Détail de l'auteur
Auteur M. Gelautz |
Documents disponibles écrits par cet auteur (2)
Ajouter le résultat dans votre panier Affiner la recherche Interroger des sources externes
A layered stereo matching algorithm using segmentation and global visibility constraints / M. Bleyer in ISPRS Journal of photogrammetry and remote sensing, vol 59 n° 3 (May 2005)
[article]
Titre : A layered stereo matching algorithm using segmentation and global visibility constraints Type de document : Article/Communication Auteurs : M. Bleyer, Auteur ; M. Gelautz, Auteur Année de publication : 2005 Article en page(s) : pp 128 - 150 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique
[Termes IGN] algorithme de décalage moyen
[Termes IGN] algorithme glouton
[Termes IGN] appariement de données localisées
[Termes IGN] compensation par moindres carrés
[Termes IGN] couche thématique
[Termes IGN] détection de partie cachée
[Termes IGN] extraction de couche
[Termes IGN] fenêtre (informatique)
[Termes IGN] graphe planaire
[Termes IGN] programmation par contraintes
[Termes IGN] segmentation d'image
[Termes IGN] visibilité
[Termes IGN] visualisation 3D
[Termes IGN] zone tamponRésumé : (Auteur) This work describes a stereo algorithm that takes advantage of image segmentation, assuming that disparity varies smoothly inside a segment of homogeneous colour and depth discontinuities coincide with segment borders. Image segmentation allows our method to generate correct disparity estimates in large untextured regions and precisely localize depth boundaries. The disparity inside a segment is represented by a planar equation. To derive the plane model, an initial disparity map is generated. We use a window-based approach that exploits the results of segmentation. The size of the match window is chosen adaptively. A segment's planar model is then derived by robust least squared error fitting using the initial disparity map. In a layer extraction step, disparity segments that are found to be similar according to a plane dissimilarity measurement are combined to form a single robust layer. We apply a modified mean-shift algorithm to extract clusters of similar disparity segments. Segments of the same cluster build a layer, the plane parameters of which are computed from its spatial extent using the initial disparity map. We then optimize the assignment of segments to layers using a global cost function. The quality of the disparity map is measured by warping the reference image to the second view and comparing it with the real image. Z-buffering enforces visibility and allows the explicit detection of occlusions. The cost function measures the colour dissimilarity between the warped and real views, and penalizes occlusions and neighbouring segments that are assigned to different layers. Since the problem of finding the assignment of segments to layers that minimizes this cost function is NP-complete, an efficient greedy algorithm is applied to find a local minimum. Layer extraction and assignment are alternately applied. Qualitative and quantitative results obtained for benchmark image pairs show that the proposed algorithm outperforms most state-of-the-art matching algorithms currently listed on the Middlebury stereo evaluation website. The technique achieves particularly good results in areas with depth discontinuities and related occlusions, where missing stereo information is substituted from surrounding regions. Furthermore, we apply the algorithm to a self-recorded image set and show 3D visualizations of the derived results. Numéro de notice : A2005-229 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2005.02.008 En ligne : https://doi.org/10.1016/j.isprsjprs.2005.02.008 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=27366
in ISPRS Journal of photogrammetry and remote sensing > vol 59 n° 3 (May 2005) . - pp 128 - 150[article]Réservation
Réserver ce documentExemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité 081-05011 SL Revue Centre de documentation Revues en salle Disponible Radar stereo- and interferometry-derived digital elevation models: comparison and combination using Radarsat and ERS-2 imagery / M. Gelautz in International Journal of Remote Sensing IJRS, vol 24 n° 24 (December 2003)
[article]
Titre : Radar stereo- and interferometry-derived digital elevation models: comparison and combination using Radarsat and ERS-2 imagery Type de document : Article/Communication Auteurs : M. Gelautz, Auteur ; P. Paillou, Auteur ; C.W. Chen, Auteur ; H. Zebker, Auteur Année de publication : 2003 Article en page(s) : pp 5243 - 5264 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications
[Termes IGN] acquisition d'images
[Termes IGN] analyse comparative
[Termes IGN] histogramme
[Termes IGN] image ERS-SAR
[Termes IGN] image Radarsat
[Termes IGN] interféromètrie par radar à antenne synthétique
[Termes IGN] modèle numérique de surface
[Termes IGN] modèle stéréoscopique
[Termes IGN] penteRésumé : (Auteur) In this experiment, we derive and compare radar stereo and interferometric digital elevation models (DEMs) of a study site in Djibouti, East Africa. A Radarsat stereo pair, as well as Radarsat and ERS-2 interferometric data, comprise the test images. The primary objective of the study was to analyse and compare the results obtained by the two techniques and explore possible synergisms between them. We find that in regions of high coherence, the DEMs produced by interferometry are of much better quality than the stereo result. However, the corresponding error histograms also show some pronounced errors due to decorrelation and phase-unwrapping problems on forested mountain slopes. On the other hand, the more robust stereo reconstruction, with an error standard deviation of 45m, is able to capture the general terrain shape, although finer ' surface details are lost. In the second part of our experiment, we demonstrate that merging the stereoscopic and interferometric DEMs by applying a user-defined weighting function to a filtered coherence map can significantly improve the accuracy of the computed elevation maps Numéro de notice : A2003-343 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/0143116031000115139 En ligne : https://doi.org/10.1080/0143116031000115139 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=22638
in International Journal of Remote Sensing IJRS > vol 24 n° 24 (December 2003) . - pp 5243 - 5264[article]Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité 080-03241 RAB Revue Centre de documentation En réserve L003 Exclu du prêt