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 540

_id ijac202220216
id ijac202220216
authors Keyvanfar, Ali; Arezou Shafaghat; Muhamad SF Rosley
year 2022
title Performance comparison analysis of 3D reconstruction modeling software in construction site visualization and mapping
source International Journal of Architectural Computing 2022, Vol. 20 - no. 2, pp. 453–475
summary Unmanned aerial vehicle (UAV) technology has overcome the limitations of conventional construction management methods using advanced and automated visualization and 3D reconstruction modeling techniques. Although the mapping techniques and reconstruction modeling software can generate real-time and high-resolution descriptive textural, physical, and spatial data, they may fail to develop an accurate and complete 3D model of the construction site. To generate a quality 3D reconstruction model, the construction manager must optimize the trade-offs among three major software-selection factors: functionalities, technical capabilities, and the system hardware specifications. These factors directly affect the robust 3D reconstruction model of the construction site and objects. Accordingly, the purpose of this research was to apply nine well-established 3D reconstruction modeling software tools (DroneDeploy, COLMAP, 3DF+Zephyr, Autodesk Recap, LiMapper, PhotoModeler, 3D Survey, AgiSoft Photoscan, and Pix4D Mapper) and compare their performances and reliabilities in generating complete 3D models. The research was conducted in an eco-home building at the University of Technology, Malaysia. A series of regression analyses were conducted to compare the performances of the selected 3D reconstruction modeling software in alignment and registration, distance computing, geometric measurement, and plugin execution. Regression analysis determined that among the software programs, LiMapper had the strongest positive linear correlation with the ground truth model. Furthermore, the correlation analysis showed a statistically significant p-value for all software, except for 3D Survey. In addition, the research found that Autodesk Recap generated the most-robust and highest-quality dense point clouds. DroneDeploy can create an accurate point cloud and triangulation without using many points as required by COLMAP and LiMapper. It was concluded that most of the software is robustly, positively, and linearly correlated with the corresponding ground truth model. In the future, other factors involving software selection should be studied, such as vendor-related, user-related, and automation factors.
keywords Construction site visualization, unmanned aerial vehicle, photogrammetry, 3D reconstruction modeling, multi-view-stereopsis, structure-from-motion, ANOVA and regression analysis
series journal
last changed 2024/04/17 14:29

_id ecaade2022_223
id ecaade2022_223
authors Tuzun Canadinc, Seda and Yan, Wei
year 2022
title 3D-Model-Based Augmented Reality for Enhancing Physical Architectural Models
source Pak, B, Wurzer, G and Stouffs, R (eds.), Co-creating the Future: Inclusion in and through Design - Proceedings of the 40th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2022) - Volume 2, Ghent, 13-16 September 2022, pp. 495–504
doi https://doi.org/10.52842/conf.ecaade.2022.2.495
summary In the presentation of architectural projects, physical models are still commonly used as a powerful and effective representation for building design and construction. On the other hand, Augmented Reality (AR) promises a wide range of possibilities in visualizing and interacting with 3D physical models, enhancing the modeling process. To benefit both, we present a novel medium for architectural representation: a marker-less AR powered physical architectural model that employs dynamic digital features. With AR enhancement, physical capabilities of a model could be extended without sacrificing its tangibility. We developed a framework to investigate the potential uses of 3D-model- based AR registration method and its augmentation on physical architectural models. To explore and demonstrate integration of physical and virtual models in AR, we designed this framework providing physical and virtual model interaction: a user can manipulate the physical model parts or control the visibility and dynamics of the virtual parts in AR. The framework consists of a LEGO model and an AR application on a hand-held device which was developed for this framework. The AR application utilizes a marker-less AR registration method and employs a 3D-model-based AR registration. A LEGO model was proposed as the physical 3D model in this registration process and machine learning training using Vuforia was utilized for the AR application to recognize the LEGO model from any point of view to register the virtual models in AR. The AR application also employs a user interface that allows user interaction with the virtual parts augmented on the physical ones. The working application was tested over its registration, physical and virtual interactions. Overall, the adoption of AR and its combination with physical models, and 3D-model-based AR registration allow for many advantages, which are discussed in the paper.
keywords Augmented Reality, AR, 3D-model based AR, Architectural Representation, Architectural Modeling
series eCAADe
email
last changed 2024/04/22 07:10

