Cumincad : CUMINCAD Papers : Search Results

CumInCAD is a Cumulative Index about publications in Computer Aided Architectural Design
supported by the sibling associations ACADIA, CAADRIA, eCAADe, SIGraDi, ASCAAD and CAAD futures

PDF papers
References

Hits 1 to 20 of 251

Reformat results as: short short into frame detailed detailed into frame

_id	cf2019_041
id	cf2019_041
authors	Erhan, Halil; Barbara Berry, John Dill and Akanksha Garg
year	2019
title	Investigating the Role of Students’ Representation Use Patterns in Spatial Thinking
source	Ji-Hyun Lee (Eds.) "Hello, Culture!" [18th International Conference, CAAD Futures 2019, Proceedings / ISBN 978-89-89453-05-5] Daejeon, Korea, pp. 331-346
summary	Teaching spatial thinking explicitly helps students develop spatial abilities. In this paper, we present our initial findings from an experiment that explored how first year students who successfully completed an introductory spatial thinking course, demonstrated their use of three design representations: sketching, digital and physical modeling. Students were asked to solve a design problem requiring spatial thinking at the same level of complexity as their course project. Video data from twelve participants were analyzed and results from an independent expert panel review of students’ solutions, and use of representations were compiled. Our results show high variability in both the quality of students’ solutions and their use of the three modes of representation. We discovered many students used embodied actions in solving the spatial problem and explaining solutions. These results will inform a revision of our course and curriculum supporting spatial thinking in undergraduate design students.
keywords	spatial thinking, design pedagogy, design representations
series	CAAD Futures
email
last changed	2019/07/29 14:15

_id	ijac201917303
id	ijac201917303
authors	Heidari, Parvin and Cigdem Polatoglu
year	2019
title	Pen-and-paper versus digital sketching in architectural design education
source	International Journal of Architectural Computing vol. 17 - no. 3, 284–302
summary	This study aimed to compare and evaluate the digital-based sketching versus conventional pen-and-paper sketching through conducting an experiment via protocol study in educational field. To this aim, the linkography analysis technique was used to obatin the related data from the protocol study. Linkography technique allows analyzing design as a system and is capable of tracing the design ideas and their connections; therefore, it facilitated the purposes of the current study. The results demonstrated that designers had a richer design process and more opportunities for generating ideas in the pen-and-paper sketching versus digital sketching. Furthermore, the designers’ performance in the digital media with two-dimensional sketching software was more satisfactory than the digital session with three-dimensional sketching software. However, digital media encouraged designers to make more integration among the ideas.
keywords	Conceptual design, pen-and-paper sketching, digital sketching, linkography
series	journal
email
last changed	2020/11/02 13:34

_id	ecaadesigradi2019_561
id	ecaadesigradi2019_561
authors	Cress, Kevan and Beesley, Philip
year	2019
title	Architectural Design in Open-Source Software - Developing MeasureIt-ARCH, an Open Source tool to create Dimensioned and Annotated Architectural drawings within the Blender 3D creation suite.
doi	https://doi.org/10.52842/conf.ecaade.2019.1.621
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 1, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 621-630
summary	MeasureIt-ARCH is A GNU GPL licensed, dimension, annotation, and drawing tool for use in the open source software Blender. By providing free and open tools for the reading and editing of architectural drawings, MeasurIt-ARCH allows works of architecture to be shared, read, and modified by anyone. The digitization of architectural practice over the last 3 decades has brought with it a new set of inter-disciplinary discourses for the profession. An attempt to utilise 'Open-Source' methodologies, co-opted from the world of software development, in order to make high quality design more affordable, participatory and responsible has emerged. The most prominent of these discussions are embodied in Carlo Raitti and Mathew Claudel's manifesto 'Open-Source Architecture' (Ratti 2015) and affordable housing initiatives like the Wikihouse project (Parvin 2016). MeasurIt-ARCH aims to be the first step towards creating a completely Open-Source design pipeline, by augmenting Blender to a level where it can be used produce small scale architectural works without the need for any proprietary software, serving as an exploratory critique on the user experience and implementations of industry standard dimensioning tools that exist on the market today.
keywords	Blender; Open-Source; Computer Aided Design ; OSArc
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:56

