Centre de documentation
scientifique

Dépouillements

A manifold alignment approach for hyperspectral image visualization with natural color / Danping Liao in IEEE Transactions on geoscience and remote sensing, vol 54 n° 6 (June 2016)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 54 n° 6 (June 2016) . - pp 3151 - 3162 Titre : A manifold alignment approach for hyperspectral image visualization with natural color Type de document : Article/Communication Auteurs : Danping Liao, Auteur ; Yuntao Qian, Auteur ; Jun Zhou, Auteur ; Yuan Yan Tang, Auteur Année de publication : 2016 Article en page(s) : pp 3151 - 3162 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte [Termes IGN] alignement semi-dirigé [Termes IGN] appariement de points [Termes IGN] couleur (variable spectrale) [Termes IGN] image à haute résolution [Termes IGN] image en couleur [Termes IGN] image hyperspectrale Résumé : (Auteur) The trichromatic visualization of hundreds of bands in a hyperspectral image (HSI) has been an active research topic. The visualized image shall convey as much information as possible from the original data and facilitate easy image interpretation. However, most existing methods display HSIs in false color, which contradicts with user experience and expectation. In this paper, we propose a new framework for visualizing an HSI with natural color by the fusion of an HSI and a high-resolution color image via manifold alignment. Manifold alignment projects several data sets to a shared embedding space where the matching points between them are pairwise aligned. The embedding space bridges the gap between the high-dimensional spectral space of the HSI and the RGB space of the color image, making it possible to transfer natural color and spatial information in the color image to the HSI. In this way, a visualized image with natural color distribution and fine spatial details can be generated. Another advantage of the proposed method is its flexible data setting for various scenarios. As our approach only needs to search a limited number of matching pixel pairs that present the same object, the HSI and the color image can be captured from the same or semantically similar sites. Moreover, the learned projection function from the hyperspectral data space to the RGB space can be directly applied to other HSIs acquired by the same sensor to achieve a quick overview. Our method is also able to visualize user-specified bands as natural color images, which is very helpful for users to scan bands of interest. Numéro de notice : A2016-849 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2015.2512659 En ligne : http://dx.doi.org/10.1109/TGRS.2015.2512659 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82930 [article]

Vector attribute profiles for hyperspectral image classification / Erchan Aptoula in IEEE Transactions on geoscience and remote sensing, vol 54 n° 6 (June 2016)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 54 n° 6 (June 2016) . - pp 3208 - 3220 Titre : Vector attribute profiles for hyperspectral image classification Type de document : Article/Communication Auteurs : Erchan Aptoula, Auteur ; Mauro Dalla Mura, Auteur ; Sébastien Lefèvre, Auteur Année de publication : 2016 Article en page(s) : pp 3208 - 3220 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] classification automatique [Termes IGN] image hyperspectrale [Termes IGN] morphologie mathématique [Termes IGN] niveau de gris (image) [Termes IGN] vecteur propre [Termes IGN] végétation Résumé : (Auteur) Morphological attribute profiles are among the most prominent spectral-spatial pixel description methods. They are efficient, effective, and highly customizable multiscale tools based on hierarchical representations of a scalar input image. Their application to multivariate images in general and hyperspectral images in particular has been so far conducted using the marginal strategy, i.e., by processing each image band (eventually obtained through a dimension reduction technique) independently. In this paper, we investigate the alternative vector strategy, which consists in processing the available image bands simultaneously. The vector strategy is based on a vector-ordering relation that leads to the computation of a single max and min tree per hyperspectral data set, from which attribute profiles can then be computed as usual. We explore known vector-ordering relations for constructing such max trees and, subsequently, vector attribute profiles and introduce a combination of marginal and vector strategies. We provide an experimental comparison of these approaches in the context of hyperspectral classification with common data sets, where the proposed approach outperforms the widely used marginal strategy. Numéro de notice : A2016-850 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2015.2513424 En ligne : https://doi.org/10.1109/TGRS.2015.2513424 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82932 [article]

