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 33

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

_id	ecaade2017_041
id	ecaade2017_041
authors	Fukuda, Tomohiro, Kuwamuro, Yasuyuki and Yabuki, Nobuyoshi
year	2017
title	Optical Integrity of Diminished Reality Using Deep Learning
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 1, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 241-250
doi	https://doi.org/10.52842/conf.ecaade.2017.1.241
summary	A new method is proposed to improve diminished reality (DR) simulations to allow the demolition and removal of entire buildings in large-scale spaces. Our research goal was to obtain optical integrity by using a scientific and reliable simulation approach. Further, we tackled presumption of the texture of the background sky by applying deep learning. Our approach extracted the background sky using information from the actual sky obtained from a photographed image. This method comprised two steps: (1) detection of the sky area from the image through image segmentation and (2) creation of an image of the sky through image inpainting. The deep convolutional neural networks developed by us to train and predict images were evaluated to be feasible and effective.
keywords	Diminished Reality; Optical Integrity; Deep Learning; Augmented Reality; Landscape assessment
series	eCAADe
email
last changed	2022/06/07 07:50

_id	ecaade2017_202
id	ecaade2017_202
authors	Sollazzo, Aldo, Trento, Armando and Baseta, Efilena
year	2017
title	Machinic Agency - Implementing aerial robotics and machine learning to map public space
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 2, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 611-618
doi	https://doi.org/10.52842/conf.ecaade.2017.2.611
summary	The research presented in this paper is focused on proposing a new digital workflow, involving unmanned aerial vehicles (UAV) and machines learning systems, in order to detect and map citizen's behaviors in the context of public spaces.Novel machinic abilities can be implemented in the understanding of the human context, decoding, through computer visions and machine learning, complex systems into intelligible outputs (Olson, 2008), mapping the relationships of our reality. In this framework, robotic and computational strategies can be implemented in order to offer a new description of public spaces, bringing to light the hidden forces and multiple layers constituting the urban habitat. The presented study focuses on the development of a methodology turning video frames collected from cameras installed on drones into large datasets used to train convolutional networks and enable machines learning systems to detect and map pedestrians in public spaces.
keywords	mapping; drones; machine learning; computer vision; city
series	eCAADe
email
last changed	2022/06/07 07:56

_id	ecaade2017_069
id	ecaade2017_069
authors	D'Uva, Domenico
year	2017
title	Unfolding the design of architecture as a strategy to assess intellectual property - Bridle pirating architecture
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 1, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 297-302
doi	https://doi.org/10.52842/conf.ecaade.2017.1.297
summary	Modeling tools are evolving the process of architectural design from the use ordinary digital tool into a role of creator of complex shapes, through coding configurations. These procedures are becoming the structural ground of the architectural shape, going beyond their sole tools role. The increasing in importance of such codes implies a major level of awareness for their use, which is worth of a deeper analysis. The system of relations among parts in an architectural design picks a single configuration among infinite others, because it is produced by a design process which find its fulfillment in the final portray. Through the spreading of digital design tools, such final configuration becomes a step in a clearly reproducible process. The project is achieved through a series of starting conditions, which undergo a parametric process, that produces the final result. An identical parametric process can be applied under slightly different starting conditions and produce completely different results. These results are connected with the code which produced them, but is the authorship still property of the original author?
keywords	Morphogenesis; Parametric; Authorship
series	eCAADe
email
last changed	2022/06/07 07:56

