Computer vision-assisted classification of recycled aggregates

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21110%2F25%3A00384552" target="_blank" >RIV/68407700:21110/25:00384552 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1016/B978-0-443-23962-5.00015-3" target="_blank" >https://doi.org/10.1016/B978-0-443-23962-5.00015-3</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1016/B978-0-443-23962-5.00015-3" target="_blank" >10.1016/B978-0-443-23962-5.00015-3</a>

Result language
angličtina
Original language name
Computer vision-assisted classification of recycled aggregates
Original language description
Efficient construction and demolition waste (CDW) recycling or reuse are crucial for sustainable development, yet current practices often underutilize valuable materials. This chapter introduces an innovative machine-learning-based system for the localization and classification of CDW fragments, possibly enhancing industrial sorting efficiency and thus promoting environmental sustainability. Our approach involves high-resolution image acquisition, preprocessing, and advanced classification using U-Net and ResNet models. We provide a detailed methodology for training these models, focusing on feature extraction, data augmentation, and segmentation. The results demonstrate improved accuracy in identifying and sorting CDW materials, highlighting the potential for integration into existing recycling systems. By combining advanced algorithms with robust hardware, this technology can significantly increase the valorization rate of CDW, reduce waste, and support circular economy principles.
Czech name
—
Czech description
—

Project
<a href="/en/project/EH22_008%2F0004590" target="_blank" >EH22_008/0004590: Robotics and advanced industrial production</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Publication year
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Book/collection name
Advances in Construction and Demolition Waste Recycling: Digital Technologies, Management, Processing and Environmental Assessment
ISBN
978-0-443-23962-5
Number of pages of the result
24
Pages from-to
57-80
Number of pages of the book
471
Publisher name
Elsevier
Place of publication
Kidlington Oxford OX GB
UT code for WoS chapter
—

Similar results(10)