Individual tree detection in urban land based on multi-source remote sensing data

Individual tree detection is crucial for ecological analysis in forestry, which plays a key role in effectively constructing land use planning and protecting biodiversity. In this paper, Hartford County, Connecticut, USA, is selected as the research area. Mask-RCNN is used to extract individual trees in the study area, and then the local maximum method is applied for extracting individual trees in high-density areas. The study shows that multi-source remote sensing data can effectively improve the accuracy of individual tree extraction, and a total of 13,274,355 trees are detected in Hartford County. The aim of this study is to provide a more effective method of tree monitoring to help governments prioritize green space management on a super-urban scale.