Abstract

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.

© 2019 Optical Society of America

Simple and effective tool for estimating tree trunk diameters and tree species classification

Kenta Itakura and Fumiki Hosoi
Appl. Opt. 59(2) 558-563 (2020)

Urban objects classification using Mueller matrix polarimetry and machine learning

Irene Estévez, Filipe Oliveira, Pedro Braga-Fernandes, Miguel Oliveira, Luís Rebouta, and Mikhail I. Vasilevskiy
Opt. Express 30(16) 28385-28400 (2022)

Structure descriptor based on just noticeable difference for texture image classification

Xikui Miao, Wei Zhao, Xiaolong Li, and Xiaoyu Yang
Appl. Opt. 58(24) 6504-6512 (2019)

Moiré–Ronchigram analysis applied in the characterization of aberration surfaces and optical surface parameters from 3D wavefronts

J. A. Arriaga-Hernández, B. T. Cuevas-Otahola, A. Jaramillo-Núñez, and J. Oliveros-Oliveros
Appl. Opt. 58(22) 5976-5981 (2019)

Beam-pointing drift prediction in pulsed lasers by a probabilistic learning approach

Hui Chang, Zhongwei Fan, Jisi Qiu, Wenqi Ge, Haocheng Wang, Ying Yan, Xiongxin Tang, Hongbo Zhang, and Hong Yuan
Appl. Opt. 58(4) 948-953 (2019)