A Machine Learning and Computer Vision Study of the Environmental Characteristics of Streetscapes That Affect Pedestrian Satisfaction

Pedestrian-friendly cities are a recent global trend due to the various urbanization problems. Since humans greatly influenced by sight while walking, this study identified physical and visual characteristics of street environment that affect pedestrian satisfaction. In study, vast amounts data were collected analyzed using computer vision techniques. Furthermore, these through machine learning prediction model SHAP algorithm. As result, every feature streetscape, for example, visible area urban design quality, had greater effect on satisfaction than any features. Therefore, build with high satisfaction, perspective pedestrians must be considered, wide sidewalks, fewer lanes, proper arrangement furniture required. conclusion, visually, low enclosure, adequate complexity, large green areas combine create highly satisfying walkway. Through we could suggest an approach from see possibility