Despite a growing literature on the topic, the association between neighbourhood greenness and body weight is inconsistent. The objective of this research is to examine the association between neighbourhood greenness and residents’ obesity levels in a high population density area. We accounted for three greenness features: green access, green exposure, and View-based Green Index. We used the novel technique of deep convolutional neural network architecture to extract eye-level information from Baidu Street View images to capture the urban vertical greenness level. The research involved a survey with 9,524 respondents from 40 communities in Shanghai. Generally, we found all aspects of horizontal, vertical, and proximity of green levels to be impactful on body weight; however, only the view-based green index consistently had an adverse effect on weight and obesity.
展开▼