_id	ecaade2017_214
id	ecaade2017_214
authors	Donato, Vincenzo, Giannetti, Stefano and Bocconcino, Maurizio Marco
year	2017
title	H-BIM and web-database to deal with the loss of information due to catastrophic events - The digital reconstruction of San Salvatore's Church in Campi di Norcia (Italy)
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 1, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 119-128
doi	https://doi.org/10.52842/conf.ecaade.2017.1.119
summary	Nowadays , we are able to produce geometric models of historical buildings at different scales of detail, using photos and measurements. This is true when you are observing something that is still under your eyes. We are faced more and more with lack of preservation actions and maintenance activities, policies framed without foresight, unexpected natural events, etc., that are forcing professionals and researchers to operate without usual data. In such cases, we need a consistent repository to collect and distribute data to produce information.Furthermore, we need to "give intelligence" to these repositories, in order to query them with respect to geometrical instances, topological issues, historical features, etc. This last aspect, (archives and databases connected with geometrical aspects), lead our digital model to a new dimension, the informative one (where spatial, temporal, historical and building parameters work together), that should always characterize speculative actions towards the constitution of a wealth of knowledge. We need to work on the efficiency of the process to reach effective methodologies of survey.
keywords	cultural heritage; Structure from Motion (SfM); loss information; H-BIM; web-database
series	eCAADe
email
last changed	2022/06/07 07:55

_id	caadria2017_118
id	caadria2017_118
authors	Kocabay, Serkan and Alaçam, Sema
year	2017
title	A Multi-Objective Genetic Algorithm Framework for Earlier Phases of Architectural Design - A Case Study
source	P. Janssen, P. Loh, A. Raonic, M. A. Schnabel (eds.), Protocols, Flows, and Glitches - Proceedings of the 22nd CAADRIA Conference, Xi'an Jiaotong-Liverpool University, Suzhou, China, 5-8 April 2017, pp. 293-302
doi	https://doi.org/10.52842/conf.caadria.2017.293
summary	This paper presents an algorithmic framework proposal for implementation of a multi-objective genetic algorithm (MOGA) in architectural design process. Different than the previous studies, we introduce a dynamic and extendible modular framework for multiple objectives. The objective modules with different fitness functions are connected simultaneously in the Rhino/Octopus interface, after multiplication with a constant value or a variable. In this study, we discuss the potentials and limitations of MOGA in 3D form generation, implications of MOGA in a case study and the qualitative and quantitative changes in relation to the change of constant value/ the impact ratio of competing objectives. The outcomes of the case study are investigated based on its potentiality in providing feedback in the earlier phases of decision processes in design.
keywords	multi-objective; genetic algorithm; architectural design process; case study
series	CAADRIA
email
last changed	2022/06/07 07:51

_id	ecaade2017_067
id	ecaade2017_067
authors	Liu, Chenjun, Wang, Tsung-Hsien, Meagher, Mark and Peng, Chengzhi
year	2017
title	Feather-inspired social media data processing for generating developable surfaces: Prototyping an affective architecture - Prototyping an affective architecture
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 1, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 181-190
doi	https://doi.org/10.52842/conf.ecaade.2017.1.181
summary	This paper presents the development of an interactive installation intended as a prototype of experimental affective architecture connected with social media data processing. Social moods and emotions are now spread more widely and faster than ever before due to pervasive uses of social media platforms. We explore how data processing of users' expressions and sharing of moods/emotions through social media can become a source of influences on shaping the form and behaviour of interactive architecture. The interactive prototyping method includes (1) a feather-inspired data-to-shape rule system together with the ShapeOp Library for generating strips as developable surfaces, (2) a physical computing platform built with Arduino micro-processor and shape memory alloy springs for actuation, and (3) physical model-making. As a prototype of social media aware affective architecture, an interactive installation design is proposed for a campus space where the actuation of the strip installation is linked to data processing of Twitter messages collated from users on campus. We reflect on the prototyping methodology and the implications of an architecture affected by people's expression of moods/emotions through social media.
keywords	social media data processing; developable surfaces; interactive prototyping; shape memory alloy; elastic morphing; ShapeOp
series	eCAADe
email
last changed	2022/06/07 07:59

