Descripteur
Termes IGN > mathématiques > statistique mathématique > analyse de données > classification > classification par séparateurs à vaste marge
classification par séparateurs à vaste margeSynonyme(s)classification SVMVoir aussi |
Documents disponibles dans cette catégorie (143)
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externes
Etendre la recherche sur niveau(x) vers le bas
Land cover classification in combined elevation and optical images supported by OSM data, mixed-level features, and non-local optimization algorithms / Dimitri Bulatov in Photogrammetric Engineering & Remote Sensing, PERS, vol 85 n° 3 (March 2019)
[article]
Titre : Land cover classification in combined elevation and optical images supported by OSM data, mixed-level features, and non-local optimization algorithms Type de document : Article/Communication Auteurs : Dimitri Bulatov, Auteur ; Gisela Häufel, Auteur ; Lucas Lucks, Auteur ; Melanie Pohl, Auteur Année de publication : 2019 Article en page(s) : pp 179 - 195 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] champ aléatoire de Markov
[Termes IGN] classification dirigée
[Termes IGN] classification par forêts d'arbres décisionnels
[Termes IGN] classification par séparateurs à vaste marge
[Termes IGN] données localisées des bénévoles
[Termes IGN] extraction automatique
[Termes IGN] milieu urbain
[Termes IGN] OpenStreetMap
[Termes IGN] orthoimageRésumé : (Auteur) Land cover classification from airborne data is considered a challenging task in Remote Sensing. Even in the case of available elevation data, shadows and strong intra-class variations of appearances are abundant in urban terrain. In this paper, we propose an approach for supervised land cover classification that has three main contributions. Firstly, for the cumbersome task of training data sampling we propose an algorithm which combines the freely available OpenStreetMap data with the actual sensor data and requires only a minimum of user interaction. The key idea of this algorithm is to rasterize the vector data using a fast segmentation result. Secondly, pixel-wise classification may take long and be quite sensitive to the resolution and quality of input data. Therefore, superpixel decomposition of images, supported by a general framework on operations with superpixels, guarantees fast grouping of pixel-wise features and their assignment to one of four important classes (building, tree, grass and road). Particularly for extraction of street canyons lying in the shadowy regions, high-level features based on stripes are introduced. Finally, the output of a probabilistic learning algorithm can be postprocessed by a non-local optimization module operating on Markov Random Fields, thus allowing to correct noisy results using a smoothness prior. Extensive tests on three datasets of quite different nature have been performed with two probabilistic learners: The well-known Random Forest and by far less known Import Vector Machine are explored. Thus, this work provides insights about promising feature sets for both classifiers. The quantitative results for the ISPRS benchmark dataset Vaihingen are promising, achieving up to 94.5% and 87.1% accuracy on superpixel and on pixel level, respectively, despite the fact that only around 10% of available labeled data were used. At the same time, the results for two additional datasets, validated with the autonomously acquired training data, yielded a significantly lower number of misclassified superpixels. This confirms that the proposed algorithm on training data extraction works quite well in reducing errors of second kind. However, it tends to extract predominantly huge and easy-to-classify areas, while in complicated, ambiguous regions, first type errors often occur. For this and other algorithm shortcomings, directions of future research are outlined. Numéro de notice : A2019-147 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.14358/PERS.85.3.179 Date de publication en ligne : 01/03/2019 En ligne : https://doi.org/10.14358/PERS.85.3.179 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92476
in Photogrammetric Engineering & Remote Sensing, PERS > vol 85 n° 3 (March 2019) . - pp 179 - 195[article]Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 105-2019031 SL Revue Centre de documentation Revues en salle Disponible Ailanthus altissima mapping from multi-temporal very high resolution satellite images / Cristina Tarantino in ISPRS Journal of photogrammetry and remote sensing, vol 147 (January 2019)
[article]
Titre : Ailanthus altissima mapping from multi-temporal very high resolution satellite images Type de document : Article/Communication Auteurs : Cristina Tarantino, Auteur ; Francesca Casella, Auteur ; Maria Adamo, Auteur ; Richard Lucas, Auteur ; Carl Beierkuhnlein, Auteur ; Palma Blonda, Auteur Année de publication : 2019 Article en page(s) : pp 90 - 103 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] Ailanthus altissima
[Termes IGN] analyse diachronique
[Termes IGN] carte d'occupation du sol
[Termes IGN] classification par maximum de vraisemblance
[Termes IGN] classification par séparateurs à vaste marge
[Termes IGN] espèce exotique envahissante
[Termes IGN] filtrage optique
[Termes IGN] filtre passe-bas
[Termes IGN] image à très haute résolution
[Termes IGN] image multitemporelle
[Termes IGN] image Worldview
[Termes IGN] indice de végétation
