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

Abstract

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