Centre de documentation
scientifique

Subpixel-pixel-superpixel-based multiview active learning for hyperspectral images classification / Yu Li in IEEE Transactions on geoscience and remote sensing, vol 58 n° 7 (July 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 58 n° 7 (July 2020) . - pp 4976 - 4988 Titre : Subpixel-pixel-superpixel-based multiview active learning for hyperspectral images classification Type de document : Article/Communication Auteurs : Yu Li, Auteur ; Ting Lu, Auteur ; Shutao Li, Auteur Année de publication : 2020 Article en page(s) : pp 4976 - 4988 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] algorithme d'apprentissage [Termes IGN] analyse infrapixellaire [Termes IGN] apprentissage semi-dirigé [Termes IGN] classification pixellaire [Termes IGN] échantillonnage [Termes IGN] image hyperspectrale [Termes IGN] image multiple [Termes IGN] segmentation sémantique [Termes IGN] superpixel Résumé : (auteur) Active learning (AL) attempts to actively select the most representative or useful training samples in an iterative manner. The aim is to simultaneously improve the classification performance and reduce the manual labeling effort. In this article, a novel subpixel-pixel-superpixel-based multiview AL (MAL) (SPS-MAL) method is proposed for hyperspectral image (HSI) classification. Here, the multiple views are generated via extracting the subpixel-level, pixel-level, and superpixel-level information. The multiple views can reflect various characteristics of HSI, i.e., spectral mixture, spectral discrimination, and spectral–spatial structure. Therefore, the joint use of diverse and complementary information in multiple views will contribute to a better identification ability of different classes. In addition, a coarse-to-fine MAL algorithm is introduced to effectively select the most representative samples with the most uncertainty. Specifically, a disagreement analysis on multiple views and joint posterior probability estimation is used to query unlabeled samples. Along with the expansion of training samples, view-specific confidence scores are estimated to adaptively integrate the classification results of multiple views, according to their discrimination performance. In this way, the classification accuracy will be further boosted while the number of necessary training samples can be significantly reduced. The experimental classification results on three well-known HSIs demonstrate the effectiveness of the proposed SPS-MAL method. Numéro de notice : A2020-392 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.2971081 Date de publication en ligne : 14/02/2020 En ligne : https://doi.org/10.1109/TGRS.2020.2971081 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95388 [article]

A greyscale voxel model for airborne lidar data applied to building detection / Liying Wang in Photogrammetric record, vol 33 n° 164 (December 2018)  

Public [article]  inPhotogrammetric record > vol 33 n° 164 (December 2018) . - pp 470 - 490 Titre : A greyscale voxel model for airborne lidar data applied to building detection Type de document : Article/Communication Auteurs : Liying Wang, Auteur ; Yuanding Zhao, Auteur ; Yu Li, Auteur Année de publication : 2018 Article en page(s) : pp 470 - 490 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] détection du bâti [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] niveau de gris (image) [Termes IGN] semis de points [Termes IGN] toit [Termes IGN] voxel Résumé : (Auteur) The existing binary voxel model algorithm for 3D building detection (3BD) from airborne lidar cannot distinguish between connected buildings and non‐buildings. As a result, a greyscale voxel structure model, using the discretised mean intensity of lidar points, is presented to support subsequent building detection in areas where buildings are adjacent to non‐buildings but with different greyscales. The resulting 3BD algorithm first detects a building roof by selecting voxels characterised by a jump in elevation as seeds, labelling them and their 3D connected regions as rooftop voxels. Then voxels which fall into buffers and possess similar greyscales to that of the corresponding building outline are assigned as building façades. The results for detected buildings are evaluated using lidar data with different densities and demonstrate a high rate of success. Numéro de notice : A2018-622 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/phor.12266 Date de publication en ligne : 10/01/2019 En ligne : https://doi.org/10.1111/phor.12266 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92866 [article]

Performance analysis of BDS/GPS precise point positioning with undifferenced ambiguity resolution / Min Wang in Advances in space research, vol 60 n° 12 (15 December 2017)  

