|
[n° ou bulletin]
est un bulletin de IEEE Transactions on geoscience and remote sensing / IEEE Geoscience and remote sensing society (Etats-Unis) (1986 -) ![]()
[n° ou bulletin]
| ![]() |
Dépouillements
![](./images/expand_all.gif)
![](./images/collapse_all.gif)
A Computationally efficient algorithm for fusing multispectral and hyperspectral images / Raúl Guerra in IEEE Transactions on geoscience and remote sensing, vol 54 n° 10 (October 2016)
![]()
[article]
Titre : A Computationally efficient algorithm for fusing multispectral and hyperspectral images Type de document : Article/Communication Auteurs : Raúl Guerra, Auteur ; Sebastian Lopez, Auteur ; Roberto Sarmiento, Auteur Année de publication : 2016 Article en page(s) : pp 5712 - 5728 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] algorithme de fusion
[Termes IGN] analyse combinatoire (maths)
[Termes IGN] fusion d'images
[Termes IGN] image hyperspectrale
[Termes IGN] image multibande
[Termes IGN] qualité d'imageRésumé : (auteur) Remote sensing systems equipped with multispectral and hyperspectral sensors are able to capture images of the surface of the Earth at different wavelengths. In these systems, hyperspectral sensors typically provide images with a high spectral resolution but a reduced spatial resolution, while on the contrary, multispectral sensors are able to produce images with a rich spatial resolution but a poor spectral resolution. Due to this reason, different fusion algorithms have been proposed during the last years in order to obtain remotely sensed images with enriched spatial and spectral resolutions by wisely combining the data acquired for the same scene by multispectral and hyperspectral sensors. However, the algorithms so far proposed that are able to obtain fused images with a good spatial and spectral quality require a formidable amount of computationally complex operations that cannot be executed in parallel, which clearly prevent the utilization of these algorithms in applications under real-time constraints in which high-performance parallel-based computing systems are normally required for accelerating the overall process. On the other hand, there are other state-of-the-art algorithms that are capable of fusing these images with a lower computational effort but at the cost of decreasing the quality of the resultant fused image. In this paper, a new algorithm named computationally efficient algorithm for fusing multispectral and hyperspectral images (CoEf-MHI) is proposed in order to obtain a high-quality image from hyperspectral and multispectral images of the same scene with a low computational effort. The proposed CoEf-MHI algorithm is based on incorporating the spatial details of the multispectral image into the hyperspectral image, without introducing spectral distortions. To achieve this goal, the CoEf-MHI algorithm first spatially upsamples, by means of a bilinear interpolation, the input hyperspectral image to the spatial resolution of the input multispectral image, and then, it independently refines each pixel of the resulting image by linearly combining the multispectral and hyperspectral pixels in its neighborhood. The simulations performed in this work with different images demonstrate that our proposal is much more efficient than state-of-the-art approaches, being this efficiency understood as the ratio between the quality of the fused image and the computational effort required to obtain such image. Numéro de notice : A2016-860 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2570433 En ligne : https://doi.org/10.1109/TGRS.2016.2570433 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82889
in IEEE Transactions on geoscience and remote sensing > vol 54 n° 10 (October 2016) . - pp 5712 - 5728[article]Fast and accurate target detection based on multiscale saliency and active contour model for high-resolution SAR images / Song Tu in IEEE Transactions on geoscience and remote sensing, vol 54 n° 10 (October 2016)
![]()
[article]
Titre : Fast and accurate target detection based on multiscale saliency and active contour model for high-resolution SAR images Type de document : Article/Communication Auteurs : Song Tu, Auteur ; Yi Su, Auteur Année de publication : 2016 Article en page(s) : pp 5729 - 5744 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications
[Termes IGN] détection de changement
[Termes IGN] détection de cible
[Termes IGN] détection de contours
[Termes IGN] granularité d'image
[Termes IGN] image optique
[Termes IGN] image radar moirée
[Termes IGN] imagerie médicale
