Centre de documentation
scientifique

Dépouillements

Kernel-based domain-invariant feature selection in hyperspectral images for transfer learning / Claudio Persello in IEEE Transactions on geoscience and remote sensing, vol 54 n° 5 (May 2016)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 54 n° 5 (May 2016) . - pp 2615 - 2626 Titre : Kernel-based domain-invariant feature selection in hyperspectral images for transfer learning Type de document : Article/Communication Auteurs : Claudio Persello, Auteur ; Lorenzo Bruzzone, Auteur Année de publication : 2016 Article en page(s) : pp 2615 - 2626 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] classification [Termes IGN] extraction automatique [Termes IGN] image hyperspectrale [Termes IGN] méthode fondée sur le noyau [Termes IGN] séparateur à vaste marge Résumé : (Auteur) This paper presents a kernel-based feature selection method for the classification of hyperspectral images. The proposed method aims at selecting a subset of the original features that are both 1) relevant (discriminant) for the considered classification problem, i.e., preserve the functional relationship between input and output variables, and 2) invariant (stable) across different domains, i.e., minimize the data-set shift between the source and the target domains. Domains can be associated with hyperspectral images collected either on different geographical areas or on the same area at different times. We propose a novel measure of data-set shift for evaluating the domain stability, which computes the distance of the conditional distributions between the source and target domains in a reproducing kernel Hilbert space. Such a measure is defined on the basis of the kernel embeddings of the conditional distributions resulting in a nonparametric approach that does not require estimating the distribution of the classes. The adopted search strategy is based on a multiobjective optimization algorithm, which optimizes the two terms of the criterion function for the estimation of the Pareto-optimal solutions. This results in an effective approach of performing feature selection in a transfer learning setting. The experimental results obtained on two hyperspectral images show the effectiveness of the proposed method in selecting features with high generalization capabilities. Numéro de notice : A2016-843 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2015.2503885 En ligne : http://dx.doi.org/10.1109/TGRS.2015.2503885 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82887 [article]

Exploiting joint sparsity for pansharpening : the J-SparseFI algorithm / Xiao Xiang Zhu in IEEE Transactions on geoscience and remote sensing, vol 54 n° 5 (May 2016)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 54 n° 5 (May 2016) . - pp 2664 - 2681 Titre : Exploiting joint sparsity for pansharpening : the J-SparseFI algorithm Type de document : Article/Communication Auteurs : Xiao Xiang Zhu, Auteur ; Claas Grohnfeldt, Auteur ; Richard Bamler, Auteur Année de publication : 2016 Article en page(s) : pp 2664 - 2681 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] algorithme de fusion [Termes IGN] données clairsemées [Termes IGN] fusion d'images [Termes IGN] image multibande [Termes IGN] image panchromatique [Termes IGN] image Worldview [Termes IGN] reconstruction d'image [Termes IGN] régularisation de Tychonoff [Termes IGN] réponse spectrale Résumé : (Auteur) Recently, sparse signal representation of image patches has been explored to solve the pansharpening problem. Although these proposed sparse-reconstruction-based methods lead to promising results, three issues remained unsolved: 1) high computational cost; 2) no consideration given to the possibility of mutually correlated information in different multispectral channels; and 3) requirement that the spectral responses of the panchromatic (Pan) image and the multispectral image cover the same wavelength range, which is not necessarily valid for most sensors. In this paper, we propose a sophisticated sparse image fusion algorithm, which is named “jointly sparse fusion of images” (J-SparseFI). It is based on the earlier proposed sparse fusion of images (SparseFI) algorithm and overcomes the aforementioned three drawbacks of the existing sparse image fusion algorithms. The computational problem is handled by reducing the problem size and by proposing a fully parallelizable scheme. Moreover, J-SparseFI exploits the possible signal structure correlations between multispectral channels by introducing the joint sparsity model (JSM) and sharpening the highly correlated adjacent multispectral channels together. This is done by exploiting the distributed compressive sensing theory that restricts the solution of an underdetermined system by considering an ensemble of signals being jointly sparse. J-SparseFI also offers a practical solution to overcome spectral range mismatch between the Pan and multispectral images. By means of sensor spectral response and channel mutual correlation analysis, the multispectral channels are assigned to primary groups of joint channels, secondary groups of joint channels, and individual channels. Primary groups of joint channels, individual channels, and secondary groups of joint channels are then reconstructed sequentially, by the JSM or by modified SparseFI, using a dictionary trained from the Pan image or previously reconstructed high-resolution multispectral channels. A recipe of how to choose appropriate algorithm parameters, including the most crucial regularization parameter, is provided. The algorithm is evaluated and validated using WorldView-2-like images that are simulated using very high resolution airborne HySpex hyperspectral imagery and further practically demonstrated using real WorldView-2 images. The algorithm's performance is compared with other state-of-the-art methods. Visual and quantitative analyses demonstrate the high quality of the proposed method. In particular, the analysis of the difference images suggests that J-SparseFI is superior in image resolution recovery. Numéro de notice : A2016-844 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2015.2504261 En ligne : http://dx.doi.org/10.1109/TGRS.2015.2504261 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82890 [article]

