Descripteur
Documents disponibles dans cette catégorie (1260)
![](./images/expand_all.gif)
![](./images/collapse_all.gif)
Etendre la recherche sur niveau(x) vers le bas
Virtual Support Vector Machines with self-learning strategy for classification of multispectral remote sensing imagery / Christian Geiss in ISPRS Journal of photogrammetry and remote sensing, vol 151 (May 2019)
![]()
[article]
Titre : Virtual Support Vector Machines with self-learning strategy for classification of multispectral remote sensing imagery Type de document : Article/Communication Auteurs : Christian Geiss, Auteur ; Patrick Aravena Pelizari, Auteur ; Lukas Blickensdörfer, Auteur ; Hannes Taubenböck, Auteur Année de publication : 2019 Article en page(s) : pp 42 - 58 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] analyse d'image orientée objet
[Termes IGN] apprentissage automatique
[Termes IGN] classification
[Termes IGN] classification par séparateurs à vaste marge
[Termes IGN] Cologne
[Termes IGN] échantillon
[Termes IGN] échantillonnage
[Termes IGN] image à très haute résolution
[Termes IGN] image multibande
[Termes IGN] invariant
[Termes IGN] Kenya
[Termes IGN] séparateur à vaste margeRésumé : (Auteur) We follow the idea of learning invariant decision functions for remote sensing image classification with Support Vector Machines (SVM). To do so, we generate artificially transformed samples (i.e., virtual samples) from available prior knowledge. Labeled samples closest to the separating hyperplane with maximum margin (i.e., the Support Vectors) are identified by learning an initial SVM model. The Support Vectors are used for generating virtual samples by perturbing the features to which the model should be invariant. Subsequently, the model is relearned using the Support Vectors and the virtual samples to eventually alter the hyperplane with maximum margin and enhance generalization capabilities of decision functions. In contrast to existing approaches, we establish a self-learning procedure to ultimately prune non-informative virtual samples from a possibly arbitrary invariance generation process to allow for robust and sparse model solutions. The self-learning strategy jointly considers a similarity and margin sampling constraint. In addition, we innovatively explore the invariance generation process in the context of an object-based image analysis framework. Image elements (i.e., pixels) are aggregated to image objects (as represented by segments/superpixels) with a segmentation algorithm. From an initial singular segmentation level, invariances are encoded by varying hyperparameters of the segmentation algorithm in terms of scale and shape. Experimental results are obtained from two very high spatial resolution multispectral data sets acquired over the city of Cologne, Germany, and the Hagadera Refugee Camp, Kenya. Comparative model accuracy evaluations underline the favorable performance properties of the proposed methods especially in settings with very few labeled samples. Numéro de notice : A2019-203 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.03.001 Date de publication en ligne : 12/03/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.03.001 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92666
in ISPRS Journal of photogrammetry and remote sensing > vol 151 (May 2019) . - pp 42 - 58[article]Réservation
Réserver ce documentExemplaires(3)
Code-barres Cote Support Localisation Section Disponibilité 081-2019051 RAB Revue Centre de documentation En réserve L003 Disponible 081-2019053 DEP-RECP Revue LASTIG Dépôt en unité Exclu du prêt 081-2019052 DEP-RECF Revue Nancy Dépôt en unité Exclu du prêt Albedo estimation for real-time 3D reconstruction using RGB-D and IR data / Patrick Stotko in ISPRS Journal of photogrammetry and remote sensing, vol 150 (April 2019)
![]()
[article]
Titre : Albedo estimation for real-time 3D reconstruction using RGB-D and IR data Type de document : Article/Communication Auteurs : Patrick Stotko, Auteur ; Michael Weinmann, Auteur ; Reinhard Klein, Auteur Année de publication : 2019 Article en page(s) : pp 213 - 225 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] albedo
[Termes IGN] image infrarouge
[Termes IGN] image RVB
[Termes IGN] longueur d'onde
[Termes IGN] méthode de réduction d'énergie
[Termes IGN] reconstruction 3D
[Termes IGN] réflectance
[Termes IGN] segmentation d'image
[Termes IGN] temps réel
