Next Article in Journal
Annual Sea Level Amplitude Analysis over the North Pacific Ocean Coast by Ensemble Empirical Mode Decomposition Method
Next Article in Special Issue
Predicting Water Stress in Wild Blueberry Fields Using Airborne Visible and Near Infrared Imaging Spectroscopy
Previous Article in Journal
Seasonal and Interannual Variability of Sea Surface Salinity Near Major River Mouths of the World Ocean Inferred from Gridded Satellite and In-Situ Salinity Products
Previous Article in Special Issue
Data Augmentation and Spectral Structure Features for Limited Samples Hyperspectral Classification
Open AccessArticle

3DeepM: An Ad Hoc Architecture Based on Deep Learning Methods for Multispectral Image Classification

1
Escuela Técnica Superior de Ingeniería de Telecomunicación (DSIE), Campus Muralla del Mar, s/n, Universidad Politécnica de Cartagena, 30202 Cartagena, Spain
2
Genética Molecular, Instituto de Biotecnología Vegetal, Edificio I+D+I, Plaza del Hospital s/n, Universidad Politécnica de Cartagena, 30202 Cartagena, Spain
3
Sociedad Cooperativa Las Cabezuelas, 30840 Alhama de Murcia, Spain
*
Author to whom correspondence should be addressed.
Academic Editor: Qi Wang
Remote Sens. 2021, 13(4), 729; https://doi.org/10.3390/rs13040729
Received: 17 January 2021 / Revised: 5 February 2021 / Accepted: 11 February 2021 / Published: 17 February 2021
(This article belongs to the Special Issue Feature Extraction and Data Classification in Hyperspectral Imaging)
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 400 nm to 1000 nm. The vision system enabled the creation of the first dataset consisting of 12210 37-channel multispectral images (12 VIS + 25 IR) of five seedless table grape varieties that have been used to validate the 3DeepM architecture. Compared to predefined classification architectures such as AlexNet, ResNet or ad hoc architectures with a very high number of parameters, 3DeepM shows the best classification performance despite using 130-fold fewer parameters than the architecture to which it was compared. 3DeepM can be used in a multitude of applications that use multispectral images, such as remote sensing or medical diagnosis. In addition, the small number of parameters of 3DeepM make it ideal for application in online classification systems aboard autonomous robots or unmanned vehicles. View Full-Text
Keywords: deep learning architectures; multispectral grape classification; multispectral computer vision system deep learning architectures; multispectral grape classification; multispectral computer vision system
Show Figures

Graphical abstract

MDPI and ACS Style

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/rs13040729

AMA Style

Navarro PJ, Miller L, Gila-Navarro A, Díaz-Galián MV, Aguila DJ, Egea-Cortines M. 3DeepM: An Ad Hoc Architecture Based on Deep Learning Methods for Multispectral Image Classification. Remote Sensing. 2021; 13(4):729. https://doi.org/10.3390/rs13040729

Chicago/Turabian Style

Navarro, Pedro J.; Miller, Leanne; Gila-Navarro, Alberto; Díaz-Galián, María V.; Aguila, Diego J.; Egea-Cortines, Marcos. 2021. "3DeepM: An Ad Hoc Architecture Based on Deep Learning Methods for Multispectral Image Classification" Remote Sens. 13, no. 4: 729. https://doi.org/10.3390/rs13040729

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop