Application of YOLO and U-Net models for building material identification on segmented images

• Autorzy: Voronkov Ruslan , Bezuglyi Mykhailo

Identyfikatory

DOI

10.35784/iapgos.6968

Warianty tytułu

PL

Zastosowanie modeli YOLO i U-Net do identyfikacji materiałów budowlanych na segmentowanych obrazach

• Języki publikacji: EN

Abstrakty

EN

This paper is devoted to the analysis of existing convolutional neuralnetworks and experimental verification of the YOLO and U-Netarchitectures for the identification and classification of building materials based on images of destroyed structures. The aim of the study is to determinethe effectiveness of these models in the tasks of recognising materials suitable for reuse and recycling. This will help reduce construction wasteand introduce a more environmentally friendly approach to resource management. The study examined several modern deep learning models for image processing, including Faster R-CNN, Mask R-CNN, FCN (Fully Convolutional Networks), and SegNet. However, the choice was made on the YOLOand U-Netarchitectures. YOLO is used for fast object identification in images, which allows for quick detection and classification of building materials, and U-Netis used for detailed image segmentation, providing accurate determination of the structure and composition of building materials. Each of these models has been adapted to the specific requirements of building materials analysis in the context of collapsed structures. Experimental results have shown that the use of these models allows achieving high accuracy of segmentation of images of destroyed buildings, which makes them promising for usein automated resource control systems.

PL

Niniejszy artykuł poświęcony jest analizie istniejących konwolucyjnych sieci neuronowych i eksperymentalnej weryfikacji architektur YOLOi U-Net do identyfikacji i klasyfikacji materiałów budowlanych na podstawie obrazów zniszczonych konstrukcji. Celem badania jest określenie skuteczności tych modeli w zadaniach rozpoznawania materiałów nadających się do ponownego wykorzystania i recyklingu. Pomoże to zmniejszyć ilość odpadów budowlanych i wprowadzić bardziej przyjazne dla środowiska podejście do zarządzania zasobami. W badaniu przeanalizowano kilkanowoczesnych modeli głębokiego uczenia do przetwarzania obrazu, w tym Faster R-CNN, Mask R-CNN, FCN (Fully Convolutional Networks) i SegNet, jednak wybór padłna architektury YOLO i U-Net. YOLO służy do szybkiej identyfikacji obiektów na obrazach, co pozwala na szybkie wykrywanie i klasyfikację materiałów budowlanych, a U-Net służy do szczegółowej segmentacji obrazu, zapewniając dokładne określenie struktury i składu materiałów budowlanych. Każdyz tych modeli został dostosowany do specyficznych wymagań analizy materiałów budowlanych w kontekście zawalonych konstrukcji.Wyniki eksperymentów wykazały, żezastosowanie tych modeli pozwala osiągnąć wysoką dokładność segmentacji obrazów zniszczonych budynków, co czynije obiecującymi do wykorzystania w zautomatyzowanych systemach kontroli zasobów.

Słowa kluczowe

EN

image segmentation; neural networks; classificationof building materials; YOLOv8; U-Net; deep learning

PL

segmentacja obrazów; sieci neuronowe; klasyfikacja materiałów budowlanych; YOLOv8; U-Net; głębokie uczenie

• Wydawca: Wydawnictwo Politechniki Lubelskiej
• Czasopismo: Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska
• Rocznik: 2025
• Tom: T. 15, nr 2
• Strony: 13--17
• Opis fizyczny: Bibliogr. 23 poz., fot., tab.

Twórcy

autor

Voronkov Ruslan

• National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute", Department of Computer-Integrated Technologies of Device Production, Kyiv, Ukraine

• https://orcid.org/0009-0000-4779-0132+

autor

Bezuglyi Mykhailo

• National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute", Department of Computer-Integrated Technologies of Device Production, Kyiv, Ukraine

