Centre de documentation
scientifique

Semantic labeling in very high resolution images via a self-cascaded convolutional neural network / Yoncheng Liu in ISPRS Journal of photogrammetry and remote sensing, vol 145 - part A (November 2018)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 145 - part A (November 2018) . - pp 78 - 95 Titre : Semantic labeling in very high resolution images via a self-cascaded convolutional neural network Type de document : Article/Communication Auteurs : Yoncheng Liu, Auteur ; Bin Fan, Auteur ; Lingfeng Wang, Auteur ; Jun Bai, Auteur ; Shiming Xiang, Auteur ; Chunhong Pan, Auteur Année de publication : 2018 Article en page(s) : pp 78 - 95 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] apprentissage profond [Termes IGN] image à très haute résolution [Termes IGN] réseau neuronal convolutif [Termes IGN] zone urbaine Résumé : (Auteur) Semantic labeling for very high resolution (VHR) images in urban areas, is of significant importance in a wide range of remote sensing applications. However, many confusing manmade objects and intricate fine-structured objects make it very difficult to obtain both coherent and accurate labeling results. For this challenging task, we propose a novel deep model with convolutional neural networks (CNNs), i.e., an end-to-end self-cascaded network (ScasNet). Specifically, for confusing manmade objects, ScasNet improves the labeling coherence with sequential global-to-local contexts aggregation. Technically, multi-scale contexts are captured on the output of a CNN encoder, and then they are successively aggregated in a self-cascaded manner. Meanwhile, for fine-structured objects, ScasNet boosts the labeling accuracy with a coarse-to-fine refinement strategy. It progressively refines the target objects using the low-level features learned by CNN’s shallow layers. In addition, to correct the latent fitting residual caused by multi-feature fusion inside ScasNet, a dedicated residual correction scheme is proposed. It greatly improves the effectiveness of ScasNet. Extensive experimental results on three public datasets, including two challenging benchmarks, show that ScasNet achieves the state-of-the-art performance. Numéro de notice : A2018-490 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2017.12.007 Date de publication en ligne : 21/12/2017 En ligne : https://doi.org/10.1016/j.isprsjprs.2017.12.007 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91226 [article]

Exemplaires(3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2018111	RAB	Revue	Centre de documentation	En réserve L003	Disponible
081-2018113	DEP-EXM	Revue	LASTIG	Dépôt en unité	Exclu du prêt
081-2018112	DEP-EAF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Facade repetition detection in a fronto-parallel view with fiducial lines extraction / Hongfei Xiao in Neurocomputing, vol 273 (January 2018)  

Public [article]  inNeurocomputing > vol 273 (January 2018) Titre : Facade repetition detection in a fronto-parallel view with fiducial lines extraction Type de document : Article/Communication Auteurs : Hongfei Xiao, Auteur ; Gaofeng Meng, Auteur ; Lingfeng Wang, Auteur ; Chunhong Pan, Auteur Année de publication : 2018 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] détection d'objet [Termes IGN] extraction de traits caractéristiques [Termes IGN] façade [Termes IGN] programmation dynamique Résumé : (auteur) Detecting repetitive structures on building facades plays an important role in facade image analysis. Observing that repetitions are usually horizontally and vertically aligned, and thereby can be localized by the horizontal and vertical lines passing along the repetition boundaries, we propose to detect repetitions by extracting these fiducial lines. Firstly, candidate lines are detected, containing both the fiducial lines and some mistaken lines passing across facade wall or repetitive structures. Secondly, to pick out the fiducial lines, we formulate a maximum a posterior problem to measure the probabilities that the lines can localize the repetitions. Finally, a dynamic programming based algorithm is developed to solve the problem efficiently. To evaluate the proposed approach, we implement a series of experiments on a dataset containing 60 facade images as well as the public Ecole Central Paris facade dataset. Both qualitative and quantitative results demonstrate the effectiveness of our approach. Numéro de notice : A2017-559 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.neucom.2017.07.040 En ligne : https://doi.org/10.1016/j.neucom.2017.07.040 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=86636 [article]

