Real-Time Leaves Segmentation in RGB Images with Deep Learning in a Single-Board Computer

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.contributorInspectral-
Autor(es): dc.contributorAeronautics Technological Institute-
Autor(es): dc.creatorde Souza Faria Júnior, Clodoaldo-
Autor(es): dc.creatorShimabukuro, Milton Hirokazu-
Autor(es): dc.creatorTommaselli, Antonio Maria Garcia-
Autor(es): dc.creatorde Albuquerque Maximo, Marcos Ricardo Omena-
Autor(es): dc.creatorPorto, Letícia Rosim-
Autor(es): dc.creatorImai, Nilton Nobuhiro-
Data de aceite: dc.date.accessioned2025-08-21T18:09:28Z-
Data de disponibilização: dc.date.available2025-08-21T18:09:28Z-
Data de envio: dc.date.issued2025-04-29-
Data de envio: dc.date.issued2024-11-03-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.5194/isprs-annals-X-3-2024-139-2024-
Fonte completa do material: dc.identifierhttps://hdl.handle.net/11449/306732-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/306732-
Descrição: dc.descriptionThis work proposed and evaluated methods for real-time leaf segmentation using a single-board computer. The main aim was to explore the state-of-the-art techniques based on the YOLO algorithm for real-time operation. For this purpose, the available variants of YOLOv8 and YOLOv9 were evaluated, and a semi-automatic labelling method based on the Segment Anything Model (SAM) algorithm was used. Given the need to delimit the leaf contour for labelling, it was possible to create a larger and more accurate dataset compared to the purely manual procedure. In addition, the cost-benefit of the applied algorithms and methods were assessed, considering the computational demand required, as well as the accuracy, recall, and precision delivered by these techniques. In this study, both quantitative analysis of the trained architectures' metrics and qualitative examination through direct observation of images were conducted to identify crucial aspects. The experiments were conducted with a post-processed dataset and the suitability for real-time applications was based on the elapsed time for segmentation. We concluded that the YOLOv8n architecture is the best one among those tested, presenting a precision and recall of 0.9064 and 0.7233, respectively. This architecture represents the best cost-benefit ratio between computational cost and real-time performance, being able to perform segmentation in 310 ms with the NVIDIA Jetson Nano board. Furthermore, when computational cost is not a problem or even when segmentation time can be higher, the YOLO8m network may be recommended when the recall metric is more important than precision. This network presented a precision and recall of 0.8556 and 0.7726, respectively, and presented a better performance in segmenting leaves located in more complex parts of the image and with a higher recall.-
Descrição: dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)-
Descrição: dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)-
Descrição: dc.descriptionCoordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)-
Descrição: dc.descriptionSão Paulo State University (UNESP), São Paulo-
Descrição: dc.descriptionInspectral, São Paulo-
Descrição: dc.descriptionAeronautics Technological Institute, São Paulo-
Descrição: dc.descriptionSão Paulo State University (UNESP), São Paulo-
Descrição: dc.descriptionFAPESP: 21/06029-7-
Descrição: dc.descriptionCNPq: 303670/2018-5-
Descrição: dc.descriptionCNPq: 308747/2021-6-
Descrição: dc.descriptionCAPES: 8888.821780/2023-00-
Descrição: dc.descriptionCAPES: 88887.817757/2023-00-
Descrição: dc.descriptionCAPES: 88887.839524/2023-00-
Formato: dc.format139-146-
Idioma: dc.languageen-
Relação: dc.relationISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectDeep Learning-
Palavras-chave: dc.subjectJetson Nano-
Palavras-chave: dc.subjectLeaf Segmentation-
Palavras-chave: dc.subjectReal-Time Application-
Palavras-chave: dc.subjectSegment Anything Model-
Título: dc.titleReal-Time Leaves Segmentation in RGB Images with Deep Learning in a Single-Board Computer-
Tipo de arquivo: dc.typeaula digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.