Centre de documentation
scientifique

Complex-valued convolutional neural network and its application in polarimetric SAR image classification / Zhimian Zhang in IEEE Transactions on geoscience and remote sensing, vol 55 n° 12 (December 2017)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 55 n° 12 (December 2017) . - pp 7177 - 7188 Titre : Complex-valued convolutional neural network and its application in polarimetric SAR image classification Type de document : Article/Communication Auteurs : Zhimian Zhang, Auteur ; Haipeng Wang, Auteur ; Feng Xu, Auteur ; Ya-Qiu Jin, Auteur Année de publication : 2017 Article en page(s) : pp 7177 - 7188 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes IGN] apprentissage dirigé [Termes IGN] données polarimétriques [Termes IGN] image radar moirée [Termes IGN] polarimétrie radar [Termes IGN] réseau neuronal convolutif Résumé : (Auteur) Following the great success of deep convolutional neural networks (CNNs) in computer vision, this paper proposes a complex-valued CNN (CV-CNN) specifically for synthetic aperture radar (SAR) image interpretation. It utilizes both amplitude and phase information of complex SAR imagery. All elements of CNN including input-output layer, convolution layer, activation function, and pooling layer are extended to the complex domain. Moreover, a complex backpropagation algorithm based on stochastic gradient descent is derived for CV-CNN training. The proposed CV-CNN is then tested on the typical polarimetric SAR image classification task which classifies each pixel into known terrain types via supervised training. Experiments with the benchmark data sets of Flevoland and Oberpfaffenhofen show that the classification error can be further reduced if employing CV-CNN instead of conventional real-valued CNN with the same degrees of freedom. The performance of CV-CNN is comparable to that of existing state-of-the-art methods in terms of overall classification accuracy. Numéro de notice : A2017-770 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2017.2743222 En ligne : https://doi.org/10.1109/TGRS.2017.2743222 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=88810 [article]

Phase unwrapping for SAR interferometry based on an ant colony optimization algorithm / Z.Q. Wei in International Journal of Remote Sensing IJRS, vol 29 n°3-4 (February 2008)  

Public [article]  inInternational Journal of Remote Sensing IJRS > vol 29 n°3-4 (February 2008) . - pp 711 - 725 Titre : Phase unwrapping for SAR interferometry based on an ant colony optimization algorithm Type de document : Article/Communication Auteurs : Z.Q. Wei, Auteur ; F. Xu, Auteur ; Ya-Qiu Jin, Auteur Année de publication : 2008 Article en page(s) : pp 711 - 725 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes IGN] image radar moirée [Termes IGN] interféromètrie par radar à antenne synthétique [Termes IGN] modèle numérique de surface [Termes IGN] optimisation par colonie de fourmis [Termes IGN] résidu Résumé : (Auteur) Phase unwrapping is a key step in extracting digital elevation models (DEMs) from interferometric synthetic aperture radar (InSAR) data. A new two-dimensional (2-D) phase unwrapping algorithm based on ant colony optimization (ACO) is proposed, which is used to configure the shortest path linking all residues in an interferogram. Using an optimization strategy to establish the branch cuts, the unwrapping error can be significantly reduced. Simulated and real InSAR image datasets are studied to evaluate the performance of the algorithm. The results of the simulated datasets show that the errors of the algorithm are lower than some conventional methods, and the results from a real InSAR image dataset demonstrate that the ACO approach has no isolated regions in comparison with some conventional approaches. It indicates that our ACO algorithm is an optional compromise strategy between preferable phase unwrapping precision and time-consuming computation.Copyright Taylor & Francis Numéro de notice : A2008-006 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/01431160701281049 En ligne : https://doi.org/10.1080/01431160701281049 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=29001 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
080-08021	RAB	Revue	Centre de documentation	En réserve L003	Disponible

An unbiased algorithm for detection of curvilinear structures in urban remote sensing images / Jinzheng Peng in International Journal of Remote Sensing IJRS, vol 28 n°23-24 (December 2007)  

Public [article]  inInternational Journal of Remote Sensing IJRS > vol 28 n°23-24 (December 2007) . - pp 5377 - 5395 Titre : An unbiased algorithm for detection of curvilinear structures in urban remote sensing images Type de document : Article/Communication Auteurs : Jinzheng Peng, Auteur ; Ya-Qiu Jin, Auteur Année de publication : 2007 Article en page(s) : pp 5377 - 5395 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] algorithme de Gauss [Termes IGN] courbe [Termes IGN] extraction automatique [Termes IGN] extraction du réseau routier [Termes IGN] image aérienne [Termes IGN] objet géographique linéaire Résumé : (Auteur) Based on the Gaussian scale-space, a Gaussian comparison function is presented for extracting the linearly road features in aerial remote sensing image. Combining the geometric and radiometric features, the curvilinear structures of the roads are extracted based on locally oriented energy in continuous scale-space. Curvilinear features of roads are verified, grouped and extracted by using both topologic and geometric methods. This algorithm is applicable to extracting the road features in different scale such as rural roads or urban highways, and significantly reduces the computation complexity of line tracing. Some discussions on the zero drift of the Gaussian comparison function are also presented. Copyright Taylor & Francis Numéro de notice : A2007-537 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/01431160601075574 En ligne : https://doi.org/10.1080/01431160601075574 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=28900 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
080-07131	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Suspended sediment concentrations in the Yangtze River estuary retrieved from the CMODIS data / Z. Han in International Journal of Remote Sensing IJRS, vol 27 n°18 - 19 - 20 (October 2006)  

Public [article]  inInternational Journal of Remote Sensing IJRS > vol 27 n°18 - 19 - 20 (October 2006) . - pp 4329 - 4336 Titre : Suspended sediment concentrations in the Yangtze River estuary retrieved from the CMODIS data Type de document : Article/Communication Auteurs : Z. Han, Auteur ; Ya-Qiu Jin, Auteur ; C.X. Yun, Auteur Année de publication : 2006 Article en page(s) : pp 4329 - 4336 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] estuaire [Termes IGN] Fleuve bleu (Chine) [Termes IGN] image CMODIS [Termes IGN] image spatiale [Termes IGN] sédiment [Termes IGN] Shanghai (Chine) [Termes IGN] turbidité des eaux Résumé : (Auteur) The Chinese Moderate Resolution Imaging Spectroradiometer (CMODIS) was loaded on the China's SZ-3 spacecraft. Using an empirical line method, the CMODIS radiance is converted to the water-leaving reflectance, and is applied to inversion of the suspended sediment concentrations in the Yangtze River estuary. The concentrations ranging between 0 mg/L and 1000 mg/L are well validated by the field measurement data. This study demonstrates an example for the feasibility of the CMODIS data for concentration retrieval of the suspended sediment. Copyright Taylor & Francis Numéro de notice : A2006-464 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/01431160600658164 En ligne : https://doi.org/10.1080/01431160600658164 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=28188 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
080-06101	RAB	Revue	Centre de documentation	En réserve L003	Disponible