_id caadria2022_302
id caadria2022_302
authors Raghu, Deepika, Markopoulou, Areti, Marengo, Mathilde, Neri, Iacopo, Chronis, Angelos and De Wolf, Catherine
year 2022
title Enabling Component Reuse from Existing Buildings through Machine Learning, Using Google Street View to Enhance Building Databases
source Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 577-586
doi https://doi.org/10.52842/conf.caadria.2022.2.577
summary Intense urbanization has led us to rethink construction and demolition practices on a global scale. There is an opportunity to respond to the climate crisis by moving towards a circular built environment. Such a paradigm shift can be achieved by critically examining the possibility of reusing components from existing buildings. This study investigates approaches and tools needed to analyze the existing building stock and methods to enable component reuse. Ocular observations were conducted in Google Street View to analyze two building-specific characteristics: (1) facade material and (2) reusable components (window, doors, and shutters) found on building facades in two cities: Barcelona and Zurich. Not all products are equally suitable for reuse and require an evaluation metric to understand which components can be reused effectively. Consequently, tailored reuse strategies that are defined by a priority order of waste prevention are put forth. Machine learning shows promising potential to visually collect building-specific characteristics that are relevant for component reuse. The data collected is used to create classification maps that can help define protocols and for urban planning. This research can upscale limited information in countries where available data about the existing building stock is insufficient.
keywords machine learning, component reuse, Google Street View, material banks, building databases, SDG 11, SDG 12
series CAADRIA
email
last changed 2022/07/22 07:34

_id caadria2022_267
id caadria2022_267
authors Toohey, Gabrielle, Nguyen, Tommy Bao Nghi, Vilppola, Ritva, Qiu, Waishan, Li, Wenjing and Luo, Dan
year 2022
title Data-Driven Evaluation of Streets to Plan for Bicycle Friendly Environments: A Case Study of Brisbane Suburbs
source Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 243-252
doi https://doi.org/10.52842/conf.caadria.2022.1.243
summary Empirical cycling data from across the world illustrates the many barriers that car-dependent cities face when implementing cycling programs and infrastructure. Most studies focus on physical criteria, while perception criteria are less addressed. The correlations between the two are still largely unknown. This paper introduces a methodology that utilises computer vision analysis techniques to evaluate 15,383 Google Street View Images (SVI) of Brisbane City against both physical and perception cycling criteria. The study seeks to better understand correlations between the quality of a street environment and an urban area's 'bicycle-friendliness'. PSPNet Image Segmentation is utilised against SVIs to determine the percentage of an image corresponding with objects and the environment related to specific cycling factors. For physical criteria, these images are then further analysed by Masked RCNN processes. For perception criteria, subjective ranking of the images is undertaken using Machine Learning (ML) techniques to score images based on survey data. The methodology effectively allows for current findings in cycling research to be further utilised in combination via computer visioning (CV) and ML applications to measure different physical elements and urban design qualities that correspond with bicycle-friendliness. Such findings can assist targeted design strategies for cities to encourage the use of safer and more sustainable modes of transport.
keywords Bicycle-friendly, Quality Streetscapes, Active Living, Visual Assessment, Computer Visioning, Machine Learning, SDG 3, SDG 11
series CAADRIA
email
last changed 2022/07/22 07:34

_id caadria2022_199
id caadria2022_199
authors Yang, Qing, Cao, Chufan, Li, Haimiao, Qiu, Waishan, Li, Wenjing and Luo, Dan
year 2022
title Quantifying the Coherence and Divergence of Planned, Visual and Perceived Streets Greening to Inform Ecological Urban Planning
source Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 565-574
doi https://doi.org/10.52842/conf.caadria.2022.1.565
summary This research attempts to combine the fields of urban planning, urban design and cognitive psychology, and propose three corresponding evaluation indicators for urban ecology, and further explore the coherence and divergence between them. This research defines land vegetation coverage, visibility of street green vegetation, and people's green perception as planned green, visual green and perceived green. Specifically, the three measures (i.e., planned, visual and perceived) refer to objectively extracting park lands and canopy areas from land use data, objectively extracting green pixels from street views, and subjectively collected through visual surveys. This study hypothesizes that there could exist large variation between the three measures, which would provide distinct implications for city planners. To test our hypothesis, this study selects Brisbane as the research area, effectively using computer deep learning, data visualization and mathematical statistics methods to achieve an accurate description of the three sets of data, and proposes a comprehensive evaluation of the urban ecological theory system. The results show the credibility and scope of application of the three types of greening, and quantitatively proposed and tested the relevant theories of urban design.
keywords Urban Green Space, Urban Ecology, Street View Image, Green Perception, Subjective Measure, SDG 3, SDG 11, SDG 13
series CAADRIA
email
last changed 2022/07/22 07:34

