Détail de l'auteur
Auteur Z. Tu |
Documents disponibles écrits par cet auteur (1)
Ajouter le résultat dans votre panier Affiner la recherche Interroger des sources externes
A framework for automatic recognition of spatial features from mobile mapping imagery / Z. Tu in Photogrammetric Engineering & Remote Sensing, PERS, vol 68 n° 3 (March 2002)
[article]
Titre : A framework for automatic recognition of spatial features from mobile mapping imagery Type de document : Article/Communication Auteurs : Z. Tu, Auteur ; R. Li, Auteur Année de publication : 2002 Article en page(s) : pp 267 - 276 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique
[Termes IGN] axiome de Bayes
[Termes IGN] chaîne de Markov
[Termes IGN] méthode de Monte-Carlo
[Termes IGN] méthode robuste
[Termes IGN] objet géographique
[Termes IGN] objet géographique 3D
[Termes IGN] point de fuite
[Termes IGN] processus stochastique
[Termes IGN] reconnaissance automatique
[Termes IGN] reconnaissance de formes
[Termes IGN] système de numérisation mobileRésumé : (Auteur) Mobile mapping is a new technology for capturing georeferenced data. It is, however, still not practical to extract spatial and attribute information of objects such as infrastructure elements fully automatically. In this article, a new framework for 3D object recognition by hypothesis-and-test techniques is proposed and developed. An example of traffic-light recognition from mobile mapping images is given in detail. The hypothesis is generated according to the viewpoint dependent theory. We formulate the hypothesis test problem based on Bayesion inference and, in particular, the MAP (Maximize A Posteriori Probability). This approach functions in two major steps: (1) generation of hot-spot maps by vanishing point detection and template matching, and (2) estimation of the parameters of 3D objects (traffic lights) by Markov Chain Monte Carlo (MCMC). The developed hot-spot map generation method is, in general, faster than general color image segmentation algorithms. For example, it can handle the recognition problem with a color image of 720 by 400 pixels within a couple of minutes rather than tens of minutes to even hours when using the segmentation algorithms. The parameter estimation method uses mcmc to simulate an ergodic stochastic process so that a robust and global optimal solution can be found. The approach shows great potential for automatic object recognition in image sequences acquired by mobile mapping systems. Numéro de notice : A2002-030 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : sans En ligne : https://www.asprs.org/wp-content/uploads/pers/2002journal/march/2002_mar_267-276 [...] Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=21947
in Photogrammetric Engineering & Remote Sensing, PERS > vol 68 n° 3 (March 2002) . - pp 267 - 276[article]