Assessment of light environment conditions for reconstruction of multispectral images by conditional adversarial networks

Simple item page
dc.article.number104305
dc.catalogadorgrr
dc.contributor.authorArevalo Ramirez, Tito Andre
dc.contributor.authorMenéndez, Oswaldo
dc.contributor.authorVillacrés, Juan
dc.contributor.authorGuevara, Javier
dc.contributor.authorGuamán-Rivera, Robert
dc.contributor.authorDemarco, Rodrigo
dc.contributor.authorAuat Cheein, Fernando
dc.date.accessioned2025-10-24T19:30:18Z
dc.date.available2025-10-24T19:30:18Z
dc.date.issued2025
dc.description.abstractUnderstanding vegetation through its reflectance in the visible and near-infrared spectrum is vital for gaining biophysical and structural insights about vegetation. However, the spectral reflectance on meaningful bands (e.g., red-edge, near-infrared) is not always available because of the camera’s spectral response restrictions. In this context, previous research addresses the lack of multispectral information by reconstructing it using deeplearning approaches. Although there are promising outcomes, the influence of varying illumination conditions on this process still needs to be explored. Thus, this work examines if conditional Generative Adversarial Networks (cGANs) can infer environment illumination for achieving an appropriate multispectral image reconstruction. In particular, the spectral reconstruction performance of cGANs is investigated under six different scenarios with different illumination (occurring over a whole day), focusing on green, red-edge, and nearinfrared bands. Note that the dataset used for this research has become publicly available. These results indicated that illumination conditions influenced the performance of cGAN models in generating spectral images. Specifically, the cGANs could not infer the source image illumination to output a reliable reconstructed spectral image. Furthermore, although including samples under different illumination improved cGANs’ performance, the generated multispectral images tended to be darker than actual images.
dc.format.extent17 páginas
dc.fuente.origenORCID
dc.identifier.doi10.1016/j.biosystemseng.2025.104305
dc.identifier.eissn1537-5129
dc.identifier.issn1537-5110
dc.identifier.scopusidSCOPUS_ID:105018585857
dc.identifier.urihttps://doi.org/10.1016/j.biosystemseng.2025.104305
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/106365
dc.information.autorucEscuela de Ingeniería; Arevalo Ramirez, Tito Andre; 0000-0003-2542-6545; 1300544
dc.language.isoen
dc.nota.accesocontenido parcial
dc.revistaBiosystems Engineering
dc.rightsacceso restringido
dc.subjectReflectance reconstruction
dc.subjectIllumination conditions
dc.subjectSun view angle
dc.subjectRemote sensing
dc.subjectVegetation shadows
dc.subject.ddc620
dc.subject.deweyIngenieríaes_ES
dc.subject.ods15 Life on land
dc.subject.odspa15 Vida de ecosistemas terrestres
dc.titleAssessment of light environment conditions for reconstruction of multispectral images by conditional adversarial networks
dc.typeartículo
dc.volumen260
sipa.codpersvinculados1300544
sipa.indexScopus
Files
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.98 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Artículos de revistas