Abstract
The urban neighbourhood is one of the most important places for public activities and behaviour spaces in cities, and the quantification of their environments is receiving increasing attention from researchers. In the era of big data, numerous urban data sources, represented by street view images, are documenting the evolution of people's lifestyles in various ways. With the rapid development of image processing technology, street view images have become an emerging data source for urban research. Street view image processing can be used to obtain spatial elements of large scale urban neighborhoods, thus enabling rapid urban neighbourhood evaluation. However, no systematic literature review has been conducted so far on the research of street view images application in urban neighbourhood environment. This paper systematically reviews the research trends of existing publications on the use of street view images for the quantitative analysis of urban neighbourhood environments. The number of publications began to grow rapidly in 2010. From 2010 to 2020, the number of publications increased from 6 to 341, with an annual growth rate of approximately 30.4%. Recent studies have focused on five areas: thermal environment, neighbourhood morphology, environmental perception, socio-economic factors, landscape design and environmental evaluation. The publications use experiment and simulation as the main research methods. Deep learning is the mainstream and advanced image processing method, and the data analysis models include numerical analysis and spatial analysis. Finally, the overall research framework and future research trends of street view images in the current quantitative research of urban streets are obtained.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have