_id	acadia17_000
id	acadia17_000
authors	Nagakura, Takehiko; Tibbits, Skylar; Iba?ez, Mariana and Mueller, Caitlin (eds.)
year	2017
title	ACADIA 2017: DISCIPLINES & DISRUPTION
source	ACADIA 2017: DISCIPLINES & DISRUPTION [Proceedings of the 37th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-96506-1] Cambridge, MA 2-4 November, 2017), 706 p.
doi	https://doi.org/10.52842/conf.acadia.2017
summary	The Proceedings of the ACADIA 2017 conference contains peer reviewed research papers presented at the 37th annual conference of the Association for Computer Aided Design in Architecture. Disciplines & Disruption initiates a dialog about the state of the discipline of architecture and the impact of technology in shaping or disrupting design, methods and cultural fronts. For the past 30 years, distinctive advancements in technologies have delivered unprecedented possibilities to architects and enabled new expressions, performance, materials, fabrication and construction processes. Simultaneously, digital technology has permeated the social fabric around architecture with broad influences ranging from digital preservation to design with the developing world. Driven by technological, data and material advances, architecture now witnesses the moment of disruption, whereby formerly distinct areas of operation become increasingly connected and accessible to architecture's sphere of concerns in ways never before possible. Distinctions between design and making, building and urban scale, architecture and engineering, real and virtual, on site and remote, physical and digital data, professionals and crowds, are diminishing as technology increases the designer's reach far beyond the confines of the drafting board. This conference provides a platform to investigate the shifting landscape of the discipline today, and to help define and navigate the future.
keywords	Computer Aided Design, ACADIA, ACADIA 2017, ACADIA Conference, Architecture
series	ACADIA
email
last changed	2022/06/07 07:49

_id	acadia17_446
id	acadia17_446
authors	Nejur, Andrei; Steinfeld, Kyle
year	2017
title	Ivy: Progress in Developing Practical Applications for a Weighted-Mesh Representation for Use in Generative Architectural Design
source	ACADIA 2017: DISCIPLINES & DISRUPTION [Proceedings of the 37th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-96506-1] Cambridge, MA 2-4 November, 2017), pp. 446- 455
doi	https://doi.org/10.52842/conf.acadia.2017.446
summary	This paper presents progress in the development of practical applications for graph representations of meshes for a variety of problems relevant to generative architectural design (GAD). In previous work (Nejur and Steinfeld 2016), the authors demonstrated that while approaches to marrying mesh and graph representations drawn from computer graphics (CG) can be effective within the domains of applications for which they have been developed, they have not adequately addressed wider classes of problems in GAD. There, the authors asserted that a generalized framework for working with graph representations of meshes can effectively bring recent advances in mesh segmentation to bear on GAD problems, a utility demonstrated through the development of a plug-in for the visual programming environment Grasshopper. Here, we describe a number of implemented solutions to mesh segmentation and transformation problems, articulated as a series of additional features developed as a part of this same software. Included are problems of mesh segmentation approached through the creation of acyclic connected graphs (trees); problems of mesh transformations, such as those that unfold a segmented mesh in anticipation of fabrication; and problems of geometry generation in relation to a segmented mesh, as demonstrated through a generalized approach to mesh weaving. We present these features in the context of their potential applications in GAD and provide a limited set of examples for their use.
keywords	design methods; information processing
series	ACADIA
email
last changed	2022/06/07 07:58

_id	ecaade2017_138
id	ecaade2017_138
authors	Nerla, Maria Giuditta, Erioli, Alessio and Garai, Massimo
year	2017
title	Modulated corrugations by differential growth - Integrated FRP tectonics towards a new approach to sustainability, fusing architectural and energy design for a new students’ space
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 2, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 593-602
doi	https://doi.org/10.52842/conf.ecaade.2017.2.593
summary	This Master Thesis research investigates the concept of 'integrated tectonics' as a new way of thinking sustainability in architecture, intended as an ecology of different, integrated factors which take part in a seamless design-to-fabrication process. In particular, this new paradigm is applied to the design of a pavilion made of a fiber-reinforced (FRP) sandwich shell integrating multiple systems and performances. A differential growth algorithm mimicking cellular tissue development modulates performance across the surface through ornamental features in the form of corrugated patterns. Iterative feedback simulations allow the exploration of the mutual relations connecting morphogenesis and performance distribution patterns at the architectural scale. Problems connected to simulation inaccuracies and difficult software integration are discussed. A 1:2 scale prototype of a shell portion was fabricated to test material properties and production feasibility.
keywords	Fiber-reinforced polymers (FRP); integrated tectonics; differential growth; composite materials; ecology; sustainability
series	eCAADe
email
last changed	2022/06/07 07:58