_id	cf2019_006
id	cf2019_006
authors	Di Mascio, Danilo
year	2019
title	Visualizing Mackintosh’s alternative design proposal for Scotland Street School
source	Ji-Hyun Lee (Eds.) "Hello, Culture!" [18th International Conference, CAAD Futures 2019, Proceedings / ISBN 978-89-89453-05-5] Daejeon, Korea, p. 25
summary	This paper describes the process of creation of a set of visualizations (elevations, perspective views and a short animation) of C.R. Mackintosh’s original but unrealized first design proposal for Scotland Street School (dated January 1904). Moreover, the piece of writing reflects upon some key aspects of the project such as how architectural historians were involved and how ambiguities due to the discrepancies between the drawings and missing details were resolved by studying multiple drawings and transferring clues from other Mackintosh’s built works. The contributions of this research are important for several reasons: it proposes a methodology that can be applied to similar research projects; it explains the educational value of the development work, which can be defined as digitally handcrafted, behind the visualisations; it contributes to studies of buildings designed by C.R. Mackintosh by using digital technologies that open up new insights to aspects still overlooked of his architectural production.
keywords	digital handcrafter, digital heritage, 3D digital reconstruction, visualisation, Charles Rennie Mackintosh
series	CAAD Futures
email
last changed	2019/07/29 14:08

_id	caadria2019_183
id	caadria2019_183
authors	Macken, Marian, Mulla, Sarosh and Paterson, Aaron
year	2019
title	Inhabiting the Drawing - 1:1 in time and space
doi	https://doi.org/10.52842/conf.caadria.2019.1.505
source	M. Haeusler, M. A. Schnabel, T. Fukuda (eds.), Intelligent & Informed - Proceedings of the 24th CAADRIA Conference - Volume 1, Victoria University of Wellington, Wellington, New Zealand, 15-18 April 2019, pp. 505-514
summary	One of the fundamental characteristics of architectural drawing is its use of scale. Since the Renaissance - during which architectural production shifted from the construction site to paper - this scalar understanding began by using bodily measurements. In developing designs, the architect projects future occupation of the drawing with their eyes and hands moving over both its physical surface and represented space. The different relationship established between the digital drawer and the body has been criticised; Paul Emmons argues that CAD's full scale - or rather scale-less - capabilities omit this bodily presence of the drawer (Emmons, 2005). Due to the use of full scale data recording, the drawer zooms in and out to consider aspects, severing the drawing's relation to the operator's body. This paper explores ways in which the body and drawings intersect, beyond Emmons definition, and hence considers the influence of the method of drawing on perceptions of scale and the inhabitation of digital drawings. It uses ongoing collaborative research projects and exhibitions to explore the inhabitation of digital drawing at full scale. These works highlight the fundamental importance of the line within architecture, not as demarcation, divider or indexical reference, but as a traces of bodily projections.
keywords	architectural drawing; architectural scale; full scale drawing; post factum documentation
series	CAADRIA
email
last changed	2022/06/07 07:59

_id	caadria2019_126
id	caadria2019_126
authors	Ng, Jennifer Mei Yee, Khean, Nariddh, Madden, David, Fabbri, Alessandra, Gardner, Nicole, Haeusler, M. Hank and Zavoleas, Yannis
year	2019
title	Optimising Image Classification - Implementation of Convolutional Neural Network Algorithms to Distinguish Between Plans and Sections within the Architectural, Engineering and Construction (AEC) Industry
doi	https://doi.org/10.52842/conf.caadria.2019.2.795
source	M. Haeusler, M. A. Schnabel, T. Fukuda (eds.), Intelligent & Informed - Proceedings of the 24th CAADRIA Conference - Volume 2, Victoria University of Wellington, Wellington, New Zealand, 15-18 April 2019, pp. 795-804
summary	Modern communication between built environment professionals are governed by the effective exchange of digital models, blueprints and technical drawings. However, the increasing quantity of such digital files, in conjunction with inconsistent filing systems, increases the potential for human-error upon their look-up and retrieval. Further, current methods are manual, thus slow and resource intensive. Evidently, the architectural, engineering and construction (AEC) industry lacks an automated classification system capable of systematically identifying and categorising different drawings. To intercede, we aim to investigate artificially intelligent solutions capable of automatically identifying and retrieving a wide set of AEC files from a company's resource library. We present a convolutional neural network (CNN) model capable of processing large sets of technical drawings - such as sections, plans and elevations - and recognise their individual patterns and features, ultimately minimising laboriousness.
keywords	Convolutional Neural Network; Artificial Intelligence; Machine Learning; Classification; Filing architectural drawings.
series	CAADRIA
email
last changed	2022/06/07 07:58

