Automated detection of Individual trees from MLS point clouds

Maintenance of green space in urban environments is demanded by inhabitants, tourists in many cities. Efficient extraction and modelling of individual trees and tree parameters with high degree of automation eases the maintenance in one way in which Mobile Laser Scanning (MLS) point clouds provides dense information over the urban scenes required for the extraction process. However, 3D point clouds of urban scenes consist of large amounts of data representing numerous objects with significant size variability, complex and incomplete structures, and holes or variable point densities. This hampers to use existing algorithms for the urban tree extraction. This book presents a novel approach for individual tree segmentation and derivation of attributes of urban trees from MLS point clouds. How knowledge about urban trees, especially tree shapes can be utilized is clearly described. The results show that the approach is suitable for the extracting trees correctly from other various urban objects, especially pole-like objects. This book can be recommended to each and every postgraduate student who works with point clouds irrespective to urban object modelling.