_id ascaad2022_086
id ascaad2022_086
authors Chehab, Aya; Nakhal, Bilal
year 2022
title Exploring Virtual Reality as an Approach to Resurrect Destroyed Historical Buildings: An Approach to Revive the Destroyed "Egg Building" through VR
source Hybrid Spaces of the Metaverse - Architecture in the Age of the Metaverse: Opportunities and Potentials [10th ASCAAD Conference Proceedings] Debbieh (Lebanon) [Virtual Conference] 12-13 October 2022, pp. 609-631
summary An important part of a city, that gives it a sense of community and character, is its history. One way of acknowledging this heritage is by preserving historic building and structures. Old buildings are witnesses to the aesthetic and cultural history of a city, helping to give people a sense of place and connection to the past. Unfortunately, despite their importance within the city, historical buildings are most of the time subject to demolition and to be replaced- leaving behind stories told and untold of what use to be. The paper, therefore, aims to explore the capability of the metaverse, using virtual reality touring, to revive the memory of historical buildings that are subject to fade. Where preserving historical buildings can not only act as a symbol of grandeur but is also vital for reviving the community’s collective memory. The case study focused upon in the research paper shows a first step in the development of an immersive virtual tour for the significant building of “The Egg” or “Beirut City Center” in Downtown- which is a building that witnessed a series of unfortunate events that lead to destruction, erasure, and demolition of the building. Therefore, examining the recovery and revival of this unique historic site in an unconventional way which is in the metaverse, specifically the Virtual Reality (VR). The paper assumes that virtual reality, as the main metaverse approach, would help people ‘remember’ and ‘mentally revive’ the destroyed historical buildings that once acted as the building blocks in the impacted city. To prove this hypothesis, two different methodologies will be used, by theorical analysis and literature review, such as analyzing the main keyword, and analyzing datum from previous works. The second method will rely on the physical methodology, where virtual 3D Models will be built in a computer software, Autodesk Revit, then imported within a VR experience for an enhanced experience within the historical site to preserve the historic buildings and revive the collective memory within the community, enabling people to view how these historic sites once were and how they have now become.
series ASCAAD
email
last changed 2024/02/16 13:29

_id caadria2022_42
id caadria2022_42
authors Chen, Jielin and Stouffs, Rudi
year 2022
title Robust Attributed Adjacency Graph Extraction Using Floor Plan Images
source Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 385-394
doi https://doi.org/10.52842/conf.caadria.2022.2.385
summary Architectural design solutions are intrinsically structured information with a broad range of interdependent scopes. Compared to conventional 2D Euclidean data such as orthographic drawings and perspectives, non-Euclidean data (e.g., attributed adjacency graphs) can be more effective and accurate for representing 3D architectural design information, which can be useful for numerous design tasks such as spatial analysis and reasoning, and practical applications such as floor plan parsing and generation. Thus, getting access to a matching attributed adjacency graph dataset of architectural design becomes a necessity. However, the task of conveniently acquiring attributed adjacency graphs from existing architectural design solutions still remains an open challenge. To this end, this project leverages state-of-the-art image segmentation techniques using an ensemble learning scheme and proposes an end-to-end framework to efficiently extract attributed adjacency graphs from floor plan images with diverse styles and varied levels of complexity, aiming at addressing generalization issues of existing approaches. The proposed graph extraction framework can be used as an innovative tool for advancing design research infrastructure, with which we construct a large-scale attributed adjacency graph dataset of architectural design using floor plan images retrieved in bulk. We have open sourced our code and dataset.
keywords attributed adjacency graph, floor plan segmentation, ensemble learning, architectural dataset, SDG 9
series CAADRIA
email
last changed 2022/07/22 07:34