[Termes IGN] ItalieRésumé : (auteur) This study presents the results of multi-seasonal WorldView-2 (WV-2) satellite images classification for the mapping of Ailanthus altissima (A. altissima), an invasive plant species thriving in a protected grassland area of Southern Italy. The technique used relied on a two-stage hybrid classification process: the first stage applied a knowledge-driven learning scheme to provide a land cover map (LC), including deciduous vegetation and other classes, without the need of reference training data; the second stage exploited a data-driven classification to: (i) discriminate pixels of the invasive species found within the deciduous vegetation layer of the LC map; (ii) determine the most favourable seasons for such recognition. In the second stage, when a traditional Maximum Likelihood classifier was used, the results obtained with multi-temporal July and October WV-2 images, showed an output Overall Accuracy (OA) value of ≈91%. To increase such a value, first a low-pass median filtering was used with a resulting OA of 99.2%, then, a Support Vector Machine classifier was applied obtaining the best A. altissima User’s Accuracy (UA) and OA values of 82.47% and 97.96%, respectively, without any filtering. When instead of the full multi-spectral bands set some spectral vegetation indices computed from the same months were used the UA and OA values decreased. The findings reported suggest that multi-temporal, very high resolution satellite imagery can be effective for A. altissima mapping, especially when airborne hyperspectral data are unavailable. Since training data are required only in the second stage to discriminate A. altissima from other deciduous plants, the use of the first stage LC mapping as pre-filter can render the hybrid technique proposed cost and time effective. Multi-temporal VHR data and the hybrid system suggested may offer new opportunities for invasive plant monitoring and follow up of management decision. Numéro de notice : A2019-035 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2018.11.013 Date de publication en ligne : 20/11/2018 En ligne : https://doi.org/10.1016/j.isprsjprs.2018.11.013 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91972
in ISPRS Journal of photogrammetry and remote sensing > vol 147 (January 2019) . - pp 90 - 103[article]Réservation
Réserver ce documentExemplaires(3)
Code-barres Cote Support Localisation Section Disponibilité 081-2019011 RAB Revue Centre de documentation En réserve L003 Disponible 081-2019013 DEP-EXM Revue LASTIG Dépôt en unité Exclu du prêt 081-2019012 DEP-EAF Revue Nancy Dépôt en unité Exclu du prêt Enhancing the predictability of least-squares collocation through the integration with least-squares-support vector machine / Hossam Talaat Elshambaky in Journal of applied geodesy, vol 13 n° 1 (January 2019)
[article]
Titre : Enhancing the predictability of least-squares collocation through the integration with least-squares-support vector machine Type de document : Article/Communication Auteurs : Hossam Talaat Elshambaky, Auteur Année de publication : 2019 Article en page(s) : pp 1 - 15 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Statistiques
[Termes IGN] classification par réseau neuronal
[Termes IGN] classification par séparateurs à vaste marge
[Termes IGN] collocation par moindres carrés
[Termes IGN] covariance
[Termes IGN] Egypte
[Termes IGN] fonction de base radiale
[Termes IGN] géoïde localRésumé : (Auteur) Least-squares collocation (LSC) is a crucial mathematical tool for solving many geodetic problems. It has the capability to adjust, filter, and predict unknown quantities that affect many geodetic applications. Hence, this study aims to enhance the predictability property of LSC through applying soft computing techniques in the stage of describing the covariance function. Soft computing techniques include the support vector machine (SVM), least-squares-support vector machine (LS-SVM), and artificial neural network (ANN). A real geodetic case study is used to predict a national geoid from the EGM2008 global geoid model in Egypt. A comparison study between parametric and soft computing techniques was performed to assess the LSC predictability accuracy. We found that the predictability accuracy increased when using soft computing techniques in the range of 10.2 %–27.7 % and 8.2 %–29.8 % based on the mean square error and the mean error terms, respectively, compared with the parametric models. The LS-SVM achieved the highest accuracy among the soft computing techniques. In addition, we found that the integration between the LS-SVM with LSC exhibits an accuracy of 20 % and 25 % higher than using LS-SVM independently as a predicting tool, based on the mean square error and mean error terms, respectively. Consequently, the LS-SVM integrated with LSC is recommended for enhanced predictability in geodetic applications. Numéro de notice : A2019-132 Affiliation des auteurs : non IGN Thématique : MATHEMATIQUE/POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1515/jag-2018-0017 Date de publication en ligne : 25/08/2018 En ligne : https://doi.org/10.1515/jag-2018-0017 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92462
in Journal of applied geodesy > vol 13 n° 1 (January 2019) . - pp 1 - 15[article]
Titre : Ensemble methods for pedestrian detection in dense crowds Type de document : Thèse/HDR Auteurs : Jennifer Vandoni, Auteur ; Sylvie Le Hégarat-Mascle, Directeur de thèse Editeur : Paris-Orsay : Université de Paris 11 Paris-Sud Centre d'Orsay Année de publication : 2019 Importance : 182 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse de Doctorat de l'Université Paris-Saclay, Sciences et technologies de l’information et de la communication (STIC), Spécialité : Traitement du Signal et des ImagesLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] algorithme d'apprentissage
[Termes IGN] apprentissage dirigé
[Termes IGN] apprentissage profond
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] classification par séparateurs à vaste marge
[Termes IGN] comportement
[Termes IGN] densité de population
[Termes IGN] détection de piéton
[Termes IGN] données multicapteurs
[Termes IGN] étalonnage
[Termes IGN] fusion de données
[Termes IGN] taxinomie
[Termes IGN] théorie de Dempster-ShaferIndex. décimale : THESE Thèses et HDR Résumé : (auteur) The interest surrounding the study of crowd phenomena spanned during the last decade across multiple fields, including computer vision, physics, sociology, simulation and visualization. There are different levels of granularity at which crowd studies can be performed, namely a finer microanalysis, aimed to detect and then track each pedestrian individually; and a coarser macro-analysis, aimed to model the crowd as a whole.
