RESNET-BASED TREE SPECIES CLASSIFICATION USING UAV IMAGES
Tree species classification at individual tree level is a challenging problem in forest management. Deep learning, a cutting-edge technology evolved from Artificial Intelligence, was seen to outperform other techniques when it comes to complex problems such as image classification. In this work, we...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2019-06-01
|
| Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-2-W13/475/2019/isprs-archives-XLII-2-W13-475-2019.pdf |
| _version_ | 1818565692781232128 |
|---|---|
| author | S. Natesan C. Armenakis U. Vepakomma |
| author_facet | S. Natesan C. Armenakis U. Vepakomma |
| author_sort | S. Natesan |
| collection | DOAJ |
| description | Tree species classification at individual tree level is a challenging problem in forest management. Deep learning, a cutting-edge technology evolved from Artificial Intelligence, was seen to outperform other techniques when it comes to complex problems such as image classification. In this work, we present a novel method to classify forest tree species through high resolution RGB images acquired with a simple consumer grade camera mounted on a UAV platform using Residual Neural Networks. We used UAV RGB images acquired over three years that varied in numerous acquisition parameters such as season, time, illumination and angle to train the neural network. To begin with, we have experimented with limited data towards the identification of two pine species namely red pine and white pine from the rest of the species. We performed two experiments, first with the images from all three acquisition years and the second with images from only one acquisition year. In the first experiment, we obtained 80% classification accuracy when the trained network was tested on a distinct set of images and in the second experiment, we obtained 51% classification accuracy. As a part of this work, a novel dataset of high-resolution labelled tree species is generated that can be used to conduct further studies involving deep neural networks in forestry. |
| first_indexed | 2024-12-14T01:44:24Z |
| format | Article |
| id | doaj.art-00b4bf24164946a2bf0f02b1cd9b9b45 |
| institution | Directory Open Access Journal |
| issn | 1682-1750 2194-9034 |
| language | English |
| last_indexed | 2024-12-14T01:44:24Z |
| publishDate | 2019-06-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj.art-00b4bf24164946a2bf0f02b1cd9b9b452022-12-21T23:21:37ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342019-06-01XLII-2-W1347548110.5194/isprs-archives-XLII-2-W13-475-2019RESNET-BASED TREE SPECIES CLASSIFICATION USING UAV IMAGESS. Natesan0C. Armenakis1U. Vepakomma2Geomatics Engineering, Department of Earth and Space Science and Engineering, Lassonde School of Engineering, York University, 4700 Keele St., Toronto, ON, M3J 1P3 CanadaGeomatics Engineering, Department of Earth and Space Science and Engineering, Lassonde School of Engineering, York University, 4700 Keele St., Toronto, ON, M3J 1P3 CanadaFPInnovations, 570 Blvd. Saint-Jean, Pointe-Claire, QC, H9R 3J9 CanadaTree species classification at individual tree level is a challenging problem in forest management. Deep learning, a cutting-edge technology evolved from Artificial Intelligence, was seen to outperform other techniques when it comes to complex problems such as image classification. In this work, we present a novel method to classify forest tree species through high resolution RGB images acquired with a simple consumer grade camera mounted on a UAV platform using Residual Neural Networks. We used UAV RGB images acquired over three years that varied in numerous acquisition parameters such as season, time, illumination and angle to train the neural network. To begin with, we have experimented with limited data towards the identification of two pine species namely red pine and white pine from the rest of the species. We performed two experiments, first with the images from all three acquisition years and the second with images from only one acquisition year. In the first experiment, we obtained 80% classification accuracy when the trained network was tested on a distinct set of images and in the second experiment, we obtained 51% classification accuracy. As a part of this work, a novel dataset of high-resolution labelled tree species is generated that can be used to conduct further studies involving deep neural networks in forestry.https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-2-W13/475/2019/isprs-archives-XLII-2-W13-475-2019.pdf |
| spellingShingle | S. Natesan C. Armenakis U. Vepakomma RESNET-BASED TREE SPECIES CLASSIFICATION USING UAV IMAGES The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | RESNET-BASED TREE SPECIES CLASSIFICATION USING UAV IMAGES |
| title_full | RESNET-BASED TREE SPECIES CLASSIFICATION USING UAV IMAGES |
| title_fullStr | RESNET-BASED TREE SPECIES CLASSIFICATION USING UAV IMAGES |
| title_full_unstemmed | RESNET-BASED TREE SPECIES CLASSIFICATION USING UAV IMAGES |
| title_short | RESNET-BASED TREE SPECIES CLASSIFICATION USING UAV IMAGES |
| title_sort | resnet based tree species classification using uav images |
| url | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-2-W13/475/2019/isprs-archives-XLII-2-W13-475-2019.pdf |
| work_keys_str_mv | AT snatesan resnetbasedtreespeciesclassificationusinguavimages AT carmenakis resnetbasedtreespeciesclassificationusinguavimages AT uvepakomma resnetbasedtreespeciesclassificationusinguavimages |