Automatic Building Height Estimation: Machine Learning Models for Urban Image Analysis
Source abstract
Abstract
Artificial intelligence (AI) is delivering major advances in the construction engineering sector in this era of building information modelling, applying data collection techniques based on urban image analysis. In this study, building heights were calculated from street-view imagery based on a semantic segmentation machine learning model. The model has a fully convolutional architecture and is based on the HRNet encoder and ResNexts depth separable convolutions, achieving fast runtime and state-of-the-art results on standard semantic segmentation tasks. Average building heights on a pilot German street were satisfactorily estimated with a maximum error of 3 m. Further research alternatives are discussed, as well as the difficulties of obtaining valuable training data to apply these models in countries with no training datasets and different urban conditions. This line of research contributes to the characterisation of buildings and the estimation of attributes essential for the assessment of seismic risk using automatically processed street-view imagery.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Infrastructure Maintenance and Monitoring · Remote Sensing and LiDAR Applications · Remote-Sensing Image Classification
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Land Morphology and Engineering, Civil Engineering School, Universidad Politécnica de Madrid, 28040 Madrid, Spain
Department of Environmental and Forestry Engineering and Management, Civil Engineering School, Universidad Politécnica de Madrid, 28040 Madrid, Spain
Funding
Comunidad de Madrid
References (47)
Show source-provided references
1. European Construction Sector Observatory (2021). Digitalisation in the Construction Sector, Publications Office of the European Union. Technical Report.
2. Baldini, G., Barboni, M., Bono, F., Delipetrev, B., Duch Brown, N., Fernandez Macias, E., Gkoumas, K., Joossens, E., Kalpaka, A., and Nepelski, D. (2019). Digital Transformation in Transport, Construction, Energy, Government and Public Administration, Publications Office of the European Union.
3. Baggio, C., Bernardini, A., Colozza, R., Pinto, A.V., and Taucer, F. (2007). Field Manual for Post-Earthquake Damage and Safety Assessment and Short Term Countermeasures (AeDES) Translation from Italian: Maria ROTA and Agostino GORETTI, Publications European Commission JRC. Technical Report.
4. Brzev, S., Scawthorn, C., Charleson, A., Allen, L., Greene, M., Jaiswal, K., and Silva, V. (2013). GEM Global Earthquake Model GEM Building Taxonomy Version 2.0 Exposure Modelling, GEM Foundation. Technical Report.
5. Machine-learning based vulnerability analysis of existing buildings10.1016/j.autcon.2021.103936 ↗
6. Cardellicchio, A., Ruggieri, S., Leggieri, V., and Uva, G. (2022). View VULMA: Data Set for Training a Machine-Learning Tool for a Fast Vulnerability Analysis of Existing Buildings. Data, 7.10.3390/data7010004 ↗
7. Remote structural characterization of thousands of buildings from San Jose, Costa Rica10.3389/fbuil.2022.947329 ↗
8. Rodríguez-Saiz, J., Marchamalo, M., Esquivel, L., Rejas-Ayuga, J., García-Lanchares, C., González-Rodrigo, B., and Benito, B. (July, January 28). Exposición sísmica de los edificios por métodos geoespaciales. Proceedings of the XIV Congreso Geológico de América Central & VII Congreso Geológico Nacional, San José, Costa Rica.
9. A new evaluation of seismic hazard for the Central America Region10.1785/0120110015 ↗
10. A machine learning framework to estimate a simple seismic vulnerability index from a photograph: The VULMA project10.1016/j.prostr.2023.01.250 ↗
11. (2013). INSPIRE Infrastructure for Spatial Information in Europe D2.8.III.2 Data Specification on Buildings-Technical Guidelines Title D2.8.III.2 INSPIRE Data Specification on Buildings-Technical Guidelines, European Commission Joint Research Centre. Technical Report.
12. Sentinel-2: ESA’s Optical High-Resolution Mission for GMES Operational Services10.1016/j.rse.2011.11.026 ↗
13. National-scale mapping of building height using Sentinel-1 and Sentinel-2 time series10.1016/j.rse.2020.112128 ↗
14. A deep learning method for building height estimation using high-resolution multi-view imagery over urban areas: A case study of 42 Chinese cities10.1016/j.rse.2021.112590 ↗
15. Building extraction from oblique airborne imagery based on robust façade detection10.1016/j.isprsjprs.2011.12.006 ↗
16. Large-scale parameterization of 3D building morphology in complex urban landscapes using aerial LiDAR and city administrative data10.1016/j.compenvurbsys.2018.09.004 ↗
17. Ala, B. (2020). An Open-Source System for Building-Height Estimation Using Street-View Images, Deep Learning, and Building Footprints Reports on Special Business Projects, Statistics Canada. Technical Report.
