Explainable identification and mapping of trees using UAV RGB image and deep learning

Abstract The identification and mapping of trees via remotely sensed data for application in forest management is an active area of research. Previously proposed methods using airborne and hyperspectral sensors can identify tree species with high accuracy but are costly and are thus unsuitable for s...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Masanori Onishi, Takeshi Ise
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/07bac437a5ee4be3ad04a36b253be0cd
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:07bac437a5ee4be3ad04a36b253be0cd
record_format dspace
spelling oai:doaj.org-article:07bac437a5ee4be3ad04a36b253be0cd2021-12-02T14:01:37ZExplainable identification and mapping of trees using UAV RGB image and deep learning10.1038/s41598-020-79653-92045-2322https://doaj.org/article/07bac437a5ee4be3ad04a36b253be0cd2021-01-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-79653-9https://doaj.org/toc/2045-2322Abstract The identification and mapping of trees via remotely sensed data for application in forest management is an active area of research. Previously proposed methods using airborne and hyperspectral sensors can identify tree species with high accuracy but are costly and are thus unsuitable for small-scale forest managers. In this work, we constructed a machine vision system for tree identification and mapping using Red–Green–Blue (RGB) image taken by an unmanned aerial vehicle (UAV) and a convolutional neural network (CNN). In this system, we first calculated the slope from the three-dimensional model obtained by the UAV, and segmented the UAV RGB photograph of the forest into several tree crown objects automatically using colour and three-dimensional information and the slope model, and lastly applied object-based CNN classification for each crown image. This system succeeded in classifying seven tree classes, including several tree species with more than 90% accuracy. The guided gradient-weighted class activation mapping (Guided Grad-CAM) showed that the CNN classified trees according to their shapes and leaf contrasts, which enhances the potential of the system for classifying individual trees with similar colours in a cost-effective manner—a useful feature for forest management.Masanori OnishiTakeshi IseNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-15 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Masanori Onishi
Takeshi Ise
Explainable identification and mapping of trees using UAV RGB image and deep learning
description Abstract The identification and mapping of trees via remotely sensed data for application in forest management is an active area of research. Previously proposed methods using airborne and hyperspectral sensors can identify tree species with high accuracy but are costly and are thus unsuitable for small-scale forest managers. In this work, we constructed a machine vision system for tree identification and mapping using Red–Green–Blue (RGB) image taken by an unmanned aerial vehicle (UAV) and a convolutional neural network (CNN). In this system, we first calculated the slope from the three-dimensional model obtained by the UAV, and segmented the UAV RGB photograph of the forest into several tree crown objects automatically using colour and three-dimensional information and the slope model, and lastly applied object-based CNN classification for each crown image. This system succeeded in classifying seven tree classes, including several tree species with more than 90% accuracy. The guided gradient-weighted class activation mapping (Guided Grad-CAM) showed that the CNN classified trees according to their shapes and leaf contrasts, which enhances the potential of the system for classifying individual trees with similar colours in a cost-effective manner—a useful feature for forest management.
format article
author Masanori Onishi
Takeshi Ise
author_facet Masanori Onishi
Takeshi Ise
author_sort Masanori Onishi
title Explainable identification and mapping of trees using UAV RGB image and deep learning
title_short Explainable identification and mapping of trees using UAV RGB image and deep learning
title_full Explainable identification and mapping of trees using UAV RGB image and deep learning
title_fullStr Explainable identification and mapping of trees using UAV RGB image and deep learning
title_full_unstemmed Explainable identification and mapping of trees using UAV RGB image and deep learning
title_sort explainable identification and mapping of trees using uav rgb image and deep learning
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/07bac437a5ee4be3ad04a36b253be0cd
work_keys_str_mv AT masanorionishi explainableidentificationandmappingoftreesusinguavrgbimageanddeeplearning
AT takeshiise explainableidentificationandmappingoftreesusinguavrgbimageanddeeplearning
_version_ 1718392121483853824