Abstract
The assessments on human perception of urban spaces are essential for the management and upkeep of surroundings. A large part of the previous studies is dedicated towards the visual appreciation and judgement of various physical features present in the surroundings. Visual qualities of the environment stimulate feelings of safety, pleasure, and belongingness. Scaling such assessments to cover city boundaries necessitates the assistance of state-of-the-art computer vision techniques. We developed a mobile-based application to collect visual datasets in the form of street-level imagery with the help of volunteers. We further utilised the potential of deep learning-based image analysis techniques in gaining insights into such datasets. In addition, we explained our findings with the help of environment variables which are related to individual satisfaction and wellbeing.
Highlights
IntroductionThe relationship between the existence of low-level environmental features [1,2] (the presence of elements such as colours, trees, grass, built architecture, etc.) and people’s perception of such an environment has not been entirely understood
The relationship between the existence of low-level environmental features [1,2] and people’s perception of such an environment has not been entirely understood
Some of the high-level environmental variables are complexity, familiarity, novelty, coherence, prospect, and refuge [3], which induce the perceptions of safety, Urban Sci. 2018, 2, 78; doi:10.3390/urbansci2030078
Summary
The relationship between the existence of low-level environmental features [1,2] (the presence of elements such as colours, trees, grass, built architecture, etc.) and people’s perception of such an environment has not been entirely understood. It has long been established that the presence of specific elements such as vegetation, in the form of trees and grass, and the presence of water bodies and mountains in the surroundings are more preferred over the human-made elements [2,4,5] Such findings, have not been converted to large-scale urban studies. Preference-based studies usually involved participants who are presented with the stimulus (such as imagery or a video depicting an urban environment), and their responses based on the assessments are recorded. These responses were usually provided in the form of ratings of the environmental variables and descriptors. Some of the high-level environmental variables are complexity, familiarity, novelty, coherence, prospect, and refuge [3], which induce the perceptions of safety, Urban Sci. 2018, 2, 78; doi:10.3390/urbansci2030078 www.mdpi.com/journal/urbansci
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
