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
Mencari tepi sepadan dianggap sebagai bahagian paling sukar dalam algoritma pemadanan stereo berasaskan tepi. Biasanya, surat-menyurat untuk titik ciri dalam imej pertama diperoleh dengan mencari di kawasan pratakrif imej kedua, berdasarkan garis epipolar dan jurang maksimum. Pengurangan kawasan carian boleh meningkatkan prestasi proses pemadanan, dalam konteks masa dan ketepatan pelaksanaan. Secara tradisinya, teknik berbilang resolusi hierarki, sebagai kaedah terpantas digunakan untuk mengurangkan ruang carian dan oleh itu meningkatkan kelajuan pemprosesan. Memandangkan maksimum terbitan ketaksamaan arah dalam adegan sebenar, kami merumuskan beberapa perkaitan antara ruang carian maksimum dalam imej kedua berkenaan dengan anjakan relatif bagi tepi bersambung (sebagai titik ciri), dalam baris imbasan berturut-turut bagi imej pertama. Kemudian kami mencadangkan strategi pemadanan baharu untuk mengurangkan ruang carian bagi algoritma pemadanan stereo berasaskan tepi. Selepas itu, kami membangunkan beberapa algoritma padanan stereo pantas berdasarkan strategi padanan yang dicadangkan dan teknik berbilang resolusi hierarki. Algoritma yang dicadangkan mempunyai dua peringkat: pengekstrakan ciri dan pemadanan ciri. Kami menggunakan algoritma baharu ini pada beberapa imej stereo dan membandingkan keputusannya dengan beberapa resolusi berbilang hierarki. Masa pelaksanaan kaedah yang dicadangkan kami dikurangkan antara 30% hingga 55%, dalam peringkat padanan ciri. Selain itu, masa pelaksanaan algoritma keseluruhan (termasuk pengekstrakan ciri dan padanan ciri) dikurangkan antara 15% hingga 40% dalam adegan sebenar. Sementara itu dalam beberapa kes, ketepatan juga meningkat. Penyiasatan teori dan keputusan percubaan menunjukkan bahawa algoritma kami mempunyai prestasi yang sangat baik dengan adegan kompleks sebenar, oleh itu algoritma baharu ini sangat sesuai untuk aplikasi stereo berasaskan tepi pantas dalam adegan sebenar seperti aplikasi robotik.
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
Payman MOALLEM, Karim FAEZ, Javad HADDADNIA, "Fast Edge-Based Stereo Matching Algorithms through Search Space Reduction" in IEICE TRANSACTIONS on Information,
vol. E85-D, no. 11, pp. 1859-1871, November 2002, doi: .
Abstract: Finding corresponding edges is considered being the most difficult part of edge-based stereo matching algorithms. Usually, correspondence for a feature point in the first image is obtained by searching in a predefined region of the second image, based on epipolar line and maximum disparity. Reduction of search region can increase performances of the matching process, in the context of execution time and accuracy. Traditionally, hierarchical multiresolution techniques, as the fastest methods are used to decrease the search space and therefore increase the processing speed. Considering maximum of directional derivative of disparity in real scenes, we formulated some relations between maximum search space in the second images with respect to relative displacement of connected edges (as the feature points), in successive scan lines of the first images. Then we proposed a new matching strategy to reduce the search space for edge-based stereo matching algorithms. Afterward, we developed some fast stereo matching algorithms based on the proposed matching strategy and the hierarchical multiresolution techniques. The proposed algorithms have two stages: feature extraction and feature matching. We applied these new algorithms on some stereo images and compared their results with those of some hierarchical multiresolution ones. The execution times of our proposed methods are decreased between 30% to 55%, in the feature matching stage. Moreover, the execution time of the overall algorithms (including the feature extraction and the feature matching) is decreased between 15% to 40% in real scenes. Meanwhile in some cases, the accuracy is increased too. Theoretical investigation and experimental results show that our algorithms have a very good performance with real complex scenes, therefore these new algorithms are very suitable for fast edge-based stereo applications in real scenes like robotic applications.
URL: https://global.ieice.org/en_transactions/information/10.1587/e85-d_11_1859/_p
Salinan
@ARTICLE{e85-d_11_1859,
author={Payman MOALLEM, Karim FAEZ, Javad HADDADNIA, },
journal={IEICE TRANSACTIONS on Information},
title={Fast Edge-Based Stereo Matching Algorithms through Search Space Reduction},
year={2002},
volume={E85-D},
number={11},
pages={1859-1871},
abstract={Finding corresponding edges is considered being the most difficult part of edge-based stereo matching algorithms. Usually, correspondence for a feature point in the first image is obtained by searching in a predefined region of the second image, based on epipolar line and maximum disparity. Reduction of search region can increase performances of the matching process, in the context of execution time and accuracy. Traditionally, hierarchical multiresolution techniques, as the fastest methods are used to decrease the search space and therefore increase the processing speed. Considering maximum of directional derivative of disparity in real scenes, we formulated some relations between maximum search space in the second images with respect to relative displacement of connected edges (as the feature points), in successive scan lines of the first images. Then we proposed a new matching strategy to reduce the search space for edge-based stereo matching algorithms. Afterward, we developed some fast stereo matching algorithms based on the proposed matching strategy and the hierarchical multiresolution techniques. The proposed algorithms have two stages: feature extraction and feature matching. We applied these new algorithms on some stereo images and compared their results with those of some hierarchical multiresolution ones. The execution times of our proposed methods are decreased between 30% to 55%, in the feature matching stage. Moreover, the execution time of the overall algorithms (including the feature extraction and the feature matching) is decreased between 15% to 40% in real scenes. Meanwhile in some cases, the accuracy is increased too. Theoretical investigation and experimental results show that our algorithms have a very good performance with real complex scenes, therefore these new algorithms are very suitable for fast edge-based stereo applications in real scenes like robotic applications.},
keywords={},
doi={},
ISSN={},
month={November},}
Salinan
TY - JOUR
TI - Fast Edge-Based Stereo Matching Algorithms through Search Space Reduction
T2 - IEICE TRANSACTIONS on Information
SP - 1859
EP - 1871
AU - Payman MOALLEM
AU - Karim FAEZ
AU - Javad HADDADNIA
PY - 2002
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E85-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2002
AB - Finding corresponding edges is considered being the most difficult part of edge-based stereo matching algorithms. Usually, correspondence for a feature point in the first image is obtained by searching in a predefined region of the second image, based on epipolar line and maximum disparity. Reduction of search region can increase performances of the matching process, in the context of execution time and accuracy. Traditionally, hierarchical multiresolution techniques, as the fastest methods are used to decrease the search space and therefore increase the processing speed. Considering maximum of directional derivative of disparity in real scenes, we formulated some relations between maximum search space in the second images with respect to relative displacement of connected edges (as the feature points), in successive scan lines of the first images. Then we proposed a new matching strategy to reduce the search space for edge-based stereo matching algorithms. Afterward, we developed some fast stereo matching algorithms based on the proposed matching strategy and the hierarchical multiresolution techniques. The proposed algorithms have two stages: feature extraction and feature matching. We applied these new algorithms on some stereo images and compared their results with those of some hierarchical multiresolution ones. The execution times of our proposed methods are decreased between 30% to 55%, in the feature matching stage. Moreover, the execution time of the overall algorithms (including the feature extraction and the feature matching) is decreased between 15% to 40% in real scenes. Meanwhile in some cases, the accuracy is increased too. Theoretical investigation and experimental results show that our algorithms have a very good performance with real complex scenes, therefore these new algorithms are very suitable for fast edge-based stereo applications in real scenes like robotic applications.
ER -