_id	ecaadesigradi2019_088
id	ecaadesigradi2019_088
authors	Sardenberg, Victor, Burger, Theron and Becker, Mirco
year	2019
title	Aesthetic Quantification as Search Criteria in Architectural Design - Archinder
doi	https://doi.org/10.52842/conf.ecaade.2019.1.017
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 1, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 17-24
summary	The paper describes a research experiment of incorporating quantitative aesthetic evaluation and feeding the metric back into a parametric model to steer the search within the design space for a high-ranking design solution. The experiment is part of a longer-standing interest and research in quantitative aesthetics. A web platform inspired by dating apps was developed to retrieve an aesthetic score of images (drawings and photographs of architectural projects). The app and scoring system was tested for functionality against an existing dataset of aesthetic measure (triangles, polygon nets). In the actual experiment, an evolutionary algorithm generated images of design candidates (phenotypes) and used the aesthetic score retrieved by the "crowd" of app users as a fitness function for the next generation/population. The research is in the tradition of empirical aesthetics of G. T. Fechner (Fechner, 1876), using a web app to crowdsource aesthetic scores and using these to evolve design candidates. The paper describes how the system is set up and presents its results in four distinct exercises.
keywords	Quantitative Aesthetics; Social Media; Crowdsourcing; Collaborative Design; Human-Computer interaction
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:57

_id	ecaadesigradi2019_118
id	ecaadesigradi2019_118
authors	Tepavèeviæ, Bojan, Stojakoviæ, Vesna and Mitov, Dejan
year	2019
title	Mass Customization of Deployable Origami-based Structures
doi	https://doi.org/10.52842/conf.ecaade.2019.1.163
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 1, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 163-170
summary	In this research we present a design for a mass customization online 3D model for deployable emergency shelter that automatically provides drawings for CNC machines. The main motivation for such research has risen from a global need to provide emergency shelters for people affected by natural disaster. The model is designed to be a flat packable, mono-material based on a double corrugated folding pattern. Based on numerous functional, structural and fabrication constraints the presented model can provide a myriad of similar geometric forms that can reflect personal needs and can be used for different purposes.
keywords	Mass customization ; folding pattern; digital fabrication; emergency shelters
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:58

_id	ecaadesigradi2019_171
id	ecaadesigradi2019_171
authors	Uzun, Can and Çolako?lu, Meryem Birgül
year	2019
title	Architectural Drawing Recognition - A case study for training the learning algorithm with architectural plan and section drawing images
doi	https://doi.org/10.52842/conf.ecaade.2019.2.029
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 2, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 29-34
summary	This paper aims to develop a case study for training an algorithm to recognize architectural drawings. In order to succeed that, the algorithm is trained with labeled pixel-based, architectural drawing (plan and section) dataset. During the training process, transfer learning (pre-training model) is applied. The supervised learning and convolutional neural network are utilized. After certain iterations, the algorithm builds awareness and can classify pixel-based plan and section drawings. When the algorithm is shown a section that is not produced with conventional drawing technic but through hybrid technics, it could predict the drawing class correctly with %80 of accuracy. On the other hand, some of the algorithm prediction is misoriented. We examined this prediction problem in the discussion section. The results illustrate that neural networks are successful in training algorithms to recognize and classify pixel-based architectural drawings. But for a highly accurate algorithm prediction, the dataset of the drawing images must be ordered, according to sample resolution, sample size and sample coherence for the dataset.
keywords	Classification Algorithm; Pixel-Based Architectural Drawing Recognition; Plan; Section
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:57

