In architecture, landscape architecture, and urban design, site planning refers to the organizational process of site layout. A fundamental step for site planning is the design of building layout across the site. This process is hard to automate due to its multi-modal nature: it takes multiple constraints such as street block shape, orientation, program, density, and plantation. The paper proposes a prototypical and extensive framework to generate building footprints as masterplan references for architects, landscape architects, and urban designers by learning from the existing built environment with Artificial Neural Networks. Pix2PixHD Conditional Generative Adversarial Neural Network is used to learn the mapping from a site boundary geometry represented with a pixelized image to that of an image containing building footprint color-coded to various programs. A dataset containing necessary information is collected from open source GIS (Geographic Information System) portals from the city of Boston, wrangled with geospatial analysis libraries in python, trained with the TensorFlow framework. The result is visualized in Rhinoceros and Grasshopper, for generating site plans interactively.
Suggestive Site Planning with Conditional GAN and Urban GIS Data
The International Conference on Computational Design and Robotic Fabrication ; 2020 ; Shanghai, China July 05, 2020 - July 06, 2020
Proceedings of the 2020 DigitalFUTURES ; Kapitel : 10 ; 103-113
2021-01-29
11 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Suggestive Sound Design Based on Virtual Gears
SAE Technical Papers | 2020
|Suggestive lines for cyclists--a case of before and after
Online Contents | 1996
|Passenger data for urban transportation planning
Engineering Index Backfile | 1959
|Online risk-aware conditional planning with qualitative autonomous driving applications
BASE | 2018
|