Centre dedocumentation
scientifique

Polarization of light reflected by grass: modeling using visible-sunlit areas / Bin Yang in Photogrammetric Engineering & Remote Sensing, PERS, vol 86 n° 12 (December 2020)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 86 n° 12 (December 2020) . - pp 745 - 752 Titre : Polarization of light reflected by grass: modeling using visible-sunlit areas Type de document : Article/Communication Auteurs : Bin Yang, Auteur ; Lei Yan, Auteur ; Siyuan Liu, Auteur Année de publication : 2020 Article en page(s) : pp 745 - 752 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] aérosol [Termes IGN] canopée [Termes IGN] distribution du coefficient de réflexion bidirectionnelle BRDF [Termes IGN] ensoleillement [Termes IGN] image POLDER [Termes IGN] image Terra-MODIS [Termes IGN] Leaf Area Index [Termes IGN] polarisation [Termes IGN] réflectance de surface [Termes IGN] réflectance végétale Résumé : (Auteur) The Bidirectional polarization distribution function (BPDF) of land surfaces is important for studies of land surfaces and aerosol. With the availability of a huge number of polarization measurements, several semi-empirical BPDF models have been proposed. However, these models do not pay much attention to canopy structure, which is fundamental for generation of polarization. In this article, we propose a new BPDF model using canopy structure information, which is parameterized by visible-sunlit areas. It is evaluated over grassland using POLDER BPDF and MODIS leaf area index data sets. Experiments suggest that compared to Nadal–Bréon and Litvinov models, the new BPDF model reduces root-mean-square error by 7% and 10%, respectively. The new BPDF model also provides better performance when it is fitted using observations clustered by sun zenith angle. The new BPDF model thus provides an effective tool for the study of land surface polarization. Numéro de notice : A2020-763 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.14358/PERS.86.12.745 Date de publication en ligne : 01/12/2020 En ligne : https://doi.org/10.14358/PERS.86.12.745 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96552 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
105-2020121	SL	Revue	Centre de documentation	Revues en salle	Disponible

PPD: Pyramid Patch Descriptor via convolutional neural network / Jie Wan in Photogrammetric Engineering & Remote Sensing, PERS, vol 85 n° 9 (September 2019)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 85 n° 9 (September 2019) . - pp 673 - 686 Titre : PPD: Pyramid Patch Descriptor via convolutional neural network Type de document : Article/Communication Auteurs : Jie Wan, Auteur ; Alper Yilmaz, Auteur ; Lei Yan, Auteur Année de publication : 2019 Article en page(s) : pp 673 - 686 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse comparative [Termes IGN] appariement d'images [Termes IGN] benchmark spatial [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] données localisées de référence [Termes IGN] échantillonnage d'image [Termes IGN] état de l'art [Termes IGN] extraction de données [Termes IGN] image aérienne [Termes IGN] image satellite [Termes IGN] jeu de données localisées Résumé : (Auteur) Local features play an important role in remote sensing image matching, and handcrafted features have been excessively used in this area for a long time. This article proposes a pyramid convolutional neural triplet network that extracts a 128-dimensional deep descriptor that significantly improves the matching performance. The proposed approach first extracts deep descriptors of the anchor patches and corresponding positive patches in a batch using the proposed pyramid convolutional neural network. Following this step, the approaches chooses the closest negative patch for each anchor patch and corresponding positive patch pair to form the triplet sample based on the descriptor distances among all other image patches in the batch. These triplets are used to optimize the parameters of the network using a new loss function. We evaluated the proposed deep descriptors on two benchmark data sets (Brown and HPatches) as well as real image data sets. The results reveal that the proposed descriptor achieves the state-of-the-art performance on the Brown data set and a comparatively very high performance on the HPatches data set. The proposed approach finds more correct matches than the classical handcrafted feature descriptors on aerial image pairs and is observed to be robust to variations in the viewpoint and illumination. Numéro de notice : A2019-416 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.14358/PERS.85.9.673 Date de publication en ligne : 01/09/2019 En ligne : https://doi.org/10.14358/PERS.85.9.673 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93543 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
105-2019091	SL	Revue	Centre de documentation	Revues en salle	Disponible