The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Oleh kerana untuk tugasan pengecaman diketahui bahawa invarian satah lebih mudah diperoleh daripada yang lain, penguraian pemandangan dari segi bahagian satah menjadi sangat menarik. Kertas kerja ini membentangkan pendekatan baharu untuk mencari unjuran permukaan planar dalam sepasang imej. Untuk tugasan ini kami perkenalkan segi itu konsep yang ditakrifkan oleh tepi bersambung (rantai) dan bucu. Kami menggunakan collineations sebagai maklumat unjuran untuk memadankan dan mengesahkan keplanarannya. Sumbangan kami terdiri daripada mendapatkan daripada sepasang imej stereo yang tidak ditentukur padanan rantai "planar" berdasarkan sudut yang dipadankan. Collineations dikekang oleh maklumat matriks asas dan pendekatan penapis Kalman digunakan untuk memperhalusi pengiraannya.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Lukas THEILER, Houda CHABBI, "Facet Matching from an Uncalibrated Pair of Images" in IEICE TRANSACTIONS on Information,
vol. E83-D, no. 7, pp. 1395-1399, July 2000, doi: .
Abstract: Since for recognition tasks it is known that planar invariants are more easily obtained than others, decomposing a scene in terms of planar parts becomes very interresting. This paper presents a new approach to find the projections of planar surfaces in a pair of images. For this task we introduce the facet concept defined by linked edges (chains) and corners. We use collineations as projective information to match and verify their planarity. Our contribution consists in obtaining from an uncalibrated stereo pair of images a match of "planar" chains based on matched corners. Collineations are constrained by the fundamental matrix information and a Kalman filter approach is used to refine its computation.
URL: https://global.ieice.org/en_transactions/information/10.1587/e83-d_7_1395/_p
Salinan
@ARTICLE{e83-d_7_1395,
author={Lukas THEILER, Houda CHABBI, },
journal={IEICE TRANSACTIONS on Information},
title={Facet Matching from an Uncalibrated Pair of Images},
year={2000},
volume={E83-D},
number={7},
pages={1395-1399},
abstract={Since for recognition tasks it is known that planar invariants are more easily obtained than others, decomposing a scene in terms of planar parts becomes very interresting. This paper presents a new approach to find the projections of planar surfaces in a pair of images. For this task we introduce the facet concept defined by linked edges (chains) and corners. We use collineations as projective information to match and verify their planarity. Our contribution consists in obtaining from an uncalibrated stereo pair of images a match of "planar" chains based on matched corners. Collineations are constrained by the fundamental matrix information and a Kalman filter approach is used to refine its computation.},
keywords={},
doi={},
ISSN={},
month={July},}
Salinan
TY - JOUR
TI - Facet Matching from an Uncalibrated Pair of Images
T2 - IEICE TRANSACTIONS on Information
SP - 1395
EP - 1399
AU - Lukas THEILER
AU - Houda CHABBI
PY - 2000
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E83-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2000
AB - Since for recognition tasks it is known that planar invariants are more easily obtained than others, decomposing a scene in terms of planar parts becomes very interresting. This paper presents a new approach to find the projections of planar surfaces in a pair of images. For this task we introduce the facet concept defined by linked edges (chains) and corners. We use collineations as projective information to match and verify their planarity. Our contribution consists in obtaining from an uncalibrated stereo pair of images a match of "planar" chains based on matched corners. Collineations are constrained by the fundamental matrix information and a Kalman filter approach is used to refine its computation.
ER -