An iterative haze optimized transformation for automatic cloud/haze detection of landsat imagery / Shuli Chen in IEEE Transactions on geoscience and remote sensing, vol 54 n° 5 (May 2016)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 54 n° 5 (May 2016) . - pp 2682 - 2694 Titre : An iterative haze optimized transformation for automatic cloud/haze detection of landsat imagery Type de document : Article/Communication Auteurs : Shuli Chen, Auteur ; Xuehong Chen, Auteur ; Jin Chen, Auteur ; et al., Auteur Année de publication : 2016 Article en page(s) : pp 2682 - 2694 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse comparative [Termes IGN] classification floue [Termes IGN] détection de flou [Termes IGN] télédétection Résumé : (Auteur) Most previous haze/cloud detection methods for Landsat imagery, e.g., haze optimized transformation (HOT), cannot adequately suppress land surface information and, in particular, often overestimate haze thickness over bright surfaces. This paper proposes an iterative HOT (IHOT) for improving haze detection with the help of a corresponding clear image. With an iterative procedure of regressions among HOT, the reflectance difference at the top of atmosphere (TOA) between hazy and clear images, and TOA reflectances of hazy and clear images, the land surface information can be removed, and the iterative HOT (IHOT) result is derived to spatially characterize the haze contamination in the Landsat images. A group of Landsat images that were acquired in different landscapes and seasons were used to test IHOT. Visual comparisons indicate that IHOT performed better than previous haze detection methods for images that were acquired in diverse landscapes and also performed robustly for hazy images that were acquired at different seasons when using the same reference clear image. Additionally, two indirect quantitative validations were used to illustrate that IHOT can provide the best transformation for accurately determining haze information. Therefore, it is expected that the proposed IHOT method will be used for automatic cloud/haze detection for large numbers of Landsat images if data sets of clear Landsat imagery are available. Numéro de notice : A2016-845 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2015.2504369 En ligne : http://dx.doi.org/10.1109/TGRS.2015.2504369 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82926 [article]

Unsupervised multitemporal spectral unmixing for detecting multiple changes in hyperspectral images / Sicong Liu in IEEE Transactions on geoscience and remote sensing, vol 54 n° 5 (May 2016)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 54 n° 5 (May 2016) . - pp 2733 - 2748 Titre : Unsupervised multitemporal spectral unmixing for detecting multiple changes in hyperspectral images Type de document : Article/Communication Auteurs : Sicong Liu, Auteur ; Lorenzo Bruzzone, Auteur ; Francesca Bovolo, Auteur ; Peijun Du, Auteur Année de publication : 2016 Article en page(s) : pp 2733 - 2748 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] analyse des mélanges spectraux [Termes IGN] analyse infrapixellaire [Termes IGN] détection de changement [Termes IGN] image hyperspectrale [Termes IGN] image multitemporelle Résumé : (Auteur) This paper presents a novel multitemporal spectral unmixing (MSU) approach to address the challenging multiple-change detection problem in bitemporal hyperspectral (HS) images. Differently from the state-of-the-art methods that are mainly designed at a pixel level, the proposed technique investigates the spectral-temporal variations at a subpixel level. The considered change detection (CD) problem is analyzed in a multitemporal domain, where a bitemporal spectral mixture model is defined to analyze the spectral composition within a pixel. Distinct multitemporal endmembers (MT-EMs) are extracted according to an automatic and unsupervised technique. Then, a change analysis strategy is designed to distinguish the change and no-change MT-EMs. An endmember-grouping scheme is applied to the changed MT-EMs to detect the unique change classes. Finally, the considered multiple-change detection problem is solved by analyzing the abundances of the change and no-change classes and their contribution to each pixel. The proposed approach has been validated on both simulated and real multitemporal HS data sets presenting multiple changes. Experimental results confirmed the effectiveness of the proposed method. Numéro de notice : A2016-846 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2015.2505183 En ligne : https://doi.org/10.1109/TGRS.2015.2505183 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82927 [article]

