Assessing streetscape greenery with deep neural network using Google Street View

• Published in: Breeding Science Vol. 72; no. 1; pp. 107 - 114
• Main Authors: Kameoka, Taishin, Uchida, Atsuhiko, Sasaki, Yu, Ise, Takeshi
• Format: Journal Article
• Language: English
• Published: Tokyo Japanese Society of Breeding 01.01.2022; Japan Science and Technology Agency
• Subjects: Artificial neural networks; Automation; chopped picture method; deep learning; GIS; Google Street View; green view index; Image segmentation; Neural networks; Object recognition; Public health; Research Paper; Urban areas; urban greenery
• ISSN: 1344-7610; 1347-3735
• DOI: 10.1270/jsbbs.21073

The importance of greenery in urban areas has traditionally been discussed from ecological and esthetic perspectives, as well as in public health and social science fields. The recent advancements in empirical studies were enabled by the combination of ‘big data’ of streetscapes and automated image recognition. However, the existing methods of automated image recognition for urban greenery have problems such as the confusion of green artificial objects and the excessive cost of model training. To ameliorate the drawbacks of existing methods, this study proposes to apply a patch-based semantic segmentation method for determining the green view index of certain urban areas by using Google Street View imagery and the ‘chopped picture method’. We expect that our method will contribute to expanding the scope of studies on urban greenery in various fields.