One of the most difficult challenges when working with human crowds is that usual pedestrian detection methodologies do not scale well to the case where only heads are visible, for a number of reasons such as absence of background, high visual homogeneity, small size of the objects, and heavy occlusions. For this reason, most micro-analysis studies by means of pedestrian detection and tracking methodologies are performed in low to medium-density crowds, whereas macro-analysis through density estimation and people counting is more suited in presence of high-density crowds, where the exact position of each individual is not necessary. Nevertheless, in order to analyze specific events involving high-density crowds for monitoring the flow and preventing disasters such as stampedes, a complete understanding of the scene must be reached. This study deals with pedestrian detection in high-density crowds from a monocamera system, striving to obtain localized detections of all the individuals which are part of an extremely dense crowd. The detections can be then used both to obtain robust density estimation, and to initialize a tracking algorithm. In presence of difficult problems such as our application, supervised learning techniques are well suited. However, two different questions arise, namely which classifier is the most adapted for the considered environment, and which data to use to learn from. We cast the detection problem as a Multiple Classifier System (MCS), composed by two different ensembles of classifiers, the first one based on SVM (SVM-ensemble) and the second one based on CNN (CNN-ensemble), combined relying on the Belief Function Theory (BFT) designing a fusion method which is able to exploit their strengths for pixel-wise classification. SVM-ensemble is composed by several SVM detectors based on different gradient, texture and orientation descriptors, able to tackle the problem from different perspectives. BFT allows us to take into account the imprecision in addition to the uncertainty value provided by each classifier, which we consider coming from possible errors in the calibration procedure and from pixel neighbor’s heterogeneity in the image space due to the close resolution of the target (head) and
descriptor respectively. However, scarcity of labeled data for specific dense crowd contexts reflects in the impossibility to easily obtain robust training and validation sets. By exploiting belief functions directly derived
from the classifiers’ combination, we therefore propose an evidential Query-by-Committee (QBC) active learning algorithm to automatically select the most informative training samples. On the other side, we explore deep learning techniques by casting the problem as a segmentation task in presence of soft labels, with a fully convolutional network architecture designed to recover small objects (heads) thanks to a tailored use of dilated convolutions. In order to obtain a pixel-wise measure of reliability about the network’s predictions, we create a CNN-ensemble by means of dropout at inference time, and we combine the different obtained realizations in the
context of BFT. To conclude, we show that the dense output map given by the MCS can be employed not only
for pedestrian detection at microscopic level, but also to perform macroscopic analysis, bridging the gap between the two levels of granularity. We therefore finally focus our attention to people counting, proposing an evaluation method that can be applied at every scale, resulting to be more precise in the error and uncertainty evaluation (disregarding possible compensations) as well as more useful for the modeling community that could use it to improve and validate local density estimation.Note de contenu : 1- Crowd understanding
2- Supervised learning and classifier combination
3- SVM descriptors for pedestrian detection in high-density crowds
4- Taking into account imprecision with Belief Function Framework
5- Evidential QBC Active Learning
6- CNNs for pedestrian detection in high-density crowds
7- CNN-ensemble and evidential Multiple Classifier System
8- Density Estimation
ConclusionNuméro de notice : 25704 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse française Note de thèse : Thèse de Doctorat : Traitement du Signal et des Images : Paris 11 : 2019 Organisme de stage : Systèmes et applications des technologies de l'information et de l'énergie (Paris) nature-HAL : Thèse DOI : sans En ligne : https://theses.hal.science/tel-02318892/document Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94838 Evaluation of time-series SAR and optical images for the study of winter land-use / Julien Denize (2019)
Titre : Evaluation of time-series SAR and optical images for the study of winter land-use Type de document : Thèse/HDR Auteurs : Julien Denize, Auteur ; Eric Pottier, Directeur de thèse ; Laurence Hubert-Moy, Directeur de thèse Editeur : Rennes : Université de Rennes 1 Année de publication : 2019 Importance : 274 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse de Doctorat de l'Université Rennes 1, Mathématiques et Sciences et Technologies de l'Information et de la Communication, Spécialité Signal Image Vision & GéomatiqueLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte
[Termes IGN] agriculture
[Termes IGN] classification par forêts d'arbres décisionnels
[Termes IGN] classification par séparateurs à vaste marge
[Termes IGN] données polarimétriques
[Termes IGN] hiver
[Termes IGN] image à haute résolution
[Termes IGN] image radar moirée
[Termes IGN] image Radarsat
[Termes IGN] image Sentinel-MSI
[Termes IGN] image Sentinel-SAR
[Termes IGN] nébulosité
[Termes IGN] Normalized Difference Vegetation Index
[Termes IGN] série temporelle
[Termes IGN] télédétection spatiale
[Termes IGN] utilisation du solIndex. décimale : THESE Thèses et HDR Résumé : (auteur) The study of winter land-use is a major challenge in order to preserve and improve the quality of soils and surface water. However, knowledge of the spatio-temporal dynamics associated with winter land-use remains a challenge for the scientific community. In this context, the objective of this study is to evaluate the potential of time series of high spatial resolution optical and SAR images for the study of winter land-use at a local and regional scale. For that purpose, a methodology has been established to: (i) determine the most suitable classification method for identifying winter land-use ; (ii) compare Sentinel-1 SAR and Sentinel-2 optical images; (iii) define the most suitable SAR configuration by comparing three image time-series (Alos-2, Radarsat-2 and Sentinel-1).The results first of all highlighted the interest of the Random Forest classification algorithm to discriminate at a fine scale the different types of land use in winter. Secondly, they showed the value of Sentinel-2 data for mapping winter land-use at a local and regional scale. Finally, they determined that a dense time series of Sentinel-1 images was the most appropriate SAR configuration to identify winter land-use. In general, while this thesis has shown that Sentinel-2 data are best suited to studying land use in winter, SAR images are of great interest in regions with significant cloud cover, dense Sentinel-1 time-series having being defined as the most efficient. Note de contenu : General Introduction
1- Winter land-use: concepts, data and methods
2- Classification procedure for the winter land-use study at a local scale
3- SAR configuration for the study of winter land-use at a local scale
4- The study of winter land-use at a regional scale
General conclusion and perspectivesNuméro de notice : 25710 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse française Note de thèse : Thèse de Doctorat : Signal Image Vision & Géomatique : Rennes1 : 2019 Organisme de stage : Institut d’Electronique et de Télécommunication de Rennes nature-HAL : Thèse DOI : sans En ligne : https://hal.science/tel-02510333/document Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94858 Machine learning and geographic information systems for large-scale mapping of renewable energy potential / Dan Assouline (2019)PermalinkPermalinkSemantic aware quality evaluation of 3D building models : Modeling and simulation / Oussama Ennafii (2019)PermalinkSpatial decision support in urban environments using machine learning, 3D geo-visualization and semantic integration of multi-source data / Nikolaos Sideris (2019)PermalinkRemote sensing scene classification using multilayer stacked covariance pooling / Nanjun He in IEEE Transactions on geoscience and remote sensing, vol 56 n° 12 (December 2018)PermalinkRobust vehicle detection in aerial images using bag-of-words and orientation aware scanning / Hailing Zhou in IEEE Transactions on geoscience and remote sensing, vol 56 n° 12 (December 2018)PermalinkEstimation of forest above-ground biomass by geographically weighted regression and machine learning with Sentinel imagery / Lin Chen in Forests, vol 9 n° 10 (October 2018)PermalinkAssessment of Sentinel-1A data for rice crop classification using random forests and support vector machines / Nguyen-Thanh Son in Geocarto international, vol 33 n° 6 (June 2018)PermalinkSpatially sensitive statistical shape analysis for pedestrian recognition from LIDAR data / Michalis A. Savelonas in Computer Vision and image understanding, vol 171 (June 2018)PermalinkAn object-based approach for mapping forest structural types based on low-density LiDAR and multispectral imagery / Luis Angel Ruiz in Geocarto international, vol 33 n° 5 (May 2018)Permalink