3deepm: An ad hoc architecture based on deep learning methods for multispectral image classification
Ver/
Compartir
Estadísticas
Ver Estadísticas de usoMetadatos
Mostrar el registro completo del ítemAutor
Navarro Lorente, Pedro Javier; Miller, Leanne Rebecca; Gila Navarro, Alberto; Egea Gutiérrez-Cortines, Marcos; Águila, Diego J.Área de conocimiento
Lenguajes y Sistemas InformáticosPatrocinadores
This research was funded by BFU 2017-88300-C2-1-R to J.W. and M.E.-C, BFU 2017-88300- C2-2-R to P.J.N. and CDTI 5117/17CTA-P to M.E.-C, P.J.N. and J.D.S.P.Fecha de publicación
2021-02-17Editorial
MDPICita bibliográfica
Navarro, P.J.; Miller, L.; Gila-Navarro, A.; Díaz-Galián, M.V.; Aguila, D.J.; Egea-Cortines, M. 3DeepM: An Ad Hoc Architecture Based on Deep Learning Methods for Multispectral Image Classification. Remote Sens. 2021, 13, 729. https:// doi.org/10.3390/rs13040729Revisión por pares
siPalabras clave
deep learning architecturesmultispectral grape classification
multispectral computer vision system
Resumen
Current predefined architectures for deep learning are computationally very heavy and use tens of millions of parameters. Thus, computational costs may be prohibitive for many experimental or technological setups. We developed an ad hoc architecture for the classification of multispectral images using deep learning techniques. The architecture, called 3DeepM, is composed of 3D filter banks especially designed for the extraction of spatial-spectral features in multichannel images. The new architecture has been tested on a sample of 12210 multispectral images of seedless table grape varieties: Autumn Royal, Crimson Seedless, Itum4, Itum5 and Itum9. 3DeepM was able to classify 100% of the images and obtained the best overall results in terms of accuracy, number of classes, number of parameters and training time compared to similar work. In addition, this paper presents a flexible and reconfigurable computer vision system designed for the acquisition of multispectral images in the range of ...
Colecciones
- Artículos [1768]
Redes sociales