Global sensitivity analysis of the L-MEB model for retrieving soil moisture / Zengyan Wang in IEEE Transactions on geoscience and remote sensing, vol 54 n° 5 (May 2016)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 54 n° 5 (May 2016) . - pp 2949 - 2962 Titre : Global sensitivity analysis of the L-MEB model for retrieving soil moisture Type de document : Article/Communication Auteurs : Zengyan Wang, Auteur ; Tao Che, Auteur ; Yuei-An Liou, Auteur Année de publication : 2016 Article en page(s) : pp 2949 - 2962 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] analyse d'image orientée objet [Termes IGN] analyse de sensibilité [Termes IGN] bande L [Termes IGN] densité de la végétation [Termes IGN] humidité du sol [Termes IGN] rugosité du sol [Termes IGN] température au sol Résumé : (Auteur) A global sensitivity analysis utilizing the extended Fourier amplitude sensitivity test is used to determine the parameter sensitivity of the L-band microwave emission of the biosphere (L-MEB) model. The results are analyzed from two perspectives of calibration and inversion. First, the parameters of surface soil moisture, soil roughness factor, vegetation optical depth at nadir, and effective land surface temperature are the four most sensitive parameters in the L-MEB model, demonstrating their possibility to be retrieved in the multiparameter retrieval approaches. Then, the high total sensitivity index (TSI) values of surface soil temperature in the analyses emphasize the importance of high-precision land surface temperature data in the surface soil moisture retrievals, especially for rougher or more vegetated surface conditions. Finally, our analysis indicates that TSI values are high for the soil surface roughness and vegetation optical depth model parameters but low for the vegetation structure, single scattering albedo, and soil roughness coefficient model parameters at incidence angles near nadir. This suggests that calibration experiments performed at small incidence angles may be appropriate for some but not all of the model parameters, which characterize the effect of soil surface roughness and vegetation on the terrestrial brightness temperature. Consequently, new calibration procedures that account for the different relative sensitivities of these model parameters at larger incidence angles may need to be developed in the future. Numéro de notice : A2016-847 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2015.2509176 En ligne : https://doi.org/10.1109/TGRS.2015.2509176 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82928 [article]

Multiple morphological component analysis based decomposition for remote sensing image classification / Xiang Xu in IEEE Transactions on geoscience and remote sensing, vol 54 n° 5 (May 2016)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 54 n° 5 (May 2016) . - pp 3083 - 3102 Titre : Multiple morphological component analysis based decomposition for remote sensing image classification Type de document : Article/Communication Auteurs : Xiang Xu, Auteur ; Jun Li, Auteur ; Xin Huang, Auteur ; et al., Auteur Année de publication : 2016 Article en page(s) : pp 3083 - 3102 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] classification [Termes IGN] décomposition d'image [Termes IGN] image multi sources [Termes IGN] morphologie mathématique Résumé : (Auteur) Remote sensing images exhibit significant contrast and intensity regions and edges, which makes them highly suitable for using different texture features to properly represent and classify the objects that they contain. In this paper, we present a new technique based on multiple morphological component analysis (MMCA) that exploits multiple textural features for decomposition of remote sensing images. The proposed MMCA framework separates a given image into multiple pairs of morphological components (MCs) based on different textural features, with the ultimate goal of improving the signal-to-noise level and the data separability. A distinguishing feature of our proposed approach is the possibility to retrieve detailed image texture information, rather than using a single spatial characteristic of the texture. In this paper, four textural features: content, coarseness, contrast, and directionality (including horizontal and vertical), are considered for generating the MCs. In order to evaluate the obtained MCs, we conduct classification by using both remotely sensed hyperspectral and polarimetric synthetic aperture radar (SAR) scenes, showing the capacity of the proposed method to deal with different kinds of remotely sensed images. The obtained results indicate that the proposed MMCA framework can lead to very good classification performances in different analysis scenarios with limited training samples. Numéro de notice : A2016-848 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2015.2511197 En ligne : https://doi.org/10.1109/TGRS.2015.2511197 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82929 [article]