[Termes IGN] précision des donnéesRésumé : (auteur) The active contour model (ACM) is widely used in target detection of optical and medical images, but multiplicative speckle noise largely interferes with its use in synthetic aperture radar (SAR) images. To overcome this difficulty, a region- and edge-based convex ACM with high efficiency is proposed for target detection in small-scale SAR images. Then, a novel detection algorithm, which combines the advantages of a multiscale saliency detection method and the proposed high-efficiency ACM, is presented to address a large-scale and high-resolution SAR image automatically. Target detection experiments in real and simulated SAR images show that the proposed methods outperform classical ACMs and the popular two-parameter constant false alarm rate detector in terms of efficiency and accuracy. Numéro de notice : A2016-861 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2571309 En ligne : https://doi.org/10.1109/TGRS.2016.2571309 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82892
in IEEE Transactions on geoscience and remote sensing > vol 54 n° 10 (October 2016) . - pp 5729 - 5744[article]A tensor decomposition-based anomaly detection algorithm for hyperspectral image / Xing Zhang in IEEE Transactions on geoscience and remote sensing, vol 54 n° 10 (October 2016)
![]()
[article]
Titre : A tensor decomposition-based anomaly detection algorithm for hyperspectral image Type de document : Article/Communication Auteurs : Xing Zhang, Auteur ; Gongjian Wen, Auteur ; Wei Dai, Auteur Année de publication : 2016 Article en page(s) : pp 5801 - 5820 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] décomposition
[Termes IGN] détection d'anomalie
[Termes IGN] image hyperspectrale
[Termes IGN] signature spectrale
[Termes IGN] tenseurRésumé : (auteur) Anomalies usually refer to targets with a spot of pixels (even subpixels) that stand out from their neighboring background clutter pixels in hyperspectral imagery (HSI). Compared to backgrounds, anomalies have two main characteristics. One is the spectral anomaly, i.e., their spectral signatures are different from those associated to their surrounding backgrounds; another is the spatial anomaly, i.e., anomalies occur as few pixels (even subpixels) embedded in the local homogeneous backgrounds. However, most of the existing anomaly detection algorithms for HSI only employed the spectral anomaly. If the two characteristics are exploited in a detection method simultaneously, better performance may be achieved. The third-order (two modes for space and one mode for spectra) tensor representation of HSI has been proved to be an effective tool to describe the spatial and spectral information equivalently; therefore, tensor representation is convenient for exhibiting the two characteristics of anomalies simultaneously. In this paper, a new anomaly detection method based on tensor decomposition is proposed and divided into three steps. Three factor matrices and a core tensor are first estimated from the third-order tensor that is constructed from the HSI data cube by using the Tucker decomposition, and their major and minor principal components (PCs) are more likely to correspond to the spectral signatures of the backgrounds and the anomalies, respectively. In the second step, a reconstruction-error-based method is presented to find the first largest PCs along each mode to eliminate the spectral signatures of the backgrounds as much as possible, and thus, the remaining data may be modeled as the spectral signatures of the anomalies with a Gaussian noise. Finally, a CFAR test is implemented to detect the anomalies from the remaining data. Experiments with simulated, synthetic, and real HSI data sets reveal that the proposed method outperforms those spectral-anomaly-based methods with better detection probability and less false alarm rate. Numéro de notice : A2016-862 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2572400 En ligne : https://doi.org/10.1109/TGRS.2016.2572400 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82894
in IEEE Transactions on geoscience and remote sensing > vol 54 n° 10 (October 2016) . - pp 5801 - 5820[article]Development of a large-format UAS imaging system with the construction of a one sensor geometry from a multicamera array / Jiann-Yeou Rau in IEEE Transactions on geoscience and remote sensing, vol 54 n° 10 (October 2016)
![]()
[article]
Titre : Development of a large-format UAS imaging system with the construction of a one sensor geometry from a multicamera array Type de document : Article/Communication Auteurs : Jiann-Yeou Rau, Auteur ; Jyun-Ping Jhan, Auteur ; Yi-Tang Li, Auteur Année de publication : 2016 Article en page(s) : pp 5925 - 5934 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Acquisition d'image(s) et de donnée(s)