_id	sigradi2017_091
id	sigradi2017_091
authors	Palavecino, Luisina; Gustavo Porta
year	2017
title	Narrativas transmedia aplicadas al diseño para la educación [Transmedia storytelling applied to design for education]
source	SIGraDi 2017 [Proceedings of the 21th Conference of the Iberoamerican Society of Digital Graphics - ISBN: 978-956-227-439-5] Chile, Concepción 22 - 24 November 2017, pp.633-639
summary	Nowadays, there is a necessity to close the gaps between the Educational System and the social-technical context in which students are immersed and give the opportunity to receive an education that takes into account their different preferences and interests. This research introduces the transmedia storytelling as an innovative resource so as to motivate significant learning which is connected with the new media production and knowledge distribution, bearing in mind the diversity of students` profiles.
series	SIGRADI
email
last changed	2021/03/28 19:59

_id	ecaade2017_143
id	ecaade2017_143
authors	Pizzigoni, Attilio, Paris, Vittorio, Micheletti, Andrea and Ruscica, Giuseppe
year	2017
title	Advanced tools and algorithms for parametric landscape urbanism
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 1, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 461-470
doi	https://doi.org/10.52842/conf.ecaade.2017.1.461
summary	In the last decades, urban design has been influenced by its relationship with landscape. This has led to a new approach formalised and called Landscape Urbanism. Defining specific reading and analysis instruments together with proper design methods, capable of a transdisciplinary dialogue with geography, plant and biological world's languages, landscape urbanism can undoubtedly obtain more performing purposes than the ones achieved by traditional urban planning. Moreover, new digital tools are appearing, providing urbanism with new instruments for an advanced and interactive way to design cities in close relationship with landscape. The process starts with the acquisition of large quantity of data, like georeferenced maps in conjunction with relevant information about the territory, such as traffic and atmospheric pollution data, important buildings and monuments or significant landscape elements (rivers, mountains, etc.). All this information is combined onto multiple layers in order to be used by different design algorithms, connected by multi-dimensional arrays, whose reciprocal relations are dynamically controlled by architects and engineers. We will present here the case study of an ecological and regenerative infrastructure for the city of Bergamo designed on the basis of these principles, using a convenient combination of parametric tools.
keywords	algorithmic city planning; landscape urbanism; post-urban architecture
series	eCAADe
email
last changed	2022/06/07 08:00