Public [article]  inAdvances in space research > vol 60 n° 12 (15 December 2017) . - pp 2581 - 2595 Titre : Performance analysis of BDS/GPS precise point positioning with undifferenced ambiguity resolution Type de document : Article/Communication Auteurs : Min Wang, Auteur ; Hongzhou Chai, Auteur ; Yu Li, Auteur Année de publication : 2017 Article en page(s) : pp 2581 - 2595 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Systèmes de référence et réseaux [Termes IGN] données BeiDou [Termes IGN] données GPS [Termes IGN] erreur systématique [Termes IGN] méthode des moindres carrés [Termes IGN] positionnement ponctuel précis [Termes IGN] résolution d'ambiguïté Résumé : (auteur) The undifferenced ambiguity resolution has been proved to be an effective method to shorten the initialization of precise point positioning (PPP) solution and improve the positioning accuracy. Several techniques were proposed for undifferenced ambiguity resolution with GPS observations. However, for BeiDou navigation satellite system (BDS), the satellite-induced variation in pseudorange observation changes the characteristics of Melbourne-Wűbbena (MW) combination observation, which leads to unacceptably low fixing rate of undifferenced ambiguity. Besides, the characteristics of satellite-induced variations in BDS observations vary with orbit type of satellite, which should be considered in correction effort. In this paper, the BDS fractional cycle biases (FCBs) are estimated with least-squares estimation method using the float undifferenced ambiguity collected from the network of reference stations. Based on the analysis of weekly stability of widelane FCBs and the distribution of fractional ambiguity parts, it is proven that the satellite-induced variation correction is necessary for the FCB estimation for IGSO and MEO satellites. Contaminated by relatively large orbit error, the ambiguities of GEO satellites should be skipped for ambiguity resolution attempt. Resolving BDS ambiguities in BDS/GPS combined PPP could significantly shorten the time needed for the first correct ambiguity resolution (FCAR). The experiment results of static PPP demonstrate that 90.6% of all sessions accomplish FCAR within 1350 s with only GPS observations. Meanwhile, by adding BDS ambiguities to the subset of ambiguity resolution, 91.9% of all sessions accomplish FCAR with only 870 s. Numéro de notice : A2017-752 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.asr.2017.01.045 En ligne : https://doi.org/10.1016/j.asr.2017.01.045 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89037 [article]

Aerial lidar point cloud voxelization with its 3D ground filtering application / Liying Wang in Photogrammetric Engineering & Remote Sensing, PERS, vol 83 n° 2 (February 2017)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 83 n° 2 (February 2017) . - pp 95 - 107 Titre : Aerial lidar point cloud voxelization with its 3D ground filtering application Type de document : Article/Communication Auteurs : Liying Wang, Auteur ; Yan Xu, Auteur ; Yu Li, Auteur Année de publication : 2017 Article en page(s) : pp 95 - 107 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] adjacence [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] filtrage de points [Termes IGN] modèle conceptuel de données [Termes IGN] semis de points [Termes IGN] visualisation 3D [Termes IGN] voxel Résumé : (Auteur) Compared to raster grid, Triangulated Irregular Network (TIN), and point cloud, the benefit of voxel representation lies in that the implicit notion of adjacency and the true 3D representation can be presented simultaneously. A binary voxel-based data (BVD) model is proposed to reconstruct aerial lidar point cloud and based on the constructed model 3D ground filtering (V3GF) is developed for separating ground points from unground ones. The proposed V3GF algorithm selects the lowest voxels with a value of 1 as ground seeds and then labels them and their 3D connected set as ground voxels. The ISPRS benchmark dataset are used to compare the performance of V3GF with those of eight other publicized filtering methods. Results indicate that the V3GF improves on Axelsson's performance on five samples in terms of total error. The average Kappa coefficients for sites with relatively flat urban areas, rough slope and discontinuous surfaces are 92.49 percent, 72.23 percent and 61.27 percent, respectively. Numéro de notice : A2017-038 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.83.2.95 En ligne : https://doi.org/10.14358/PERS.83.2.95 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=84139 [article]

SAR change detection based on intensity and texture changes / Maoguo Gong in ISPRS Journal of photogrammetry and remote sensing, vol 93 (July 2014)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 93 (July 2014) . - pp. 123 - 135 Titre : SAR change detection based on intensity and texture changes Type de document : Article/Communication Auteurs : Maoguo Gong, Auteur ; Yu Li, Auteur ; Licheng Jiao, Auteur ; et al., Auteur Année de publication : 2014 Article en page(s) : pp. 123 - 135 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes IGN] graphe [Termes IGN] image radar moirée [Termes IGN] texture d'image Résumé : (Auteur)In this paper, a novel change detection approach is proposed for multitemporal synthetic aperture radar (SAR) images. The approach is based on two difference images, which are constructed through intensity and texture information, respectively. In the extraction of the texture differences, robust principal component analysis technique is used to separate irrelevant and noisy elements from Gabor responses. Then graph cuts are improved by a novel energy function based on multivariate generalized Gaussian model for more accurately fitting. The effectiveness of the proposed method is proved by the experiment results obtained on several real SAR images data sets. Numéro de notice : A2014-331 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2014.04.010 En ligne : https://doi.org/10.1016/j.isprsjprs.2014.04.010 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=73698 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2014071	RAB	Revue	Centre de documentation	En réserve L003	Disponible