Mostrar el registro sencillo del ítem
dc.contributor.author
Díaz, Gastón Mauro
dc.contributor.author
Negri, Pablo Augusto
dc.contributor.author
Lencinas, José Daniel
dc.date.available
2022-10-14T16:49:42Z
dc.date.issued
2021-01
dc.identifier.citation
Díaz, Gastón Mauro; Negri, Pablo Augusto; Lencinas, José Daniel; Toward making canopy hemispherical photography independent of illumination conditions: A deep-learning-based approach; Elsevier Science; Agricultural And Forest Meteorology; 296; 1-2021; 1-13
dc.identifier.issn
0168-1923
dc.identifier.uri
http://hdl.handle.net/11336/173290
dc.description.abstract
Hemispherical photography produces the most accurate results when working with well-exposed photographs acquired under diffuse light conditions (diffuse-light images). Obtaining such data can be prohibitively expensive when surveying hundreds of plots is required. A relatively inexpensive alternative is using photographs acquired under direct sunlight (sunlight images). However, this practice leads to high errors since the standard processing algorithms expect diffuse-light imagery. Here, instead of using classification algorithms, which is the unique dominant practice, we approached the processing of sunlight images using deep learning (DL) regression. We implemented DL systems by using the general-purpose convolutional neural networks known as VGGNet 16, VGGNet 19, Res-Net, and SE-ResNet. We trained them with 608 samples acquired in a South American temperate forest populated by Nothofagus pumilio. For their evaluation, we used 113 independent samples. Each sample (X, Y) consisted of one or several sunlight images (X), and the plant area index (PAI) and effective PAI (PAIe) extracted from a diffuse-light image (Y). The sunlight images include clear sky and broken clouds with sun elevation from 15° to 47°. We obtained the best results with the SE-ResNet architecture. The system requires a low-resolution input reprojected to cylindrical, and it can make predictions with 10% root mean square error, even from pictures acquired with automatic exposure, which challenge previous findings. Furthermore, similar results (R2= 0.9, n = 104) can be obtained by feeding the system with photographs acquired with an inexpensive fisheye converter attached to a smartphone. Altogether, results indicate that our approach is a cost-efficient option for surveying hundreds of plots under direct sunlight. Therefore, combining our method with the traditional procedures provides processing solutions for virtually all kinds of illumination conditions.
dc.format
application/pdf
dc.language.iso
eng
dc.publisher
Elsevier Science
dc.rights
info:eu-repo/semantics/restrictedAccess
dc.rights.uri
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.subject
COMPUTER VISION
dc.subject
FISHEYE LENS
dc.subject
FOREST STRUCTURE
dc.subject
LEAF AREA INDEX
dc.subject
MACHINE LEARNING
dc.subject
NON-DIFFUSE LIGHT
dc.subject.classification
Ciencias de las Plantas, Botánica
dc.subject.classification
Ciencias Biológicas
dc.subject.classification
CIENCIAS NATURALES Y EXACTAS
dc.title
Toward making canopy hemispherical photography independent of illumination conditions: A deep-learning-based approach
dc.type
info:eu-repo/semantics/article
dc.type
info:ar-repo/semantics/artículo
dc.type
info:eu-repo/semantics/publishedVersion
dc.date.updated
2022-09-22T16:15:59Z
dc.journal.volume
296
dc.journal.pagination
1-13
dc.journal.pais
Países Bajos
dc.journal.ciudad
Amsterdam
dc.description.fil
Fil: Díaz, Gastón Mauro. Centro de Investigación y Extensión Forestal Andino Patagónico; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
dc.description.fil
Fil: Negri, Pablo Augusto. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Investigación en Ciencias de la Computación; Argentina
dc.description.fil
Fil: Lencinas, José Daniel. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Centro de Investigación y Extensión Forestal Andino Patagónico; Argentina
dc.journal.title
Agricultural And Forest Meteorology
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/doi/http://dx.doi.org/10.1016/j.agrformet.2020.108234
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/url/https://www.sciencedirect.com/science/article/abs/pii/S0168192320303361
Archivos asociados