_id	acadia17_502
id	acadia17_502
authors	Rosenwasser, David; Mantell, Sonya; Sabin, Jenny
year	2017
title	Clay Non-Wovens: Robotic Fabrication and Digital Ceramics
source	ACADIA 2017: DISCIPLINES & DISRUPTION [Proceedings of the 37th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-96506-1] Cambridge, MA 2-4 November, 2017), pp. 502- 511
doi	https://doi.org/10.52842/conf.acadia.2017.502
summary	Clay Non-Wovens develops a new approach for robotic fabrication, applying traditional craft methods and materials to a fundamentally technical and precise fabrication methodology. This paper includes new explorations in robotic fabrication, additive manufacturing, complex patterning, and techniques bound in the arts and crafts. Clay Non-Wovens seeks to develop a system of porous cladding panels that negotiate circumstances of natural daylighting through parameters dealing with textile (woven and non-woven) patterning and line typologies. While additive manufacturing has been built predominantly on the basis of extrusion, technological developments in the field of 3D printing seldom acknowledge the bead or line of such extrusions as more than a nuisance. Blurring of recognizable layers is often seen as progress, but it does away with visible traces of a fabrication process. Historically, however, construction methods in architecture and the building industry have celebrated traces of making ranging from stone cutting to log construction. With growing interest in digital craft within the fields of architecture and design, we seek to reconcile our relationship with the extruded bead and reinterpret it as a fiber and three-dimensional drawing tool. The traditional clay coil is to be reconsidered as a structural fiber rather than a tool for solid construction. Building upon this body of robotically fabricated clay structures required the development of three distinct but connected techniques: 1. construction of a simple end effector for extrusion; 2. development of a clay body and; 3. using computational design tools to develop formwork and toolpath geometries.
keywords	design methods; information processing; fabrication; digital craft; manual craft; prototyping
series	ACADIA
email
last changed	2022/06/07 07:56

_id	acadia17_544
id	acadia17_544
authors	Schleicher, Simon; La Magna, Riccardo; Zabel, Joshua
year	2017
title	Bending-active Sandwich Shells: Studio One Research Pavilion 2017
source	ACADIA 2017: DISCIPLINES & DISRUPTION [Proceedings of the 37th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-96506-1] Cambridge, MA 2-4 November, 2017), pp. 544- 551
doi	https://doi.org/10.52842/conf.acadia.2017.544
summary	The goal of this paper is to advance the research on bending-active structures by investigating the system’s inherent structural characteristics and introducing an alternative approach to their design and fabrication. With this project, the authors propose the use of sandwich-structured composites to improve the load-bearing behavior of bending-active shells. By combining digital form-finding and form-conversion processes, it becomes possible to discretize a double-curved shell geometry into an assembly of single-curved sandwich strips. Due to the clever use of bending in the construction process, these strips can be made out of inexpensive and flat sheet materials. The assembly itself takes advantage of two fundamentally different structural states. When handled individually, the thin panels are characterized by their high flexibility, yet when cross-connected to a sandwich, they gain bending stiffness and increase the structure’s rigidity. To explain the possible impacts of this approach, the paper will discuss the advantages and disadvantages of bending-active structures in general and outline the potential of sandwich shells in particular. Furthermore, the authors will address the fundamental question of how to build a load-bearing system from flexible parts by using the practical example of the Studio One Research Pavilion. To illustrate this project in more detail, the authors will present the digital design process involved as well as demonstrate the technical feasibility of this approach through a built prototype in full scale. Finally, the authors will conclude with a critical discussion of the design approach proposed here and point out interesting topics for future research.
keywords	material and construction
series	ACADIA
email
last changed	2022/06/07 07:57

_id	acadia17_582
id	acadia17_582
authors	Staback, Danniely; Nguy?n, M?Dung; Addison, James; Angles, Zachary; Karsan, Zain; Tibbits, Skylar
year	2017
title	Aerial Pop-Up Structures
source	ACADIA 2017: DISCIPLINES & DISRUPTION [Proceedings of the 37th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-96506-1] Cambridge, MA 2-4 November, 2017), pp. 582- 589
doi	https://doi.org/10.52842/conf.acadia.2017.582
summary	Research into self-assembly systems has been growing in recent years, focusing on the design and engineering of materials to react to environmental factors, which trigger a chain of reactions promoting the components to build themselves. This paper attempts to expand this field with the design and testing of a full-scale structure that could be dropped high above the ground, self-assemble in the air in a matter of seconds, and form an inhabitable space on the ground. This system uses spline-based fiberglass rods, folded in specific configurations and connected with parachute surfaces as the main material system, enabling the global aerial performance. A series of drop tests were conducted from a 100? crane to investigate the unfolding sequence, the release mechanisms, and the parachute configurations, leading to its successful aerial assembly.
keywords	paper material and construction; physics; smart materials; smart assembly; construction; form finding
series	ACADIA
email
last changed	2022/06/07 07:56

_id	ecaade2017_033
id	ecaade2017_033
authors	Yan, Wei
year	2017
title	WP-BIM: Web-based Parametric BIM Towards Online Collaborative Design and Optimization
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 2, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 527-534
doi	https://doi.org/10.52842/conf.ecaade.2017.2.527
summary	We present initial experiments of Web-based Parametric Building Information Modeling (WP-BIM) towards collaborative design, modeling, simulation, and optimization. A new framework that integrates Web-based information technology (WebGL graphics, networking, and Web browsers), and design computing technology (visual programming) into parametric BIM is prototyped for the experiments. The integration of Web technology is going to enable online collaborative and user participatory design. Connected through the Web platform, a BIM model, visual programming-based user interfaces for parametric changes, and an optimization algorithm, which may reside in different servers or local computers in different geographical locations, have the potential to be integrated and working together to resolve design optimization problems, especially if combined with cloud-based performance simulation tools. After future development, this may allow architects, engineers, clients, etc. to collaboratively work on a project with up-to-date building data and different design and simulation tools.
keywords	Web-based; Parametric Modeling; BIM; Collaborative Design; Optimization
series	eCAADe
email
last changed	2022/06/07 07:57

_id	ecaade2017_294
id	ecaade2017_294
authors	Zreik, Khaldoun and Bouhai, Nasreddine
year	2017
title	Post-Digital Design - The Hyperheritage project
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 2, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 49-54
doi	https://doi.org/10.52842/conf.ecaade.2017.2.049
summary	The cultural heritage domain, as many other domains, is invited to experience new "designs" in harmony with new development and consuming approaches. It should accept to deal with under continuous design objects & information on the first hand and the fact that every information consumer could become, somewhere and/or sometime, information broadcaster, on the other hand. In this paper we present some exploratory projects newly realized within the workshop "HyperHeritage" (Augmented Cultural Heritage) of the Master Program Net. This workshop, which is animated by three staff members of the department of digital humanities, invites 15 master program students to rethink the cultural heritage objects and information by considering the potential uses of information and communication technologies and their socio-cultural impacts. By the following, we intend to present four projects on "HyperHeritage" resulting from this collaborative approach. The suggested prototypes have considered advanced digital technologies, mainly the Internet of Things and the Contact-Less Communication, to experience new form and strategies of mediation and communication of the cultural heritage.Please write your abstract here by clicking this paragraph.
keywords	Augmented Cultural Heritage; Collaborative Design; Connected Objects; Contact-Less Communication; HyperHeritage; Internet of Things
series	eCAADe
email
last changed	2022/06/07 07:57

_id	acadia17_474
id	acadia17_474
authors	Peng, Wenzhe; Zhang, Fan; Nagakura, Takehiko
year	2017
title	Machines’ Perception of Space: Employing 3D Isovist Methods and a Convolutional Neural Network in Architectural Space Classification
source	ACADIA 2017: DISCIPLINES & DISRUPTION [Proceedings of the 37th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-96506-1] Cambridge, MA 2-4 November, 2017), pp. 474- 481
doi	https://doi.org/10.52842/conf.acadia.2017.474
summary	Simple and common architectural elements can be combined to create complex spaces. Different spatial compositions of elements define different spatial boundaries, and each produces a unique local spatial experience to observers inside the space. Therefore an architectural style brings about a distinct spatial experience. While multiple representation methods are practiced in the field of architecture, there lacks a compelling way to capture and identify spatial experiences. Describing an observer’s spatial experiences quantitatively and efficiently is a challenge. In this paper, we propose a method that employs 3D isovist methods and a convolutional neural network (CNN) to achieve recognition of local spatial compositions. The case studies conducted validate that this methodology works well in capturing and identifying local spatial conditions, illustrates the pattern and frequency of their appearance in designs, and indicates peculiar spatial experiences embedded in an architectural style. The case study used small designs by Mies van der Rohe and Aldo van Eyck. The contribution of this paper is threefold. First, it introduces a sampling method based on 3D Isovist that generates a 2D image that can be used to represent a 3D space from a specific observation point. Second, it employs a CNN model to extract features from the sampled images, then classifies their corresponding space. Third, it demonstrates a few case studies where this space classification method is applied to different architectural styles.
keywords	design methods; information processing; AI; machine learning; computer vision; representation
series	ACADIA
email
last changed	2022/06/07 08:00

