustainable Construction, IUT La Rochelle, La Rochelle University, 17000 La Rochelle, France
  • Philippe Turcry orcid

    Laboratoire des Sciences de l’Ingénieur pour l’Environnement (LaSIE), UMR CNRS 7356, La Rochelle University, 17000 La Rochelle, France

    Department of Civil Engineering and Sustainable Construction, IUT La Rochelle, La Rochelle University, 17000 La Rochelle, France
Article ID: 4151
DOI: https://doi.org/10.59400/mtr4151
Keywords: circular economy, construction and demolition waste, recycled aggregates, convolutional neural networks, instance segmentation, classification, mass prediction

Abstract

The large-scale use of recycled aggregates (RA) in high-grade construction applications is currently hindered by the high variability of their physical properties. Current quality control relies on manual sorting, which is labor-intensive and limits scalability. This study presents RAMSES (Recycled Aggregates Mass estimation and Segmentation), an automated framework based on deep learning, designed to bridge the gap between high-speed production and rigorous material characterization. A central contribution of this work is the introduction of a large-scale, publicly available dataset comprising 90,000 labeled and batch-weighed aggregate instances. This extensive dataset supports a strong statistical robustness across diverse RA compositions and serves as a benchmark for automated waste characterization. Using this dataset, RAMSES performs simultaneous instance segmentation and direct mass estimation from 2D images. By integrating a dual-branch architecture, the model effectively decouples morphological features from instance-dependent density factors. The framework achieves high precision in particle identification (mean Average Precision mAP@[0.5:0.95] = 0.84, mAP@0.5 = 0.91) and a 0.3% relative error in total mass prediction, which meets industrial requirements for batch monitoring. By providing a scalable alternative to manual inspection, this approach improves the consistency of RA-based concrete mixes, directly supporting the transition to a circular construction economy.

Published
2026-05-14
How to Cite
Lux, J., Mahieux, P.-Y., & Turcry, P. (2026). Automated quality control of recycled aggregates via deep learning: A unified framework for instance segmentation and mass estimation. Materials Technology Reports, 4(1). https://doi.org/10.59400/mtr4151
Issue
Vol. 4 No. 1 (2026)
Section
Article

Copyright (c) 2026 Jérôme Lux, Pierre-Yves Mahieux, Philippe Turcry

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

References

[1]de Larrard F, Colina H (editors). Concrete Recycling: Research and Practice. CRC Press; 2019. doi: 10.1201/9781351052825

[2]Wang B, Yan L, Fu Q, et al. A Comprehensive Review on Recycled Aggregate and Recycled Aggregate Concrete. Resources, Conservation and Recycling. 2021; 171: 105565. doi: 10.1016/j.resconrec.2021.105565

[3]EN 933-11:2009. Tests for Geometrical Properties of Aggregates—Part 11: Classification Test for the Constituents of Coarse Recycled Aggregate. 2009.

[4]He K, Gkioxari G, Dollár P, et al. Mask R-CNN. In: Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV); 22–29 October 2017; Venice, Italy. pp. 2980–2988. doi: 10.1109/ICCV.2017.322

[5]Wang X, Zhang R, Kong T, et al. SOLOv2: Dynamic and Fast Instance Segmentation. In: Larochelle H, Ranzato M, Hadsell R, et al. (editors). NIPS '20: Proceedings of the 34th International Conference on Advances in Neural Information Processing Systems, Proceedings of the 34th Conference on Neural Information Processing Systems (NeurIPS 2020); 6–12 December 2020; Vancouver, BC, Canada. Curran Associates, Inc.; 2020. pp. 17721–17732.

[6]Bolya D, Zhou C, Xiao F, et al. YOLACT++: Better Real-time Instance Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2020; 42(2): 1108–1121. doi: 10.1109/TPAMI.2020.3014297

[7]Terven J, Córdova-Esparza DM, Romero-González JA. A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS. Machine Learning and Knowledge Extraction. 2023; 5(4): 1680–1716. doi: 10.3390/make5040083

[8]Li F, Zhang H, Xu H, et al. Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation. In: Proceedinhs of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 17–24 June 2023; Vancouver, BC, Canada. pp. 3041–3050. doi: 10.1109/CVPR52729.2023.00297

[9]Cheng B, Misra I, Schwing AG, et al. Masked-attention Mask Transformer for Universal Image Segmentation. In: Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 18–24 June 2022; New Orleans, LA, USA. pp. 1280–1289. doi: 10.1109/CVPR52688.2022.00135

[10]Carion N, Massa F, Synnaeve G, et al. End-to-End Object Detection with Transformers. In: Vedaldi A, Bischof H, Brox T, et al. (editors). Computer Vision—ECCV 2020, Proceedings of the European Conference on Computer Vision; 23–28 August 2020; Glasgow, UK. Springer International Publishing; 2020. 12346, pp. 213–229. doi: 10.1007/978-3-030-58452-8_13

[11]Guo R, Niu D, Qu L, et al. SOTR: Segmenting Objects with Transformers. In: Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV); 10–17 October 2021; Montreal, QC, Canada. pp. 7137–7146. doi: 10.1109/ICCV48922.2021.00707

[12]Gao Y, Wang J, Xu X. Machine Learning in Construction and Demolition Waste Management: Progress, Challenges, and Future Directions. Automation in Construction. 2024; 162: 105380. doi: 10.1016/j.autcon.2024.105380

[13]Demetriou D, Mavromatidis P, Petrou MF, et al. CODD: A Benchmark Dataset for the Automated Sorting of Construction and Demolition Waste. Waste Management. 2024; 178: 35–45. doi: 10.1016/j.wasman.2024.02.017

