Solution to the correspondence problem in multiview imagery

Luuk Spreeuwers; Klamer Schutte; Zweitze Houkes

doi:10.1117/12.226843

Solution to the correspondence problem in multiview imagery

Luuk Spreeuwers^*, Klamer Schutte, Zweitze Houkes

^*Corresponding author for this work

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

123 Downloads (Pure)

Abstract

This paper consists of two parts. First a system is proposed that performs a recognition operation of single aerial photographs using a shape-constrained segmentation method and least squares estimation for the parameters of buildings. In the second part this system is extended to multi-view imagery. The advantage of using multi-view imagery is that buildings not recognized from one image (e.g. due to occlusion) may still be recognized, because they are observable from other images. However, this also complicates processing, because objects recognized from different images should correspond if they originate from the same physical objects. A solution to this correspondence problem is presented on object hypothesis level.

Original language	English
Title of host publication	Image and Signal Processing for Remote Sensing II
Subtitle of host publication	Satellite Remote Sensing II, 1995, Paris, France
Editors	Jacky Desachy
Publisher	SPIE
Pages	274-284
Number of pages	11
ISBN (Print)	9780819419439
DOIs	https://doi.org/10.1117/12.226843
Publication status	Published - 1 Dec 1995
Event	Satellite Remote Sensing II 1995 - Paris, France Duration: 25 Sept 1995 → 27 Sept 1995

Conference

Conference	Satellite Remote Sensing II 1995
Country/Territory	France
City	Paris
Period	25/09/95 → 27/09/95

Access to Document

10.1117/12.226843

ArticleAccepted author version, 501 KB

Cite this

@inproceedings{098ce90ffad24d01b5c3169e2d9822b3,

title = "Solution to the correspondence problem in multiview imagery",

abstract = "This paper consists of two parts. First a system is proposed that performs a recognition operation of single aerial photographs using a shape-constrained segmentation method and least squares estimation for the parameters of buildings. In the second part this system is extended to multi-view imagery. The advantage of using multi-view imagery is that buildings not recognized from one image (e.g. due to occlusion) may still be recognized, because they are observable from other images. However, this also complicates processing, because objects recognized from different images should correspond if they originate from the same physical objects. A solution to this correspondence problem is presented on object hypothesis level.",

author = "Luuk Spreeuwers and Klamer Schutte and Zweitze Houkes",

year = "1995",

month = dec,

day = "1",

doi = "10.1117/12.226843",

language = "English",

isbn = "9780819419439",

pages = "274--284",

editor = "Jacky Desachy",

booktitle = "Image and Signal Processing for Remote Sensing II",

publisher = "SPIE",

address = "United States",

note = "Satellite Remote Sensing II 1995 ; Conference date: 25-09-1995 Through 27-09-1995",

}

Solution to the correspondence problem in multiview imagery. / Spreeuwers, Luuk; Schutte, Klamer; Houkes, Zweitze.
Image and Signal Processing for Remote Sensing II: Satellite Remote Sensing II, 1995, Paris, France. ed. / Jacky Desachy. SPIE, 1995. p. 274-284.

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

TY - GEN

T1 - Solution to the correspondence problem in multiview imagery

AU - Spreeuwers, Luuk

AU - Schutte, Klamer

AU - Houkes, Zweitze

PY - 1995/12/1

Y1 - 1995/12/1

N2 - This paper consists of two parts. First a system is proposed that performs a recognition operation of single aerial photographs using a shape-constrained segmentation method and least squares estimation for the parameters of buildings. In the second part this system is extended to multi-view imagery. The advantage of using multi-view imagery is that buildings not recognized from one image (e.g. due to occlusion) may still be recognized, because they are observable from other images. However, this also complicates processing, because objects recognized from different images should correspond if they originate from the same physical objects. A solution to this correspondence problem is presented on object hypothesis level.

AB - This paper consists of two parts. First a system is proposed that performs a recognition operation of single aerial photographs using a shape-constrained segmentation method and least squares estimation for the parameters of buildings. In the second part this system is extended to multi-view imagery. The advantage of using multi-view imagery is that buildings not recognized from one image (e.g. due to occlusion) may still be recognized, because they are observable from other images. However, this also complicates processing, because objects recognized from different images should correspond if they originate from the same physical objects. A solution to this correspondence problem is presented on object hypothesis level.

UR - http://www.scopus.com/inward/record.url?scp=0029530986&partnerID=8YFLogxK

U2 - 10.1117/12.226843

DO - 10.1117/12.226843

M3 - Conference contribution

AN - SCOPUS:0029530986

SN - 9780819419439

SP - 274

EP - 284

BT - Image and Signal Processing for Remote Sensing II

A2 - Desachy, Jacky

PB - SPIE

T2 - Satellite Remote Sensing II 1995

Y2 - 25 September 1995 through 27 September 1995

ER -

Solution to the correspondence problem in multiview imagery

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this