Next Article in Journal
Optimization of UAV Flight Missions in Steep Terrain
Next Article in Special Issue
Voxel-Based Automatic Tree Detection and Parameter Retrieval from Terrestrial Laser Scans for Plot-Wise Forest Inventory
Previous Article in Journal
Potato Late Blight Detection at the Leaf and Canopy Levels Based in the Red and Red-Edge Spectral Regions
Previous Article in Special Issue
Tree Species Classification of Drone Hyperspectral and RGB Imagery with Deep Learning Convolutional Neural Networks
Article

A Novel Deep Learning Method to Identify Single Tree Species in UAV-Based Hyperspectral Images

1
Graduate Program in Cartographic Sciences, São Paulo State University (UNESP), Presidente Prudente 19060-900, SP, Brazil
2
Graduate Program in Computer Sciences, Faculty of Computer Science, Federal University of Mato Grosso do Sul (UFMS), Av. Costa e Silva, Campo Grande 79070-900, Brazil
3
Faculty of Engineering and Architecture and Urbanism, University of Western São Paulo (UNOESTE), R. José Bongiovani, Cidade Universitária, Presidente Prudente 19050-920, SP, Brazil
4
Faculty of Engineering, Architecture, and Urbanism and Geography, Federal University of Mato Grosso do Sul (UFMS), Av. Costa e Silva, Campo Grande 79070-900, Brazil
5
Department of Cartography, São Paulo State University (UNESP), Presidente Prudente 19060-900, SP, Brazil
6
Finnish Geospatial Research Institute, National Land Survey of Finland, Geodeetinrinne 2, 02430 Masala, Finland
*
Author to whom correspondence should be addressed.
Remote Sens. 2020, 12(8), 1294; https://doi.org/10.3390/rs12081294
Received: 2 April 2020 / Revised: 15 April 2020 / Accepted: 17 April 2020 / Published: 19 April 2020
(This article belongs to the Special Issue Thematic Information Extraction and Application in Forests)
Deep neural networks are currently the focus of many remote sensing approaches related to forest management. Although they return satisfactory results in most tasks, some challenges related to hyperspectral data remain, like the curse of data dimensionality. In forested areas, another common problem is the highly-dense distribution of trees. In this paper, we propose a novel deep learning approach for hyperspectral imagery to identify single-tree species in highly-dense areas. We evaluated images with 25 spectral bands ranging from 506 to 820 nm taken over a semideciduous forest of the Brazilian Atlantic biome. We included in our network’s architecture a band combination selection phase. This phase learns from multiple combinations between bands which contributed the most for the tree identification task. This is followed by a feature map extraction and a multi-stage model refinement of the confidence map to produce accurate results of a highly-dense target. Our method returned an f-measure, precision and recall values of 0.959, 0.973, and 0.945, respectively. The results were superior when compared with a principal component analysis (PCA) approach. Compared to other learning methods, ours estimate a combination of hyperspectral bands that most contribute to the mentioned task within the network’s architecture. With this, the proposed method achieved state-of-the-art performance for detecting and geolocating individual tree-species in UAV-based hyperspectral images in a complex forest. View Full-Text
Keywords: high-density object; data-reduction; band selection; convolutional neural network; tree species identification high-density object; data-reduction; band selection; convolutional neural network; tree species identification
Show Figures

Graphical abstract

MDPI and ACS Style

Miyoshi, G.T.; Arruda, M.d.S.; Osco, L.P.; Marcato Junior, J.; Gonçalves, D.N.; Imai, N.N.; Tommaselli, A.M.G.; Honkavaara, E.; Gonçalves, W.N. A Novel Deep Learning Method to Identify Single Tree Species in UAV-Based Hyperspectral Images. Remote Sens. 2020, 12, 1294. https://doi.org/10.3390/rs12081294

AMA Style

Miyoshi GT, Arruda MdS, Osco LP, Marcato Junior J, Gonçalves DN, Imai NN, Tommaselli AMG, Honkavaara E, Gonçalves WN. A Novel Deep Learning Method to Identify Single Tree Species in UAV-Based Hyperspectral Images. Remote Sensing. 2020; 12(8):1294. https://doi.org/10.3390/rs12081294

Chicago/Turabian Style

Miyoshi, Gabriela T.; Arruda, Mauro d.S.; Osco, Lucas P.; Marcato Junior, José; Gonçalves, Diogo N.; Imai, Nilton N.; Tommaselli, Antonio M.G.; Honkavaara, Eija; Gonçalves, Wesley N. 2020. "A Novel Deep Learning Method to Identify Single Tree Species in UAV-Based Hyperspectral Images" Remote Sens. 12, no. 8: 1294. https://doi.org/10.3390/rs12081294

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop