Automatic edge matching across an image sequence based on reliable points

Yixiang Tian; M. Gerke; G. Vosselman; Qing Zhu

Automatic edge matching across an image sequence based on reliable points

Yixiang Tian, M. Gerke, G. Vosselman, Qing Zhu

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

54 Downloads (Pure)

Abstract

This paper presents a new method for matching edges across a video image sequence. The method can deal with uncalibrated images acquired with a hand held camera. Compared to previous work, the method employs geometric constraints between edges based on reliable matched points, which reduces the search space for corresponding 2D edges in the frames. The 3D edge parameters are estimated from these matched 2D edges by using the Gauss-Markoff model with constraints. End points of each 3D edge are found by analyzing the end points of the corresponding 2D edges. The results show that the developed algorithms are able to efficiently and accurately reconstruct 3D edges from image sequences.

Original language	English
Title of host publication	XXIst ISPRS Congress : Silk road for information from imagery
Subtitle of host publication	Technical Commission III, July 3-11, 2008 Beijing, China
Editors	Jun Chen, Jie Jiang, Wolfgang Förstner
Publisher	International Society for Photogrammetry and Remote Sensing (ISPRS)
Pages	657-662
Number of pages	6
Volume	Part B3b
Publication status	Published - 2008
Event	XXI ISPRS Congress 2008: Silk Road for Information from Imagery - Beijing, China Duration: 3 Jul 2008 → 11 Jul 2008 Conference number: 21 https://www.isprs.org/congresses/beijing2008/default.aspx

Conference

Conference	XXI ISPRS Congress 2008
Country/Territory	China
City	Beijing
Period	3/07/08 → 11/07/08
Internet address	https://www.isprs.org/congresses/beijing2008/default.aspx

Keywords

ADLIB-ART-1531
EOS

Access to Document

ArticleFinal published version, 602 KB

http://www.isprs.org/proceedings/XXXVII/congress/3b_pdf/31.pdf

Cite this

Tian, Y., Gerke, M., Vosselman, G., & Zhu, Q. (2008). Automatic edge matching across an image sequence based on reliable points. In J. Chen, J. Jiang, & W. Förstner (Eds.), XXIst ISPRS Congress : Silk road for information from imagery: Technical Commission III, July 3-11, 2008 Beijing, China (Vol. Part B3b, pp. 657-662). International Society for Photogrammetry and Remote Sensing (ISPRS). http://www.isprs.org/proceedings/XXXVII/congress/3b_pdf/31.pdf

Tian, Yixiang ; Gerke, M. ; Vosselman, G. et al. / Automatic edge matching across an image sequence based on reliable points. XXIst ISPRS Congress : Silk road for information from imagery: Technical Commission III, July 3-11, 2008 Beijing, China. editor / Jun Chen ; Jie Jiang ; Wolfgang Förstner. Vol. Part B3b International Society for Photogrammetry and Remote Sensing (ISPRS), 2008. pp. 657-662

@inproceedings{121b4342a1ca40a19d11d027b7c544d5,

title = "Automatic edge matching across an image sequence based on reliable points",

abstract = "This paper presents a new method for matching edges across a video image sequence. The method can deal with uncalibrated images acquired with a hand held camera. Compared to previous work, the method employs geometric constraints between edges based on reliable matched points, which reduces the search space for corresponding 2D edges in the frames. The 3D edge parameters are estimated from these matched 2D edges by using the Gauss-Markoff model with constraints. End points of each 3D edge are found by analyzing the end points of the corresponding 2D edges. The results show that the developed algorithms are able to efficiently and accurately reconstruct 3D edges from image sequences.",

keywords = "ADLIB-ART-1531, EOS",

author = "Yixiang Tian and M. Gerke and G. Vosselman and Qing Zhu",

year = "2008",

language = "English",

volume = "Part B3b",

pages = "657--662",

editor = "Jun Chen and Jie Jiang and Wolfgang F{\"o}rstner",

booktitle = "XXIst ISPRS Congress : Silk road for information from imagery",

publisher = "International Society for Photogrammetry and Remote Sensing (ISPRS)",