_id caadria2022_231
id caadria2022_231
authors Kim, Frederick Chando and Huang, Jeffrey
year 2022
title Deep Architectural Archiving (DAA), Towards a Machine Understanding of Architectural Form
source Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 727-736
doi https://doi.org/10.52842/conf.caadria.2022.1.727
summary With the ‚digital turn‚, machines now have the intrinsic capacity to learn from big data in order to understand the intricacies of architectural form. This paper explores the research question: how can architectural form become machine computable? The research objective is to develop "Deep Architectural Archiving‚ (DAA), a new method devised to address this question. DAA consists of the combination of four distinct steps: (1) Data mining, (2) 3D Point cloud extraction, (3) Deep form learning, as well as (4) Form mapping and clustering. The paper discusses the DAA method using an extensive dataset of architecture competitions in Switzerland (with over 360+ architectural projects) as a case study resource. Machines learn the particularities of forms using 'architectural' point clouds as an opportune machine-learnable format. The result of this procedure is a multidimensional, spatialized, and machine-enabled clustering of forms that allows for the visualization of comparative relationships among form-correlated datasets that exceeds what the human eye can generally perceive. Such work is necessary to create a dedicated digital archive for enhancing the formal knowledge of architecture and enabling a better understanding of innovation, both of which provide architects a basis for developing effective architectural form in a post-carbon world.
keywords artificial intelligence, deep learning, architectural form, architectural competitions, architectural archive, 3D dataset, SDG 11
series CAADRIA
email
last changed 2022/07/22 07:34

_id ecaade2022_203
id ecaade2022_203
authors Kim, Frederick Chando and Huang, Jeffrey
year 2022
title Perspectival GAN - Architectural form-making through dimensional transformation
source Pak, B, Wurzer, G and Stouffs, R (eds.), Co-creating the Future: Inclusion in and through Design - Proceedings of the 40th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2022) - Volume 1, Ghent, 13-16 September 2022, pp. 341–350
doi https://doi.org/10.52842/conf.ecaade.2022.1.341
summary With the ascendance of Generative Adversarial Networks (GAN), promising prospects have arisen from the abilities of machines to learn and recognize patterns in 2D datasets and generate new results as an inspirational tool in architectural design. Insofar as the majority of ML experiments in architecture are conducted with imagery based on readily available 2D data, architects and designers are faced with the challenge of transforming machine-generated images into 3D. On the other hand, GAN-generated images are found to be able to learn the 3D information out of 2D perspectival images. To facilitate such transformation from 2D and 3D data in the framework of deep learning in architecture, this paper explores making new architectural forms from flat GAN images by employing traditional tools of projective geometry. The experiments draw on Brook Taylor’s 19th- century theorem of inverse projection system for creating architectural form from perspectival information learned from GAN images of Swiss alpine architecture. The research develops a parametric tool that automates the dimensional transformation of 2D images into 3D architectural forms. This research identifies potential synergic interactions between traditional tools and techniques of architects and deep learning algorithms to achieve collective intelligence in designing and representing creative architecture forms between humans and machines.
keywords Machine Learning, GAN, Architectural Form, Perspective Projection, Inverse Perspective, Digital Representation
series eCAADe
email
last changed 2024/04/22 07:10

