Automated Delineation of Microstands in Hemiboreal Mixed Forests Using Stereo GeoEye-1 Data
A microstand is a small forest area with a homogeneous tree species, height, and density composition. High-spatial-resolution GeoEye-1 multispectral (MS) images and GeoEye-1-based canopy height models (CHMs) allow delineating microstands automatically. This paper studied the potential benefits of tw...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-03-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/14/6/1471 |
_version_ | 1797442637522796544 |
---|---|
author | Linda Gulbe Juris Zarins Ints Mednieks |
author_facet | Linda Gulbe Juris Zarins Ints Mednieks |
author_sort | Linda Gulbe |
collection | DOAJ |
description | A microstand is a small forest area with a homogeneous tree species, height, and density composition. High-spatial-resolution GeoEye-1 multispectral (MS) images and GeoEye-1-based canopy height models (CHMs) allow delineating microstands automatically. This paper studied the potential benefits of two microstand segmentation workflows: (1) our modification of JSEG and (2) generic region merging (GRM) of the Orfeo Toolbox, both intended for the microstand border refinement and automated stand volume estimation in hemiboreal forests. Our modification of JSEG uses a CHM as the primary data source for segmentation by refining the results using MS data. Meanwhile, the CHM and multispectral data fusion were achieved as multiband segmentation for the GRM workflow. The accuracy was evaluated using several sets of metrics (unsupervised, supervised direct assessment, and system-level assessment). Metrics were calculated for a regular segment grid to check the benefits compared with the simple image patches. The metrics showed very similar results for both workflows. The most successful combinations in the workflow parameters retrieved over 75 % of the boundaries selected by a human interpreter. However, the impact of data fusion and parameter combinations on stand volume estimation accuracy was minimal, causing variations of the RMSE within approximately 7 m<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mrow></mrow><mn>3</mn></msup></semantics></math></inline-formula>/ha. |
first_indexed | 2024-03-09T12:44:50Z |
format | Article |
id | doaj.art-5e7634223b5e46a488009d026adc4957 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-09T12:44:50Z |
publishDate | 2022-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-5e7634223b5e46a488009d026adc49572023-11-30T22:13:31ZengMDPI AGRemote Sensing2072-42922022-03-01146147110.3390/rs14061471Automated Delineation of Microstands in Hemiboreal Mixed Forests Using Stereo GeoEye-1 DataLinda Gulbe0Juris Zarins1Ints Mednieks2Institute of Electronics and Computer Science, Dzērbenes 14, LV-1006 Riga, LatviaLatvian State Forest Research Institute “Silava”, Rīgas 111, LV-2169 Salaspils, LatviaInstitute of Electronics and Computer Science, Dzērbenes 14, LV-1006 Riga, LatviaA microstand is a small forest area with a homogeneous tree species, height, and density composition. High-spatial-resolution GeoEye-1 multispectral (MS) images and GeoEye-1-based canopy height models (CHMs) allow delineating microstands automatically. This paper studied the potential benefits of two microstand segmentation workflows: (1) our modification of JSEG and (2) generic region merging (GRM) of the Orfeo Toolbox, both intended for the microstand border refinement and automated stand volume estimation in hemiboreal forests. Our modification of JSEG uses a CHM as the primary data source for segmentation by refining the results using MS data. Meanwhile, the CHM and multispectral data fusion were achieved as multiband segmentation for the GRM workflow. The accuracy was evaluated using several sets of metrics (unsupervised, supervised direct assessment, and system-level assessment). Metrics were calculated for a regular segment grid to check the benefits compared with the simple image patches. The metrics showed very similar results for both workflows. The most successful combinations in the workflow parameters retrieved over 75 % of the boundaries selected by a human interpreter. However, the impact of data fusion and parameter combinations on stand volume estimation accuracy was minimal, causing variations of the RMSE within approximately 7 m<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mrow></mrow><mn>3</mn></msup></semantics></math></inline-formula>/ha.https://www.mdpi.com/2072-4292/14/6/1471forest microstandssegmentationGeoEye-1 stereoJSEGgeneric region mergingdata fusion |
spellingShingle | Linda Gulbe Juris Zarins Ints Mednieks Automated Delineation of Microstands in Hemiboreal Mixed Forests Using Stereo GeoEye-1 Data Remote Sensing forest microstands segmentation GeoEye-1 stereo JSEG generic region merging data fusion |
title | Automated Delineation of Microstands in Hemiboreal Mixed Forests Using Stereo GeoEye-1 Data |
title_full | Automated Delineation of Microstands in Hemiboreal Mixed Forests Using Stereo GeoEye-1 Data |
title_fullStr | Automated Delineation of Microstands in Hemiboreal Mixed Forests Using Stereo GeoEye-1 Data |
title_full_unstemmed | Automated Delineation of Microstands in Hemiboreal Mixed Forests Using Stereo GeoEye-1 Data |
title_short | Automated Delineation of Microstands in Hemiboreal Mixed Forests Using Stereo GeoEye-1 Data |
title_sort | automated delineation of microstands in hemiboreal mixed forests using stereo geoeye 1 data |
topic | forest microstands segmentation GeoEye-1 stereo JSEG generic region merging data fusion |
url | https://www.mdpi.com/2072-4292/14/6/1471 |
work_keys_str_mv | AT lindagulbe automateddelineationofmicrostandsinhemiborealmixedforestsusingstereogeoeye1data AT juriszarins automateddelineationofmicrostandsinhemiborealmixedforestsusingstereogeoeye1data AT intsmednieks automateddelineationofmicrostandsinhemiborealmixedforestsusingstereogeoeye1data |