Prior-knowledge-based single-tree extraction

Abstract

The automatic extraction of single trees from remotely sensed data is approached in numerous studies, but results are still insufficient in areas of dense temperate forest. Common watershed-based algorithms using digital surface models tend to produce erroneous results in difficult constellations because the treetop determination lacks an exact criterion for smoothing. In this article, a new approach is introduced that classifies crown size in advance and uses this information as prior knowledge for single-tree extraction. Crown size is classified from texture with an improved grey-scale granulometry followed by a crown size adapted watershed segmentation of single trees. The method is applied on a large area of 10 km² and verified on six reference plots reflecting diverse and difficult compositions. The accuracy varies between 64% and 88%, and shows an average improvement of about 30% for deciduous and mixed stands compared to a non-crown-size-dependent algorithm.

Acknowledgements

The authors express their gratitude to the German Research Foundation for funding of the project and the aerial prospection. The Warsaw University of Life Science provided the remote sensing data of the Milicz district. Sincere thanks are given to Gyde Lund from Forest Information Services, USA, and James Little from the Cork Constraint Computation Centre at University College Cork, Ireland, for proofreading the manuscript.