Leaf Segmentation Based on <i>k</i>-Means Algorithm to Obtain Leaf Angle Distribution Using Terrestrial LiDAR
It is critical to take the variability of leaf angle distribution into account in a remote sensing analysis of a canopy system. Due to the physical limitations of field measurements, it is difficult to obtain leaf angles quickly and accurately, especially with a complicated canopy structure. An appl...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-10-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/11/21/2536 |
id |
doaj-76e763b47c6b47e4a5b9dcef67ea327c |
---|---|
record_format |
Article |
spelling |
doaj-76e763b47c6b47e4a5b9dcef67ea327c2020-11-24T21:10:45ZengMDPI AGRemote Sensing2072-42922019-10-011121253610.3390/rs11212536rs11212536Leaf Segmentation Based on <i>k</i>-Means Algorithm to Obtain Leaf Angle Distribution Using Terrestrial LiDARKuangting Kuo0Kenta Itakura1Fumiki Hosoi2Graduate School of Agricultural and Life Sciences, The University of Tokyo, Yayoi 1-1-1, Bunkyo-ku, Tokyo 113-8657, JapanGraduate School of Agricultural and Life Sciences, The University of Tokyo, Yayoi 1-1-1, Bunkyo-ku, Tokyo 113-8657, JapanGraduate School of Agricultural and Life Sciences, The University of Tokyo, Yayoi 1-1-1, Bunkyo-ku, Tokyo 113-8657, JapanIt is critical to take the variability of leaf angle distribution into account in a remote sensing analysis of a canopy system. Due to the physical limitations of field measurements, it is difficult to obtain leaf angles quickly and accurately, especially with a complicated canopy structure. An application of terrestrial LiDAR (Light Detection and Ranging) is a common solution for the purposes of leaf angle estimation, and it allows for the measurement and reconstruction of 3D canopy models with an arbitrary volume of leaves. However, in most cases, the leaf angle is estimated incorrectly due to inaccurate leaf segmentation. Therefore, the objective of this study was an emphasis on the development of efficient segmentation algorithms for accurate leaf angle estimation. Our study demonstrates a leaf segmentation approach based on a <i>k</i>-means algorithm coupled with an octree structure and the subsequent application of plane-fitting to estimate the leaf angle. Furthermore, the accuracy of the segmentation and leaf angle estimation was verified. The results showed average segmentation accuracies of 95% and 90% and absolute angular errors of 3° and 6° in the leaves sampled from mochi and Japanese camellia trees, respectively. It is our conclusion that our method of leaf angle estimation has high potential and is expected to make a significant contribution to future plant and forest research.https://www.mdpi.com/2072-4292/11/21/2536<i>k</i>-meansleaf angle distributionleaf angle estimationlidaroctree structureplane-fitting |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Kuangting Kuo Kenta Itakura Fumiki Hosoi |
spellingShingle |
Kuangting Kuo Kenta Itakura Fumiki Hosoi Leaf Segmentation Based on <i>k</i>-Means Algorithm to Obtain Leaf Angle Distribution Using Terrestrial LiDAR Remote Sensing <i>k</i>-means leaf angle distribution leaf angle estimation lidar octree structure plane-fitting |
author_facet |
Kuangting Kuo Kenta Itakura Fumiki Hosoi |
author_sort |
Kuangting Kuo |
title |
Leaf Segmentation Based on <i>k</i>-Means Algorithm to Obtain Leaf Angle Distribution Using Terrestrial LiDAR |
title_short |
Leaf Segmentation Based on <i>k</i>-Means Algorithm to Obtain Leaf Angle Distribution Using Terrestrial LiDAR |
title_full |
Leaf Segmentation Based on <i>k</i>-Means Algorithm to Obtain Leaf Angle Distribution Using Terrestrial LiDAR |
title_fullStr |
Leaf Segmentation Based on <i>k</i>-Means Algorithm to Obtain Leaf Angle Distribution Using Terrestrial LiDAR |
title_full_unstemmed |
Leaf Segmentation Based on <i>k</i>-Means Algorithm to Obtain Leaf Angle Distribution Using Terrestrial LiDAR |
title_sort |
leaf segmentation based on <i>k</i>-means algorithm to obtain leaf angle distribution using terrestrial lidar |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2019-10-01 |
description |
It is critical to take the variability of leaf angle distribution into account in a remote sensing analysis of a canopy system. Due to the physical limitations of field measurements, it is difficult to obtain leaf angles quickly and accurately, especially with a complicated canopy structure. An application of terrestrial LiDAR (Light Detection and Ranging) is a common solution for the purposes of leaf angle estimation, and it allows for the measurement and reconstruction of 3D canopy models with an arbitrary volume of leaves. However, in most cases, the leaf angle is estimated incorrectly due to inaccurate leaf segmentation. Therefore, the objective of this study was an emphasis on the development of efficient segmentation algorithms for accurate leaf angle estimation. Our study demonstrates a leaf segmentation approach based on a <i>k</i>-means algorithm coupled with an octree structure and the subsequent application of plane-fitting to estimate the leaf angle. Furthermore, the accuracy of the segmentation and leaf angle estimation was verified. The results showed average segmentation accuracies of 95% and 90% and absolute angular errors of 3° and 6° in the leaves sampled from mochi and Japanese camellia trees, respectively. It is our conclusion that our method of leaf angle estimation has high potential and is expected to make a significant contribution to future plant and forest research. |
topic |
<i>k</i>-means leaf angle distribution leaf angle estimation lidar octree structure plane-fitting |
url |
https://www.mdpi.com/2072-4292/11/21/2536 |
work_keys_str_mv |
AT kuangtingkuo leafsegmentationbasedonikimeansalgorithmtoobtainleafangledistributionusingterrestriallidar AT kentaitakura leafsegmentationbasedonikimeansalgorithmtoobtainleafangledistributionusingterrestriallidar AT fumikihosoi leafsegmentationbasedonikimeansalgorithmtoobtainleafangledistributionusingterrestriallidar |
_version_ |
1716755414991765504 |