[Termes IGN] capteur aérien
[Termes IGN] chambre à grand format
[Termes IGN] drone
[Termes IGN] géométrie de l'image
[Termes IGN] image 3D
[Termes IGN] image multicapteurRésumé : (auteur) For the purpose of large-area topographic mapping, this study proposes an imaging system based on a multicamera array unmanned aerial system (UAS) comprised of five small-format digital cameras with a total field of view of 127°. The five digital cameras are aligned in a row along the across-track direction with overlap between two neighboring cameras. The suggested system has higher data acquisition efficiency than the single-camera UAS imaging system. For topographic mapping purposes, we develop a modified projective transformation method to stitch all five raw images into one sensor geometry. In this method, the transformation coefficients are obtained by on-the-job multicamera self-calibration, including interior and relative orientations. During the stitching process, two systematic errors are detected and corrected. In the end, a large-format digital image can be produced for each trigger event independently. The photogrammetric collinearity condition is evaluated using several external accuracy assessments, such as conventional aerial triangulation, stereoplotting, and digital surface model generation procedures. From the accuracy assessment results, we conclude that the presented raw image stitching method can be used to construct a one sensor geometry from a multicamera array and is feasible for 3-D mapping applications. Numéro de notice : A2016-863 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2575066 En ligne : http://dx.doi.org/10.1109/TGRS.2016.2575066 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82896
in IEEE Transactions on geoscience and remote sensing > vol 54 n° 10 (October 2016) . - pp 5925 - 5934[article]Object-based morphological profiles for classification of remote sensing imagery / Christian Geiss in IEEE Transactions on geoscience and remote sensing, vol 54 n° 10 (October 2016)
![]()
[article]
Titre : Object-based morphological profiles for classification of remote sensing imagery Type de document : Article/Communication Auteurs : Christian Geiss, Auteur ; Martin Klotz, Auteur ; Andreas Schmitt, Auteur ; Hannes Taubenböck, Auteur Année de publication : 2016 Article en page(s) : pp 5952 - 5963 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] analyse d'image orientée objet
[Termes IGN] classification automatique
[Termes IGN] classification orientée objet
[Termes IGN] décomposition d'image
[Termes IGN] image hyperspectrale
[Termes IGN] image multibande
[Termes IGN] morphologie mathématique
[Termes IGN] reconstruction d'imageRésumé : (auteur) Morphological operators (MOs) and their enhancements such as morphological profiles (MPs) are subject to a lively scientific contemplation since they are found to be beneficial for, for example, classification of very high spatial resolution panchromatic, multi-, and hyperspectral imagery. They account for spatial structures with differing magnitudes and, thus, provide a comprehensive multilevel description of an image. In this paper, we introduce the concept of object-based MPs (OMPs) to also encode shape-related, topological, and hierarchical properties of image objects in an exhaustive way. Thereby, we seek to benefit from the so-called object-based image analysis framework by partitioning the original image into objects with a segmentation algorithm on multiple scales. The obtained spatial entities (i.e., objects) are used to aggregate multiple sequences obtained with MOs according to statistical measures of central tendency. This strategy is followed to simultaneously preserve and characterize shape properties of objects and enable both the topological and hierarchical decompositions of an image with respect to the progressive application of MOs. Subsequently, supervised classification models are learned by considering this additionally encoded information. Experimental results are obtained with a random forest classifier with heuristically tuned hyperparameters and a wrapper-based feature selection scheme. We evaluated the results for two test sites of panchromatic WorldView-II imagery, which was acquired over an urban environment. In this setting, the proposed OMPs allow for significant improvements with respect to classification accuracy compared to standard MPs (i.e., obtained by paired sequences of erosion, dilation, opening, closing, opening by top-hat, and closing by top-hat operations). Numéro de notice : A2016-864 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2576978 En ligne : https://doi.org/10.1109/TGRS.2016.2576978 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82899