_id	caadria2019_396
id	caadria2019_396
authors	Cao, Rui, Fukuda, Tomohiro and Yabuki, Nobuyoshi
year	2019
title	Quantifying Visual Environment by Semantic Segmentation Using Deep Learning - A Prototype for Sky View Factor
doi	https://doi.org/10.52842/conf.caadria.2019.2.623
source	M. Haeusler, M. A. Schnabel, T. Fukuda (eds.), Intelligent & Informed - Proceedings of the 24th CAADRIA Conference - Volume 2, Victoria University of Wellington, Wellington, New Zealand, 15-18 April 2019, pp. 623-632
summary	Sky view factor (SVF) is the ratio of radiation received by a planar surface from the sky to that received from the entire hemispheric radiating environment, in the past 20 years, it was more applied to urban-climatic areas such as urban air temperature analysis. With the urbanization and the development of cities, SVF has been paid more and more attention on as the important parameter in urban construction and city planning area because of increasing building coverage ratio to promote urban forms and help creating a more comfortable and sustainable urban residential building environment to citizens. Therefore, efficient, low cost, high precision, easy to operate, rapid building-wide SVF estimation method is necessary. In the field of image processing, semantic segmentation based on deep learning have attracted considerable research attention. This study presents a new method to estimate the SVF of residential environment by constructing a deep learning network for segmenting the sky areas from 360-degree camera images. As the result of this research, an easy-to-operate estimation system for SVF based on high efficiency sky label mask images database was developed.
keywords	Visual environment; Sky view factor; Semantic segmentation; Deep learning; Landscape simulation
series	CAADRIA
email
last changed	2022/06/07 07:54

_id	cf2019_021
id	cf2019_021
authors	Cheng, Chi-Li and June-Hao Hou
year	2019
title	A Method of Mesh Simplification for Drone 3D Modeling with Architectural Feature Extraction
source	Ji-Hyun Lee (Eds.) "Hello, Culture!" [18th International Conference, CAAD Futures 2019, Proceedings / ISBN 978-89-89453-05-5] Daejeon, Korea, p. 169
summary	This paper proposes a method of mesh simplification for 3D terrain or city models generated photogrammetrically from drone captured images, enabled by the ability of extracting the architectural features. Compare to traditional geometric computational method, the proposed method recognizes and processes the features from the architectural perspectives. In addition, the workflow also allows exporting the simplified models and geometric features to open platforms, e.g. OpenStreetMap, for practical usages in site analysis, city generation, and contributing to the open data communities.
keywords	Mesh Reconstruction, photogrammetry, mesh simplification, procedural mode, machine learning
series	CAAD Futures
email
last changed	2019/07/29 14:08

_id	caadria2019_223
id	caadria2019_223
authors	Han, Yunsong, Pan, Yongjie, Zhao, Tianyu, Wang, Chunxing and Sun, Cheng
year	2019
title	Use of UAV Photogrammetry to Estimate the Solar Energy Potential of Residential Buildings in Severe Cold Region
doi	https://doi.org/10.52842/conf.caadria.2019.2.613
source	M. Haeusler, M. A. Schnabel, T. Fukuda (eds.), Intelligent & Informed - Proceedings of the 24th CAADRIA Conference - Volume 2, Victoria University of Wellington, Wellington, New Zealand, 15-18 April 2019, pp. 613-622
summary	In this paper, a method based on UAV photogrammetry is proposed to estimate the solar energy potential of the building surface. This methodology goes from the acquired aerial images captured by the camera mounted on UAV. 3D model of the urban context in study area was extracted from the aerial images using SFM and MVS algorithms, which could be directly applied to the Ladybug plugin as analysis objects. Estimates of solar radiation are expressed by means of data visualization. The results showed that the UAV photogrammetry could demonstrate the geometry and texture of residential buildings precisely and the solar radiation simulation results showed significant spatial and temporal variations in solar radiation on residential buildings.
keywords	Residential buildings; UAV photogrammetry; 3D reconstruction; Solar energy potential; Severe cold region
series	CAADRIA
email
last changed	2022/06/07 07:50

