Open AccessAutomated tree detection from 3D lidar images using image processing and machine learning
Author(s) -
Kenta Itakura,
Fumiki Hosoi
Publication year - 2019
Publication title -
applied optics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.668
H-Index - 197
eISSN - 2155-3165
pISSN - 1559-128X
DOI - 10.1364/ao.58.003807
Subject(s) - lidar , image processing , computer science , optics , computer vision , artificial intelligence , remote sensing , tree (set theory) , digital image processing , atmospheric optics , image (mathematics) , geology , physics , mathematical analysis , mathematics
Trees in 3D images obtained from lidar were automatically extracted in the presence of other objects that were not trees. We proposed a method combining 3D image processing and machine learning techniques for this automatic detection. Consequently, tree detection could be done with 95% accuracy. First, the objects in the 3D images were segmented one by one; then, each of the segmented objects was projected onto 2D images. Finally, the 2D image was classified into "tree" and "not tree" using a one-class support vector machine, and trees in the 3D image were successfully extracted.