Abstract : We address the problem of building 3D object models from image sequences obtained with known camera motion. An approach based on a local reconstruction method is presented. Recovered surfaces are described as polygonal meshes. To this purpose, reconstructed points are triangulated and surface areas which are not covered by rims are detected since they may lead to false reconstructed points. Resulting meshes are then regularised in order to correct noise perturbations which affect the reconstruction. Experimental results on real data are presented.
Type de document :
Communication dans un congrès
Bernard F. Buxton and Roberto Cipolla. 4th European Conference on Computer Vision (ECCV'96), Apr 1996, Cambridge, United Kingdom. Springer-Verlag, 1065, pp.109--118, 1996, Lecture Notes in Computer Science (LNCS). 〈10.1007/3-540-61123-1_131〉
https://hal.inria.fr/inria-00590062
Contributeur : Team Perception
<>
Soumis le : mardi 3 mai 2011 - 09:14:40
Dernière modification le : jeudi 11 janvier 2018 - 06:23:18
Document(s) archivé(s) le : jeudi 4 août 2011 - 02:47:08
Edmond Boyer. Object Models From Contour Sequences. Bernard F. Buxton and Roberto Cipolla. 4th European Conference on Computer Vision (ECCV'96), Apr 1996, Cambridge, United Kingdom. Springer-Verlag, 1065, pp.109--118, 1996, Lecture Notes in Computer Science (LNCS). 〈10.1007/3-540-61123-1_131〉. 〈inria-00590062〉
