Centre de documentation
scientifique

Coregistration refinement of hyperspectral images and DSM: An object-based approach using spectral information / Janja Avbelj in ISPRS Journal of photogrammetry and remote sensing, vol 100 (February 2015)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 100 (February 2015) . - pp 23 - 34 Titre : Coregistration refinement of hyperspectral images and DSM: An object-based approach using spectral information Type de document : Article/Communication Auteurs : Janja Avbelj, Auteur ; Dorota Iwaszczuk, Auteur ; Rupert Müller, Auteur ; et al., Auteur Année de publication : 2015 Article en page(s) : pp 23 - 34 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse spectrale [Termes IGN] appariement d'images [Termes IGN] classification orientée objet [Termes IGN] détection du bâti [Termes IGN] données multicapteurs [Termes IGN] image hyperspectrale [Termes IGN] milieu urbain [Termes IGN] modèle numérique de surface [Termes IGN] superposition d'images Résumé : (auteur) For image fusion in remote sensing applications the georeferencing accuracy using position, attitude, and camera calibration measurements can be insufficient. Thus, image processing techniques should be employed for precise coregistration of images. In this article a method for multimodal object-based image coregistration refinement between hyperspectral images (HSI) and digital surface models (DSM) is presented. The method is divided in three parts: object outline detection in HSI and DSM, matching, and determination of transformation parameters. The novelty of our proposed coregistration refinement method is the use of material properties and height information of urban objects from HSI and DSM, respectively. We refer to urban objects as objects which are typical in urban environments and focus on buildings by describing them with 2D outlines. Furthermore, the geometric accuracy of these detected building outlines is taken into account in the matching step and for the determination of transformation parameters. Hence, a stochastic model is introduced to compute optimal transformation parameters. The feasibility of the method is shown by testing it on two aerial HSI of different spatial and spectral resolution, and two DSM of different spatial resolution. The evaluation is carried out by comparing the accuracies of the transformations parameters to the reference parameters, determined by considering object outlines at much higher resolution, and also by computing the correctness and the quality rate of the extracted outlines before and after coregistration refinement. Results indicate that using outlines of objects instead of only line segments is advantageous for coregistration of HSI and DSM. The extraction of building outlines in comparison to the line cue extraction provides a larger amount of assigned lines between the images and is more robust to outliers, i.e. false matches. Numéro de notice : A2015-051 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2014.05.010 En ligne : https://doi.org/10.1016/j.isprsjprs.2014.05.010 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=75237 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2015021	RAB	Revue	Centre de documentation	En réserve L003	Disponible

A classification algorithm for hyperspectral images based on synergetics theory / Daniele Cerra in IEEE Transactions on geoscience and remote sensing, vol 51 n° 5 Tome 1 (May 2013)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 51 n° 5 Tome 1 (May 2013) . - pp 2887 - 2898 Titre : A classification algorithm for hyperspectral images based on synergetics theory Type de document : Article/Communication Auteurs : Daniele Cerra, Auteur ; Rupert Müller, Auteur ; Peter Reinartz, Auteur Année de publication : 2013 Article en page(s) : pp 2887 - 2898 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse d'image numérique [Termes IGN] classification [Termes IGN] image hyperspectrale Résumé : (Auteur) This paper presents a classification methodology for hyperspectral data based on synergetics theory. Pattern recognition algorithms based on synergetics have been applied to images in the spatial domain with limited success in the past, given their dependence on the rotation, shifting, and scaling of the images. These drawbacks can be discarded if such methods are applied to data acquired by a hyperspectral sensor in the spectral domain, as each single spectrum, related to an image element in the hyperspectral scene, can be analyzed independently. The spectrum is first projected in a space spanned by a set of user-defined prototype vectors, which belong to some classes of interest, and then attracted by a final state associated to a prototype. The spectrum can thus be classified, establishing a first attempt at performing a pixel-wise image classification using notions derived from synergetics. As typical synergetics-based systems have the drawback of a rigid training step, we introduce a new procedure which allows the selection of a training area for each class of interest, used to weight the prototype vectors through attention parameters and to produce a more accurate classification map through plurality vote of independent classifications. As each classification is in principle obtained on the basis of a single training sample per class, the proposed technique could be particularly effective in tasks where only a small training data set is available. The results presented are promising and often outperform state-of-the-art classification methodologies, both general and specific to hyperspectral data. Numéro de notice : A2013-269 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2012.2219059 En ligne : https://doi.org/10.1109/TGRS.2012.2219059 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=32407 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2013051A	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Accuracy analysis for DSM and orthoimages derived from SPOT HRS stereo data using direct georeferencing / Peter Reinartz in ISPRS Journal of photogrammetry and remote sensing, vol 60 n° 3 (May 2006)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 60 n° 3 (May 2006) . - pp 160 - 169 Titre : Accuracy analysis for DSM and orthoimages derived from SPOT HRS stereo data using direct georeferencing Type de document : Article/Communication Auteurs : Peter Reinartz, Auteur ; Rupert Müller, Auteur ; Manfred Lehner, Auteur ; Manfred Schroeder, Auteur Année de publication : 2006 Article en page(s) : pp 160 - 169 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie spatiale [Termes IGN] caméra numérique [Termes IGN] couple stéréoscopique [Termes IGN] géoréférencement direct [Termes IGN] image MOMS-2P [Termes IGN] image SPOT-HRS [Termes IGN] modèle numérique de surface [Termes IGN] orientation du capteur [Termes IGN] orthoimage [Termes IGN] point d'appui [Termes IGN] points homologues [Termes IGN] précision du positionnement Résumé : (Auteur) During the HRS (High Resolution Stereo) Scientific Assessment Program the French space agency CNES delivered data sets from the HRS camera System with high precision ancillary data. Two test data sets from this program were evaluated: one is located in Germany, the other in Spain. The first goal was to derive orthoimages and digital surface models (DSM) from the along track stereo data by applying the rigorous model with direct georeferencing and without ground control points (GCPs). For the derivation of DSM, the stereo processing software, developed at DLR for the MOMS-2P three line stereo camera was used. As a first step, the interior and exterior orientation of the camera, delivered as ancillary data from positioning and attitude Systems were extracted. A dense image matching, using nearly all pixels as kernel centers provided the parallaxes. The quality of the stereo lie points was controlled by forward and backward matching of the two stereo partners using the local least squares matching method. Forward intersection lead to points in object space which are subsequently interpolated to a DSM in a regular grid. DEM filtering methods were also applied and evaluations carried out differentiating between accuracies in forest and other areas. Additionally, orthoimages were generated from the images of the two stereo looking directions. The orthoimage and DSM accuracy was determined by using GCPs and available reference DEMs of superior accuracy (DEM derived from laser data and/or classical airborne photogrammetry). As expected the results obtained without using GCPs showed a bias in the order of 5-20 m to the reference data for ail three coordinates. By image matching it could be shown that the two independently derived orthoimages exhibit a very constant shift behaviour. In a second step few GCPs (3-4) were used to calculate bore-sight alignment angles, introduced into the direct georeferencing process of each image independently. This method improved the absolute accuracy of the resulting orthoimages and DSM significantly. Copyright ISPRS Numéro de notice : A2006-227 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2005.12.003 En ligne : https://doi.org/10.1016/j.isprsjprs.2005.12.003 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=27954 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-06031	SL	Revue	Centre de documentation	Revues en salle	Disponible