Investigation on Dimensionality Reduction methods for Tree-Crown Segmentation in Hyperspectral imagery using Segment Anything Model
Forests play a vital role in global ecosystems, and accurate monitoring of tree crowns is essential for forest management and biodiversity conservation. This study investigates the use of hyperspectral imagery and dimensionality reduction methods for individual tree-crown (ITC) segmentation, a cruci...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2025-07-01
|
| Series: | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://isprs-annals.copernicus.org/articles/X-G-2025/705/2025/isprs-annals-X-G-2025-705-2025.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849704058460307456 |
|---|---|
| author | R. Ravindran Y. Treitz D. Iwaszczuk |
| author_facet | R. Ravindran Y. Treitz D. Iwaszczuk |
| author_sort | R. Ravindran |
| collection | DOAJ |
| description | Forests play a vital role in global ecosystems, and accurate monitoring of tree crowns is essential for forest management and biodiversity conservation. This study investigates the use of hyperspectral imagery and dimensionality reduction methods for individual tree-crown (ITC) segmentation, a crucial task in forest monitoring. Traditional LiDAR-based methods are often expensive and computationally intensive, making hyperspectral imagery a promising alternative due to its data-richness. However, since most deep learning segmentation methods accept only 3-channel images, we adapt hyperspectral images from a benchmark dataset by applying dimensionality reduction techniques such as Principle Component Analysis (PCA), Factor Analysis, and Uniform Manifold Approximation and Projection (UMAP) to transform high-dimensional data into 3-channels, before performing segmentation using Segment Anything Model (SAM). The results show significant improvements over RGB imagery with dimensionality reduction methods, however the overall segmentation accuracy remains poor. With an average F1-score of 0.26, some methods achieved up-to 0.38 at specific sites. The results varied between sites due to different density and tree types in the image data. Factor Analysis and an approach with UMAP utilising vegetation indices produced the most promising results. |
| format | Article |
| id | doaj-art-63f9bff941f8477ca94dca417f9d9822 |
| institution | DOAJ |
| issn | 2194-9042 2194-9050 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj-art-63f9bff941f8477ca94dca417f9d98222025-08-20T03:16:56ZengCopernicus PublicationsISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences2194-90422194-90502025-07-01X-G-202570571210.5194/isprs-annals-X-G-2025-705-2025Investigation on Dimensionality Reduction methods for Tree-Crown Segmentation in Hyperspectral imagery using Segment Anything ModelR. Ravindran0Y. Treitz1D. Iwaszczuk2Technical University of Darmstadt, Dept. of Civil and Environmental Engineering Sciences, Remote Sensing and Image Analysis, Darmstadt, GermanyTechnical University of Darmstadt, Dept. of Civil and Environmental Engineering Sciences, Remote Sensing and Image Analysis, Darmstadt, GermanyTechnical University of Darmstadt, Dept. of Civil and Environmental Engineering Sciences, Remote Sensing and Image Analysis, Darmstadt, GermanyForests play a vital role in global ecosystems, and accurate monitoring of tree crowns is essential for forest management and biodiversity conservation. This study investigates the use of hyperspectral imagery and dimensionality reduction methods for individual tree-crown (ITC) segmentation, a crucial task in forest monitoring. Traditional LiDAR-based methods are often expensive and computationally intensive, making hyperspectral imagery a promising alternative due to its data-richness. However, since most deep learning segmentation methods accept only 3-channel images, we adapt hyperspectral images from a benchmark dataset by applying dimensionality reduction techniques such as Principle Component Analysis (PCA), Factor Analysis, and Uniform Manifold Approximation and Projection (UMAP) to transform high-dimensional data into 3-channels, before performing segmentation using Segment Anything Model (SAM). The results show significant improvements over RGB imagery with dimensionality reduction methods, however the overall segmentation accuracy remains poor. With an average F1-score of 0.26, some methods achieved up-to 0.38 at specific sites. The results varied between sites due to different density and tree types in the image data. Factor Analysis and an approach with UMAP utilising vegetation indices produced the most promising results.https://isprs-annals.copernicus.org/articles/X-G-2025/705/2025/isprs-annals-X-G-2025-705-2025.pdf |
| spellingShingle | R. Ravindran Y. Treitz D. Iwaszczuk Investigation on Dimensionality Reduction methods for Tree-Crown Segmentation in Hyperspectral imagery using Segment Anything Model ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | Investigation on Dimensionality Reduction methods for Tree-Crown Segmentation in Hyperspectral imagery using Segment Anything Model |
| title_full | Investigation on Dimensionality Reduction methods for Tree-Crown Segmentation in Hyperspectral imagery using Segment Anything Model |
| title_fullStr | Investigation on Dimensionality Reduction methods for Tree-Crown Segmentation in Hyperspectral imagery using Segment Anything Model |
| title_full_unstemmed | Investigation on Dimensionality Reduction methods for Tree-Crown Segmentation in Hyperspectral imagery using Segment Anything Model |
| title_short | Investigation on Dimensionality Reduction methods for Tree-Crown Segmentation in Hyperspectral imagery using Segment Anything Model |
| title_sort | investigation on dimensionality reduction methods for tree crown segmentation in hyperspectral imagery using segment anything model |
| url | https://isprs-annals.copernicus.org/articles/X-G-2025/705/2025/isprs-annals-X-G-2025-705-2025.pdf |
| work_keys_str_mv | AT rravindran investigationondimensionalityreductionmethodsfortreecrownsegmentationinhyperspectralimageryusingsegmentanythingmodel AT ytreitz investigationondimensionalityreductionmethodsfortreecrownsegmentationinhyperspectralimageryusingsegmentanythingmodel AT diwaszczuk investigationondimensionalityreductionmethodsfortreecrownsegmentationinhyperspectralimageryusingsegmentanythingmodel |