_id	ecaade2017_009
id	ecaade2017_009
authors	Takizawa, Atsushi and Furuta, Airi
year	2017
title	3D Spatial Analysis Method with First-Person Viewpoint by Deep Convolutional Neural Network with Omnidirectional RGB and Depth Images
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 2, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 693-702
doi	https://doi.org/10.52842/conf.ecaade.2017.2.693
summary	The fields of architecture and urban planning widely apply spatial analysis based on images. However, many features can influence the spatial conditions, not all of which can be explicitly defined. In this research, we propose a new deep learning framework for extracting spatial features without explicitly specifying them and use these features for spatial analysis and prediction. As a first step, we establish a deep convolution neural network (DCNN) learning problem with omnidirectional images that include depth images as well as ordinary RGB images. We then use these images as explanatory variables in a game engine to predict a subjects' preference regarding a virtual urban space. DCNNs learn the relationship between the evaluation result and the omnidirectional camera images and we confirm the prediction accuracy of the verification data.
keywords	Space evaluation; deep convolutional neural network; omnidirectional image; depth image; Unity; virtual reality
series	eCAADe
email
last changed	2022/06/07 07:56

_id	ecaade2017_101
id	ecaade2017_101
authors	Ayoub, Mohammed and Wissa, Magdi
year	2017
title	Daylight Optimization - A Parametric Study of Urban Façades Design within Hybrid Settlements in Hot-Desert Climate
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 2, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 193-202
doi	https://doi.org/10.52842/conf.ecaade.2017.2.193
summary	Unprecedented growth of hybrid settlements causes deterioration to the indoor environmental quality. Due to their narrow street-networks and fully packed urban fabric, lower floors are subjected to severe overshadow condition, which has adverse effects on the health of the inhabitants. This paper aims to investigate techniques to mitigate the under-lit indoor environment for a group of buildings with variable heights and orientations, with regard to the urban façades parameters. It reflects an intervention in an existing hybrid settlements, within hot-desert climate, to alter façades configurations for daylight optimization, and ultimately recover the lost indoor quality of users in such contexts.
keywords	Daylight Optimization; Urban Façade; Simulation; Hybrid Settlements ; Parametric Design
series	eCAADe
email
last changed	2022/06/07 07:54

_id	acadia17_164
id	acadia17_164
authors	Brugnaro, Giulio; Hanna, Sean
year	2017
title	Adaptive Robotic Training Methods for Subtractive Manufacturing
source	ACADIA 2017: DISCIPLINES & DISRUPTION [Proceedings of the 37th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-96506-1] Cambridge, MA 2-4 November, 2017), pp. 164-169
doi	https://doi.org/10.52842/conf.acadia.2017.164
summary	This paper presents the initial developments of a method to train an adaptive robotic system for subtractive manufacturing with timber, based on sensor feedback, machine-learning procedures and material explorations. The methods were evaluated in a series of tests where the trained networks were successfully used to predict fabrication parameters for simple cutting operations with chisels and gouges. The results suggest potential benefits for non-standard fabrication methods and a more effective use of material affordances.
keywords	design methods; information processing; construction; robotics; ai & machine learning; digital craft; manual craft
series	ACADIA
email
last changed	2022/06/07 07:52

For more results click below: