Centre de documentation
scientifique

Dépouillements

Robust multitask learning with three-dimensional empirical mode decomposition-based features for hyperspectral classification / Zhi He in ISPRS Journal of photogrammetry and remote sensing, vol 121 (November 2016)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 121 (November 2016) . - pp 11 – 27 Titre : Robust multitask learning with three-dimensional empirical mode decomposition-based features for hyperspectral classification Type de document : Article/Communication Auteurs : Zhi He, Auteur ; Lin Liu, Auteur Année de publication : 2016 Article en page(s) : pp 11 – 27 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage automatique [Termes IGN] classification [Termes IGN] décomposition d'image [Termes IGN] image hyperspectrale [Termes IGN] module d'extension Résumé : (Auteur) Empirical mode decomposition (EMD) and its variants have recently been applied for hyperspectral image (HSI) classification due to their ability to extract useful features from the original HSI. However, it remains a challenging task to effectively exploit the spectral-spatial information by the traditional vector or image-based methods. In this paper, a three-dimensional (3D) extension of EMD (3D-EMD) is proposed to naturally treat the HSI as a cube and decompose the HSI into varying oscillations (i.e. 3D intrinsic mode functions (3D-IMFs)). To achieve fast 3D-EMD implementation, 3D Delaunay triangulation (3D-DT) is utilized to determine the distances of extrema, while separable filters are adopted to generate the envelopes. Taking the extracted 3D-IMFs as features of different tasks, robust multitask learning (RMTL) is further proposed for HSI classification. In RMTL, pairs of low-rank and sparse structures are formulated by trace-norm and l1,2l1,2-norm to capture task relatedness and specificity, respectively. Moreover, the optimization problems of RMTL can be efficiently solved by the inexact augmented Lagrangian method (IALM). Compared with several state-of-the-art feature extraction and classification methods, the experimental results conducted on three benchmark data sets demonstrate the superiority of the proposed methods. Numéro de notice : A2016--011 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2016.08.007 En ligne : http://dx.doi.org/10.1016/j.isprsjprs.2016.08.007 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=83873 [article]

Localization of a mobile laser scanner via dimensional reduction / Ville V. Lehtola, in ISPRS Journal of photogrammetry and remote sensing, vol 121 (November 2016)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 121 (November 2016) . - pp 48 – 59 Titre : Localization of a mobile laser scanner via dimensional reduction Type de document : Article/Communication Auteurs : Ville V. Lehtola,, Auteur ; Juho-Pekka Virtanen, Auteur ; Matti Vaaja, Auteur ; et al., Auteur Année de publication : 2016 Article en page(s) : pp 48 – 59 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] acquisition simultanée [Termes IGN] positionnement inertiel [Termes IGN] service fondé sur la position [Termes IGN] télémétrie laser mobile [Termes IGN] télémétrie laser terrestre Résumé : (Auteur) We extend the concept of intrinsic localization from a theoretical one-dimensional (1D) solution onto a 2D manifold that is embedded in a 3D space, and then recover the full six degrees of freedom for a mobile laser scanner with a simultaneous localization and mapping algorithm (SLAM). By intrinsic localization, we mean that no reference coordinate system, such as global navigation satellite system (GNSS), nor inertial measurement unit (IMU) are used. Experiments are conducted with a 2D laser scanner mounted on a rolling prototype platform, VILMA. The concept offers potential in being extendable to other wheeled platforms. Numéro de notice : A2016--014 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2016.09.004 En ligne : https://doi.org/10.1016/j.isprsjprs.2016.09.004 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=83875 [article]

Semi-supervised hyperspectral classification from a small number of training samples using a co-training approach / Michał Romaszewski in ISPRS Journal of photogrammetry and remote sensing, vol 121 (November 2016)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 121 (November 2016) . - pp 60 – 76 Titre : Semi-supervised hyperspectral classification from a small number of training samples using a co-training approach Type de document : Article/Communication Auteurs : Michał Romaszewski, Auteur ; Przemysław Głomb, Auteur ; Michał Cholewa, Auteur Année de publication : 2016 Article en page(s) : pp 60 – 76 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] algorithme d'apprentissage [Termes IGN] classification automatique [Termes IGN] détection de cible [Termes IGN] données localisées [Termes IGN] image hyperspectrale [Termes IGN] performance Résumé : (Auteur) We present a novel semi-supervised algorithm for classification of hyperspectral data from remote sensors. Our method is inspired by the Tracking-Learning-Detection (TLD) framework, originally applied for tracking objects in a video stream. TLD introduced the co-training approach called P-N learning, making use of two independent ‘experts’ (or learners) that scored samples in different feature spaces. In a similar fashion, we formulated the hyperspectral classification task as a co-training problem, that can be solved with the P-N learning scheme. Our method uses both spatial and spectral features of data, extending a small set of initial labelled samples during the process of region growing. We show that this approach is stable and achieves very good accuracy even for small training sets. We analyse the algorithm’s performance on several publicly available hyperspectral data sets. Numéro de notice : A2016--015 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2016.08.011 En ligne : https://doi.org/10.1016/j.isprsjprs.2016.08.011 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=83877 [article]

Skeletal camera network embedded structure-from-motion for 3D scene reconstruction from UAV images / Zhihua Xua in ISPRS Journal of photogrammetry and remote sensing, vol 121 (November 2016)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 121 (November 2016) . - pp 113 - 127 Titre : Skeletal camera network embedded structure-from-motion for 3D scene reconstruction from UAV images Type de document : Article/Communication Auteurs : Zhihua Xua, Auteur ; Lixin Wud, Auteur ; Markus Gerke, Auteur ; et al., Auteur Année de publication : 2016 Article en page(s) : pp 113 - 127 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Acquisition d'image(s) et de donnée(s) [Termes IGN] appariement de points [Termes IGN] connexité (topologie) [Termes IGN] drone [Termes IGN] prise de vue aérienne [Termes IGN] reconstruction 3D [Termes IGN] squelettisation [Termes IGN] structure-from-motion [Termes IGN] topologie Résumé : (Auteur) Structure-from-Motion (SfM) techniques have been widely used for 3D scene reconstruction from multi-view images. However, due to the large computational costs of SfM methods there is a major challenge in processing highly overlapping images, e.g. images from unmanned aerial vehicles (UAV). This paper embeds a novel skeletal camera network (SCN) into SfM to enable efficient 3D scene reconstruction from a large set of UAV images. First, the flight control data are used within a weighted graph to construct a topologically connected camera network (TCN) to determine the spatial connections between UAV images. Second, the TCN is refined using a novel hierarchical degree bounded maximum spanning tree to generate a SCN, which contains a subset of edges from the TCN and ensures that each image is involved in at least a 3-view configuration. Third, the SCN is embedded into the SfM to produce a novel SCN-SfM method, which allows performing tie-point matching only for the actually connected image pairs. The proposed method was applied in three experiments with images from two fixed-wing UAVs and an octocopter UAV, respectively. In addition, the SCN-SfM method was compared to three other methods for image connectivity determination. The comparison shows a significant reduction in the number of matched images if our method is used, which leads to less computational costs. At the same time the achieved scene completeness and geometric accuracy are comparable. Numéro de notice : A2016--016 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2016.08.013 En ligne : https://doi.org/10.1016/j.isprsjprs.2016.08.013 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=83878 [article]

A global study of NDVI difference among moderate-resolution satellite sensors / Xingwang Fan in ISPRS Journal of photogrammetry and remote sensing, vol 121 (November 2016)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 121 (November 2016) . - pp 177 – 191 Titre : A global study of NDVI difference among moderate-resolution satellite sensors Type de document : Article/Communication Auteurs : Xingwang Fan, Auteur ; Yuanbo Liu, Auteur Année de publication : 2016 Article en page(s) : pp 177 – 191 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] analyse comparative [Termes IGN] effet atmosphérique [Termes IGN] image Aqua-MODIS [Termes IGN] image multicapteur [Termes IGN] image NPP-VIIRS [Termes IGN] image Terra-MODIS [Termes IGN] image TIROS-AVHRR [Termes IGN] Normalized Difference Vegetation Index [Termes IGN] occupation du sol [Termes IGN] variation saisonnière Résumé : (Auteur) Moderate-resolution sensors, including AVHRR (Advanced Very High Resolution Radiometer), MODIS (MODerate-resolution Imaging Spectroradiometer) and VIIRS (Visible-Infrared Imager-Radiometer Suite), have provided over forty years of global scientific data. In the form of NDVI (Normalized Difference Vegetation Index), these data greatly benefit environmental studies. However, their usefulness is compromised by sensor differences. This study investigates the global NDVI difference and its spatio-temporal patterns among typical moderate-resolution sensors, as supported by state-of-the-art remote sensing derived products. Our study demonstrates that the atmosphere plays a secondary role to LULC (Land Use/Land Cover) in inter-sensor NDVI differences. With reference to AVHRR/3, AVHRR/1 and 2 exhibit negative NDVI biases for vegetated land cover types. In summer (July), the area of negative bias shifts northward, and the magnitude increases in the Northern Hemisphere. For most LULC types, the bias generally shifts in the negative direction from winter (January) to summer. A linear regression of the NDVI difference versus NDVI shows a close correlation between the slope value and vegetation phenology. Overall, NDVI differences are controlled by LULC type and vegetation phenology. Our study can be used to generate a long-term, consistent NDVI data set from composite MODIS and AVHRR NDVI data. LULC-dependent and temporally variable correction equations are recommended to reduce inter-sensor NDVI differences. Numéro de notice : A2016--017 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2016.09.008 En ligne : http://dx.doi.org/10.1016/j.isprsjprs.2016.09.008 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=83879 [article]

Non-rigid registration of 3D point clouds under isometric deformation / Xuming Ge in ISPRS Journal of photogrammetry and remote sensing, vol 121 (November 2016)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 121 (November 2016) . - pp 192 – 202 Titre : Non-rigid registration of 3D point clouds under isometric deformation Type de document : Article/Communication Auteurs : Xuming Ge, Auteur Année de publication : 2016 Article en page(s) : pp 192 – 202 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] alignement [Termes IGN] déformation géométrique [Termes IGN] image 3D [Termes IGN] isométrie [Termes IGN] semis de points Résumé : (Auteur) An algorithm for pairwise non-rigid registration of 3D point clouds is presented in the specific context of isometric deformations. The critical step is registration of point clouds at different epochs captured from an isometric deformation surface within overlapping regions. Based on characteristics invariant under isometric deformation, a variant of the four-point congruent sets algorithm is applied to generate correspondences between two deformed point clouds, and subsequently a RANSAC framework is used to complete cluster extraction in preparation for global optimal alignment. Examples are presented and the results compared with existing approaches to demonstrate the two main contributions of the technique: a success rate for generating true correspondences of 90% and a root mean square error after final registration of 2–3 mm. Numéro de notice : A2016--018 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2016.09.009 En ligne : https://doi.org/10.1016/j.isprsjprs.2016.09.009 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=83880 [article]