Architectural design methods based on image recognition technology and virtual VR

• Autorzy: Li Feng

Identyfikatory

DOI

10.24425/ace.2025.154126

• Języki publikacji: EN

Abstrakty

EN

To enhance the conceptual expression of architectural design and enhance the interactive experience, and to strengthen the application of computer technology in architectural design drawings, this study explores architectural design methods on the ground of image deep learning image recognition technology and augmented reality technology. The experiment demonstrated that when the accuracy of the improved You Only Look Once version 4 (YOLOv4) model was 0.9, the recall rate was 0.98, and the curve area was 0.93. The model loss function curve converged to the minimum value of 0.04, with the fastest convergence speed and the highest model recognition efficiency. Its time consumption was decreased by as much as 70.06%, indicating better overall performance. Meanwhile, the clustering strategy design of the model was relatively optimal, with the highest values of purity, standard mutual information, and Rand coefficient reaching 0.944, 0.931, and 0.942, respectively. In practical analysis of architectural design, the average accuracy and intersection over union of the improved YOLOv4 model confirmed the good detection performance of this method. The application of virtual reality technology in building information models has significantly improved the visualization delay rate, and the subjective evaluation of users was relatively high. The combination of visible image recognition and augmented reality can achieve intelligent processing and application of drawing information, improve design efficiency and quality, and optimize design experience.

• Wydawca: Komitet Inżynierii Lądowej i Wodnej PAN ; Politechnika Warszawska, Wydział Inżynierii Lądowej
• Czasopismo: Archives of Civil Engineering
• Rocznik: 2025
• Tom: Vol. 71, nr 2
• Strony: 363--376
• Opis fizyczny: Bibliogr. 22 poz., il., tab.

Twórcy

autor

Li Feng

• Shanxi Vocational University of Engineering Science and Technology, College of Architecture and Design, Jinzhong, China

