Urban Beauty: Quantifying and Predicting Crowd-sourced Subjective Evaluation using Machine Vision

Online Workshop

Beauty of cityscapes has long been studied anecdotally through accounts of novels and historical notes; and manually through analysis of scale, order, rigidity, etc. This 2-day workshop is designed to be an introduction to the use of machine vision and machine learning to interrogate how urban fabric explicitly affects the perception of beauty, and in the process, address the age-old question of “How to quantify subjective spatial experience?”
Machine vision algorithm (such as semantic segmentation) will be used to quantify urban features (e.g., road, people, trees, vehicles, sky, building, signage, etc.) of photographs of cityscapes. Subsequently, participants will rate the photographs. The corresponding quantification of the urban features and beauty scores will be analysed to extract spatial beauty principles. Finally, using the same dataset, a neural network will be trained to predict the perceived beauty of new cityscapes. Google Colab shall be used for semantic segmentation and training neural network.

Workshop Author: Joy Mondal

WEsearch lab

Author Biography: Joy Mondal leads WEsearch lab which offers design computation consultancy to architecture practices in South-east Asia. His research focuses on automating design workflows and predicting subjective spatial assessment with the use of AI. He has released Grasshopper plugins to automate column-beam placement (Eelish) and to generate Piet Mondrian inspired 3D massing (Chingree). Joy is a TEDx fellow, presenting ways of democratising architecture for everyone by using graph theory and shape grammar to automate residential design generation, thereby making design service more affordable. He has tutored multiple international workshops including at Digital FUTURES, ASCAAD 2021, CAADRIA 2021 and SimAUD 2021.

Workshop Duration: 2×6 hours

6. September (Monday) Morning and Afternoon Session
7. September (Tuesday) Morning and Afternoon Session