_id ecaade2022_51
id ecaade2022_51
authors Lüling, Claudia and Carl, Timo
year 2022
title Fuzzy 3D Fabrics & Precise 3D Printing - Combining research with design-build investigations
source Pak, B, Wurzer, G and Stouffs, R (eds.), Co-creating the Future: Inclusion in and through Design - Proceedings of the 40th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2022) - Volume 1, Ghent, 13-16 September 2022, pp. 67–76
doi https://doi.org/10.52842/conf.ecaade.2022.1.067
summary We present a synergetic combination of two previously separate process technologies to create novel lightweight structures. 3D textiles and 3D printing. We will outline the development of a novel material system that consisted of flexible and foldable 3D textiles that are combined with stiff, linear 3D printed materials. Our aim is to produce material-reduced lightweight elements for building applications with an extended functionality and recyclability. Within an ongoing research project (6dTEX), we explore a mono-material system, which uses the same base materials for both the filament for 3D printing and the yarn of the fabrication of the 3D textiles. Based on preliminary 3D printing tests on flat textiles key process parameters were identified. Expertise has been established for 3D printing on textiles as well as for using printable recycled polyester materials (PES textile and PETG filament. Lastly for 3D printing on non-combustible material (alkali-resistant (AR) glass textiles and for 3D concrete printing (3DCP). The described process- knowledge facilitates textile architectures with an extended vocabulary, ranging from flat to single curved and folded topologies. Whereas the foundations are laid in the research project on a meso scale, we also extended our explorations into an architectural macro scale. For this, we used a more speculative design-build studio that was based on a more loose combination of 3D textiles and 3D printed elements. Lastly, we will discuss, how this first architectural application beneficially informed the research project.
keywords Material-Based Design, Additive Manufacturing, Design-Build, Parametric Modelling, Form-Finding, Co-Creation, Lightweight Structures, Single-Origin Composites, Space Fabrics
series eCAADe
email
last changed 2024/04/22 07:10

_id caadria2022_177
id caadria2022_177
authors Pan, Yongjie and Zhang, Tong
year 2022
title Outdoor Thermal Environment Assessment of Existing Residential Areas Supported by UAV Thermal Infrared and 3D Reconstruction Technology
source Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 729-738
doi https://doi.org/10.52842/conf.caadria.2022.2.729
summary The underlying surface temperature is an effective evaluation index to study the urban micro-scale thermal environment. For surface temperature acquisition, the thermal infrared camera mounted on a unmanned aerial vehicle (UAV) can reduce field work intensity, improve data collection efficiency, and ensure high accuracy at low cost. In order to convert the 2D thermal image into a more intuitive 3D thermal model, the UAV-based thermal infrared 3D reconstruction is adopted. The key element of thermal infrared 3D model reconstruction lies in the processing of thermal infrared images with low resolution and different temperature scales. In order to improve the quality of the final thermal 3D model, this paper proposes the reconstruction of the detailed 3D mesh using visible images (higher resolution), and map then mapping thermal textures onto the mesh using thermal images (low resolution). In addition, absolute temperature values are extracted from thermal images with different temperature ranges to ensure consistence between color and temperature values in the reconstructed thermal 3D model. The thermal 3D model generated for an existing residential area in Nanjing successfully displays the temperature distribution of the underlying surface and provides a valuable basis for outdoor thermal environment assessment.
keywords Thermal image, UAV, 3D reconstruction, Residential outdoor space, Underlying surface temperature, SDG 3, SDG 11
series CAADRIA
email
last changed 2022/07/22 07:34

_id ecaade2022_64
id ecaade2022_64
authors Sopher, Hadas and Dorta, Tomás
year 2022
title Using Social VR System in Multidisciplinary Codesign
source Pak, B, Wurzer, G and Stouffs, R (eds.), Co-creating the Future: Inclusion in and through Design - Proceedings of the 40th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2022) - Volume 1, Ghent, 13-16 September 2022, pp. 547–556
doi https://doi.org/10.52842/conf.ecaade.2022.1.547
summary Social VR (SVR) systems are potentially adequate to support remote collaboration by allowing multidisciplinary students to codesign through an immersive shared display and 3D sketching. These characteristics become substantial for Multidisciplinary Codesign (MC) courses with the appreciation of the skills gained as knowledge is co-constructed. In codesign, participants ideate and develop together a design solution through verbal exchanges and design representations, relying on each participant’s expertise. Considering that non-design students lack design skills, design progress becomes highly challenging. Research focusing on how SVRs support MC is limited, what hinders integrating SVRs in these courses. Aiming to demonstrate how SVRs are used in MC courses, we monitored MC sessions involving three universities, from Industrial design, Ergonomics and Engineering. Data include three sessions of three remote multidisciplinary teams using three interconnected SVRs and three sessions involving collocated Industrial design students using a single SVR. The verbal and representational activities generated during the sessions were analysed, accounting for elements of collaborative ideation. Results showed a dominance of Industrial design students in generating representations and collaborative ideation. A rise in 3D representations in advanced MC sessions indicates the SVRs’ role in the process, understandings that enable the integration of SVRs in inter-university collaborations.
keywords Social VR, Multidisciplinary Codesign, Codesign Learning, Design Conversations, 3D Sketching, Immersive Learning Environments
series eCAADe
email
last changed 2024/04/22 07:10

_id sigradi2022_53
id sigradi2022_53
authors Stuart-Smith, Robert; Danahy, Patrick
year 2022
title 3D Generative Design for Non-Experts: Multiview Perceptual Similarity with Agent-Based Reinforcement Learning
source Herrera, PC, Dreifuss-Serrano, C, Gómez, P, Arris-Calderon, LF, Critical Appropriations - Proceedings of the XXVI Conference of the Iberoamerican Society of Digital Graphics (SIGraDi 2022), Universidad Peruana de Ciencias Aplicadas, Lima, 7-11 November 2022 , pp. 115–126
summary Advances in additive manufacturing allow architectural elements to be fabricated with increasingly complex geometrical designs, however, corresponding 3D design software requires substantial knowledge and skill to operate, limiting adoption by non-experts or people with disabilities. Established non-expert approaches typically constrain geometry, topology, or character to a pre-established configuration, rather than aligning to figural and aesthetic characteristics defined by a user. A methodology is proposed that enables a user to develop multi-manifold designs from sketches or images in several 3d camera projections. An agent-based design approach responds to computer vision analysis (CVA) and Deep Reinforcement Learning (RL) to design outcomes with perceptual similarity to user input images evaluated by Structural Similarity Indexing (SSIM). Several CVA and RL ratios were explored in training models and tested on untrained images to evaluate their effectiveness. Results demonstrate a combination of CVA and RL motion behavior can produce meshes with perceptual similarity to image content.
keywords Generative Design, Machine Learning, Agent-Based Systems, Non-Expert Design
series SIGraDi
email
last changed 2023/05/16 16:55

_id caadria2022_275
id caadria2022_275
authors Sukegawa, Chika, Khajehee, Arastoo, Kawakami, Takuma, Someya, Syunsuke, Hirano, Yuji, Shibuya, Masako, Ito, Koki, Watanabe, Yoshiaki, Wang, Qiang, Inaba, Tooru, Lee, Alric, Hotta, Kensuke, Miyaguchi, Mikita and Ikeda, Yasushi
year 2022
title Smart Hand for Digital Twin Timber Work -The interactive procedural scanning by industrial arm robot
source Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 131-140
doi https://doi.org/10.52842/conf.caadria.2022.2.131
summary This paper describes a 3D automated scanning method for building materials, namely "The Interactive Procedural Scanning‚, in a collaborative environment composed of a human worker and a CNC robot. This procedure aims to translate the observation skill of an experienced carpenter into an intelligent robotic system. The system frames its function on the first stage of a traditional timber examination process, called ‚Kidori‚, in which observations and findings are marked on the timber surface to provide hints for the subsequent cutting process. This paper aims to recreate the procedures using an industrial robotic arm, computer vision, and a human worker. A digital twin model of the timber is created with a depth camera serving as a base map to exchange information and receive instruction from the human worker. The margin of a discrepancy between the original processing location and the location of the actual end effector, where the tools are, is minimised in this system.
keywords 3D scanning, computer vision, traditional technique, phycology, machine learning, SDG 9
series CAADRIA
email
last changed 2022/07/22 07:34

_id caadria2022_114
id caadria2022_114
authors Dong, Zhiyong, Lin, Jinru, Wang, Siqi, Xu, Yijia, Xu, Jiaqi and Liu, Xiao
year 2022
title Where Will Romance Occur, A New Prediction Method of Urban Love Map through Deep Learning
source Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 213-222
doi https://doi.org/10.52842/conf.caadria.2022.1.213
summary Romance awakens fond memories of the city. Finding out the relationship between romantic scene and urban morphology, and providing a prediction, can potentially facilitate the better urban design and urban life. Taking the Yangtze River Delta region of China as an example, this study aims to predict the distribution of romantic locations using deep learning based on multi-source data. Specifically, we use web crawlers to extract romance-related messages and geographic locations from social media platforms, and visualize them as romance heatmap. The urban environment and building features associated with romantic information are identified by Pearson correlation analysis and annotated in the city map. Then, both city labelled maps and romance heatmaps are fed into a Generative Adversarial Networks (GAN) as the training dataset to achieve final romance distribution predictions across regions for other cities. The ideal prediction results highlight the ability of deep learning techniques to quantify experience-based decision-making strategies that can be used in further research on urban design.
keywords Romance Heatmap, Generative Adversarial Networks, Deep Learning, Big Data Analysis, Correlation Analysis, SDG 11
series CAADRIA
email
last changed 2022/07/22 07:34

_id sigradi2022_35
id sigradi2022_35
authors Tu, Han
year 2022
title Eyes on the Street: Assessing Window-to-Wall Ratios in Google Street Views using Machine Learning
source Herrera, PC, Dreifuss-Serrano, C, Gómez, P, Arris-Calderon, LF, Critical Appropriations - Proceedings of the XXVI Conference of the Iberoamerican Society of Digital Graphics (SIGraDi 2022), Universidad Peruana de Ciencias Aplicadas, Lima, 7-11 November 2022 , pp. 175–186
summary Windows play an important role in ‘Eyes on the Street’ in Jane Jacobs’ theory. However, vital street-level parameters in her theory, most notably windows, are rarely assessed at the urban scale due to imprecise existing datasets. To resolve this challenge, this study proposes an automated computer vision-based methodology to extract the window-to-wall ratios (WWRs) of buildings in the Bronx, New York, using semantic segmentation machine learning. This study brings together machine learning and Google Street View (GSV) to accurately assess WWRs at the urban scale. The WWR distribution results show that street-level WWRs help to analyze with other urban data, with controlled parameters, such as land use and building age. Our WWR assessment can be universally applied to other cities using geotagged street view imagery of GSV. This study can help provide a reference for precise future urban design and management assessments.
keywords Machine Learning, Data Analytics, Google Street View (GSV), Visual quality, Window-to-wall ratio
series SIGraDi
email
last changed 2023/05/16 16:55

_id ecaade2022_158
id ecaade2022_158
authors Zhao, Xingjian, Wang, Tsung-Hsien and Peng, Chengzhi
year 2022
title Automatic Room Type Classification using Machine Learning for Two-Dimensional Residential Building Plans
source Pak, B, Wurzer, G and Stouffs, R (eds.), Co-creating the Future: Inclusion in and through Design - Proceedings of the 40th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2022) - Volume 2, Ghent, 13-16 September 2022, pp. 593–600
doi https://doi.org/10.52842/conf.ecaade.2022.2.593
summary Building plan semantic retrieval is of interest in every stage of construction and facility management processes. A conceptual design model with a space layout can be used for the early building evaluation, such as functional spatial validation, circulation and security checking, cost estimation, and preliminary energy consumption simulation. With the development of information technology, existing machine learning methods applied to semantic segmentation of building plan images have successfully identified building elements such as doors, windows, and walls. However, for the higher level of room type/function recognition, the prediction accuracy is low when building plans do not contain sufficient details such as furniture. In this paper, we present a workflow and a predictive model for residential room type classification. Given a building plan image, the building elements are first identified, followed by room feature extraction by connectivity and morphological characterization using a rule-based algorithm. The Multi-Layer Perceptron (MLP) is trained with the feature set and then predicts the room type of test samples. We collected 1,586 residential room samples from 165 building layout plans and categorized rooms into nine types. Finally, our current model can achieve a classification accuracy of 0.82.
keywords Floor Plan Semantic Retrieval, Room Type Classification, Machine Learning
series eCAADe
email
last changed 2024/04/22 07:10

