Assessment of tree detection methods in multispectral aerial images
Detecting individual trees and quantifying their biomass is crucial for carbon accounting procedures at the stand, landscape, and national levels. A significant challenge for many organizations is the amount of effort necessary to document carbon storage levels, especially in terms of human labor. T...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
Multidisciplinary Digital Publishing Institute
2020
|
| Online Access: | https://hdl.handle.net/1721.1/127684 |
| _version_ | 1826200266162044928 |
|---|---|
| author | Pulido, Dagoberto Salas, Joaquín Rös, Matthias Puettmann, Klaus Karaman, Sertac |
| author2 | Massachusetts Institute of Technology. Department of Aeronautics and Astronautics |
| author_facet | Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Pulido, Dagoberto Salas, Joaquín Rös, Matthias Puettmann, Klaus Karaman, Sertac |
| author_sort | Pulido, Dagoberto |
| collection | MIT |
| description | Detecting individual trees and quantifying their biomass is crucial for carbon accounting procedures at the stand, landscape, and national levels. A significant challenge for many organizations is the amount of effort necessary to document carbon storage levels, especially in terms of human labor. To advance towards the goal of efficiently assessing the carbon content of forest, we evaluate methods to detect trees from high-resolution images taken from unoccupied aerial systems (UAS). In the process, we introduce the Digital Elevated Vegetation Model (DEVM), a representation that combines multispectral images, digital surface models, and digital terrain models. We show that the DEVM facilitates the development of refined synthetic data to detect individual trees using deep learning-based approaches. We carried out experiments in two tree fields located in different countries. Simultaneously, we perform comparisons among an array of classical and deep learning-based methods highlighting the precision and reliability of the DEVM. |
| first_indexed | 2024-09-23T11:33:50Z |
| format | Article |
| id | mit-1721.1/127684 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T11:33:50Z |
| publishDate | 2020 |
| publisher | Multidisciplinary Digital Publishing Institute |
| record_format | dspace |
| spelling | mit-1721.1/1276842022-10-01T04:28:25Z Assessment of tree detection methods in multispectral aerial images Pulido, Dagoberto Salas, Joaquín Rös, Matthias Puettmann, Klaus Karaman, Sertac Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Detecting individual trees and quantifying their biomass is crucial for carbon accounting procedures at the stand, landscape, and national levels. A significant challenge for many organizations is the amount of effort necessary to document carbon storage levels, especially in terms of human labor. To advance towards the goal of efficiently assessing the carbon content of forest, we evaluate methods to detect trees from high-resolution images taken from unoccupied aerial systems (UAS). In the process, we introduce the Digital Elevated Vegetation Model (DEVM), a representation that combines multispectral images, digital surface models, and digital terrain models. We show that the DEVM facilitates the development of refined synthetic data to detect individual trees using deep learning-based approaches. We carried out experiments in two tree fields located in different countries. Simultaneously, we perform comparisons among an array of classical and deep learning-based methods highlighting the precision and reliability of the DEVM. 2020-09-23T17:24:15Z 2020-09-23T17:24:15Z 2020-07-24 2020-08-21T13:50:42Z Article http://purl.org/eprint/type/JournalArticle 2072-4292 https://hdl.handle.net/1721.1/127684 Pulido, Dagoberto et al. "Assessment of tree detection methods in multispectral aerial images." Remote Sensing 12, 15 (July 2020): 2379 ©2020 Author(s) 10.3390/rs12152379 Remote Sensing Creative Commons Attribution https://creativecommons.org/licenses/by/4.0/ application/pdf Multidisciplinary Digital Publishing Institute Multidisciplinary Digital Publishing Institute |
| spellingShingle | Pulido, Dagoberto Salas, Joaquín Rös, Matthias Puettmann, Klaus Karaman, Sertac Assessment of tree detection methods in multispectral aerial images |
| title | Assessment of tree detection methods in multispectral aerial images |
| title_full | Assessment of tree detection methods in multispectral aerial images |
| title_fullStr | Assessment of tree detection methods in multispectral aerial images |
| title_full_unstemmed | Assessment of tree detection methods in multispectral aerial images |
| title_short | Assessment of tree detection methods in multispectral aerial images |
| title_sort | assessment of tree detection methods in multispectral aerial images |
| url | https://hdl.handle.net/1721.1/127684 |
| work_keys_str_mv | AT pulidodagoberto assessmentoftreedetectionmethodsinmultispectralaerialimages AT salasjoaquin assessmentoftreedetectionmethodsinmultispectralaerialimages AT rosmatthias assessmentoftreedetectionmethodsinmultispectralaerialimages AT puettmannklaus assessmentoftreedetectionmethodsinmultispectralaerialimages AT karamansertac assessmentoftreedetectionmethodsinmultispectralaerialimages |