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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal.inria.fr/hal-01055647
Contributor : Hal Ifip <>
Submitted on : Wednesday, August 13, 2014 - 12:13:06 PM
Last modification on : Wednesday, August 16, 2017 - 5:33:53 PM
Long-term archiving on : Thursday, November 27, 2014 - 12:17:39 AM

File

icec2010_submission_59.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

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⟩

Share

Metrics

Record views

99

Files downloads

176