_id ecaade2022_399
id ecaade2022_399
authors Johanes, Mikhael and Huang, Jeffrey
year 2022
title Deep Learning Spatial Signature - Inverted GANs for Isovist representation in architectural floorplan
source Pak, B, Wurzer, G and Stouffs, R (eds.), Co-creating the Future: Inclusion in and through Design - Proceedings of the 40th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2022) - Volume 2, Ghent, 13-16 September 2022, pp. 621–629
doi https://doi.org/10.52842/conf.ecaade.2022.2.621
summary The advances of Generative Adversarial Networks (GANs) have provided a new experimental ground for creative architecture processes. However, the analytical potential of the latent representation of GANs is yet to be explored for architectural spatial analysis. Furthermore, most research on GANs for floorplan learning in architecture uses images as its main representation medium. This paper presents an experimental framework that uses one-dimensional periodic isovist samples and GANs inversion to recover its latent representation. Access to GANs’ latent space will open up a possibility for discriminative tasks such as classification and clustering analysis. The resulting latent representation will be investigated to discover its analytical capacity in extracting isovist spatial patterns from thousands of floorplans data. In this experiment, we hypothetically conclude that the spatial signature of the architectural floor plan could be derived from the degree of regularity of isovist samples in the latent space structure. The finding of this research will enable a new data-driven strategy to measure spatial quality using isovist and provide a new way for indexing architectural floorplan.
keywords Machine Learning, Isovist, Latent Representation, GANs Inversion, Spatial Signature
series eCAADe
email
last changed 2024/04/22 07:10

_id caadria2022_279
id caadria2022_279
authors Kim, Dongyun, Guida, George and Garcia del Castillo y Lopez, Jose Luis
year 2022
title PlacemakingAI : Participatory Urban Design with Generative Adversarial Networks
source Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 485-494
doi https://doi.org/10.52842/conf.caadria.2022.2.485
summary Machine Learning (ML) is increasingly present within the architectural discipline, expanding the current possibilities of procedural computer-aided design processes. Practical 2D design applications used within concept design stages are however limited by the thresholds of entry, output image fidelity, and designer agency. This research proposes to challenge these limitations within the context of urban planning and make the design processes accessible and collaborative for all urban stakeholders. We present PlacemakingAI, a design tool made to envision sustainable urban spaces. By converging supervised and unsupervised Generative Adversarial Networks (GANs) with a real-time user interface, the decision-making process of planning future urban spaces can be facilitated. Several metrics of walkability can be extracted from curated Google Street View (GSV) datasets when overlayed on existing street images. The contribution of this framework is a shift away from traditional design and visualization processes, towards a model where multiple design solutions can be rapidly visualized as synthetic images and iteratively manipulated by users. In this paper, we discuss the convergence of both a generative image methodology and this real-time urban prototyping and visualization tool, ultimately fostering engagement within the urban design process for citizens, designers, and stakeholders alike.
keywords Machine Learning, Generative Adversarial Networks, user interface, real-time, walkability, SDG 11
series CAADRIA
email
last changed 2022/07/22 07:34

_id ecaade2022_75
id ecaade2022_75
authors Sardenberg, Victor and Becker, Mirco
year 2022
title Computational Quantitative Aesthetics Evaluation - Evaluating architectural images using computer vision, machine learning and social media
source Pak, B, Wurzer, G and Stouffs, R (eds.), Co-creating the Future: Inclusion in and through Design - Proceedings of the 40th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2022) - Volume 2, Ghent, 13-16 September 2022, pp. 567–574
doi https://doi.org/10.52842/conf.ecaade.2022.2.567
summary This paper correlates two methods of aesthetic evaluation of architectural images utilising computer vision (CV) and machine learning (ML) for automating aesthetic evaluation: Calibrated aesthetic measure (CalAM) and aesthetic scoring model (ASM). From a database of images of proposals for a single location, users are invited to like or dislike it on social media to feed an ML model and calibrate an aesthetic measure formula (AMF). A possible application is to assist designers in making decisions according to the hedonic response given by users previously, enabling a faster way of popular participation.
keywords Quantitative Aesthetics, Crowdsourcing, Aesthetic Measure, Computer Vision, Machine Learning, Social Media
series eCAADe
email
last changed 2024/04/22 07:10

For more results click below:

this is page 0show page 1show page 2show page 3show page 4show page 5... show page 26HOMELOGIN (you are user _anon_809667 from group guest) CUMINCAD Papers Powered by SciX Open Publishing Services 1.002