[14]Demetriou D, Mavromatidis P, Robert PM, et al. Real-time Construction Demolition Waste Detection Using State-of-the-art Deep Learning Methods; Single-stage vs Two-stage Detectors. Waste Management. 2023; 167: 194–203. doi: 10.1016/j.wasman.2023.05.039

[15]Zhou Q, Liu H, Qiu Y, et al. Object Detection for Construction Waste Based on an Improved YOLOv5 Model. Sustainability. 2023; 15: 681. doi: 10.3390/su15010681

[16]Serranti S, Palmieri R, Bonifazi G, et al. An Automated Classification of Recycled Aggregates for the Evaluation of Product Standard Compliance. Sustainability. 2023; 15: 2009. doi: 10.3390/su152015009

[17]Hamdan M, Rover D, Darr M, et al. Mass Estimation from Images Using Deep Neural Network and Sparse Ground Truth. In: Proceedings of the 2019 18th IEEE International Conference on Machine Learning and Applications (ICMLA); 16–19 December 2019; Boca Raton, FL, USA. pp. 1987–1992. doi: 10.1109/ICMLA.2019.00318

[18]Miura Y, Sawamura Y, Shinomiya Y, et al. Vegetable Mass Estimation Based on Monocular Camera Using Convolutional Neural Network. In: Proceedings of the 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC); 11–14 October 2020; Toronto, ON, Canada. pp. 2106–2112. doi: 10.1109/SMC42975.2020.9282930

[19]Dohmen R, Catal C, Liu Q. Image-based Body Mass Prediction of Heifers Using Deep Neural Networks. Biosystems Engineering. 2021; 204: 283–293. doi: 10.1016/j.biosystemseng.2021.02.001

[20]Standley T, Sener O, Chen D, et al. image2mass: Estimating the Mass of an Object from Its Image. In: Levine S, Vanhoucke V, Goldberg K, et al. (editors). Proceedings of the 1st Annual Conference on Robot Learning, Proceedings of the 1st Conference on Robot Learning (CoRL 2017); 13–15 November 2017; Mountain View, CA, USA. PMLR; 2017. 78, pp. 324–333.

[21]Lux J, Lau Hiu Hoong JD, Mahieux PY, et al. Classification and Estimation of the Mass Composition of Recycled Aggregates by Deep Neural Networks. Computers in Industry. 2023; 148: 103889. doi: 10.1016/j.compind.2023.103889

[22]He K, Zhang X, Ren S, et al. Identity Mappings in Deep Residual Networks. In: Leibe B, Matas J, Sebe N, et al. (editors). Computer Vision—ECCV 2016, Proceedings of the 14th European Conference, October 11–14, 2016; Amsterdam, The Netherlands. Springer International Publishing; 2016. 9905, pp. 630–645.

[23]Gu W, Bai S, Kong L. A Review on 2D Instance Segmentation Based on Deep Neural Networks. Image and Vision Computing. 2022; 120: 104401. doi: 10.1016/j.imavis.2022.104401

[24]Lee Y, Park J. CenterMask: Real-Time Anchor-Free Instance Segmentation. In: Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 13–19 June 2022; Seattle, WA, USA. pp. 13903–13912. 10.1109/CVPR42600.2020.01392

[25]Chen H, Sun K, Tian Z, et al. BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation. arXiv preprint. 2020. doi: 10.48550/arXiv.2001.00309

[26]Tian Z, Shen C, Chen H. Conditional Convolutions for Instance Segmentation. In: Vedaldi A, Bischof H, Brox T, et al. (editors). Computer Vision—ECCV 2020, Proceedings of the European Conference on Computer Vision; 23–28 August 2020; Glasgow, UK. Springer International Publishing; 2020. pp. 282–298.

[27]Tian Z, Shen C, Chen H, et al. FCOS: Fully Convolutional One-Stage Object Detection. In: Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV); 27 October 2019–2 November 2019; Seoul, South Korea. pp. 9626–9635. doi: 10.1109/ICCV.2019.00972

[28]Lau Hiu Hoong JD, Lux J, Mahieux PY, et al. Determination of the Composition of Recycled Aggregates Using a Deep Learning-based Image Analysis. Automation in Construction. 2020; 116: 103204. doi: 10.1016/j.autcon.2020.103204

[29]Kirillov A, Mintun E, Ravi N, et al. Segment Anything. In: Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision (ICCV); 1–6 October 2023; Paris, France. pp. 3992–4003. doi: 10.1109/ICCV51070.2023.00371

[30]Cvat.ai/cvat. Available online: https://github.com/cvat-ai/cvat (accessed on 11 February 2026).

[31]Woo S, Debnath S, Hu R, et al. ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders. In: Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 17–24 June 2023; Vancouver, BC, Canada. pp. 16133–16142. doi: 10.1109/CVPR52729.2023.01548

[32]Lin TY, Goyal P, Girshick R, et al. Focal Loss for Dense Object Detection. In: Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV); 22–29 October 2017; Venice, Italy. pp. 2999–3007. doi: 10.1109/ICCV.2017.324

[33]Loshchilov I, Hutter F. Decoupled Weight Decay Regularization. arXiv preprint. 2019. doi: 10.48550/arXiv.1711.05101

[34]Padilla R, Passos, WL, Dias, TL, et al. A Comparative Analysis of Object Detection Metrics With a Companion Open-Source Toolkit. Electronics. 10(3): 279. doi: 10.3390/electronics10030279

[35]Lin TY, Dollar P, Girshick R, et al. Feature Pyramid Networks for Object Detection. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 21–26 July 2017; pp. 936–944. doi: 10.1109/CVPR.2017.106