Unnecessary Image Pair Detection for a Large Scale Reconstruction

Abstract : This paper proposes an algorithm to detect unnecessary image pairs for efficient structure from motion. Since image pair with small baseline is considered as a poor condition for reconstruction, we focus on computing cameras closely located. We address a term, "remoteness" which indicates the distance between two images in this paper. The remoteness is not affected by image's intrinsic parameters because camera intrinsic matrix is applied to put the extracted features in the normalized coordinate. The remoteness is computed using feature disparity in normalized coordinate. Therefore, we can detect redundant image pair captured at the near position without reconstruction. The proposed algorithm is proved by experimental results with Notre Dame images.
Type de document :
Communication dans un congrès
Hyun Seung Yang; Rainer Malaka; Junichi Hoshino; Jung Hyun Han. 9th International Conference on Entertainment Computing (ICEC), Sep 2010, Seoul, South Korea. Springer, Lecture Notes in Computer Science, LNCS-6243, pp.151-159, 2010, Entertainment Computing - ICEC 2010. 〈10.1007/978-3-642-15399-0_14〉
Liste complète des métadonnées

Littérature citée [14 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01055647
Contributeur : Hal Ifip <>
Soumis le : mercredi 13 août 2014 - 12:13:06
Dernière modification le : mercredi 16 août 2017 - 17:33:53
Document(s) archivé(s) le : jeudi 27 novembre 2014 - 00:17:39

Fichier

icec2010_submission_59.pdf
Fichiers produits par l'(les) auteur(s)

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Citation

Jaekwang Lee, Chang-Joon Park. Unnecessary Image Pair Detection for a Large Scale Reconstruction. Hyun Seung Yang; Rainer Malaka; Junichi Hoshino; Jung Hyun Han. 9th International Conference on Entertainment Computing (ICEC), Sep 2010, Seoul, South Korea. Springer, Lecture Notes in Computer Science, LNCS-6243, pp.151-159, 2010, Entertainment Computing - ICEC 2010. 〈10.1007/978-3-642-15399-0_14〉. 〈hal-01055647〉

Partager

Métriques

Consultations de la notice

54

Téléchargements de fichiers

80