Residential and Commercial Building Classification Based on Street-Level Images Using Deep Learning
DOI:
https://doi.org/10.57152/malcom.v6i3.2676Keywords:
Building Classification , CNN , Computer Vision, Google Street Images, MobileNetV2Abstract
The classification of buildings into residential and commercial categories is essential for computer vision applications that support urban analysis and automated decision-making. Accurate identification of building functions from visual data enables downstream applications, such as service differentiation and resource allocation. However, manual image-based classification is inefficient and subjective, particularly when applied to large-scale datasets. This study proposes a deep learning approach to classifying residential and commercial buildings using street-level images. A dataset comprising 882 images was collected from publicly available sources and categorized based on visual characteristics. The dataset was divided into training, validation, and test sets in a 60:20:20 ratio. The preprocessing stages included data cleaning, labeling, cropping, and resizing. Two models were evaluated: a conventional Convolutional Neural Network (CNN) and MobileNetV2 with transfer learning. Model performance was optimized by tuning the batch size and learning rate. The experimental results show that MobileNetV2 achieved the best performance with a batch size of 32 and a learning rate of 0.0001, attaining an accuracy of 92.05% and precision, recall, and F1-score values of 91.46%. Evaluation using a confusion matrix indicated low misclassification rates both building categories. These results demonstrate that deep learning models can effectively classify buildings based on visual data.
Downloads
References
A. Ziaee and G. Suter, “Benchmarking methods for classifying space functions and access elements in multi-unit apartment buildings,” Autom. Constr., vol. 176, 2025, doi: 10.1016/j.autcon.2025.106237.
N. Lazar and K. Chithra, “Benchmarking critical criteria for assessing sustainability of residential buildings in tropical climate,” Journal of Building Engineering, vol. 45, 2022, doi: 10.1016/j.jobe.2021.103467.
L. Dahlström, F. Johari, and J. Widén, “Regional building energy modelling: A residential building stock model for a Swedish island,” Energy Build., vol. 346, 2025, doi: 10.1016/j.enbuild.2025.116178.
D. Sadhukhan et al., “Estimating surface temperature from thermal imagery of buildings for accurate thermal transmittance (U-value): A machine learning perspective,” Journal of Building Engineering, vol. 32, 2020, doi: 10.1016/j.jobe.2020.101637.
P. Helber, B. Bischke, A. Dengel, and D. Borth, “Introducing eurosat: A novel dataset and deep learning benchmark for land use and land cover classification,” in International Geoscience and Remote Sensing Symposium (IGARSS), Institute of Electrical and Electronics Engineers Inc., 2018, pp. 204–207. doi: 10.1109/IGARSS.2018.8519248.
Y. Yuan, X. Shi, and J. Gao, “Building extraction from remote sensing images with deep learning: A survey on vision techniques,” Computer Vision and Image Understanding, vol. 251, 2025, doi: 10.1016/j.cviu.2024.104253.
T. K. Soni and P. Pujari, “Emerging deep learning approaches for urban satellite image analysis: a survey on classification, segmentation, and change detection,” Evol. Intell., vol. 18, no. 5, 2025, doi: 10.1007/s12065-025-01090-2.
K. Chen, Z. Zou, and Z. Shi, “Building extraction from remote sensing images with sparse token transformers,” Remote Sens. (Basel)., vol. 13, no. 21, 2021, doi: 10.3390/rs13214441.
B. Sariturk, D. Z. Seker, O. Ozturk, and B. Bayram, “Performance evaluation of shallow and deep CNN architectures on building segmentation from high-resolution images,” Earth Sci. Inform., vol. 15, no. 3, pp. 1801–1823, 2022, doi: 10.1007/s12145-022-00840-5.
S. T. Seydi, H. Rastiveis, B. Kalantar, A. A. Halin, and N. Ueda, “BDD-Net: An End-to-End Multiscale Residual CNN for Earthquake-Induced Building Damage Detection,” Remote Sens. (Basel)., vol. 14, no. 9, 2022, doi: 10.3390/rs14092214.
H. Xu, Q. Huang, H. Liao, G. Nong, and W. Wei, “MFFP-Net: Building Segmentation in Remote Sensing Images via Multi-Scale Feature Fusion and Foreground Perception Enhancement,” Remote Sens. (Basel)., vol. 17, no. 11, 2025, doi: 10.3390/rs17111875.
K. Diao, J. Zhu, G. Liu, and M. Li, “MDTrans: Multi-scale and dual-branch feature fusion network based on Swin Transformer for building extraction in remote sensing images,” IET Image Process., vol. 18, no. 11, pp. 2930–2942, 2024, doi: 10.1049/ipr2.13145.
Q. Yuan, H. Z. Mohd Shafri, A. H. Alias, and S. J. Bin Hashim, “Multiscale semantic feature optimization and fusion network for building extraction using high-resolution aerial images and lidar data,” Remote Sens. (Basel)., vol. 13, no. 13, 2021, doi: 10.3390/rs13132473.
