Deep learning in urban green space extraction in remote sensing: a comprehensive systematic review

• DOI: 10.1080/01431161.2024.2424511
• Publication Date: 2024-11-27T09:24:48Z
• Authors: Yuhong Huang; Lihui Wang; Pengcheng Zhao; Yifan Zhao; Qichi Yang; Yun Du; Feng Ling
• Keywords: Urban Green Space

Urban green spaces play indispensable roles in various aspects, including the urban soil environment, thermal and human environment. Accurately capturing characteristics such as spatial distribution of is essential for effective planning, construction, assessment space, it represents a focal point ecological research. Leveraging its remarkable self-learning capability, deep learning has emerged prominent research direction extracting space features. However, given diverse range methods unique features spaces, next focus will be on how to exploit more effectively apply advantages advance survey spaces. Therefore, this study comprehensively reviews large body relevant literature, categorizing applied extraction into supervised, unsupervised, semi-supervised approaches. It systematically summarizes technical foundations, progress, applicable public datasets field, provides reasoned outlook future directions, aims provide geographers planners with comprehensive scientifically grounded reference.