_id	caadria2019_143
id	caadria2019_143
authors	Kato, Yuri and Matsukawa, Shohei
year	2019
title	Development of Generating System for Architectural Color Icons Using Google Map Platform and Tensorflow-Segmentation
doi	https://doi.org/10.52842/conf.caadria.2019.2.081
source	M. Haeusler, M. A. Schnabel, T. Fukuda (eds.), Intelligent & Informed - Proceedings of the 24th CAADRIA Conference - Volume 2, Victoria University of Wellington, Wellington, New Zealand, 15-18 April 2019, pp. 81-90
summary	In this research, the goal is to develop a generating system for architectural color icons using Google Map Platform and Tensorflow-Segmentation. There has been no case of developing a system that allows users to visualize the color tendency of buildings as architectural color icons for each building element from images of various regions. It is considered meaningful to be able to create criteria for decision making in architecture and the urban design by developing a system to clarify the current state of the architectural colors. It will contribute a rise in the consciousness of landscape conservation and be essential for the design of architectures and public objects. This paper includes the explanation of development method, use experiments, and consideration of five problems among architectural color icons creation. It is assumed that the accuracy of the present system will be better as the technology improves.
keywords	Google street view; machine learning; image segmentation; color palette; color analysis
series	CAADRIA
email
last changed	2022/06/07 07:52

_id	ecaadesigradi2019_339
id	ecaadesigradi2019_339
authors	Kinugawa, Hina and Takizawa, Atsushi
year	2019
title	Deep Learning Model for Predicting Preference of Space by Estimating the Depth Information of Space using Omnidirectional Images
doi	https://doi.org/10.52842/conf.ecaade.2019.2.061
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 2, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 61-68
summary	In this study, we developed a method for generating omnidirectional depth images from corresponding omnidirectional RGB images of streetscapes by learning each pair of omnidirectional RGB and depth images created by computer graphics using pix2pix. Then, the models trained with different series of images shot under different site and weather conditions were applied to Google street view images to generate depth images. The validity of the generated depth images was then evaluated visually. In addition, we conducted experiments to evaluate Google street view images using multiple participants. We constructed a model that estimates the evaluation value of these images with and without the depth images using the learning-to-rank method with deep convolutional neural network. The results demonstrate the extent to which the generalization performance of the streetscape evaluation model changes depending on the presence or absence of depth images.
keywords	Omnidirectional image; depth image; Unity; Google street view; pix2pix; RankNet
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:52

_id	acadia19_298
id	acadia19_298
authors	Leach, Neil
year	2019
title	Do Robots Dream of Digital Sleep?
doi	https://doi.org/10.52842/conf.acadia.2019.298
source	ACADIA 19:UBIQUITY AND AUTONOMY [Proceedings of the 39th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-59179-7] (The University of Texas at Austin School of Architecture, Austin, Texas 21-26 October, 2019) pp. 298-309
summary	AI is playing an increasingly important role in everyday life. But can AI actually design? This paper takes its point of departure from Philip K Dick’s novel, Do Androids Dream of Electric Sheep? and refers to Google’s DeepDream software, and other AI techniques such as GANs, Progressive GANs, CANs and StyleGAN, that can generate increasingly convincing images, a process often described as ‘dreaming’. It notes that although generative AI does not possess consciousness, and therefore cannot literally dream, it can still be a powerful design tool that becomes a prosthetic extension to the human imagination. Although the use of GANs and other deep learning AI tools is still in its infancy, we are at the dawn of an exciting – but also potentially terrifying – new era for architectural design. Most importantly, the paper concludes, the development of AI is also helping us to understand human intelligence and 'creativity'.
series	ACADIA
type	normal paper
email
last changed	2022/06/07 07:52

