Green View Index is a QGIS plugin that can be used to easily calculate Green View Index through Google Street View images.
Calculating the amount of vegetation street level imagery
The Green View Index (GVI) has emerged in the literature of the latest years as an objective measurement of urban green at the street level. Unlike satellite derived NDVI, which provides a mapping of vegetation from the top level, GVI utilizes street-level imagery to quantify the presence of vegetation from a human-eye point of view.
How Green View Image is calculated
Most popularly, Google Street View images are used as input. Very simply put, the GVI for an image is the ratio of vegetation pixels to the total number of pixels of the image.
With the availability of APIs for street level imagery (such as Google Street View, Bing Streetside View or Tencent Maps), it is possible to acquire images at multiple angles to capture a person’s view more realistically. It has generally been established in the literature to use a total of 18 angles (Li et. al., 2015): 6 in the horizontal plane and 3 in the vertical plane.
Therefore, to calculate GVI for a point in space, the GVIs of each individual image from each angle are summed together:
where i and j denote the image acquired at horizontal and vertical angle respectively.
The Green View Index plugin for QGIS performs the three main operations required for Green View Index calculations of a given area. They are organized in three separate scripts:
- Generate Sample Points: Creates random points within an area. Those points can be used as input in the next tools
- Access Google Street View Images: For a point dataset, it accesses street view locations with parameters given by the user (such as field of view, image size and direction angles)
- Calculate Green View Index: For the images accessed by the previous tool, the vegetation pixels are extracted, and the Green View Index of its point is calculated
The plugin requires a registration for Google Street View Static API (instructions can be found here). No charges are made for registration and there are several thousands of requests that can be made each month for free. It also requires installing the libraries scikit-image and gpsphoto through OSGeo4W Shell and pip (pip install gpsphoto & pip install scikit-image).
The Green View Index for QGIS plugin can be accessed through the plugin repository in QGIS (recommended) or the latest version as zip file through the code repository.
Contributions and feedback are welcome.
Li, X., Zhang, C., Li, W., Ricard, R., Meng, Q., & Zhang, W. (2015). Assessing street-level urban greenery using Google Street View and a modified green view index. Urban Forestry & Urban Greening, 14(3), 675-685. https://doi.org/10.1016/j.ufug.2015.06.006
Yang, J., Zhao, L., Mcbride, J., & Gong, P. (2009). Can you see green? Assessing the visibility of urban forests in cities. Landscape and Urban Planning, 91(2), 97-104. https://doi.org/10.1016/j.landurbplan.2008.12.004