[Termes IGN] texture d'imageRésumé : (Auteur) Reconstructing scenes in real-time using low-cost sensors has gained increasing attention in recent research and enabled numerous applications in graphics, vision, and robotics. While current techniques offer a substantial improvement regarding the quality of the reconstructed geometry, the degree of realism of the overall appearance is still lacking as the reconstruction of accurate surface appearance is highly challenging due to the complex interplay of surface geometry, reflectance properties and surrounding illumination. We present a novel approach that allows the reconstruction of both the geometry and the spatially varying surface albedo of a scene from RGB-D and IR data obtained via commodity sensors. In comparison to previous approaches, our approach offers an improved robustness and a significant speed-up to even fulfill the real-time requirements. For this purpose, we exploit the benefits of scene segmentation to improve albedo estimation due to the resulting better segment-wise coupling of IR and RGB data that takes into account the wavelength characteristics of different materials within the scene. The estimated albedo is directly integrated into the dense volumetric reconstruction framework using a novel weighting scheme to generate high-quality results. In our evaluation, we demonstrate that our approach allows albedo capturing of complicated scenarios including complex, high-frequent and strongly varying lighting as well as shadows. Numéro de notice : A2019-141 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.01.018 Date de publication en ligne : 04/03/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.01.018 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92479
in ISPRS Journal of photogrammetry and remote sensing > vol 150 (April 2019) . - pp 213 - 225[article]Réservation
Réserver ce documentExemplaires(3)
Code-barres Cote Support Localisation Section Disponibilité 081-2019041 RAB Revue Centre de documentation En réserve L003 Disponible 081-2019043 DEP-RECP Revue LASTIG Dépôt en unité Exclu du prêt 081-2019042 DEP-RECF Revue Nancy Dépôt en unité Exclu du prêt 3D hyperspectral point cloud generation: Fusing airborne laser scanning and hyperspectral imaging sensors for improved object-based information extraction / Maximilian Brell in ISPRS Journal of photogrammetry and remote sensing, vol 149 (March 2019)
![]()
[article]
Titre : 3D hyperspectral point cloud generation: Fusing airborne laser scanning and hyperspectral imaging sensors for improved object-based information extraction Type de document : Article/Communication Auteurs : Maximilian Brell, Auteur ; Karl Segl, Auteur ; Luis Guanter, Auteur ; Bodo Bookhagen, Auteur Année de publication : 2019 Article en page(s) : pp 200 - 214 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques
[Termes IGN] analyse des mélanges spectraux
[Termes IGN] capteur hyperspectral
[Termes IGN] classification orientée objet
[Termes IGN] données lidar
[Termes IGN] données localisées 3D
[Termes IGN] fusion de données
[Termes IGN] image hyperspectrale
[Termes IGN] impulsion laser
[Termes IGN] niveau de détail
[Termes IGN] segmentation d'image
[Termes IGN] segmentation sémantique
[Termes IGN] semis de pointsRésumé : (Auteur) Remote Sensing technologies allow to map biophysical, biochemical, and earth surface parameters of the land surface. Of especial interest for various applications in environmental and urban sciences is the combination of spectral and 3D elevation information. However, those two data streams are provided separately by different instruments, namely airborne laser scanner (ALS) for elevation and a hyperspectral imager (HSI) for high spectral resolution data. The fusion of ALS and HSI data can thus lead to a single data entity consistently featuring rich structural and spectral information. In this study, we present the application of fusing the first pulse return information from ALS data at a sub-decimeter spatial resolution with the lower-spatial resolution hyperspectral information available from the HSI into a hyperspectral point cloud (HSPC). During the processing, a plausible hyperspectral spectrum is assigned to every first-return ALS point. We show that the complementary implementation of spectral and 3D information at the point-cloud scale improves object-based classification and information extraction schemes. This improvements have great potential for numerous land-cover mapping and environmental applications. Numéro de notice : A2019-119 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.01.022 Date de publication en ligne : 06/02/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.01.022 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92448
in ISPRS Journal of photogrammetry and remote sensing > vol 149 (March 2019) . - pp 200 - 214[article]Réservation
Réserver ce documentExemplaires(3)
Code-barres Cote Support Localisation Section Disponibilité 081-2019031 RAB Revue Centre de documentation En réserve L003 Disponible 081-2019033 DEP-RECP Revue LASTIG Dépôt en unité Exclu du prêt 081-2019032 DEP-RECF Revue Nancy Dépôt en unité Exclu du prêt Conditional random field and deep feature learning for hyperspectral image classification / Fahim Irfan Alam in IEEE Transactions on geoscience and remote sensing, vol 57 n° 3 (March 2019)
![]()
[article]
Titre : Conditional random field and deep feature learning for hyperspectral image classification Type de document : Article/Communication Auteurs : Fahim Irfan Alam, Auteur ; Jun Zhou, Auteur ; Alan Wee-Chung Liew, Auteur ; Xiuping Jia, Auteur ; et al., Auteur Année de publication : 2019 Article en page(s) : pp 1612 - 1628 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] analyse multibande
[Termes IGN] champ aléatoire conditionnel
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] déconvolution
[Termes IGN] données localisées 3D
