Feature correspondence with even distribution

Xiao Tan; Changming Sun; Xavier Sirault; Robert Furbank; Tuan D. Pham

doi:10.1109/DICTA.2012.6411723

Feature correspondence with even distribution

Xiao Tan^*, Changming Sun, Xavier Sirault, Robert Furbank, Tuan D. Pham

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Citations (Scopus)

Abstract

This paper presents a new method for finding feature correspondences between a pair of stereo images, which can be used to perform 3D reconstruction and object recognition. This paper uses epiploar geometry to determine the location of potential matching points which allow the finding of the correspondences faster and more accurately. An adaptive smoothness algorithm is also proposed to filter out false matches based on the disparity jump in neighboring correspondences. More correspondences are then identified in such a way that they are evenly distributed in the images. Experimental results show that the proposed method effectively improve the percentage of correct matches, total number of correct matches, and even distribution of the correspondences.

Original language	English
Title of host publication	2012 International Conference on Digital Image Computing Techniques and Applications, DICTA 2012
DOIs	https://doi.org/10.1109/DICTA.2012.6411723
Publication status	Published - 2012
Externally published	Yes
Event	2012 14th International Conference on Digital Image Computing Techniques and Applications, DICTA 2012 - Fremantle, WA, Australia Duration: 3 Dec 2012 → 5 Dec 2012

Publication series

Name	2012 International Conference on Digital Image Computing Techniques and Applications, DICTA 2012

Conference

Conference	2012 14th International Conference on Digital Image Computing Techniques and Applications, DICTA 2012
Country/Territory	Australia
City	Fremantle, WA
Period	3/12/12 → 5/12/12

Access to Document

10.1109/DICTA.2012.6411723

Cite this

Tan, X., Sun, C., Sirault, X., Furbank, R., & Pham, T. D. (2012). Feature correspondence with even distribution. In 2012 International Conference on Digital Image Computing Techniques and Applications, DICTA 2012 Article 6411723 (2012 International Conference on Digital Image Computing Techniques and Applications, DICTA 2012). https://doi.org/10.1109/DICTA.2012.6411723

@inproceedings{e018018c1c5f4f978176966ab58c80b1,

title = "Feature correspondence with even distribution",

abstract = "This paper presents a new method for finding feature correspondences between a pair of stereo images, which can be used to perform 3D reconstruction and object recognition. This paper uses epiploar geometry to determine the location of potential matching points which allow the finding of the correspondences faster and more accurately. An adaptive smoothness algorithm is also proposed to filter out false matches based on the disparity jump in neighboring correspondences. More correspondences are then identified in such a way that they are evenly distributed in the images. Experimental results show that the proposed method effectively improve the percentage of correct matches, total number of correct matches, and even distribution of the correspondences.",

author = "Xiao Tan and Changming Sun and Xavier Sirault and Robert Furbank and Pham, {Tuan D.}",

year = "2012",

doi = "10.1109/DICTA.2012.6411723",

language = "English",

isbn = "9781467321815",

series = "2012 International Conference on Digital Image Computing Techniques and Applications, DICTA 2012",

booktitle = "2012 International Conference on Digital Image Computing Techniques and Applications, DICTA 2012",

note = "2012 14th International Conference on Digital Image Computing Techniques and Applications, DICTA 2012 ; Conference date: 03-12-2012 Through 05-12-2012",

}

Tan, X, Sun, C, Sirault, X, Furbank, R & Pham, TD 2012, Feature correspondence with even distribution. in 2012 International Conference on Digital Image Computing Techniques and Applications, DICTA 2012., 6411723, 2012 International Conference on Digital Image Computing Techniques and Applications, DICTA 2012, 2012 14th International Conference on Digital Image Computing Techniques and Applications, DICTA 2012, Fremantle, WA, Australia, 3/12/12. https://doi.org/10.1109/DICTA.2012.6411723

Feature correspondence with even distribution. / Tan, Xiao; Sun, Changming; Sirault, Xavier et al.
2012 International Conference on Digital Image Computing Techniques and Applications, DICTA 2012. 2012. 6411723 (2012 International Conference on Digital Image Computing Techniques and Applications, DICTA 2012).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Feature correspondence with even distribution

AU - Tan, Xiao

AU - Sun, Changming

AU - Sirault, Xavier

AU - Furbank, Robert

AU - Pham, Tuan D.

PY - 2012

Y1 - 2012

N2 - This paper presents a new method for finding feature correspondences between a pair of stereo images, which can be used to perform 3D reconstruction and object recognition. This paper uses epiploar geometry to determine the location of potential matching points which allow the finding of the correspondences faster and more accurately. An adaptive smoothness algorithm is also proposed to filter out false matches based on the disparity jump in neighboring correspondences. More correspondences are then identified in such a way that they are evenly distributed in the images. Experimental results show that the proposed method effectively improve the percentage of correct matches, total number of correct matches, and even distribution of the correspondences.

AB - This paper presents a new method for finding feature correspondences between a pair of stereo images, which can be used to perform 3D reconstruction and object recognition. This paper uses epiploar geometry to determine the location of potential matching points which allow the finding of the correspondences faster and more accurately. An adaptive smoothness algorithm is also proposed to filter out false matches based on the disparity jump in neighboring correspondences. More correspondences are then identified in such a way that they are evenly distributed in the images. Experimental results show that the proposed method effectively improve the percentage of correct matches, total number of correct matches, and even distribution of the correspondences.

UR - http://www.scopus.com/inward/record.url?scp=84874359216&partnerID=8YFLogxK

U2 - 10.1109/DICTA.2012.6411723

DO - 10.1109/DICTA.2012.6411723

M3 - Conference contribution

SN - 9781467321815

T3 - 2012 International Conference on Digital Image Computing Techniques and Applications, DICTA 2012

BT - 2012 International Conference on Digital Image Computing Techniques and Applications, DICTA 2012

T2 - 2012 14th International Conference on Digital Image Computing Techniques and Applications, DICTA 2012

Y2 - 3 December 2012 through 5 December 2012

ER -

Feature correspondence with even distribution

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this