Q. Yuan and B. Xia, “Cross-level and multiscale CNN-Transformer network for automatic building extraction from remote sensing imagery,” Int. J. Remote Sens., vol. 45, no. 9, pp. 2893–2914, 2024, doi: 10.1080/01431161.2024.2339199.
J. Herman, R. Zewail, T. Ogawa, and S. Elsagheer, “A Lightweight Transfer Learning-Based Model for Building Classification in Aerial Imagery,” in 2023 15th International Conference on Computer Research and Development, ICCRD 2023, Institute of Electrical and Electronics Engineers Inc., 2023, pp. 181–186. doi: 10.1109/ICCRD56364.2023.10080643.
D. S. Adams, T. Hauser, H. L. Yang, and P. Li, “Multivariate Testing of Sampling Techniques to Address Class Imbalance in Building Use Type Classification,” in GeoAI 2024 - Proceedings of the 7th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, S. Gao, G. Mai, S. Newsam, L. Yang, D. Lunga, D. Zhu, B. Martins, and S. Arundel, Eds., Association for Computing Machinery, Inc, 2024, pp. 15–26. doi: 10.1145/3687123.3698282.
A. Karkehabadi and S. Sadeghmalakabadi, “Evaluating Deep Learning Models for Architectural Image Classification: A Case Study on the UC Davis Campus,” in 2024 IEEE 8th International Conference on Information and Communication Technology, CICT 2024, Institute of Electrical and Electronics Engineers Inc., 2024. doi: 10.1109/CICT64037.2024.10899686.
O. M. Mogaka, R. Zewail, K. Inoue, and M. S. Sayed, “TinyEmergencyNet: a hardware-friendly ultra-lightweight deep learning model for aerial scene image classification,” J. Real. Time. Image Process., vol. 21, no. 2, 2024, doi: 10.1007/s11554-024-01430-y.
M. Yang, “Efficiency and Adaptability of Deep Learning Architectures: A Performance Comparison of CNN, Transformer, and Hybrid Models,” in 2025 5th International Conference on Computer Vision, Application and Algorithm, CVAA 2025, Institute of Electrical and Electronics Engineers Inc., 2025, pp. 1–4. doi: 10.1109/CVAA66438.2025.11193320.
S. P. Ramalingam and V. Kumar, “Building usage prediction in complex urban scenes by fusing text and facade features from street view images using deep learning,” Build. Environ., vol. 267, 2025, doi: 10.1016/j.buildenv.2024.112174.
S. Wang, “Development of approach to an automated acquisition of static street view images using transformer architecture for analysis of Building characteristics,” Sci. Rep., vol. 15, no. 1, 2025, doi: 10.1038/s41598-025-14786-3.
U. Kumar Lilhore et al., “A precise model for skin cancer diagnosis using hybrid U-Net and improved MobileNet-V3 with hyperparameters optimization,” Sci. Rep., vol. 14, no. 1, p. 4299, 2024, doi: 10.1038/s41598-024-54212-8.
D. Yang, X. Gao, Y. Yang, K. Guo, K. Han, and L. Xu, “Advances and Future Prospects in Building Extraction From High-Resolution Remote Sensing Images,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 18, pp. 6994–7016, 2025, doi: 10.1109/JSTARS.2025.3538662.
A. Shoaib, M. Vadiveloo, and S. P. Lim, “Performance Comparison of Convolutional Neural Network Deep Learning Architectures for Remote Sensing Image Segmentation,” in Lecture Notes in Electrical Engineering, V. Thiruchelvam, R. Alfred, I. Z.I.B.A., H. Haviluddin, and A. Baharum, Eds., Springer Science and Business Media Deutschland GmbH, 2024, pp. 199–211. doi: 10.1007/978-981-97-2977-7_12.
B. Kalantar, S. S. Ojogbane, S. T. Seydi, A. A. Halin, S. Mansor, and N. Ueda, “A Deep Learning Approach for Automated Building Outlines Extraction in Compact Urban Environments,” in International Geoscience and Remote Sensing Symposium (IGARSS), Institute of Electrical and Electronics Engineers Inc., 2022, pp. 7491–7494. doi: 10.1109/IGARSS46834.2022.9884697.
T. D. Akinosho et al., “Deep learning in the construction industry: A review of present status and future innovations,” Journal of Building Engineering, vol. 32, 2020, doi: 10.1016/j.jobe.2020.101827.
Y. Li, J. Lu, Y. Meng, Y. Luo, and J. Ren, “Exploring Urban Spatial Quality Through Street View Imagery and Human Perception Analysis,” Buildings, vol. 15, no. 17, p. 3116, Aug. 2025, doi: 10.3390/buildings15173116.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Najmi Fadhila Atsari, Tisha Melia, Aland Polma Naek Sihombing, Fatayat Fatayat
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Copyright © by Author; Published by Institut Riset dan Publikasi Indonesia (IRPI)
This Indonesian Journal of Machine Learning and Computer Science is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
