基于街景和POI数据的街道空间品质评价

Spatial Quality Evaluation of Streets Based on Street View and POI Data

街道空间是居民生活的主要场所之一,其空间品质的优劣程度不仅是城市居民幸福感的体现,也是反映城市形象的重要因素。以渝中区道路为研究对象,利用图像语义分割技术、空间句法及空间连接等方法,分别从街景图像、路网和POI数据中获得绿视率、道路接近度、太阳辐射强度、生活服务便捷度等13个评价指标,基于层次分析法构建包含舒适度、安全性、便捷性和活力度4个感知维度的街道空间品质评价体系。最终分别对整体4个感知维度及道路等级的街道空间品质分布特征进行分析,结果表明渝中区各街道空间品质多样性与差异性并存,且未出现明显的两极分化现象。

Street space is one of the main places where residents live,and its quality is not only a reflection of the happiness of city residents,but also an essential factor that reflecting the urban image.Taking the roads in Yuzhong District as the research object,we used the image semantic segmentation technology,spatial syntax method and spatial connectivity to construct a street space quality evaluation system based on analytic hi-erarchy process(AHP)including four perceptual dimensions of comfort,safety,convenience,and vibrancy,from 13 evaluation indicators such as green view rate,road proximity,solar radiation intensity,and convenience of living services from streetscape images,road network,and POI data respectively.We analyzed the spatial quality of the streets as a whole,the four perceptual dimensions and the road classes.The results show that the spatial quality of streets in the Yuzhong District is diverse and different,but there is no obvious polarization.