Unnecessary Image Pair Detection for a Large Scale Reconstruction - Entertainment Computing - ICEC 2010 Access content directly
Conference Papers Year : 2010

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.
Fichier principal
Vignette du fichier
icec2010_submission_59.pdf (760.34 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01055647 , version 1 (13-08-2014)

Licence

Attribution

Identifiers

Cite

Jaekwang Lee, Chang-Joon Park. Unnecessary Image Pair Detection for a Large Scale Reconstruction. 9th International Conference on Entertainment Computing (ICEC), Sep 2010, Seoul, South Korea. pp.151-159, ⟨10.1007/978-3-642-15399-0_14⟩. ⟨hal-01055647⟩
48 View
70 Download

Altmetric

Share

Gmail Facebook X LinkedIn More