• https://orcid.org/0009-0008-7784-4566

Bibliografia

• [1] P.P.W. Aung, W. Choi, A.S. Kulinan, G. Cha, and S. Park, “Three-dimensional engine-based geometric model optimization algorithm for BIM visualization with augmented reality”, Sensors, vol. 22, no. 19, pp. 7622-7634, 2022, doi: 10.3390/s22197622.
• [2] Y.Y. Al-Ashmori, I. Othman, Y. Rahmawati, Y.H. Mugahed Amran, S.H. Abo Sabah, A. D. Rafindadi, and M. Mikic, “BIM benefits and its influence on the BIM implementation in Malaysia”, Ain Shams Engineering Journal, vol. 11, no. 4, pp. 1013-1019, 2020, doi: 10.1016/j.asej.2020.02.002.
• [3] A.M. Usman and M.K.Abdullah, “An assessment of building energy consumption characteristics using analytical energy and carbon footprint assessment model”, Green and Low-Carbon Economy, vol. 1, no. 1, pp. 28-40, 2023, doi: 10.47852/bonviewGLCE3202545.
• [4] Z. Zhuang, “Optimization of building model based on 5G virtual reality technology in computer vision software”, Mathematical Biosciences and Engineering, vol. 18. no. 6, pp. 7936-7954, 2021, doi: 10.3934/mbe.2021393.
• [5] M. Masana, X. Liu, B. Twardowski, M. Menta, A.D. Bagdanov, and D.W.J. Van, “Class-incremental learning: survey and performance evaluation on image classification”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 5, pp. 5513-5533, 2022, doi: 10.1109/TPAMI.2022.3213473.
• [6] J.F. Fernández Rodríguez, “Implementation of BIM virtual models in industry for the graphical coordination of engineering and architecture projects”, Buildings, vol. 13, no. 3, pp. 743-765, 2023, doi: 10.3390/buildings13030743.
• [7] M. Sherif, K. Nassar, O. Hosny, S. Safar, and I. Abotaleb, “Automated BIM-based structural design and cost optimization model for reinforced concrete buildings”, Scientific Reports, vol. 12, no. 1, pp. 21616-21627, 2022, doi: 10.1038/s41598-022-26146-6.
• [8] S. Wu, N. Zhang, Y. Xiang, D. Wu, D. Qiao, X. Luo, and W.Z. Lu, “Automated layout design approach of floor tiles: based on building information modeling (BIM) via parametric design (PD) platform”, Buildings, vol. 12, no. 2, pp. 250-272, 2022, doi: 10.3390/buildings12020250.
• [9] V. Croce, G. Caroti, A. Piemonte, L. De Luca, and P. Véron, “H-BIM and artificial intelligence: classification of architectural heritage for semi-automatic scan-to-BIM reconstruction”, Sensors, vol. 23, no. 5, pp. 2497-2536, 2023, doi: 10.3390/s23052497.
• [10] M. Urbieta, M. Urbieta, T. Laborde, G. Villarreal, and G. Rossi, “Generating BIM model from structural and architectural plans using artificial intelligence”, Journal of Building Engineering, vol. 78, no. 17, pp. 107672-107701, 2023, doi: 10.1016/j.jobe.2023.107672.
• [11] G.J. Kim, H. Gu, H. Park, and S.Y. Choo, “Development of spatial adjacency graph extraction algorithm for improving pre-design efficiency in architectural design process”, Journal of the Architectural Institute of Korea, vol. 38, no. 1, pp. 67-74, 2022, doi: 10.5659/JAIK.2022.38.1.67.
• [12] Y. Gulzar, “Fruit image classification model based on MobileNetV2 with deep transfer learning technique”, Sustainability, vol. 15, no. 3, pp. 1906-1919, 2023, doi: 10.3390/su15031906.
• [13] G. Chen, Q. Chen, S. Long, W. Zhu, Z. Yuan, and Y. Wu, “Quantum convolutional neural network for image classification”, Pattern Analysis and Applications, vol. 26, no. 2, pp. 655-667, 2023, doi: 10.1007/s10044-022-01113-z.
• [14] W. Liang, Y. Liang, and J. Jia, “MiAMix: enhancing image classification through a multi-stage augmented mixed sample data augmentation method”, Processes, vol. 11, no. 12, pp. 3284-3302, 2023, doi: 10.3390/pr11123284.
• [15] R. Yu, N. Gu, G. Lee, and A. Khan, “A systematic review of architectural design collaboration in immersive virtual environments”, Designs, vol. 6, no. 5, pp. 93-115, 2022, doi: 10.3390/designs6050093.
• [16] B. Yang, T. Fang, X. Luo, B. Liu, and M. Dong, “A bim-based approach to automated prefabricated building construction site layout planning”, KSCE Journal of Civil Engineering, vol. 26, no. 4, pp. 1535-1552, 2022, doi: 10.1007/s12205-021-0746-x.
• [17] S. S. Pibal, K. Khoss, and I. Kovacic, “Framework of an algorithm-aided BIM approach for modular residential building information models”, International Journal of Architectural Computing, vol. 20, no. 4, pp. 777-800, 2022, doi: 10.1177/14780771221138320.
• [18] L. Zarantonello and B.H. Schmitt, “Experiential AR/VR: a consumer and service framework and research agenda”, Journal of Service Management, vol. 34, no. 1, pp. 34-55, 2023, doi: 10.1108/josm-12-2021-0479.
• [19] V.S. Chan, H.N.H. Haron, M.I.B.M. Isham, and F.B. Mohamed, “VR and AR virtual welding for psychomotor skills: a systematic review”, Multimedia Tools and Applications, vol. 81, no. 9, pp. 12459-12493, 2022, doi: 10.1007/s11042-022-12293-5.
• [20] R. Gai, N. Chen, and H. Yuan, “A detection algorithm for cherry fruits based on the improved YOLO-v4 model”, Neural Computing and Applications, vol. 35, no. 19, pp. 13895-13906, 2023, doi: 10.1007/s00521-021-06029-z.
• [21] C. Dewi, R.C. Chen, X. Jiang, and H. Yu, “Deep convolutional neural network for enhancing traffic sign recognition developed on Yolo V4”, Multimedia Tools and Applications, vol. 81, no. 26, pp. 37821-37845, 2022, doi: 10.1007/s11042-022-12962-5.
• [22] M. Goncikowski, “Research by design: architectural and structural solutions allowing the integration of the skyscraper complex with the urban space in Warsaw”, Archives of Civil Engineering, vol. 4, no. 4, pp. 21-36, 2023, doi: 10.24425/ace.2023.147645.