in IEEE Transactions on geoscience and remote sensing > vol 54 n° 10 (October 2016) . - pp 5952 - 5963[article]SAR image change detection based on correlation kernel and multistage extreme learning machine / Lu Jia in IEEE Transactions on geoscience and remote sensing, vol 54 n° 10 (October 2016)
![]()
[article]
Titre : SAR image change detection based on correlation kernel and multistage extreme learning machine Type de document : Article/Communication Auteurs : Lu Jia, Auteur ; Ming Li, Auteur ; Peng Zhang, Auteur ; Yan Wu, Auteur Année de publication : 2016 Article en page(s) : pp 5993 - 6006 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications
[Termes IGN] appariement d'images
[Termes IGN] apprentissage automatique
[Termes IGN] détection de changement
[Termes IGN] détection de contours
[Termes IGN] image radar moirée
[Termes IGN] méthode fondée sur le noyau
[Termes IGN] séparateur à vaste margeRésumé : (auteur) Designing a kernel function with good discriminating ability and a highly application-adaptive kernelized classifier is the key of many kernel methods. However, not many kernel functions combining directly the bitemporal images' information are designed specifically for change detection tasks. In addition, extreme learning machine (ELM) has not found wide applications in change detection tasks, even though it is a potential kernel method possessing outstanding approximation and generalization capabilities as well as great classification accuracy and efficiency. Therefore, an approach relying on a difference correlation kernel (DCK) and a multistage ELM (MS-ELM) is proposed in this paper for synthetic aperture radar (SAR) image change detection. First, a DCK function is constructed specifically for change detection by measuring the “distance” between any two pixels. The DCK function depicts the cross-time similarities between couples of bitemporal image patches at any cyclic shifts with a kernel correlation operation and the high-order spatial distances between two differently located pixels with an algebraic subtraction. The DCK function possesses strong noise immunity and good identification of changed areas simultaneously. Second, an MS-ELM classifier is constructed for obtaining the change detection result. In MS-ELM, the hidden nodes and weights between the hidden and output layers are updated stage by stage by improving the kernel functions that compose them. Each stage of the MS-ELM is a standard kernel-ELM, and the DCK function is utilized in the first stage. The regenerative kernel functions incorporate the output spatial-neighborhood information of the previous stage for enhancing remarkably the MS-ELM's discriminating ability and noise resistance. The converged result at the last stage of MS-ELM is the final change detection result. Experiments on real SAR image change detection demonstrate the effectiveness of the DCK function and the MS-ELM algorithm, particularly its good identification of changed areas and strong robustness against noise in SAR images. Numéro de notice : A2016-865 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2578438 En ligne : http://dx.doi.org/10.1109/TGRS.2016.2578438 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82901
in IEEE Transactions on geoscience and remote sensing > vol 54 n° 10 (October 2016) . - pp 5993 - 6006[article]A statistical model and simulator for ocean-reflected GNSS signals / James L. Garrison in IEEE Transactions on geoscience and remote sensing, vol 54 n° 10 (October 2016)
![]()
[article]
Titre : A statistical model and simulator for ocean-reflected GNSS signals Type de document : Article/Communication Auteurs : James L. Garrison, Auteur Année de publication : 2016 Article en page(s) : pp 6007 - 6019 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géodésie spatiale
[Termes IGN] atmosphère terrestre
[Termes IGN] modélisation
[Termes IGN] positionnement par GNSS
[Termes IGN] réflectométrie par GNSS
