| dc.description.abstract | Urban green spaces provide numerous benefits, including augmenting the aesthetic appeal of urban landscapes and improving mental wellbeing. While diverse methods have been used to evaluate greenery, the assessment of green visibility using street-view level images is frequently recommended due to its greater compatibility with human perception. Although many existing studies predominantly rely on Google Street View (GSV) data, the usage restrictions and lack of alignment with FAIR (Findability, Accessibility, Interoperability and Reusability) principles presents challenges. Therefore, the incorporation of Volunteered Street View Imagery (VSVI) platforms, such as Mapillary, is emerging as a promising alternative. This research presents a scalable and reproducible framework for assessing the Green View Index (GVI) using Mapillary data in diverse global urban contexts. By documenting a step-by-step procedure encompassing data acquisition, image segmentation, and GVI calculation, this study ensures the accuracy and consistency of future analyses. To address the research questions, the study examines the variations in image availability and usability of Mapillary data for green view assessments across different cities worldwide. The findings reveal significant disparities in open-source image availability, highlighting cities with high image availability in the USA and Europe, as well as cities with limited availability located in Africa and South Asia. Furthermore, the study evaluates the suitability of using Normalised Difference Vegetation Index (NDVI) values to fill in missing data points in GVI assessments. The analysis demonstrates that the NDVI can effectively calibrate a Linear Regression model to estimate GVI values, even in regions where street-view imagery is limited. Additionally, the analysis reveals notable disparities in GVI across cities, particularly in high-density, lower-income cities in Africa and South Asia compared to low-density, high-income cities in the USA and Europe. | |
| dc.subject | Urban green spaces provide various benefits, but assessing their visibility is challenging. Traditional methods and Google Street View have limitations, therefore integrating Volunteered Street View Imagery platforms has been proposed. Mapillary offers open data and a large community of contributors, but it has its own limitations in terms of data quality and coverage. However, for areas with insufficient street image data, Normalised Difference Vegetation Index can be used as an alternative. | |
