Détail de l'auteur
Auteur Konstantinos D. Koutroumbas |
Documents disponibles écrits par cet auteur (2)
Ajouter le résultat dans votre panier Affiner la recherche Interroger des sources externes
A methodology for near real-time change detection between Unmanned Aerial Vehicle and wide area satellite images / Anastasios L. Fytsilis in ISPRS Journal of photogrammetry and remote sensing, vol 119 (September 2016)
[article]
Titre : A methodology for near real-time change detection between Unmanned Aerial Vehicle and wide area satellite images Type de document : Article/Communication Auteurs : Anastasios L. Fytsilis, Auteur ; Anthony Prokos, Auteur ; Konstantinos D. Koutroumbas, Auteur ; et al., Auteur Année de publication : 2016 Article en page(s) : pp 165- 186 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] classification hybride
[Termes IGN] drone
[Termes IGN] gradient
[Termes IGN] image aérienne
[Termes IGN] image satellite
[Termes IGN] méthodologie
[Termes IGN] orthorectification automatique
[Termes IGN] recalage d'imageRésumé : (Auteur) In this paper a novel integrated hybrid methodology for unsupervised change detection between Unmanned Aerial Vehicle (UAV) and satellite images, which can be utilized in various fields like security applications (e.g. border surveillance) and damage assessment, is proposed. This is a challenging problem mainly due to the difference in geographic coverage and the spatial resolution of the two images, as well as to the acquisition modes which lead to misregistration errors. The methodology consists of the following steps: (a) pre-processing, where the part of the satellite image that corresponds to the UAV image is determined and the UAV image is ortho-rectified using information provided by a Digital Terrain Model, (b) the detection of potential changes, which is based exclusively on intensity and image gradient information, (c) the generation of the region map, where homogeneous regions are produced by the previous potential changes via a seeded region growing algorithm and placed on the region map, and (d) the evaluation of the above regions, in order to characterize them as true changes or not. The methodology has been applied on demanding real datasets with very encouraging results. Finally, its robustness to the misregistration errors is assessed via extensive experimentation. Numéro de notice : A2016-782 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2016.06.001 En ligne : http://dx.doi.org/10.1016/j.isprsjprs.2016.06.001 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82479
in ISPRS Journal of photogrammetry and remote sensing > vol 119 (September 2016) . - pp 165- 186[article]Simultaneously sparse and low-rank abundance matrix estimation for hyperspectral image unmixing / Paris V. Giampouras in IEEE Transactions on geoscience and remote sensing, vol 54 n° 8 (August 2016)
[article]
Titre : Simultaneously sparse and low-rank abundance matrix estimation for hyperspectral image unmixing Type de document : Article/Communication Auteurs : Paris V. Giampouras, Auteur ; Konstantinos E. Themelis, Auteur ; Athanasios A. Rontogiannis, Auteur ; Konstantinos D. Koutroumbas, Auteur Année de publication : 2016 Article en page(s) : pp 4775 - 4789 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] analyse des mélanges spectraux
[Termes IGN] corrélation automatique de points homologues
[Termes IGN] données clairsemées
[Termes IGN] image hyperspectrale
[Termes IGN] matrice creuseRésumé : (Auteur) In a plethora of applications dealing with inverse problems, e.g., image processing, social networks, compressive sensing, and biological data processing, the signal of interest is known to be structured in several ways at the same time. This premise has recently guided research into the innovative and meaningful idea of imposing multiple constraints on the unknown parameters involved in the problem under study. For instance, when dealing with problems whose unknown parameters form sparse and low-rank matrices, the adoption of suitably combined constraints imposing sparsity and low rankness is expected to yield substantially enhanced estimation results. In this paper, we address the spectral unmixing problem in hyperspectral images. Specifically, two novel unmixing algorithms are introduced in an attempt to exploit both spatial correlation and sparse representation of pixels lying in the homogeneous regions of hyperspectral images. To this end, a novel mixed penalty term is first defined consisting of the sum of the weighted ℓ1 and the weighted nuclear norm of the abundance matrix corresponding to a small area of the image determined by a sliding square window. This penalty term is then used to regularize a conventional quadratic cost function and impose simultaneous sparsity and low rankness on the abundance matrix. The resulting regularized cost function is minimized by: 1) an incremental proximal sparse and low-rank unmixing algorithm; and 2) an algorithm based on the alternating direction method of multipliers. The effectiveness of the proposed algorithms is illustrated in experiments conducted both on simulated and real data. Numéro de notice : A2016-891 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2551327 En ligne : https://doi.org/10.1109/TGRS.2016.2551327 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=83071
in IEEE Transactions on geoscience and remote sensing > vol 54 n° 8 (August 2016) . - pp 4775 - 4789[article]