Research on Green View Index of Urban Roads Based on Street View Image Recognition: A Case Study of Changsha Downtown Areas

In this paper, we took the urban roads in Changsha downtown areas as an example to identify green view index (GVI) of based on street images (SVIs). First, road network information was obtained through OpenStreetMap, and coordinate sampling points processed using ArcGIS. Secondly, SVIs were downloaded from Baidu Map according latitude longitude coordinates points. Moreover, semantic segmentation neural software used semantically segment for recognizing objects each part images. Finally, related vegetation statistically analyzed obtain GVI The mapped map ArcGIS data visualization analysis. results showed average study area 12.56%. An amount 27% have very poor perception, 40% 19% general 10% strong 4% perception. administrative districts, highest is Yuhua District with 14.15%, while lowest Kaifu 8.75%. new higher than that old area, has building density a lower greenery level. This paper systematically evaluated levels greening status streets within analysis, provided guidance suggestions development City.