_id	ijac201917104
id	ijac201917104
authors	Matthews, Linda and Gavin Perin
year	2019
title	Exploiting ambiguity: The diffraction artefact and the architectural surface
source	International Journal of Architectural Computing vol. 17 - no. 1, 103-115
summary	In the contemporary ‘envisioned’ environment, Internet webcams, low- and high-altitude unmanned aerial vehicles and satellites are the new vantage points from which to construct the image of the city. Armed with hi-resolution digital optical technologies, these vantage points effectively constitute a ubiquitous visioning apparatus serving either the politics of promotion or surveillance. Given the political dimensions of this apparatus, it is important to note that this digital imaging of public urban space refers to the human visual system model. In order to mimic human vision, a set of algorithm patterns are used to direct numerous ‘soft’ and ‘hard’ technologies. Mimicry thus has a cost because this insistence on the human visual system model necessitates multiple transformative moments in the production and transmission pipeline. If each transformative moment opens a potential vulnerability within the visioning apparatus, then every glitch testifies to the artificiality of the image. Moreover, every glitch potentially interrupts the political narratives be communicated in contemporary image production and transmission. Paradoxically, the current use of scripting to create glitch-like images has reimagined glitches as a discrete aesthetic category. This article counters this aestheticisation by asserting glitching as a disruption in communication. The argument will rely on scaled tests produced by one of the authors who show how duplicating the digital algorithmic patterns used within the digital imaging pipeline on any exterior building surface glitches the visual data captured within that image. Referencing image-based techniques drawn from the Baroque and contemporary modes of camouflage, it will be argued that the visual aberrations created by these algorithm-based patterned facades can modify strategically the ‘emission signature’ of selected parts of the urban fabric. In this way, the glitch becomes a way to intercede in the digital portrayal of city.
keywords	Surveillance, algorithms, diffraction, pattern, disruptive, optics
series	journal
email
last changed	2019/08/07 14:04

_id	ecaadesigradi2019_550
id	ecaadesigradi2019_550
authors	Rhee, Jinmo, Cardoso Llach, Daniel and Krishnamurti, Ramesh
year	2019
title	Context-rich Urban Analysis Using Machine Learning - A case study in Pittsburgh, PA
doi	https://doi.org/10.52842/conf.ecaade.2019.3.343
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 3, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 343-352
summary	This paper reports on the analytical potential of machine learning methods for urban analysis. It documents a new method for data-driven urban analysis based on diagrammatic images describing each building in a city in relation to its immediate urban context. By statistically analyzing architectural and contextual features in this new dataset, the method can identify clusters of similar urban conditions and produce a detailed picture of a city's morphological structure. Remapping the clusters from data to 2D space, our method enables a new kind of urban plan that displays gradients of urban similarity. Taking Pittsburgh as a case study we demonstrate this method, and propose "morphological types" as a new category of urban analysis describing a given city's specific set of distinct morphological conditions. The paper concludes with a discussion of the implications of this method and its limitations, as well as its potentials for architecture, urban studies, and computation.
keywords	Urban Morphology; Machine Learning; Architectural Contexts; Urban Analysis; GIS
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:56

_id	ecaade2023_259
id	ecaade2023_259
authors	Sonne-Frederiksen, Povl Filip, Larsen, Niels Martin and Buthke, Jan
year	2023
title	Point Cloud Segmentation for Building Reuse - Construction of digital twins in early phase building reuse projects
doi	https://doi.org/10.52842/conf.ecaade.2023.2.327
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 327–336
summary	Point cloud processing has come a long way in the past years. Advances in computer vision (CV) and machine learning (ML) have enabled its automated recognition and processing. However, few of those developments have made it through to the Architecture, Engineering and Construction (AEC) industry. Here, optimizing those workflows can reduce time spent on early-phase projects, which otherwise could be spent on developing innovative design solutions. Simplifying the processing of building point cloud scans makes it more accessible and therefore, usable for design, planning and decision-making. Furthermore, automated processing can also ensure that point clouds are processed consistently and accurately, reducing the potential for human error. This work is part of a larger effort to optimize early-phase design processes to promote the reuse of vacant buildings. It focuses on technical solutions to automate the reconstruction of point clouds into a digital twin as a simplified solid 3D element model. In this paper, various ML approaches, among others KPConv Thomas et al. (2019), ShapeConv Cao et al. (2021) and Mask-RCNN He et al. (2017), are compared in their ability to apply semantic as well as instance segmentation to point clouds. Further it relies on the S3DIS Armeni et al. (2017), NYU v2 Silberman et al. (2012) and Matterport Ramakrishnan et al. (2021) data sets for training. Here, the authors aim to establish a workflow that reduces the effort for users to process their point clouds and obtain object-based models. The findings of this research show that although pure point cloud-based ML models enable a greater degree of flexibility, they incur a high computational cost. We found, that using RGB-D images for classifications and segmentation simplifies the complexity of the ML model but leads to additional requirements for the data set. These can be mitigated in the initial process of capturing the building or by extracting the depth data from the point cloud.
keywords	Point Clouds, Machine Learning, Segmentation, Reuse, Digital Twins
series	eCAADe
email
last changed	2023/12/10 10:49

