2D tree detection in large urban landscapes using aerial LiDAR data

摘要: We present a scalable approach to tree detection in large urban landscapes using aerial LiDAR data. Similar our previous work 2006, current method consists of segmentation followed by classification. However, unlike work, the does not use color information or imagery, and hence is more generally applicable. Also, has been successfully tested on two very datasets, which are many orders magnitude larger than dataset used 2006. Specifically, we North American dataset, containing 125 million returns over 3 km2, European 200 7 km2. For both report precision recall rates 95%.