Detecting Irrigated Croplands: A Comparative Study with Segment Anything Model and Region-Growing Algorithms

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorNational Institute for Space Research (INPE)-
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.creatorPetrone, Felipe Gomes-
Autor(es): dc.creatorda Silva, Darlan Teles-
Autor(es): dc.creatorMaia, Aluizio Brito-
Autor(es): dc.creatorDel’Arco Sanches, Ieda-
Autor(es): dc.creatorChaves, Michel Eustáquio Dantas-
Autor(es): dc.creatorAdami, Marcos-
Autor(es): dc.creatorFonseca, Leila Maria Garcia-
Data de aceite: dc.date.accessioned2025-08-21T19:54:30Z-
Data de disponibilização: dc.date.available2025-08-21T19:54:30Z-
Data de envio: dc.date.issued2025-04-29-
Data de envio: dc.date.issued2022-12-31-
Fonte completa do material: dc.identifierhttps://hdl.handle.net/11449/302967-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/302967-
Descrição: dc.descriptionThe advance of remote sensing and geotechnologies has helped to solve agricultural-related problems, especially those connected to management practices as irrigation. Segmentation techniques, for example, bring the possibility of identifying areas and borders of irrigated croplands, a factor that can enhance area and yield estimates. In this area, a recent innovation is the Segment Anything Model (SAM) algorithm. Thus, this study aimed to compare SAM with two segmentation algorithms, Region Growing and Baatz-Schape, for identifying irrigated croplands in the Brazilian semiarid region. Results show that SAM has potential to generate homogeneous segments when analyzing irrigated croplands but needs adjustments to separate crop fields with different crops.-
Descrição: dc.descriptionDivision of Earth Observation and Geoinformatics National Institute for Space Research (INPE), SP-
Descrição: dc.descriptionSão Paulo State University (Unesp) School of Sciences and Engineering-
Descrição: dc.descriptionSão Paulo State University (Unesp) School of Sciences and Engineering-
Formato: dc.format199-209-
Idioma: dc.languageen-
Relação: dc.relationProceedings of the Brazilian Symposium on GeoInformatics-
???dc.source???: dc.sourceScopus-
Título: dc.titleDetecting Irrigated Croplands: A Comparative Study with Segment Anything Model and Region-Growing Algorithms-
Tipo de arquivo: dc.typeaula digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.