A multilevel point-cluster-based discriminative feature for ALS point cloud classification / Zhenxin Zhang in IEEE Transactions on geoscience and remote sensing, vol 54 n° 6 (June 2016)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 54 n° 6 (June 2016) . - pp 3309 - 3321 Titre : A multilevel point-cluster-based discriminative feature for ALS point cloud classification Type de document : Article/Communication Auteurs : Zhenxin Zhang, Auteur ; Liqiang Zhang, Auteur ; Xiaohua Tong, Auteur ; et al., Auteur Année de publication : 2016 Article en page(s) : pp 3309 - 3321 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] classification automatique [Termes IGN] codage [Termes IGN] extraction de traits caractéristiques [Termes IGN] semis de points [Termes IGN] séparateur à vaste marge [Termes IGN] télémétrie laser aéroporté Résumé : (Auteur) Point cloud classification plays a critical role in point cloud processing and analysis. Accurately classifying objects on the ground in urban environments from airborne laser scanning (ALS) point clouds is a challenge because of their large variety, complex geometries, and visual appearances. In this paper, a novel framework is presented for effectively extracting the shape features of objects from an ALS point cloud, and then, it is used to classify large and small objects in a point cloud. In the framework, the point cloud is split into hierarchical clusters of different sizes based on a natural exponential function threshold. Then, to take advantage of hierarchical point cluster correlations, latent Dirichlet allocation and sparse coding are jointly performed to extract and encode the shape features of the multilevel point clusters. The features at different levels are used to capture information on the shapes of objects of different sizes. This way, robust and discriminative shape features of the objects can be identified, and thus, the precision of the classification is significantly improved, particularly for small objects. Numéro de notice : A2016-851 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2514508 En ligne : https://doi.org/10.1109/TGRS.2016.2514508 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82983 [article]

Toward a generalizable image representation for large-scale change detection : application to generic damage analysis / Lionel Gueguen in IEEE Transactions on geoscience and remote sensing, vol 54 n° 6 (June 2016)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 54 n° 6 (June 2016) . - pp 3378 - 3387 Titre : Toward a generalizable image representation for large-scale change detection : application to generic damage analysis Type de document : Article/Communication Auteurs : Lionel Gueguen, Auteur ; Raffay Hamid, Auteur Année de publication : 2016 Article en page(s) : pp 3378 - 3387 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] analyse combinatoire (maths) [Termes IGN] analyse spatiale [Termes IGN] codage [Termes IGN] détection automatique [Termes IGN] géovisualisation [Termes IGN] image à haute résolution [Termes IGN] image multicapteur Résumé : (Auteur) Each year, multiple catastrophic events impact vulnerable populations around the planet. Assessing the damage caused by these events in a timely and accurate manner is crucial for efficient execution of relief efforts to help the victims of these calamities. Given the low accessibility of the damaged areas, high-resolution optical satellite imagery has emerged as a valuable source of information to quickly asses the extent of damage by manually analyzing the pre- and postevent imagery of the region. To make this analysis more efficient, multiple learning techniques using a variety of image representations have been proposed. However, most of these representations are prone to variabilities in capture angle, sun location, and seasonal variations. To evaluate these representations in the context of damage detection, we present a benchmark of 86 pre- and postevent image pairs with respective reference data derived from United Nation Operational Satellite Applications Programme (UNOSAT) assessment maps, spanning a total area of 4665 km2 from 11 different locations around the world. The technical contribution of our work is a novel image representation based on shape distributions of image patches encoded with locality-constrained linear coding. We empirically demonstrate that our proposed representation provides an improvement of at least 5%, in equal error rate, over alternate approaches. Finally, we present a thorough robustness analysis of the considered representational schemes, with respect to capture-angle variabilities and multiple sensor combinations. Numéro de notice : A2016-852 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2516402 En ligne : https://doi.org/10.1109/TGRS.2016.2516402 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82986 [article]

Automated bias-compensation approach for pushbroom sensor modeling using digital elevation model / Kwan-Young Oh in IEEE Transactions on geoscience and remote sensing, vol 54 n° 6 (June 2016)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 54 n° 6 (June 2016) . - pp 3400 - 3409 Titre : Automated bias-compensation approach for pushbroom sensor modeling using digital elevation model Type de document : Article/Communication Auteurs : Kwan-Young Oh, Auteur ; Hyung-Sup Jung, Auteur Année de publication : 2016 Article en page(s) : pp 3400 - 3409 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] compensation [Termes IGN] image Kompsat [Termes IGN] image SRTM [Termes IGN] modèle numérique de terrain [Termes IGN] modèle par fonctions rationnelles [Termes IGN] pouvoir de résolution géométrique Résumé : (Auteur) Bias compensation of rational polynomial coefficients (RPCs) is one of the most important preprocessing steps in high-resolution satellite image processing. It generally requires accurate ground control points (GCPs), but GCP acquisition is both time consuming and laborious. In this paper, we propose a time- and cost-efficient method for automated bias compensation of the RPC of high-resolution stereo image pairs. Two Korean Multi-purpose Satellite-2 (KOMPSAT-2) stereo image pairs acquired in Daejeon and Busan, Korea, and the Shuttle Radar Topographic Mission (SRTM) digital elevation model (DEM) with the spatial resolution of 3 arcsec (~90 m) were used for analysis. In the two study areas, 33 and 29 check points were respectively used for the performance evaluation. After bias compensation with the proposed method, the root-mean-square (RMS) errors for both of the study areas were less than 10 m, in all coordinate components, while the RMS error vectors were approximately 10 m. Although the RMS error vectors were slightly larger than the standard deviations of the residual errors of the initial ground coordinates, it would seem that they yielded acceptable values because the proposed method largely depends on the spatial resolution, the error of the SRTM DEM, the tie point selection error, and so on. Therefore, it can be concluded that the proposed method allows for the automated bias compensation of RPCs of KOMPSAT-2 images. Numéro de notice : A2016-853 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2517100 En ligne : http://dx.doi.org/10.1109/TGRS.2016.2517100 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82990 [article]

A simple method for detecting phenological change from time series of vegetation index / Jin Chen in IEEE Transactions on geoscience and remote sensing, vol 54 n° 6 (June 2016)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 54 n° 6 (June 2016) . - pp 3436 - 3449 Titre : A simple method for detecting phenological change from time series of vegetation index Type de document : Article/Communication Auteurs : Jin Chen, Auteur ; Yuhan Rao, Auteur ; Miaogen Shen, Auteur ; et al., Auteur Année de publication : 2016 Article en page(s) : pp 3436 - 3449 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] changement climatique [Termes IGN] Chine [Termes IGN] Enhanced vegetation index [Termes IGN] image Aqua-MODIS [Termes IGN] image Terra-MODIS [Termes IGN] indice de végétation [Termes IGN] phénologie [Termes IGN] série temporelle Résumé : (Auteur) Remote sensing is a valuable way to retrieve spatially continuous information on vegetation phenological changes, which are widely used as an indicator of climate change. We propose a simple method called weighted cross-correlogram spectral matching-phenology (CCSM-P), which combines CCSM and a weighted correlation system, for detecting vegetation phenological changes by using multiyear vegetation index (VI) time series. In experiments with simulated enhanced VI (EVI) for various scenarios, CCSM-P exhibited high accuracy and robustness to noise and the potential to capture long-term phenological change trends. For a temperate grassland in northern China, CCSM-P retrieved more reasonable vegetation spring phenology from Moderate Resolution Imaging Spectroradiometer (MODIS) EVI images than the MODIS phenology product (MCD12Q2). When validated against field phenological observations in five of the AmeriFlux Network sites in the U.S. (four deciduous broadleaf forest sites and a closed shrublands site), and a cropland site in China, CCSM-P exhibited mean absolute differences (MADs) ranging from 2 to 10 days (median: 4.2 days), whereas MAD of non-CCSM methods showed larger variations, ranging from 5 to 58 days (median: 21.3 days). This is because CCSM-P integrates field phenological observations. Compared with non-CCSM methods, which are widely used to identify phenological events, CCSM-P is more accurate and less dependent on prior knowledge (thresholds or predefined functions), which indicates its effectiveness and applicability for detecting year-to-year variations and long-term change trends in phenology, and should facilitate more reliable assessments of phenological changes in climate change studies. Numéro de notice : A2016-854 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2518167 En ligne : http://dx.doi.org/10.1109/TGRS.2016.2518167 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82992 [article]

Improving sensor fusion : a parametric method for the geometric coalignment of airborne hyperspectral and lidar data / Maximilian Brell in IEEE Transactions on geoscience and remote sensing, vol 54 n° 6 (June 2016)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 54 n° 6 (June 2016) . - pp 3460 - 3474 Titre : Improving sensor fusion : a parametric method for the geometric coalignment of airborne hyperspectral and lidar data Type de document : Article/Communication Auteurs : Maximilian Brell, Auteur ; Christian Rogass, Auteur ; Karl Segl, Auteur ; et al., Auteur Année de publication : 2016 Article en page(s) : pp 3460 - 3474 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte [Termes IGN] alignement semi-dirigé [Termes IGN] appariement géométrique [Termes IGN] données lidar [Termes IGN] image aérienne [Termes IGN] image hyperspectrale [Termes IGN] image multicapteur [Termes IGN] points homologues [Termes IGN] superposition d'images [Termes IGN] télémétrie laser aéroporté Résumé : (Auteur) Synergistic applications based on integrated hyperspectral and lidar data are receiving a growing interest from the remote-sensing community. A prerequisite for the optimum sensor fusion of hyperspectral and lidar data is an accurate geometric coalignment. The simple unadjusted integration of lidar elevation and hyperspectral reflectance causes a substantial loss of information and does not exploit the full potential of both sensors. This paper presents a novel approach for the geometric coalignment of hyperspectral and lidar airborne data, based on their respective adopted return intensity information. The complete approach incorporates ray tracing and subpixel procedures in order to overcome grid inherent discretization. It aims at the correction of extrinsic and intrinsic (camera resectioning) parameters of the hyperspectral sensor. In additional to a tie-point-based coregistration, we introduce a ray-tracing-based back projection of the lidar intensities for area-based cost aggregation. The approach consists of three processing steps. First is a coarse automatic tie-point-based boresight alignment. The second step coregisters the hyperspectral data to the lidar intensities. Third is a parametric coalignment refinement with an area-based cost aggregation. This hybrid approach of combining tie-point features and area-based cost aggregation methods for the parametric coregistration of hyperspectral intensity values to their corresponding lidar intensities results in a root-mean-square error of 1/3 pixel. It indicates that a highly integrated and stringent combination of different coalignment methods leads to an improvement of the multisensor coregistration. Numéro de notice : A2016-855 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2518930 En ligne : https://doi.org/10.1109/TGRS.2016.2518930 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82994 [article]

