Single Tree Classification Using Multi-Temporal ALS Data and CIR Imagery in Mixed Old-Growth Forest in Poland
Tree species classification is important for a variety of environmental applications, including biodiversity monitoring, wildfire risk assessment, ecosystem services assessment, and sustainable forest management. In this study we used a fusion of three remote sensing (RM) datasets including ALS (lea...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/24/5101 |
| _version_ | 1797500997921144832 |
|---|---|
| author | Agnieszka Kamińska Maciej Lisiewicz Krzysztof Stereńczak |
| author_facet | Agnieszka Kamińska Maciej Lisiewicz Krzysztof Stereńczak |
| author_sort | Agnieszka Kamińska |
| collection | DOAJ |
| description | Tree species classification is important for a variety of environmental applications, including biodiversity monitoring, wildfire risk assessment, ecosystem services assessment, and sustainable forest management. In this study we used a fusion of three remote sensing (RM) datasets including ALS (leaf-on and leaf-off) and colour-infrared (CIR) imagery (leaf-on), to classify different coniferous and deciduous tree species, including dead class, in a mixed temperate forest in Poland. We used intensity and structural variables from the ALS data and spectral information derived from aerial imagery for the classification procedure. Additionally, we tested the differences in classification accuracy of all the variants included in the data integration. The random forest classifier was used in the study. The highest accuracies were obtained for classification based on both point clouds and including image spectral information. The mean values for overall accuracy and kappa were 84.3% and 0.82, respectively. Analysis of the leaf-on and leaf-off alone is not sufficient to identify individual tree species due to their different discriminatory power. Leaf-on and leaf-off ALS point cloud features alone gave the lowest accuracies of 72% ≤ OA ≤ 74% and 0.67 ≤ κ ≤ 0.70. Classification based on both point clouds was found to give satisfactory and comparable results to classification based on combined information from all three sources (83% ≤ OA ≤ 84% and 0.81 ≤ κ ≤ 0.82). The classification accuracy varied between species. The classification results for coniferous trees were always better than for deciduous trees independent of the datasets. In the classification based on both point clouds (leaf-on and leaf-off), the intensity features seemed to be more important than the other groups of variables, especially the coefficient of variation, skewness, and percentiles. The NDVI was the most important CIR-based feature. |
| first_indexed | 2024-03-10T03:11:56Z |
| format | Article |
| id | doaj.art-c394c8f69a134e8dbd86203ffddc9baa |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T03:11:56Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-c394c8f69a134e8dbd86203ffddc9baa2023-11-23T10:24:49ZengMDPI AGRemote Sensing2072-42922021-12-011324510110.3390/rs13245101Single Tree Classification Using Multi-Temporal ALS Data and CIR Imagery in Mixed Old-Growth Forest in PolandAgnieszka Kamińska0Maciej Lisiewicz1Krzysztof Stereńczak2Department of Geomatics, Forest Research Institute, Sękocin Stary, 3 Braci Leśnej Street, 05-090 Raszyn, PolandDepartment of Geomatics, Forest Research Institute, Sękocin Stary, 3 Braci Leśnej Street, 05-090 Raszyn, PolandDepartment of Geomatics, Forest Research Institute, Sękocin Stary, 3 Braci Leśnej Street, 05-090 Raszyn, PolandTree species classification is important for a variety of environmental applications, including biodiversity monitoring, wildfire risk assessment, ecosystem services assessment, and sustainable forest management. In this study we used a fusion of three remote sensing (RM) datasets including ALS (leaf-on and leaf-off) and colour-infrared (CIR) imagery (leaf-on), to classify different coniferous and deciduous tree species, including dead class, in a mixed temperate forest in Poland. We used intensity and structural variables from the ALS data and spectral information derived from aerial imagery for the classification procedure. Additionally, we tested the differences in classification accuracy of all the variants included in the data integration. The random forest classifier was used in the study. The highest accuracies were obtained for classification based on both point clouds and including image spectral information. The mean values for overall accuracy and kappa were 84.3% and 0.82, respectively. Analysis of the leaf-on and leaf-off alone is not sufficient to identify individual tree species due to their different discriminatory power. Leaf-on and leaf-off ALS point cloud features alone gave the lowest accuracies of 72% ≤ OA ≤ 74% and 0.67 ≤ κ ≤ 0.70. Classification based on both point clouds was found to give satisfactory and comparable results to classification based on combined information from all three sources (83% ≤ OA ≤ 84% and 0.81 ≤ κ ≤ 0.82). The classification accuracy varied between species. The classification results for coniferous trees were always better than for deciduous trees independent of the datasets. In the classification based on both point clouds (leaf-on and leaf-off), the intensity features seemed to be more important than the other groups of variables, especially the coefficient of variation, skewness, and percentiles. The NDVI was the most important CIR-based feature.https://www.mdpi.com/2072-4292/13/24/5101tree species classificationairborne laser scanning (ALS)colour-infrared (CIR) aerial imagesmulti-temporal dataindividual treerandom forest (RF) |
| spellingShingle | Agnieszka Kamińska Maciej Lisiewicz Krzysztof Stereńczak Single Tree Classification Using Multi-Temporal ALS Data and CIR Imagery in Mixed Old-Growth Forest in Poland Remote Sensing tree species classification airborne laser scanning (ALS) colour-infrared (CIR) aerial images multi-temporal data individual tree random forest (RF) |
| title | Single Tree Classification Using Multi-Temporal ALS Data and CIR Imagery in Mixed Old-Growth Forest in Poland |
| title_full | Single Tree Classification Using Multi-Temporal ALS Data and CIR Imagery in Mixed Old-Growth Forest in Poland |
| title_fullStr | Single Tree Classification Using Multi-Temporal ALS Data and CIR Imagery in Mixed Old-Growth Forest in Poland |
| title_full_unstemmed | Single Tree Classification Using Multi-Temporal ALS Data and CIR Imagery in Mixed Old-Growth Forest in Poland |
| title_short | Single Tree Classification Using Multi-Temporal ALS Data and CIR Imagery in Mixed Old-Growth Forest in Poland |
| title_sort | single tree classification using multi temporal als data and cir imagery in mixed old growth forest in poland |
| topic | tree species classification airborne laser scanning (ALS) colour-infrared (CIR) aerial images multi-temporal data individual tree random forest (RF) |
| url | https://www.mdpi.com/2072-4292/13/24/5101 |
| work_keys_str_mv | AT agnieszkakaminska singletreeclassificationusingmultitemporalalsdataandcirimageryinmixedoldgrowthforestinpoland AT maciejlisiewicz singletreeclassificationusingmultitemporalalsdataandcirimageryinmixedoldgrowthforestinpoland AT krzysztofsterenczak singletreeclassificationusingmultitemporalalsdataandcirimageryinmixedoldgrowthforestinpoland |