Centre de documentation
scientifique

Dépouillements

A wavelet decomposition and polynomial fitting-based method for the estimation of time-varying residual motion error in airborne interferometric SAR / Hai Qiang Fu in IEEE Transactions on geoscience and remote sensing, vol 56 n° 1 (January 2018)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 56 n° 1 (January 2018) . - pp 49 - 59 Titre : A wavelet decomposition and polynomial fitting-based method for the estimation of time-varying residual motion error in airborne interferometric SAR Type de document : Article/Communication Auteurs : Hai Qiang Fu, Auteur ; Jian Jun Zhu, Auteur ; Chang Cheng Wang, Auteur ; Hui Qiang Wang, Auteur ; Rong Zhao, Auteur Année de publication : 2018 Article en page(s) : pp 49 - 59 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes IGN] estimation statistique [Termes IGN] interféromètrie par radar à antenne synthétique [Termes IGN] polarisation [Termes IGN] résidu [Termes IGN] transformation en ondelettes Résumé : (Auteur) Compensating the residual motion error (RME) is very important in airborne interferometric synthetic aperture radar (InSAR). In this paper, the wavelet decomposition and polynomial fitting-based (WDPF) method is proposed for detecting and correcting the RME. Wavelet decomposition with root-mean-square error (RMSE) change ratio-based decomposition scale identification is used to detect the RME from the differential interferogram. Polynomial fitting in combination with robust estimation-based least squares is used to absorb the incidence-angle-dependent and topography-dependent components of the RME. A simulated experiment was conducted to test the proposed WDPF method. High-precision RME (with an RMSE of 0.0375 rad) was obtained, which can meet the requirements of InSAR. Real-data L- and P-band InSAR experiments were also performed to test the WDPF method. The results confirmed that the WDPF method can effectively correct the RME for the interferogram. The RMSE of the estimated digital elevation model (DEM) was reduced from 8.03 to 3.46 m and 8.18 to 3.10 m for the L- and P-band interferograms, respectively. Finally, the effects of the external DEM error and polarization on the RME calibration were investigated. The results indicated that the global InSAR DEM products can fulfill the requirement of differential interferogram generation for the WDPF method, and the multipolarization interferograms can help to reduce the effect of the topographic error phase on RME estimation. Numéro de notice : A2018-184 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2017.2727076 Date de publication en ligne : 09/11/2017 En ligne : https://doi.org/10.1109/TGRS.2017.2727076 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89841 [article]

Learning multiscale deep features for high-resolution satellite image scene classification / Qingshan Liu in IEEE Transactions on geoscience and remote sensing, vol 56 n° 1 (January 2018)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 56 n° 1 (January 2018) . - pp 117 - 126 Titre : Learning multiscale deep features for high-resolution satellite image scene classification Type de document : Article/Communication Auteurs : Qingshan Liu, Auteur ; Renlong Hang, Auteur ; Huihui Song, Auteur ; Zhi Li, Auteur Année de publication : 2018 Article en page(s) : pp 117 - 126 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] apprentissage profond [Termes IGN] classification [Termes IGN] image satellite [Termes IGN] méthode fondée sur le noyau [Termes IGN] réseau neuronal convolutif Résumé : (Auteur) In this paper, we propose a multiscale deep feature learning method for high-resolution satellite image scene classification. Specifically, we first warp the original satellite image into multiple different scales. The images in each scale are employed to train a deep convolutional neural network (DCNN). However, simultaneously training multiple DCNNs is time-consuming. To address this issue, we explore DCNN with spatial pyramid pooling (SPP-net). Since different SPP-nets have the same number of parameters, which share the identical initial values, and only fine-tuning the parameters in fully connected layers ensures the effectiveness of each network, thereby greatly accelerating the training process. Then, the multiscale satellite images are fed into their corresponding SPP-nets, respectively, to extract multiscale deep features. Finally, a multiple kernel learning method is developed to automatically learn the optimal combination of such features. Experiments on two difficult data sets show that the proposed method achieves favorable performance compared with other state-of-the-art methods. Numéro de notice : A2018-185 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2017.2743243 Date de publication en ligne : 13/09/2017 En ligne : https://doi.org/10.1109/TGRS.2017.2743243 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89842 [article]

Object-based superresolution land-cover mapping from remotely sensed imagery / Yuehong Chen in IEEE Transactions on geoscience and remote sensing, vol 56 n° 1 (January 2018)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 56 n° 1 (January 2018) . - pp 328 - 340 Titre : Object-based superresolution land-cover mapping from remotely sensed imagery Type de document : Article/Communication Auteurs : Yuehong Chen, Auteur ; Yong Ge, Auteur ; Gerard B.M. Heuvelink, Auteur ; Ru An, Auteur ; Yu Chen, Auteur Année de publication : 2018 Article en page(s) : pp 328 - 340 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] classification orientée objet [Termes IGN] classification pixellaire [Termes IGN] déconvolution [Termes IGN] krigeage [Termes IGN] occupation du sol [Termes IGN] programmation linéaire [Termes IGN] variogramme Résumé : (Auteur) Superresolution mapping (SRM) is a widely used technique to address the mixed pixel problem in pixel-based classification. Advanced object-based classification will face a similar mixed phenomenon-a mixed object that contains different land-cover classes. Currently, most SRM approaches focus on estimating the spatial location of classes within mixed pixels in pixel-based classification. Little if any consideration has been given to predicting where classes spatially distribute within mixed objects. This paper, therefore, proposes a new object-based SRM strategy (OSRM) to deal with mixed objects in object-based classification. First, it uses the deconvolution technique to estimate the semivariograms at target subpixel scale from the class proportions of irregular objects. Then, an area-to-point kriging method is applied to predict the soft class values of subpixels within each object according to the estimated semivariograms and the class proportions of objects. Finally, a linear optimization model at object level is built to determine the optimal class labels of subpixels within each object. Two synthetic images and a real remote sensing image were used to evaluate the performance of OSRM. The experimental results demonstrated that OSRM generated more land-cover details within mixed objects than did the traditional object-based hard classification and performed better than an existing pixel-based SRM method. Hence, OSRM provides a valuable solution to mixed objects in object-based classification. Numéro de notice : A2018-186 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2017.2747624 Date de publication en ligne : 20/09/2017 En ligne : https://doi.org/10.1109/TGRS.2017.2747624 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89843 [article]