note = "XXI ISPRS Congress 2008 : Silk Road for Information from Imagery ; Conference date: 03-07-2008 Through 11-07-2008",

url = "https://www.isprs.org/congresses/beijing2008/default.aspx",

}

Tian, Y, Gerke, M, Vosselman, G & Zhu, Q 2008, Automatic edge matching across an image sequence based on reliable points. in J Chen, J Jiang & W Förstner (eds), XXIst ISPRS Congress : Silk road for information from imagery: Technical Commission III, July 3-11, 2008 Beijing, China. vol. Part B3b, International Society for Photogrammetry and Remote Sensing (ISPRS), pp. 657-662, XXI ISPRS Congress 2008, Beijing, China, 3/07/08. <http://www.isprs.org/proceedings/XXXVII/congress/3b_pdf/31.pdf>

Automatic edge matching across an image sequence based on reliable points. / Tian, Yixiang; Gerke, M.; Vosselman, G. et al.
XXIst ISPRS Congress : Silk road for information from imagery: Technical Commission III, July 3-11, 2008 Beijing, China. ed. / Jun Chen; Jie Jiang; Wolfgang Förstner. Vol. Part B3b International Society for Photogrammetry and Remote Sensing (ISPRS), 2008. p. 657-662.

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

TY - GEN

T1 - Automatic edge matching across an image sequence based on reliable points

AU - Tian, Yixiang

AU - Gerke, M.

AU - Vosselman, G.

AU - Zhu, Qing

N1 - Conference code: 21

PY - 2008

Y1 - 2008

N2 - This paper presents a new method for matching edges across a video image sequence. The method can deal with uncalibrated images acquired with a hand held camera. Compared to previous work, the method employs geometric constraints between edges based on reliable matched points, which reduces the search space for corresponding 2D edges in the frames. The 3D edge parameters are estimated from these matched 2D edges by using the Gauss-Markoff model with constraints. End points of each 3D edge are found by analyzing the end points of the corresponding 2D edges. The results show that the developed algorithms are able to efficiently and accurately reconstruct 3D edges from image sequences.

AB - This paper presents a new method for matching edges across a video image sequence. The method can deal with uncalibrated images acquired with a hand held camera. Compared to previous work, the method employs geometric constraints between edges based on reliable matched points, which reduces the search space for corresponding 2D edges in the frames. The 3D edge parameters are estimated from these matched 2D edges by using the Gauss-Markoff model with constraints. End points of each 3D edge are found by analyzing the end points of the corresponding 2D edges. The results show that the developed algorithms are able to efficiently and accurately reconstruct 3D edges from image sequences.

KW - ADLIB-ART-1531

KW - EOS

UR - https://ezproxy2.utwente.nl/login?url=https://webapps.itc.utwente.nl/library/2008/conf/gerke_aut.pdf

M3 - Conference contribution

VL - Part B3b

SP - 657

EP - 662

BT - XXIst ISPRS Congress : Silk road for information from imagery

A2 - Chen, Jun

A2 - Jiang, Jie

A2 - Förstner, Wolfgang

PB - International Society for Photogrammetry and Remote Sensing (ISPRS)

T2 - XXI ISPRS Congress 2008

Y2 - 3 July 2008 through 11 July 2008

ER -

Tian Y, Gerke M, Vosselman G, Zhu Q. Automatic edge matching across an image sequence based on reliable points. In Chen J, Jiang J, Förstner W, editors, XXIst ISPRS Congress : Silk road for information from imagery: Technical Commission III, July 3-11, 2008 Beijing, China. Vol. Part B3b. International Society for Photogrammetry and Remote Sensing (ISPRS). 2008. p. 657-662

Automatic edge matching across an image sequence based on reliable points

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this