_id	acadia19_392
id	acadia19_392
authors	Steinfeld, Kyle
year	2019
title	GAN Loci
doi	https://doi.org/10.52842/conf.acadia.2019.392
source	ACADIA 19:UBIQUITY AND AUTONOMY [Proceedings of the 39th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-59179-7] (The University of Texas at Austin School of Architecture, Austin, Texas 21-26 October, 2019) pp. 392-403
summary	This project applies techniques in machine learning, specifically generative adversarial networks (or GANs), to produce synthetic images intended to capture the predominant visual properties of urban places. We propose that imaging cities in this manner represents the first computational approach to documenting the Genius Loci of a city (Norberg-Schulz, 1980), which is understood to include those forms, textures, colors, and qualities of light that exemplify a particular urban location and that set it apart from similar places. Presented here are methods for the collection of urban image data, for the necessary processing and formatting of this data, and for the training of two known computational statistical models (StyleGAN (Karras et al., 2018) and Pix2Pix (Isola et al., 2016)) that identify visual patterns distinct to a given site and that reproduce these patterns to generate new images. These methods have been applied to image nine distinct urban contexts across six cities in the US and Europe, the results of which are presented here. While the product of this work is not a tool for the design of cities or building forms, but rather a method for the synthetic imaging of existing places, we nevertheless seek to situate the work in terms of computer-assisted design (CAD). In this regard, the project is demonstrative of a new approach to CAD tools. In contrast with existing tools that seek to capture the explicit intention of their user (Aish, Glynn, Sheil 2017), in applying computational statistical methods to the production of images that speak to the implicit qualities that constitute a place, this project demonstrates the unique advantages offered by such methods in capturing and expressing the tacit.
series	ACADIA
type	normal paper
email
last changed	2022/06/07 07:56

_id	acadia19_380
id	acadia19_380
authors	Özel, Güvenç; Ennemoser, Benjamin
year	2019
title	Interdisciplinary AI
doi	https://doi.org/10.52842/conf.acadia.2019.380
source	ACADIA 19:UBIQUITY AND AUTONOMY [Proceedings of the 39th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-59179-7] (The University of Texas at Austin School of Architecture, Austin, Texas 21-26 October, 2019) pp. 380- 391
summary	Architecture does not exist in a vacuum. Its cultural, conceptual, and aesthetic agendas are constantly influenced by other visual and artistic disciplines ranging from film, photography, painting and sculpture to fashion, graphic and industrial design. The formal qualities of the cultural zeitgeist are perpetually influencing contemporary architectural aesthetics. In this paper, we aim to introduce a radical yet methodical approach toward regulating the relationship between human agency and computational form-making by using Machine Learning (ML) as a conceptual design tool for interdisciplinary collaboration and engagement. Through the use of a highly calibrated and customized ML systems that can classify and iterate stylistic approaches that exist outside the disciplinary boundaries of architecture, the technique allows for machine intelligence to design, coordinate, randomize, and iterate external formal and aesthetic qualities as they relate to pattern, color, proportion, hierarchy, and formal language. The human engagement in this design process is limited to the initial curation of input data in the form of image repositories of non-architectural disciplines that the Machine Learning system can extrapolate from, and consequently in regulating and choosing from the iterations of images the Artificial Neural Networks are capable of producing. In this process the architect becomes a curator that samples and streamlines external cultural influences while regulating their significance and weight in the final design. By questioning the notion of human agency in the design process and providing creative license to Artificial Intelligence in the conceptual design phase, we aim to develop a novel approach toward human-machine collaboration that rejects traditional notions of disciplinary autonomy and streamlines the influence of external aesthetic disciplines on contemporary architectural production.
series	ACADIA
type	normal paper
email
last changed	2022/06/07 07:57

For more results click below: