Výsledky vyhledávání - "Gonçalves, Diogo Nunes"

Report

MTLSegFormer: Multi-task Learning with Transformers for Semantic Segmentation in Precision Agriculture

Autor: Goncalves, Diogo Nunes, Junior, Jose Marcato, Zamboni, Pedro, Pistori, Hemerson, Li, Jonathan, Nogueira, Keiller, Goncalves, Wesley Nunes

Multi-task learning has proven to be effective in improving the performance of correlated tasks. Most of the existing methods use a backbone to extract initial features with independent branches for each task, and the exchange of information between

Externí odkaz: http://arxiv.org/abs/2305.02813

Zobrazit plný text záznamu

Report

Semantic Segmentation with Labeling Uncertainty and Class Imbalance

Autor: Bressan, Patrik Olã, Junior, José Marcato, Martins, José Augusto Correa, Gonçalves, Diogo Nunes, Freitas, Daniel Matte, Osco, Lucas Prado, Silva, Jonathan de Andrade, Luo, Zhipeng, Li, Jonathan, Garcia, Raymundo Cordero, Gonçalves, Wesley Nunes

Publikováno v: International Journal of Applied Earth Observation and Geoinformation, 2022

Recently, methods based on Convolutional Neural Networks (CNN) achieved impressive success in semantic segmentation tasks. However, challenges such as the class imbalance and the uncertainty in the pixel-labeling process are not completely addressed.

Externí odkaz: http://arxiv.org/abs/2102.04566

Zobrazit plný text záznamu

Report

Counting and Locating High-Density Objects Using Convolutional Neural Network

Autor: de Arruda, Mauro dos Santos, Osco, Lucas Prado, Acosta, Plabiany Rodrigo, Gonçalves, Diogo Nunes, Junior, José Marcato, Ramos, Ana Paula Marques, Matsubara, Edson Takashi, Luo, Zhipeng, Li, Jonathan, Silva, Jonathan de Andrade, Gonçalves, Wesley Nunes

Publikováno v: Expert Systems with Applications, 2022

This paper presents a Convolutional Neural Network (CNN) approach for counting and locating objects in high-density imagery. To the best of our knowledge, this is the first object counting and locating method based on a feature map enhancement and a

Externí odkaz: http://arxiv.org/abs/2102.04366

Zobrazit plný text záznamu

Report

A Deep Learning Approach Based on Graphs to Detect Plantation Lines

Autor: Gonçalves, Diogo Nunes, de Arruda, Mauro dos Santos, Pistori, Hemerson, Fernandes, Vanessa Jordão Marcato, Ramos, Ana Paula Marques, Furuya, Danielle Elis Garcia, Osco, Lucas Prado, He, Hongjie, Li, Jonathan, Junior, José Marcato, Gonçalves, Wesley Nunes

Deep learning-based networks are among the most prominent methods to learn linear patterns and extract this type of information from diverse imagery conditions. Here, we propose a deep learning approach based on graphs to detect plantation lines in U

Externí odkaz: http://arxiv.org/abs/2102.03213

Zobrazit plný text záznamu

Report

A CNN Approach to Simultaneously Count Plants and Detect Plantation-Rows from UAV Imagery

Autor: Osco, Lucas Prado, de Arruda, Mauro dos Santos, Gonçalves, Diogo Nunes, Dias, Alexandre, Batistoti, Juliana, de Souza, Mauricio, Gomes, Felipe David Georges, Ramos, Ana Paula Marques, Jorge, Lúcio André de Castro, Liesenberg, Veraldo, Li, Jonathan, Ma, Lingfei, Junior, José Marcato, Gonçalves, Wesley Nunes

Publikováno v: ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING 174 (2021) 1-17

In this paper, we propose a novel deep learning method based on a Convolutional Neural Network (CNN) that simultaneously detects and geolocates plantation-rows while counting its plants considering highly-dense plantation configurations. The experime

Externí odkaz: http://arxiv.org/abs/2012.15827

Zobrazit plný text záznamu