The utilization of deep learning for form analysis facilitates the classification of an extensive number of forms based on their morphological features. A critical consideration for implementing such analysis methods in architectural or urban forms is whether building orientation should be embedded within the data. Orientation functions as a form variable significantly influenced by environmental, social, and cultural contexts within a city. In contrast to other domains where forms are extrapolated in relation to their context, in the city, domain orientation uniquely characterizes building form. In this paper, we introduce a pipeline for constructing an extensive building form dataset and scrutinizing the morphological identity of building forms, with a particular focus on the implications of building orientation as a manifestation of urban locality. Through a case study situated in Montreal, we engage in a comparative analysis employing two distinct datasets—those with orientation-embedded forms and those with orientation-normalized forms. Our research aims to investigate the typo-morphological characteristics of the building forms of the city and to examine how building orientation contributes to the identification of these traits and mirrors urban locality.
BiljeckiFLedouxHStoterJ (2016) An improved LOD specification for 3D building models. Computers, Environment and Urban Systems59: 25–37. DOI: 10.1016/j.compenvurbsys.2016.04.005.
2.
BoeingG (2017) OSMnx: new methods for acquiring, constructing, analyzing, and visualizing complex street networks. Computers, Environment and Urban Systems65: 126–139. DOI: 10.1016/j.compenvurbsys.2017.05.004.
3.
BooksteinFL (1992) Morphometric Tools for Landmark Data: Geometry and Biology. Cambridge: Cambridge University Press. DOI: 10.1017/CBO9780511573064.
4.
CaiCGuoZZhangB, et al. (2021) Urban morphological feature extraction and multi-dimensional similarity analysis based on deep learning approaches. Sustainability13(12): 6859. DOI: 10.3390/su13126859.
DinsdaleNKSmithSMAryaZ, et al. (2021) Learning Patterns of the Ageing Brain in MRI Using Deep Convolutional Networks. NeuroImage224: 117401. DOI: 10.1016/j.neuroimage.2020.117401.
10.
Escamilla-RiveraCAlejandra Carvajal QuinteroMCapozzielloS (2020) A deep learning approach to cosmological dark energy models. Journal of Cosmology and Astroparticle Physics2020(03). DOI: 10.1088/1475-7516/2020/03/008.
11.
EsterMKriegelHPSanderJ, et al. (1996) A density-based algorithm for discovering clusters in large spatial databases with noise. Proceedings of the Second International Conference on Knowledge Discovery and Data Mining (KDD-96) -Portland, OR, USA. August2-4, 1996: 226-232.
12.
FleischmannMFeliciottiAKerrW (2021) Evolution of urban patterns: urban morphology as an open reproducible data science. Geographical Analysis54(3): 536–558. DOI: 10.1111/gean.12302.
KleinebergMFeyMFrankW (2020) Adversarial generation of continuous implicit shape representations.” In The Eurographics Association. May25-29: 2020. doi: 10.2312/egs.20201013
20.
LarsenLindboABSorenKSLarochelleH, et al. (2016) Autoencoding beyond pixels using a learned similarity metric. Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume. New York, NY, USA. June19-24, 2016: 1558–1566.
MaatenLvan derHintonG (2008) Viualizing data using T-SNE. Journal of Machine Learning Research9: 2579–2605.
23.
MarcusLF (1990) Traditional morphometrics. Proceedings of the Michigan Morphometric Workshop: Ann Arbor MI: The University of Michigan Museum of Zoology: Rohlf and F. L. Bookstein: 77–122.
MiguelJdeEugenia VillafañeMPiškorecL, et al. (2019) Deep form finding: using variational autoencoders for deep form FInding of structural typologies. Architecture in the Age of the 4th Industrial Revolution: Porto, Portugal: University of Porto: 71–80. https://papers.cumincad.org/data/works/att/ecaadesigradi2019_514.pdf
26.
MoosaviV (2017) Urban morphology meets deep learning: exploring urban forms in one million cities, town and villages across the planet. arXiv:1709.02939 [Cs]. https://arxiv.org/abs/1709.02939
27.
NewtonD (2019) Generative deep learning in architectural design. Technology Architecture Design3(2): 176–189. DOI: 10.1080/24751448.2019.1640536
28.
OstwaldMVaughanJ (2012) Significant Lines: Representing Architecture for Computational Analysis. Proceedings of the 45th Annual Conference of the Australian and New Zealand Architectural Science Association. November 14-16,2012. Gold Coast, Australia.
29.
ParkJJFlorencePStraubJ, et al. (2019) DeepSDF: learning continuous signed distance functions for shape representation. CVPR 2019. https://arxiv.org/abs/1901.05103
30.
QuanSJ (2022) Urban-GAN: an artificial intelligence-aided computation system for plural urban design. Environment and Planning B: Urban Analytics and City Science49(9): 2500–2515. DOI: 10.1177/23998083221100550.
31.
RebsamenMSuterYRolandW, et al. (2020) Brain morphometry estimation: from hours to Seconds using deep learning. Frontiers in Neurology11: 244. DOI: 10.3389/fneur.2020.00244.
32.
RenYZhengH (2020) “The Spire of AI - voxel-based 3D neural style transfer.” In Reinwardtia: Anthropocene, Design in the Age of Humans - Proceedings of the 25th CAADRIA Conference, Bangkok, Thailand. Chulalongkorn University. https://papers.cumincad.org/cgi-bin/works/paper/caadria2020_091
33.
RheeJCardoso LlachDKrishnamurtiR (2019) Context-rich urban analysis using machine learning - a case study in Pittsburgh In Architecture in the Age of the 4th Industrial Revolution, Porto, Portugal: University of Porto. https://papers.cumincad.org/cgi-bin/works/paper/ecaadesigradi2019_550
34.
SchirmerPKayA (2015) A multiscale classi;cation of urban morphology. Journal of Transport and Land Use9. DOI: 10.5198/jtlu.2015.667.
SteadmanPBruhnsHHoltierS, et al. (2000) A classification of built forms. Environment and Planning B: Planning and Design27: 73–91. DOI: 10.1068/bst7.
38.
Urban Analytics Lab, National University of Singapore. (2019) “3D City Model of Singapore Public Housing Buildings.”https://github.com/ualsg/hdb3d-data
39.
WebsterMDavid SheetsH (2010) A practical introduction to landmark-based geometric morphometrics. Quant Meth Paleobiol16: 163–188.
40.
WuJZhangCXueT, et al. (2016) Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling. Red Hook, NY, USA: Curran Associates Inc.
41.
YaoJ (2021) Generative design method of building group - based on generative adversarial network and genetic algorithm. In: GlobaAvan AmeijdeJFingrutA, et al. (eds) PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 1, the Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021. 61–70. https://papers.cumincad.org/cgi-bin/works/paper/caadria2021_156
42.
ZhangFTianSChenS, et al. (2019) Voxel-based morphometry: improving the diagnosis of Alzheimer’s disease based on an extreme learning machine method from the ADNI cohort. Neuroscience414: 273–279. DOI: 10.1016/j.neuroscience.2019.05.014.
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
