Centre dedocumentation
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 descripteurs IGN] algorithme d'apprentissage [Termes descripteurs IGN] analyse infrapixellaire [Termes descripteurs IGN] classification pixellaire [Termes descripteurs IGN] échantillonnage [Termes descripteurs IGN] étiquette [Termes descripteurs IGN] image multiple [Termes descripteurs 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 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]

Hyperspectral classification with noisy label detection via superpixel-to-pixel weighting distance / Bing Tu in IEEE Transactions on geoscience and remote sensing, vol 58 n° 6 (June 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 58 n° 6 (June 2020) . - pp 4116 - 4131 Titre : Hyperspectral classification with noisy label detection via superpixel-to-pixel weighting distance Type de document : Article/Communication Auteurs : Bing Tu, Auteur ; Chengle Zhou, Auteur ; Danbing He, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 4116 - 4131 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] analyse de groupement [Termes descripteurs IGN] classification barycentrique [Termes descripteurs IGN] classification dirigée [Termes descripteurs IGN] classification par séparateurs à vaste marge [Termes descripteurs IGN] erreur d'échantillon [Termes descripteurs IGN] étiquette [Termes descripteurs IGN] image hyperspectrale [Termes descripteurs IGN] pondération [Termes descripteurs IGN] précision de la classification [Termes descripteurs IGN] superpixel Résumé : (auteur) Classification is an important technique for remotely sensed hyperspectral image (HSI) exploitation. Often, the presence of wrong (noisy) labels presents a drawback for accurate supervised classification. In this article, we introduce a new framework for noisy label detection that combines a superpixel-to-pixel weighting distance (SPWD) and density peak clustering. The proposed method is able to accurately detect and remove noisy labels in the training set before HSI classification. It considers two weak assumptions when exploiting the spectral–spatial information contained in the HSI: 1) all the pixels in a superpixel belong to the same class and 2) close pixels in spectral space have the same label. The proposed method consists of the following steps. First, a superpixel segmentation step is used to obtain self-adaptive spatial information for each training sample. Then, a metric is utilized to measure the spectral distance information between each superpixel and pixel. Meanwhile, in order to overcome the first weak assumption, we use K nearest neighbors to obtain the closest neighborhoods of pixels around each superpixel, and a Gaussian weight is employed to mitigate the second weak assumption by adapting the original distance information. Next, the noisy labels in the original training set are removed by a density threshold-based decision function. Finally, the support vector machine (SVM) classifier is employed to evaluate the effectiveness of the proposed SPWD detection method in terms of classification accuracy. Experiments performed on several real HSI data sets demonstrate that the method can effectively improve the performance of classifiers trained with noisy training sets in terms of classification accuracy. Numéro de notice : A2020-283 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2019.2961141 date de publication en ligne : 13/01/2020 En ligne : https://doi.org/10.1109/TGRS.2019.2961141 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95105 [article]

What, Where, and How to Transfer in SAR Target Recognition Based on Deep CNNs / Zhongling Huang in IEEE Transactions on geoscience and remote sensing, vol 58 n° 4 (April 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 58 n° 4 (April 2020) . - pp 2324 - 2336 Titre : What, Where, and How to Transfer in SAR Target Recognition Based on Deep CNNs Type de document : Article/Communication Auteurs : Zhongling Huang, Auteur ; Zongxu Pan, Auteur ; Bin Lei, Auteur Année de publication : 2020 Article en page(s) : pp 2324 - 2336 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] détection de cible [Termes descripteurs IGN] données multisources [Termes descripteurs IGN] étiquette [Termes descripteurs IGN] image optique [Termes descripteurs IGN] image radar moirée [Termes descripteurs IGN] source de données [Termes descripteurs IGN] télédétection spatiale [Termes descripteurs IGN] transmission de données Résumé : (auteur) Deep convolutional neural networks (DCNNs) have attracted much attention in remote sensing recently. Compared with the large-scale annotated data set in natural images, the lack of labeled data in remote sensing becomes an obstacle to train a deep network very well, especially in synthetic aperture radar (SAR) image interpretation. Transfer learning provides an effective way to solve this problem by borrowing knowledge from the source task to the target task. In optical remote sensing application, a prevalent mechanism is to fine-tune on an existing model pretrained with a large-scale natural image data set, such as ImageNet. However, this scheme does not achieve satisfactory performance for SAR applications because of the prominent discrepancy between SAR and optical images. In this article, we attempt to discuss three issues that are seldom studied before in detail: 1) what network and source tasks are better to transfer to SAR targets; 2) in which layer are transferred features more generic to SAR targets; and 3) how to transfer effectively to SAR targets recognition. Based on the analysis, a transitive transfer method via multisource data with domain adaptation is proposed in this article to decrease the discrepancy between the source data and SAR targets. Several experiments are conducted on OpenSARShip. The results indicate that the universal conclusions about transfer learning in natural images cannot be completely applied to SAR targets, and the analysis of what and where to transfer in SAR target recognition is helpful to decide how to transfer more effectively. Numéro de notice : A2020-195 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2019.2947634 date de publication en ligne : 20/11/2019 En ligne : https://doi.org/10.1109/TGRS.2019.2947634 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94863 [article]

Tree annotations in LiDAR data using point densities and convolutional neural networks / Ananya Gupta in IEEE Transactions on geoscience and remote sensing, vol 58 n° 2 (February 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 58 n° 2 (February 2020) . - pp 971 - 981 Titre : Tree annotations in LiDAR data using point densities and convolutional neural networks Type de document : Article/Communication Auteurs : Ananya Gupta, Auteur ; Jonathan Byrne, Auteur ; David Moloney, Auteur Année de publication : 2020 Article en page(s) : pp 971 - 981 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] Dublin (Irlande ; ville) [Termes descripteurs IGN] étiquette [Termes descripteurs IGN] extraction d'arbres [Termes descripteurs IGN] image spectrale [Termes descripteurs IGN] Montréal (Québec) [Termes descripteurs IGN] segmentation [Termes descripteurs IGN] semis de points [Termes descripteurs IGN] voxel [Termes descripteurs IGN] zone urbaine Résumé : (auteur) LiDAR provides highly accurate 3-D point clouds. However, data need to be manually labeled in order to provide subsequent useful information. Manual annotation of such data is time-consuming, tedious, and error prone, and hence, in this article, we present three automatic methods for annotating trees in LiDAR data. The first method requires high-density point clouds and uses certain LiDAR data attributes for the purpose of tree identification, achieving almost 90% accuracy. The second method uses a voxel-based 3-D convolutional neural network on low-density LiDAR data sets and is able to identify most large trees accurately but struggles with smaller ones due to the voxelization process. The third method is a scaled version of the PointNet++ method and works directly on outdoor point clouds and achieves an F score of 82.1% on the ISPRS benchmark data set, comparable to the state-of-the-art methods but with increased efficiency. Numéro de notice : A2020-095 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2019.2942201 date de publication en ligne : 11/10/2019 En ligne : https://doi.org/10.1109/TGRS.2019.2942201 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94658 [article]

Very high resolution land cover mapping of urban areas at global scale with convolutional neural network / Thomas Tilak (2020)  

Public contenu dans ArXiv / Université Cornell (Etats-Unis) (1991)   Titre : Very high resolution land cover mapping of urban areas at global scale with convolutional neural network Type de document : Article/Communication Auteurs : Thomas Tilak, Auteur ; Arnaud Braun, Auteur ; David Chandler, Auteur ; Nicolas David , Auteur ; Sylvain Galopin, Auteur ; Mickaël Michaud, Auteur ; Camille Parisel, Auteur ; Matthieu Porte, Auteur ; Marjorie Robert, Auteur Editeur : Ithaca [New York - Etats-Unis] : ArXiv - Université Cornell Année de publication : 2020 Importance : 8 p. Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] BD Alti [Termes descripteurs IGN] carte d'occupation du sol [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] corrélation croisée maximale [Termes descripteurs IGN] étiquette [Termes descripteurs IGN] Gironde (33) [Termes descripteurs IGN] image à très haute résolution [Termes descripteurs IGN] image aérienne [Termes descripteurs IGN] image multibande [Termes descripteurs IGN] modèle numérique de surface [Termes descripteurs IGN] segmentation sémantique [Termes descripteurs IGN] vectorisation [Termes descripteurs IGN] zone d'intérêt [Termes descripteurs IGN] zone urbaine Résumé : (auteur) This paper describes a methodology to produce a 7-classes land cover map of urban areas from very high resolution images and limited noisy labeled data. The objective is to make a segmentation map of a large area (a french department) with the following classes: asphalt, bare soil, building, grassland, mineral material (permeable artificialized areas), forest and water from 20cm aerial images and Digital Height Model. We created a training dataset on a few areas of interest aggregating databases, semi-automatic classification, and manual annotation to get a complete ground truth in each class. A comparative study of different encoder-decoder architectures (U-Net, U-Net with Resnet encoders, Deeplab v3+) is presented with different loss functions. The final product is a highly valuable land cover map computed from model predictions stitched together, binarized, and refined before vectorization. Numéro de notice : P2020-006 Thématique : IMAGERIE Nature : Article nature-HAL : Préprint En ligne : https://arxiv.org/pdf/2005.05652.pdf Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95079

Land cover mapping at very high resolution with rotation equivariant CNNs : Towards small yet accurate models / Diego Marcos in ISPRS Journal of photogrammetry and remote sensing, vol 145 - part A (November 2018)  

Permalink

Label propagation with ensemble of pairwise geometric relations : towards robust large-scale retrieval of object instances / Xiaomeng Wu in International journal of computer vision, vol 126 n° 7 (July 2018)  

Permalink

Large-scale supervised learning for 3D Point cloud labeling : Semantic3d.Net / Timo Hackel in Photogrammetric Engineering & Remote Sensing, PERS, vol 84 n° 5 (mai 2018)  

Permalink

Open land cover from OpenStreetMap and remote sensing / Michael Schultz in International journal of applied Earth observation and geoinformation, vol 63 (December 2017)  

Permalink

A novel semisupervised active-learning algorithm for hyperspectral image classification / Zengmao Wang in IEEE Transactions on geoscience and remote sensing, vol 55 n° 6 (June 2017)  

Permalink

Mixed map labeling / Maarten Löffler in Journal of Spatial Information Science (JoSIS), n° 13 (September 2016)  

Permalink

Label embedding : a frugal baseline for text recognition / Jose A. Rodriguez-Serrano in International journal of computer vision, vol 113 n° 3 (July 2015)  

Permalink

Confounds and Consequences in Geotagged Twitter Data / Umashanthi Pavalanathan (7/06/2015)    

Permalink

Génération de modèles numériques de surface et détection de changements 3D à partir d'imagerie satellite stéréoscopique très haute résolution / Cyrielle Guerin (2014)  

Permalink

Assessing the veracity of methods for extracting place semantics from Flickr tags / William A Mackaness in Transactions in GIS, vol 17 n° 4 (August 2013)  

Permalink