• https://orcid.org/0000-0003-0624-0585+

Bibliografia

• [1] Aimaiti Y. et al.: War Related Building Damage Assessment in Kyiv, Ukraine, Using Sentinel-1 Radar and Sentinel-2 Optical Images. Remote Sens. 14, 2022, 6239 [https://doi.org/10.3390/rs14246239].
• [2] Ahmed F., et al.: Recent Advances in Unmanned Aerial Vehicles: A Review. Arabian Journal for Science and Engineering 47(7), 2022, 7963–7984.
• [3] Ansari M. et al.: Significance of Color Spaces and Their Selection for Image Processing: A Survey. Recent Advances in Computer Science and Communications 15(7), 2022, 946-956.
• [4] Bouguettaya A., et al.: Deep Learning Techniques to Classify Agricultural Crops through UAV Imagery: A Review. Neural Computing and Applications 34(12), 2022, 9511-9536.
• [5] Calantropio A. et al.: Deep Learning for Automatic Building Damage Assessment: Application in Post-Disaster Scenarios Using UAV Data. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 1, 2021, 113-120.
• [6] Choi H. W. et al.: An Overview of Drone Applications in the Construction Industry. Drones 7(8), 2023, 515.
• [7] Feroz S., Abu Dabous S.: UAV-Based Remote Sensing Applications for Bridge Condition Assessment. Remote Sensing 13(9), 2021, 1809.
• [8] Ghandour Ali J., Jezzini A. A.: Post-War Building Damage Detection. Proceedings 2(7), 2018, 359 [https://doi.org/10.3390/ecrs-2-05172].
• [9] He K. et al.: Deep Residual Learning for Image Recognition. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, 770-778.
• [10] Jiao Z. et al.: A Deep Learning Based Forest Fire Detection Approach Using UAV and YOLOv3. 1st International Conference on Industrial Artificial Intelligence (IAI), IEEE, 2019, 1-5.
• [11] Levchenko N. M., Beiner P. S., Beiner N. V.: Reconstruction of buildings using BIM technologies during city renewal in Ukraine. Physical Metallurgy and Heat Treatment of Metals 4(4), 2022, 64-70.
• [12] Mahami H. et al.: Material Recognition for Automated Progress Monitoring Using Deep Learning Methods. preprint arXiv: 2006.16344, 2020.
• [13] Mavroulis S. et al.: UAV and GIS Based Rapid Earthquake-Induced Building Damage Assessment and Methodology for EMS-98 Isoseismal Map Drawing: The June 12, 2017 Mw 6.3 Lesvos (Northeastern Aegean, Greece) Earthquake. International Journal of Disaster Risk Reduction 37, 2019, 101169.
• [14] Myroniuk D. M., Blagitko B. Ya., Zayachuk I. M.: Computer Simulation of Deep Learning for Image Recognition. Computer Printing Technologies 42(2), 2019, 57-71.
• [15] Paymode A. S., Malode V. B.: Transfer Learning for Multi-Crop Leaf Disease Image Classification Using Convolutional Neural Network VGG. Artificial Intelligence in Agriculture 6, 2022, 23-33.
• [16] Ronneberger O., Fischer P., Brox T.: U-Net: Convolutional Networks for Biomedical Image Segmentation. 18th International Conference Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, Munich, Germany, 2015, Part III, Springer International Publishing, 2015, 234-241.
• [17] Sony S. et al.: A Systematic Review of Convolutional Neural Network-Based Structural Condition Assessment Techniques. Engineering Structures 226, 2021, 111347.
• [18] Sonkar S. et al.: Real-Time Object Detection and Recognition Using FixedWing Lale VTOL UAV. IEEE Sensors Journal 22(21), 2022, 20738-20747.
• [19] Su S., Nawata T.: Demolished Building Detection from Aerial Imagery Using Deep Learning. Proceedings of the ICA 2, 2019, 122.
• [20] Wang H. et al.: YOLOv8-QSD: An Improved Small Object Detection Algorithm for Autonomous Vehicles Based on YOLOv8. IEEE Transactions on Instrumentation and Measurement, 2024.
• [21] Wang, S. et al.: A Deep-Learning-Based Sea Search and Rescue Algorithm by UAV Remote Sensing. IEEE CSAA Guidance, Navigation and Control Conference (CGNCC), IEEE, 2018, 1-5.
• [22] Wu W. et al.: Coupling Deep Learning and UAV for Infrastructure Condition Assessment Automation. IEEE International Smart Cities Conference (ISC2), IEEE, 2018, 1-7.
• [23] Yin D. et al.: Mask R-CNN for Object Detection and Segmentation: A Comprehensive Review. Journal of Visual Communication and Image Representation 80, 2021, 103278.