Mapillary Street Vegetation Scoring: End-to-End Process

This paper developed and validated a novel framework for quantifying urban street greenery by integrating crowdsourced street-level images with advanced computer vision techniques. This study provides a detailed, human-centered perspective on urban greenery by leveraging 360° images captured by volunteers and applying semantic segmentation using the Mask2Former model. The framework not only quantifies greenery at the street level but also establishes meaningful correlations with national tree coverage data derived from aerial imagery. Key contributions include developing and validating a robust methodology for scoring street-level greenery, demonstrating its alignment with large-scale national tree data, and showcasing its potential to enhance urban environmental analysis. These findings provide valuable insights into the automation of green space accessibility analysis and have significant implications in cities.