[Termes IGN] surface de la merRésumé : (auteur) Global Navigation Satellite Systems Reflectometry (GNSS-R) methods sense ocean roughness by cross correlating scattered GNSS signals with a locally generated replica of the transmitted signal. The resulting delay-Doppler map (DDM) is related to surface slope statistics through established scattering models. DDM samples are correlated in time and between delay and Doppler coordinates, limiting the number of independent samples available to reduce measurement error. Performance predictions for future GNSS-R missions depend on a model with sufficient fidelity to represent these statistics. A previously developed model for the correlation in time and a new model for the correlation between delays are used to create a GNSS-R signal simulator. A change of variables reduces these models to the numerically efficient form of a single integral and a convolution. Independent normally distributed white noise is passed through a filter bank implementing these models to generate an ensemble of synthetic noisy measurements having realistic correlation in time and between delay bins. Correlation between Doppler bins, however, is not represented by this model. The output of this simulator is compared to 1-D (delay-only) DDMs collected during a 2009 airborne experiment in the North Atlantic, with winds from 5 to 25 m/s. Good agreement is found in the variance, time correlation, and covariance matrix. The probability density functions show reasonable agreement. A bias between the synthetic and observed data was found to result from a bias in the wind/roughness retrieval. Agreement was worse for the low-wind (5.8 m/s) example, perhaps due to a component of specular reflection. One application of this simulator is in generating synthetic DDMs, maintaining accurate representation of statistics following nonlinear processing (e.g., incoherent averaging). The simulator presents a numerically efficient method for generating large statistically significant ensembles of DDMs under identical conditions. Numéro de notice : A2016-866 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2579504 En ligne : http://dx.doi.org/ 10.1109/TGRS.2016.2579504 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82903
in IEEE Transactions on geoscience and remote sensing > vol 54 n° 10 (October 2016) . - pp 6007 - 6019[article]SMAP L-Band microwave radiometer: RFI mitigation prelaunch analysis and first year on-orbit observations / Priscilla N. Mohammed in IEEE Transactions on geoscience and remote sensing, vol 54 n° 10 (October 2016)
![]()
[article]
Titre : SMAP L-Band microwave radiometer: RFI mitigation prelaunch analysis and first year on-orbit observations Type de document : Article/Communication Auteurs : Priscilla N. Mohammed, Auteur ; Mustafa Aksoy, Auteur ; Jeffrey R. Piepmeier, Auteur ; et al., Auteur Année de publication : 2016 Article en page(s) : pp 6035 - 6047 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement du signal
[Termes IGN] acquisition de données
[Termes IGN] bande L
[Termes IGN] glace
[Termes IGN] humidité du sol
[Termes IGN] interférence
[Termes IGN] mission SMAP
[Termes IGN] mitigation
[Termes IGN] radiomètre à hyperfréquenceRésumé : (auteur) The National Aeronautics and Space Administration's (NASA) Soil Moisture Active and Passive (SMAP) mission, which was launched on January 31, 2015, is providing global measurements of soil moisture and freeze/thaw state. The SMAP radiometer operates within the protected Earth Exploration Satellite Service passive frequency allocation of 1400-1427 MHz. However, unauthorized in-band transmitters and out-of-band emissions from transmitters operating at frequencies adjacent to this allocated spectrum are known to cause interference to microwave radiometry in this band. Because measurement corruption by these terrestrial transmissions, which is referred to as radio-frequency interference (RFI), threatens mission success, the SMAP radiometer includes special flight hardware to enable the detection and filtering of RFI. Results from the first year of SMAP data show the presence of RFI with frequent occurrence over Asia and Europe. During the calibration/validation stage of the mission, the RFI detection and mitigation algorithms were modified to provide enhanced performance. Analysis of the L1B_TB products indicates good algorithmic performance with respect to RFI detection and removal. However, some regions of the globe (e.g., Japan) continue to experience complete data loss. This paper summarizes updates to the SMAP RFI processing algorithms based on prelaunch tests and on-orbit measurements, as well as RFI information obtained in SMAP's first year on orbit. Numéro de notice : A2016-867 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2580459 En ligne : https://doi.org/10.1109/TGRS.2016.2580459 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82907
in IEEE Transactions on geoscience and remote sensing > vol 54 n° 10 (October 2016) . - pp 6035 - 6047[article]Robust collaborative nonnegative matrix factorization for hyperspectral unmixing / Jun Li in IEEE Transactions on geoscience and remote sensing, vol 54 n° 10 (October 2016)