Automatic spatial–spectral feature selection for hyperspectral image via discriminative sparse multimodal learning / Qian Zhang in IEEE Transactions on geoscience and remote sensing, vol 53 n° 1 (January 2015)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 53 n° 1 (January 2015) . - pp 261 - 279 Titre : Automatic spatial–spectral feature selection for hyperspectral image via discriminative sparse multimodal learning Type de document : Article/Communication Auteurs : Qian Zhang, Auteur ; Yuan Tian, Auteur ; Yuan Yang, Auteur ; Chunhong Pan, Auteur Année de publication : 2015 Article en page(s) : pp 261 - 279 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse discriminante [Termes IGN] apprentissage (cognition) [Termes IGN] apprentissage dirigé [Termes IGN] classification spectrale [Termes IGN] image hyperspectrale [Termes IGN] matrice [Termes IGN] méthode des moindres carrés [Termes IGN] programmation non linéaire Résumé : (Auteur) Spectral-spatial feature combination for hyperspectral image analysis has become an important research topic in hyperspectral remote sensing applications. A simple and straightforward way to integrate spectral-spatial features is to concatenate heterogeneous features into a long vector. Then, the dimensionality reduction techniques, i.e., feature selection, are applied before subsequent utilizations. However, such representation can introduce redundancy and noise. Moreover, traditional single-feature selection methods treat different features equally and ignore their complementary properties. As a result, the performance of subsequent tasks, i.e., classification, would drop down. In this paper, we propose a novel approach to integrate the spectral-spatial features based on the concatenating strategy, termed discriminative sparse multimodal learning for feature selection (DSML-FS). In the proposed method, joint structured sparsity regularizations are used to exploit the intrinsic data structure and relationships among different features. Discriminative least squares regression is applied to enlarge the distance between classes. Therefore, the weight matrix incorporating the information of feature wise and individual properties is automatically learned for spectral-spatial feature selection. We develop an alternative iterative algorithm to solve the nonlinear optimization problem in DSML-FS with global convergence. We systematically evaluate the proposed algorithm on three available hyperspectral data sets, and the encouraging experimental results demonstrate the effectiveness of DSML-FS. Numéro de notice : A2015-032 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2014.2321277 En ligne : https://doi.org/10.1109/TGRS.2014.2321277 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=75114 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2015011	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Structured sparse method for hyperspectral unmixing / Feiyun Zhu in ISPRS Journal of photogrammetry and remote sensing, vol 88 (February 2014)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 88 (February 2014) . - pp 101 - 118 Titre : Structured sparse method for hyperspectral unmixing Type de document : Article/Communication Auteurs : Feiyun Zhu, Auteur ; Yin Wang, Auteur ; Shiming Xiang, Auteur ; Bin Fan, Auteur ; Chunhong Pan, Auteur Année de publication : 2014 Article en page(s) : pp 101 - 118 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse des mélanges spectraux [Termes IGN] factorisation [Termes IGN] image hyperspectrale [Termes IGN] matrice creuse [Termes IGN] programmation par contraintes Résumé : (Auteur) Hyperspectral Unmixing (HU) has received increasing attention in the past decades due to its ability of unveiling information latent in hyperspectral data. Unfortunately, most existing methods fail to take advantage of the spatial information in data. To overcome this limitation, we propose a Structured Sparse regularized Nonnegative Matrix Factorization (SS-NMF) method based on the following two aspects. First, we incorporate a graph Laplacian to encode the manifold structures embedded in the hyperspectral data space. In this way, the highly similar neighboring pixels can be grouped together. Second, the lasso penalty is employed in SS-NMF for the fact that pixels in the same manifold structure are sparsely mixed by a common set of relevant bases. These two factors act as a new structured sparse constraint. With this constraint, our method can learn a compact space, where highly similar pixels are grouped to share correlated sparse representations. Experiments on real hyperspectral data sets with different noise levels demonstrate that our method outperforms the state-of-the-art methods significantly. Numéro de notice : A2014-087 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2013.11.014 En ligne : https://doi.org/10.1016/j.isprsjprs.2013.11.014 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=32992 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2014021	RAB	Revue	Centre de documentation	En réserve L003	Disponible