18. Zhao, Y., Qi, J., and Zhang, R. (2019, January 13–17). CBHE: Corner-based building height estimation for complex street scene images. Proceedings of the Web Conference 2019—World Wide Web Conference (WWW 2019), San Francisco, CA, USA.10.1145/3308558.3313394 ↗
19. Estimation of building height using a single street view image via deep neural networks10.1016/j.isprsjprs.2022.08.006 ↗
20. Díaz, E., and Arguello, H. (2016, January 19). An algorithm to estimate building heights from Google street-view imagery using single view metrology across a representational state transfer system. Proceedings of the Dimensional Optical Metrology and Inspection for Practical Applications V SPIE, Baltimore, MD, USA.10.1117/12.2224312 ↗
21. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2021, January 5). An Image is Worth 16 × 16 Words: Transformers for Image Recognition at Scale. Proceedings of the International Conference on Learning Representations ICLR, Online. Available online: https://iclr.cc/virtual/2021/session/4343.
22. Strudel, R., Garcia, R., Laptev, I., and Schmid, C. (2021). Segmenter: Transformer for Semantic Segmentation. arXiv.10.1109/ICCV48922.2021.00717 ↗
23. Xie, S., Girshick, R., Dollár, P., Tu, Z., and He, K. (2016). Aggregated Residual Transformations for Deep Neural Networks. arXiv.10.1109/CVPR.2017.634 ↗
24. Hitawala, S. (2018). Evaluating ResNeXt Model Architecture for Image Classification. arXiv.
25. Wang, J., Sun, K., Cheng, T., Jiang, B., Deng, C., Zhao, Y., Liu, D., Mu, Y., Tan, M., and Wang, X. (2019). Deep High-Resolution Representation Learning for Visual Recognition. arXiv.
26. Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., and Schiele, B. (2016). The Cityscapes Dataset for Semantic Urban Scene Understanding. arXiv.10.1109/CVPR.2016.350 ↗
27. Neuhold, G., Ollmann, T., Rotabuì, S., Kontschieder, P., and Research, M. (2017, January 22–29). The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy. Technical Report.10.1109/ICCV.2017.534 ↗
28. Chollet, F. (2016). Xception: Deep Learning with Depthwise Separable Convolutions. arXiv.10.1109/CVPR.2017.195 ↗
29. Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., and Yuille, A.L. (2016). DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. arXiv.
30. O’Shea, K., and Nash, R. (2015). An Introduction to Convolutional Neural Networks. arXiv.
31. Janocha, K., and Czarnecki, W.M. (2017). On Loss Functions for Deep Neural Networks in Classification. arXiv.10.4467/20838476SI.16.004.6185 ↗
32. Bridle, J.S. (1989, January 1). Training Stochastic Model Recognition Algorithms as Networks Can Lead to Maximum Mutual Information Estimation of Parameters. Proceedings of the 2nd International Conference on Neural Information Processing Systems, Cambridge, MA, USA.
33. Ruder, S. (2016). An overview of gradient descent optimization algorithms. arXiv.
34. Kingma, D.P., and Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv.
35. Lorente, O., Riera, I., and Rana, A. (2021). Image Classification with Classic and Deep Learning Techniques. arXiv.
36. Recent progress in semantic image segmentation10.1007/s10462-018-9641-3 ↗
37. Buslaev, A., Iglovikov, V.I., Khvedchenya, E., Parinov, A., Druzhinin, M., and Kalinin, A.A. (2020). Albumentations: Fast and flexible image augmentations. Information, 11.10.3390/info11020125 ↗
38. Huang, G., Liu, Z., van der Maaten, L., and Weinberger, K.Q. (2016). Densely Connected Convolutional Networks. arXiv.10.1109/CVPR.2017.243 ↗
39. Bezanson, J., Edelman, A., Karpinski, S., and Shah, V.B. (2014). Julia: A Fresh Approach to Numerical Computing. arXiv.
40. Innes, M., Edelman, A., Fischer, K., Rackauckas, C., Saba, E., Shah, V.B., and Tebbutt, W. (2019). A Differentiable Programming System to Bridge Machine Learning and Scientific Computing. arXiv.
41. Innes, M., Saba, E., Fischer, K., Gandhi, D., Rudilosso, M.C., Joy, N.M., Karmali, T., Pal, A., and Shah, V. (2018). Fashionable Modelling with Flux. arXiv.
42. Zhang, Z., and Sabuncu, M.R. (2018). Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels. arXiv.
43. Glorot, X., and Bengio, Y. (2010, January 13–15). Understanding the Difficulty of Training Deep Feedforward Neural Networks. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, Montreal, QC, Canada.
44. Li, Z., Wang, X., Liu, X., and Jiang, J. (2022). BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation; Technical Report. arXiv.
45. Instant neural graphics primitives with a multiresolution hash encoding
46. Richter, S.R., Vineet, V., Roth, S., and Koltun, V. (2016). Playing for Data: Ground Truth from Computer Games. arXiv.10.1007/978-3-319-46475-6_7 ↗
47. FEMA (2001). Hazus-MH 2.1. Technical Manual, Publications FEMA.