![]()
[article]
Titre : Robust collaborative nonnegative matrix factorization for hyperspectral unmixing Type de document : Article/Communication Auteurs : Jun Li, Auteur ; José M. Bioucas-Dias, Auteur ; Antonio J. Plaza, Auteur ; Lin Liu, Auteur Année de publication : 2016 Article en page(s) : pp 6076 - 6090 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] analyse des mélanges spectraux
[Termes IGN] factorisation de matrice non-négative
[Termes IGN] modèle de mélange multilinéaire
[Termes IGN] signature spectraleRésumé : (auteur) Spectral unmixing is an important technique for remotely sensed hyperspectral data exploitation. It amounts to identifying a set of pure spectral signatures, which are called endmembers, and their corresponding fractional, draftrulesabun-dances in each pixel of the hyperspectral image. Over the last years, different algorithms have been developed for each of the three main steps of the spectral unmixing chain: 1) estimation of the number of endmembers in a scene; 2) identification of the spectral signatures of the endmembers; and 3) estimation of the fractional abundance of each endmember in each pixel of the scene. However, few algorithms can perform all the stages involved in the hyperspectral unmixing process. Such algorithms are highly desirable to avoid the propagation of errors within the chain. In this paper, we develop a new algorithm, which is termed robust collaborative nonnegative matrix factorization (R-CoNMF), that can perform the three steps of the hyperspectral unmixing chain. In comparison with other conventional methods, R-CoNMF starts with an overestimated number of endmembers and removes the redundant endmembers by means of collaborative regularization. Our experimental results indicate that the proposed method provides better or competitive performance when compared with other widely used methods. Numéro de notice : A2016-868 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2580702 En ligne : http://dx.doi.org/10.1109/TGRS.2016.2580702 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=83025
in IEEE Transactions on geoscience and remote sensing > vol 54 n° 10 (October 2016) . - pp 6076 - 6090[article]Deep feature extraction and classification of hyperspectral images based on convolutional neural networks / Yushi Chen in IEEE Transactions on geoscience and remote sensing, vol 54 n° 10 (October 2016)
![]()
[article]
Titre : Deep feature extraction and classification of hyperspectral images based on convolutional neural networks Type de document : Article/Communication Auteurs : Yushi Chen, Auteur ; Hanlu Jiang, Auteur ; Chunyang Li, Auteur ; et al., Auteur Année de publication : 2016 Article en page(s) : pp 6232 - 6251 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] classification par réseau neuronal
[Termes IGN] détection de cible
[Termes IGN] filtrage numérique d'image
[Termes IGN] image hyperspectrale
[Termes IGN] régularisation de Tychonoff
[Termes IGN] réseau neuronal convolutifRésumé : (auteur) Due to the advantages of deep learning, in this paper, a regularized deep feature extraction (FE) method is presented for hyperspectral image (HSI) classification using a convolutional neural network (CNN). The proposed approach employs several convolutional and pooling layers to extract deep features from HSIs, which are nonlinear, discriminant, and invariant. These features are useful for image classification and target detection. Furthermore, in order to address the common issue of imbalance between high dimensionality and limited availability of training samples for the classification of HSI, a few strategies such as L2 regularization and dropout are investigated to avoid overfitting in class data modeling. More importantly, we propose a 3-D CNN-based FE model with combined regularization to extract effective spectral-spatial features of hyperspectral imagery. Finally, in order to further improve the performance, a virtual sample enhanced method is proposed. The proposed approaches are carried out on three widely used hyperspectral data sets: Indian Pines, University of Pavia, and Kennedy Space Center. The obtained results reveal that the proposed models with sparse constraints provide competitive results to state-of-the-art methods. In addition, the proposed deep FE opens a new window for further research. Numéro de notice : A2016-869 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2584107 En ligne : http://dx.doi.org/10.1109/TGRS.2016.2584107 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=83026
in IEEE Transactions on geoscience and remote sensing > vol 54 n° 10 (October 2016) . - pp 6232 - 6251[article]