Scale effect in indirect measurement of leaf area index / Guangjian Yan in IEEE Transactions on geoscience and remote sensing, vol 54 n° 6 (June 2016)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 54 n° 6 (June 2016) . - pp 3475 - 3484 Titre : Scale effect in indirect measurement of leaf area index Type de document : Article/Communication Auteurs : Guangjian Yan, Auteur ; Ronghai Hu, Auteur ; Yiting Wang, Auteur ; et al., Auteur Année de publication : 2016 Article en page(s) : pp 3475 - 3484 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] indice foliaire [Termes IGN] longueur [Termes IGN] mesure optique [Termes IGN] méthode de mesure [Termes IGN] modèle non linéaire [Termes IGN] surface hétérogène Résumé : (Auteur) Scale effect, which is caused by a combination of model nonlinearity and surface heterogeneity, has been of interest to the remote sensing community for decades. However, there is no current analysis of scale effect in the ground-based indirect measurement of leaf area index (LAI), where model nonlinearity and surface heterogeneity also exist. This paper examines the scale effect on the indirect measurement of LAI. We built multiscale data sets based on realistic scenes and field measurements. We then implemented five representative methods of indirect LAI measurement at scales (segment lengths) that range from meters to hundreds of meters. The results show varying degrees of deviation and fluctuation that exist in all five methods when the segment length is shorter than 20 m. The retrieved LAI from either Beer's law or the gap-size distribution method shows a decreasing trend with increasing segment lengths. The length at which the LAI values begin to stabilize is about a full period of row in row crops and 100 m in broadleaf or coniferous forests. The impacts of segment length on the finite-length averaging method, the combination of gap-size distribution and finite-length methods, and the path-length distribution method are relatively small. These three methods stabilize at the segment scale longer than 20 m in all scenes. We also find that computing the average LAI of all of the short segment lengths, which is commonly done, is not as good as merging these short segments into a longer one and computing the LAI value of the merged one. Numéro de notice : A2016-856 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2519098 En ligne : https://doi.org/10.1109/TGRS.2016.2519098 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82995 [article]

Supervised classification of very high resolution optical images using wavelet-based textural features / Olivier Regniers in IEEE Transactions on geoscience and remote sensing, vol 54 n° 6 (June 2016)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 54 n° 6 (June 2016) . - pp 3722 - 3735 Titre : Supervised classification of very high resolution optical images using wavelet-based textural features Type de document : Article/Communication Auteurs : Olivier Regniers, Auteur ; Lionel Bombrun, Auteur ; Virginie Lafon, Auteur ; Christian Germain, Auteur Année de publication : 2016 Article en page(s) : pp 3722 - 3735 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse multivariée [Termes IGN] classification dirigée [Termes IGN] extraction automatique [Termes IGN] image à très haute résolution [Termes IGN] image optique [Termes IGN] image panchromatique [Termes IGN] image Pléiades [Termes IGN] texture d'image Résumé : (Auteur) In this paper, we explore the potentialities of using wavelet-based multivariate models for the classification of very high resolution optical images. A strategy is proposed to apply these models in a supervised classification framework. This strategy includes a content-based image retrieval analysis applied on a texture database prior to the classification in order to identify which multivariate model performs the best in the context of application. Once identified, the best models are further applied in a supervised classification procedure by extracting texture features from a learning database and from regions obtained by a presegmentation of the image to classify. The classification is then operated according to the decision rules of the chosen classifier. The use of the proposed strategy is illustrated in two real case applications using Pléiades panchromatic images: the detection of vineyards and the detection of cultivated oyster fields. In both cases, at least one of the tested multivariate models displays higher classification accuracies than gray-level cooccurrence matrix descriptors. Its high adaptability and the low number of parameters to be set are other advantages of the proposed approach. Numéro de notice : A2016-858 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2526078 En ligne : http://dx.doi.org/10.1109/TGRS.2016.2526078 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=83002 [article]