Multiobjective subpixel land-cover mapping / Ailong Ma in IEEE Transactions on geoscience and remote sensing, vol 56 n° 1 (January 2018)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 56 n° 1 (January 2018) . - pp 422 - 435 Titre : Multiobjective subpixel land-cover mapping Type de document : Article/Communication Auteurs : Ailong Ma, Auteur ; Yanfei Zhong, Auteur ; Da He, Auteur ; Liangpei Zhang, Auteur Année de publication : 2018 Article en page(s) : pp 422 - 435 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] carte d'occupation du sol [Termes IGN] image hyperspectrale [Termes IGN] optimisation (mathématiques) [Termes IGN] problème inverse Résumé : (Auteur) The hyperspectral subpixel mapping (SPM) technique can generate a land-cover map at the subpixel scale by modeling the relationship between the abundance map and the spatial distribution image of the subpixels. However, this is an inverse ill-posed problem. The most widely used way to resolve the problem is to introduce additional information as a regularization term and acquire the unique optimal solution. However, the regularization parameter either needs to be determined manually or it cannot be determined in a fully adaptive manner. Thus, in this paper, the multiobjective subpixel land-cover mapping (MOSM) framework for hyperspectral remote sensing imagery is proposed, in which the two function terms [the fidelity term and the prior term (i.e., the regularization term)] can be optimized simultaneously, and there is no need to determine the regularization parameter explicitly. In order to achieve this goal, two strategies are designed in MOSM: 1) a high-resolution distribution image-based individual encoding strategy is designed in order to calculate the prior term accurately and 2) a subfitness-based individual comparison strategy is designed in order to generate subpixel land-cover mapping solutions with a high quality to update the population. Four data sets (one simulated, two synthetic, and one real hyperspectral image) were used to test the proposed method. The experimental results show that MOSM can perform better than the other subpixel land-cover mapping methods, demonstrating the effectiveness of MOSM in balancing the fidelity term and prior term in the SPM model. Numéro de notice : A2018-187 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2017.2748701 Date de publication en ligne : 10/11/2017 En ligne : https://doi.org/10.1109/TGRS.2017.2748701 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89845 [article]

Active learning-based optimized training library generation for object-oriented image classification / Rajeswari Balasubramaniam in IEEE Transactions on geoscience and remote sensing, vol 56 n° 1 (January 2018)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 56 n° 1 (January 2018) . - pp 575 - 585 Titre : Active learning-based optimized training library generation for object-oriented image classification Type de document : Article/Communication Auteurs : Rajeswari Balasubramaniam, Auteur ; Srivalsan Namboodiri, Auteur ; Rama Rao Nidamanuri, Auteur ; Rama Krishna Sai Subrahmanyam Gorthi, Auteur Année de publication : 2018 Article en page(s) : pp 575 - 585 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse d'image orientée objet [Termes IGN] apprentissage dirigé [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] image aérienne [Termes IGN] image multibande Résumé : (Auteur) In this paper, we introduce an active learning (AL)-based object training library generation for a multiclassifier object-oriented image analysis (OOIA) system. While several AL approaches do exist for pixel-based training library generation and for hyperspectral image classification, there is no standard training library generation strategy for OOIA of very high spatial resolution images. Given a sufficient number of training samples, supervised classification is the method of choice for image classification. However, this strategy becomes computationally expensive with the increase in the number of classes or the number of images to be classified. The above-mentioned issue is solved in this proposed method, where an optimized training library of objects (superpixels) is generated based on a batch mode AL approach. A softmax classifier is used as a detector in this method, which helps in determining the right samples to be chosen for library updation. To this end, we construct a multiclassifier system with max-voting decision to classify an image at pixel level. This algorithm was applied on three different very high-resolution airborne data sets, each with varying complexity in terms of variations in geographical context, sensors, illumination, and view angles. Our method has empirically outperformed the traditional OOIA by producing equivalent accuracy with a training library that is orders of magnitude smaller. In addition, the most distinctive ability of the algorithm is experienced in the most heterogeneous data set, where its performance in terms of accuracy is around twice the performance of the traditional method in the same situation. The generality of this classification strategy is proved through its performance on multispectral images and for cross-domain application. Finally, the robustness of this method is identified by comparing its performance with an alternative AL approach-self-learning-based semisupervised SVM. The capability of the proposed method to handle highly heterogeneous data is identified as the primary reason for its robustness. Numéro de notice : A2018-188 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2017.2751568 Date de publication en ligne : 29/09/2017 En ligne : https://doi.org/10.1109/TGRS.2017.2751568 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89847 [article]