Individual tree detection and species classification of Amazonian palms using UAV images and deep learning.

Vista sencilla de ítem
dc.contributorMATHEUS PINHEIRO FERREIRA, INSTITUTO MILITAR DE ENGENHARIA
dc.contributorDANILO ROBERTI ALVES DE ALMEIDA, UNIVERSIDADE DE SÃO PAULO
dc.contributorDANIEL DE ALMEIDA PAPA, CPAF-AC
dc.contributorJULIANO BALDEZ SILVA MINERVINO, UNIVERSIDADE FEDERAL DO ACRE
dc.contributorHUDSON FRANKLIN PESSOA VERAS, UNIVERSIDADE FEDERAL DO PARANÁ
dc.contributorARTHUR FORMIGHIERI, UNIVERSIDADE FEDERAL DO ACRE
dc.contributorCAIO ALEXANDRE NASCIMENTO SANTOS, UNIVERSIDADE FEDERAL DO ACRE
dc.contributorMARCIO AURÉLIO DANTAS FERREIRA, FUNDAÇÃO DE TECNOLOGIA DO ESTADO DO ACRE
dc.contributorEVANDRO ORFANO FIGUEIREDO, CPAF-AC
dc.contributorEVANDRO JOSÉ LINHARES FERREIRA, INSTITUTO NACIONAL DE PESQUISAS DA AMAZÔNIA.
dc.creatorFERREIRA, M. P.
dc.creatorALMEIDA, D. R. A. de
dc.creatorPAPA, D. de A.
dc.creatorMINERVINO, J. B. S.
dc.creatorVERAS, H. F. P.
dc.creatorFORMIGHIERI, A.
dc.creatorSANTOS, C. A. N.
dc.creatorFERREIRA, M. A. D.
dc.creatorFIGUEIREDO, E. O.
dc.creatorFERREIRA, E. J. L.
dc.date2020-08-01T11:12:33Z
dc.date2020-08-01T11:12:33Z
dc.date2020-07-31
dc.date2020
dc.date.accessioned2026-06-30T22:52:09Z
dc.descriptionInformation 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.
dc.identifierForest Ecology and Management, v. 475, n. 118397, p. 1-11, 2020.
dc.identifier0378-1127
dc.identifierhttp://www.alice.cnptia.embrapa.br/alice/handle/doc/1124129
dc.identifierhttps://doi.org/10.1016/j.foreco.2020.118397
dc.identifier.urihttp://hdl.handle.net/123456789/369882
dc.languageeng
dc.rightsopenAccess
dc.subjectPalmeira
dc.subjectPalm trees
dc.subjectMapeamento
dc.subjectDrone
dc.subjectAerial surveys
dc.subjectImagem RGB
dc.subjectDeepLabv3+
dc.subjectBosques lluviosos
dc.subjectMadera tropical
dc.subjectTeledetección
dc.subjectVehículos aéreos no tripulados
dc.subjectFotografía aérea
dc.subjectEmbrapa Acre
dc.subjectRio Branco (AC)
dc.subjectAcre
dc.subjectAmazônia Ocidental
dc.subjectWestern Amazon
dc.subjectAmaz
dc.subjectAmazonia Occidental
dc.subjectFloresta Tropical
dc.subjectEspécie Nativa
dc.subjectAçaí
dc.subjectPopulação de Planta
dc.subjectBiogeografia
dc.subjectSensoriamento Remoto
dc.subjectAerofotogrametria
dc.subjectRain forests
dc.subjectArecaceae
dc.subjectEuterpe precatoria
dc.subjectTropical wood
dc.subjectBiogeography
dc.subjectRemote sensing
dc.subjectUnmanned aerial vehicles
dc.subjectAerial photography
dc.titleIndividual tree detection and species classification of Amazonian palms using UAV images and deep learning.
dc.typeArtigo de periódico

Archivos

Colecciones

Embrapa Acre (CPAF-AC)