[Termes IGN] image hyperspectrale
[Termes IGN] voxelRésumé : (Auteur) Image classification is considered to be one of the critical tasks in hyperspectral remote sensing image processing. Recently, a convolutional neural network (CNN) has established itself as a powerful model in classification by demonstrating excellent performances. The use of a graphical model such as a conditional random field (CRF) contributes further in capturing contextual information and thus improving the classification performance. In this paper, we propose a method to classify hyperspectral images by considering both spectral and spatial information via a combined framework consisting of CNN and CRF. We use multiple spectral band groups to learn deep features using CNN, and then formulate deep CRF with CNN-based unary and pairwise potential functions to effectively extract the semantic correlations between patches consisting of 3-D data cubes. Furthermore, we introduce a deep deconvolution network that improves the final classification performance. We also introduced a new data set and experimented our proposed method on it along with several widely adopted benchmark data sets to evaluate the effectiveness of our method. By comparing our results with those from several state-of-the-art models, we show the promising potential of our method. Numéro de notice : A2019-131 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2018.2867679 Date de publication en ligne : 20/09/2018 En ligne : https://doi.org/10.1109/TGRS.2018.2867679 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92461
in IEEE Transactions on geoscience and remote sensing > vol 57 n° 3 (March 2019) . - pp 1612 - 1628[article]Hyperspectral image classification with squeeze multibias network / Leyuan Fang in IEEE Transactions on geoscience and remote sensing, vol 57 n° 3 (March 2019)
![]()
[article]
Titre : Hyperspectral image classification with squeeze multibias network Type de document : Article/Communication Auteurs : Leyuan Fang, Auteur ; Guangyun Liu, Auteur ; Shutao Li, Auteur ; Pedram Ghamisi, Auteur ; Jon Atli Benediktsson, Auteur Année de publication : 2019 Article en page(s) : pp 1291 - 1301 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] erreur systématique
[Termes IGN] image hyperspectraleRésumé : (Auteur) A convolutional neural network (CNN) has recently demonstrated its outstanding capability for the classification of hyperspectral images (HSIs). Typical CNN-based methods usually adopt image patches as inputs to the network. However, a fixed-size image patch in HSI with complex spatial contexts may contain multiple ground objects of different classes, which will deteriorate the classification performance of the CNN. In addition, traditional convolutional layers adopted in the CNN have a huge amount of parameters needed to be tuned, which will cause high computational cost. To address the above-mentioned issues, a novel squeeze multibias network (SMBN) is proposed for HSI classification. Specifically, the proposed SMBN first introduces the multibias module (MBM), which incorporates multibias into the rectified linear unit layers. The MBM can decouple the feature maps of input patches into multiple response maps (corresponding to different ground objects) and adaptively select the meaningful maps for classification. Furthermore, the proposed SMBN replaces the traditional convolutional layer with a squeeze convolution module, which can greatly reduce the number of parameters in the network, thus saving the running time, while still maintaining high classification accuracy. Experimental results on three real HSIs demonstrate the superiority of the proposed SMBN method over several state-of-the-art classification approaches. Numéro de notice : A2019-113 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2018.2865953 Date de publication en ligne : 13/09/2018 En ligne : https://doi.org/10.1109/TGRS.2018.2865953 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92453
in IEEE Transactions on geoscience and remote sensing > vol 57 n° 3 (March 2019) . - pp 1291 - 1301[article]A novel sharpening approach for superresolving multiresolution optical images / Claudia Paris in IEEE Transactions on geoscience and remote sensing, vol 57 n° 3 (March 2019)
PermalinkTree species classification in tropical forests using visible to shortwave infrared WorldView-3 images and texture analysis / Matheus Pinheiro Ferreira in ISPRS Journal of photogrammetry and remote sensing, vol 149 (March 2019)
PermalinkLearning spectral-spatial-temporal features via a recurrent convolutional neural network for change detection in multispectral imagery / Lichao Mou in IEEE Transactions on geoscience and remote sensing, vol 57 n° 2 (February 2019)
PermalinkTree cover mapping using hybrid fuzzy C-means method and multispectral satellite images / Linda Gulbe in Baltic forestry, vol 25 n° 1 ([01/02/2019])
PermalinkPermalinkPermalinkChallenges in grassland mowing event detection with multimodal Sentinel images / Anatol Garioud (2019)
PermalinkDétection et localisation d'objets 3D par apprentissage profond en topologie capteur / Pierre Biasutti (2019)
![]()
PermalinkPermalinkPermalink