Busca avançada
Ano de início
Entree


Crop Anomaly Identification with Color Filters and Convolutional Neural Networks

Texto completo
Autor(es):
Mostrar menos -
Nardari, Guilherme V. ; Romero, Roseli A. F. ; Guizilini, Vitor C. ; Mareco, Willy E. C. ; Milori, Debora M. B. P. ; Villas-Boas, Paulino R. ; Dias Santos, Igor Araujo ; DoNascimento, TP ; Colombini, EL ; DeBrito, AV ; Garcia, LTD ; Sa, STD ; Goncalves, LMG
Número total de Autores: 13
Tipo de documento: Artigo Científico
Fonte: 15TH LATIN AMERICAN ROBOTICS SYMPOSIUM 6TH BRAZILIAN ROBOTICS SYMPOSIUM 9TH WORKSHOP ON ROBOTICS IN EDUCATION (LARS/SBR/WRE 2018); v. N/A, p. 7-pg., 2018-01-01.
Resumo

Monitoring crops is a time consuming yet important task to ensure production quality. In this paper we present a comparison of convolutional neural network-based methods, evaluating model complexity and performance based on multiple metrics for the binary classification task of segmenting trees from the environment. An Unmanned Aerial Vehicle (UAV) is used to obtain RGB video of orange crops in different altitudes. Keyframes are extracted based on drone trajectory and speed for training and evaluation of the models. The effect on performance of multiple data augmentation techniques is also evaluated. The preferred model is then applied to a reconstruction of a region from multiple images and a color filter is applied for anomaly detection. Experimental and visual results show that these methods are able to segment the environment efficiently without any feature engineering, being a viable pre-processing method for reducing noise in disease identification applications. (AU)

Processo FAPESP: 14/50851-0 - INCT 2014: Instituto Nacional de Ciência e Tecnologia para Sistemas Autônomos Cooperativos Aplicados em Segurança e Meio Ambiente
Beneficiário:Marco Henrique Terra
Modalidade de apoio: Auxílio à Pesquisa - Temático
Processo FAPESP: 17/17444-0 - Monitoramento de plantações usando robôs heterogêneos
Beneficiário:Guilherme Vicentim Nardari
Modalidade de apoio: Bolsas no Brasil - Doutorado Direto