| |
|
|
|
Registro Completo |
|
Biblioteca(s): |
Embrapa Acre. |
|
Data corrente: |
31/07/2020 |
|
Data da última atualização: |
28/06/2021 |
|
Tipo da produção científica: |
Artigo em Periódico Indexado |
|
Autoria: |
FERREIRA, M. P.; ALMEIDA, D. R. A. de; PAPA, D. de A.; MINERVINO, J. B. S.; VERAS, H. F. P.; FORMIGHIERI, A.; SANTOS, C. A. N.; FERREIRA, M. A. D.; FIGUEIREDO, E. O.; FERREIRA, E. J. L. |
|
Afiliação: |
Matheus Pinheiro Ferreira, Instituto Militar de Engenharia (IME); Danilo Roberti Alves de Almeida, Universidade de São Paulo (USP); DANIEL DE ALMEIDA PAPA, CPAF-AC; Juliano Baldez Silva Minervino, Universidade Federal do Acre (Ufac); Hudson Franklin Pessoa Veras, Universidade Federal do Paraná (UFPR); Arthur Formighieri, Universidade Federal do Acre (Ufac); Caio Alexandre Nascimento Santos, Bolsista Embrapa Acre; Marcio Aurélio Dantas Ferreira, Fundação de Tecnologia do Estado do Acre (Funtac); EVANDRO ORFANO FIGUEIREDO, CPAF-AC; Evandro José Linhares Ferreira, Instituto Nacional de Pesquisas da Amazônia (Inpa). |
|
Título: |
Individual tree detection and species classification of Amazonian palms using UAV images and deep learning. |
|
Ano de publicação: |
2020 |
|
Fonte/Imprenta: |
Forest Ecology and Management, v. 475, n. 118397, p. 1-11, 2020. |
|
ISSN: |
0378-1127 |
|
DOI: |
https://doi.org/10.1016/j.foreco.2020.118397 |
|
Idioma: |
Inglês |
|
Conteúdo: |
Information regarding the spatial distribution of palm trees in tropical forests is crucial for commercial exploitation and management. However, spatially continuous knowledge of palms occurrence is scarce and difficult to obtain with conventional approaches such as field inventories. Here, we developed a new method to map Amazonian palm species at the individual tree crown (ITC) level using RGB images acquired by a low-cost unmanned aerial vehicle (UAV). Our approach is based on morphological operations performed in the score maps of palm species derived from a fully convolutional neural network model. We first constructed a labeled dataset by dividing the study area (135 ha within an old-growth Amazon forest) into 28 plots of 250 m×150 m. Then, we manually outlined all palm trees seen in RGB images with 4 cm pixels. We identified three palm species: Attalea butyracea, Euterpe precatoria and Iriartea deltoidea. We randomly selected 22 plots (80%) for training and six plots (20%) for testing. We changed the plots for training and testing to evaluate the variabilityn, in the classification accuracy and assess model generalization. Our method outperformed the average producer?s accuracy of conventional patch-wise semantic segmentation (CSS) in 4.7%. Moreover, our method correctly identified, on average, 34.7 percentage points more ITCs than CSS, which tended to merge trees that are close to each other. The producer's accuracy of A. butyracea, E. precatoria and I. deltoidea was 78.6 ± 5.5%, 8.6 ± 1.4% and 96.6 ± 3.4%, respectively. Fortunately, one of the most exploited and commercialized palm species in the Amazon (E. precatoria, a.k.a, Açaí) was mapped with the highest classification accuracy. Maps of E. precatoria derived from low-cost UAV systems can support management projects and community-based forest monitoring programs in the Amazon. MenosInformation regarding the spatial distribution of palm trees in tropical forests is crucial for commercial exploitation and management. However, spatially continuous knowledge of palms occurrence is scarce and difficult to obtain with conventional approaches such as field inventories. Here, we developed a new method to map Amazonian palm species at the individual tree crown (ITC) level using RGB images acquired by a low-cost unmanned aerial vehicle (UAV). Our approach is based on morphological operations performed in the score maps of palm species derived from a fully convolutional neural network model. We first constructed a labeled dataset by dividing the study area (135 ha within an old-growth Amazon forest) into 28 plots of 250 m×150 m. Then, we manually outlined all palm trees seen in RGB images with 4 cm pixels. We identified three palm species: Attalea butyracea, Euterpe precatoria and Iriartea deltoidea. We randomly selected 22 plots (80%) for training and six plots (20%) for testing. We changed the plots for training and testing to evaluate the variabilityn, in the classification accuracy and assess model generalization. Our method outperformed the average producer?s accuracy of conventional patch-wise semantic segmentation (CSS) in 4.7%. Moreover, our method correctly identified, on average, 34.7 percentage points more ITCs than CSS, which tended to merge trees that are close to each other. The producer's accuracy of A. butyracea, E. precatoria and I. deltoidea was... Mostrar Tudo |
|
Palavras-Chave: |
Acre; Aerial surveys; Amaz; Amazonia Occidental; Amazônia Ocidental; Bosques lluviosos; DeepLabv3+; Drone; Embrapa Acre; Fotografía aérea; Imagem RGB; Madera tropical; Mapeamento; Palm trees; Palmeira; Rio Branco (AC); Teledetección; Vehículos aéreos no tripulados; Western Amazon. |
|
Thesagro: |
Açaí; Aerofotogrametria; Biogeografia; Espécie Nativa; Floresta Tropical; População de Planta; Sensoriamento Remoto. |
|
Thesaurus Nal: |
Aerial photography; Arecaceae; Biogeography; Euterpe precatoria; Rain forests; Remote sensing; Tropical wood; Unmanned aerial vehicles. |
|
Categoria do assunto: |
X Pesquisa, Tecnologia e Engenharia |
|
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/item/215053/1/27014.pdf
|
|
Marc: |
LEADER 03750naa a2200661 a 4500
001 2124129
005 2021-06-28
008 2020 bl uuuu u00u1 u #d
022 $a0378-1127
024 7 $ahttps://doi.org/10.1016/j.foreco.2020.118397$2DOI
100 1 $aFERREIRA, M. P.
245 $aIndividual tree detection and species classification of Amazonian palms using UAV images and deep learning.$h[electronic resource]
260 $c2020
520 $aInformation regarding the spatial distribution of palm trees in tropical forests is crucial for commercial exploitation and management. However, spatially continuous knowledge of palms occurrence is scarce and difficult to obtain with conventional approaches such as field inventories. Here, we developed a new method to map Amazonian palm species at the individual tree crown (ITC) level using RGB images acquired by a low-cost unmanned aerial vehicle (UAV). Our approach is based on morphological operations performed in the score maps of palm species derived from a fully convolutional neural network model. We first constructed a labeled dataset by dividing the study area (135 ha within an old-growth Amazon forest) into 28 plots of 250 m×150 m. Then, we manually outlined all palm trees seen in RGB images with 4 cm pixels. We identified three palm species: Attalea butyracea, Euterpe precatoria and Iriartea deltoidea. We randomly selected 22 plots (80%) for training and six plots (20%) for testing. We changed the plots for training and testing to evaluate the variabilityn, in the classification accuracy and assess model generalization. Our method outperformed the average producer?s accuracy of conventional patch-wise semantic segmentation (CSS) in 4.7%. Moreover, our method correctly identified, on average, 34.7 percentage points more ITCs than CSS, which tended to merge trees that are close to each other. The producer's accuracy of A. butyracea, E. precatoria and I. deltoidea was 78.6 ± 5.5%, 8.6 ± 1.4% and 96.6 ± 3.4%, respectively. Fortunately, one of the most exploited and commercialized palm species in the Amazon (E. precatoria, a.k.a, Açaí) was mapped with the highest classification accuracy. Maps of E. precatoria derived from low-cost UAV systems can support management projects and community-based forest monitoring programs in the Amazon.
650 $aAerial photography
650 $aArecaceae
650 $aBiogeography
650 $aEuterpe precatoria
650 $aRain forests
650 $aRemote sensing
650 $aTropical wood
650 $aUnmanned aerial vehicles
650 $aAçaí
650 $aAerofotogrametria
650 $aBiogeografia
650 $aEspécie Nativa
650 $aFloresta Tropical
650 $aPopulação de Planta
650 $aSensoriamento Remoto
653 $aAcre
653 $aAerial surveys
653 $aAmaz
653 $aAmazonia Occidental
653 $aAmazônia Ocidental
653 $aBosques lluviosos
653 $aDeepLabv3+
653 $aDrone
653 $aEmbrapa Acre
653 $aFotografía aérea
653 $aImagem RGB
653 $aMadera tropical
653 $aMapeamento
653 $aPalm trees
653 $aPalmeira
653 $aRio Branco (AC)
653 $aTeledetección
653 $aVehículos aéreos no tripulados
653 $aWestern Amazon
700 1 $aALMEIDA, D. R. A. de
700 1 $aPAPA, D. de A.
700 1 $aMINERVINO, J. B. S.
700 1 $aVERAS, H. F. P.
700 1 $aFORMIGHIERI, A.
700 1 $aSANTOS, C. A. N.
700 1 $aFERREIRA, M. A. D.
700 1 $aFIGUEIREDO, E. O.
700 1 $aFERREIRA, E. J. L.
773 $tForest Ecology and Management$gv. 475, n. 118397, p. 1-11, 2020.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Acre (CPAF-AC) |
|
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
URL |
Voltar
|
|
|
| Registros recuperados : 1 | |
| 1. |  | FERREIRA, M. P.; ALMEIDA, D. R. A. de; PAPA, D. de A.; MINERVINO, J. B. S.; VERAS, H. F. P.; FORMIGHIERI, A.; SANTOS, C. A. N.; FERREIRA, M. A. D.; FIGUEIREDO, E. O.; FERREIRA, E. J. L. Individual tree detection and species classification of Amazonian palms using UAV images and deep learning. Forest Ecology and Management, v. 475, n. 118397, p. 1-11, 2020.| Tipo: Artigo em Periódico Indexado | Circulação/Nível: A - 1 |
| Biblioteca(s): Embrapa Acre. |
|    |
| Registros recuperados : 1 | |
|
| Nenhum registro encontrado para a expressão de busca informada. |
|
|
