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
Kami membentangkan asas baharu untuk perwakilan diskret surat-menyurat stereo. Asas rujukan pusat ini membenarkan perwakilan kekangan yang lebih semula jadi, lengkap dan ringkas dalam padanan stereo. Dalam konteks ini rumusan MAP untuk anggaran ketaksamaan diperolehi dan dikurangkan kepada pengecilan tanpa kekangan fungsi tenaga. Menggabungkan kekangan semula jadi, masalah dipermudahkan kepada masalah laluan terpendek dalam struktur trellis yang jarang disambungkan yang dilakukan oleh algoritma pengaturcaraan dinamik yang cekap. Kerumitan pengiraan adalah sama dengan kaedah pengaturcaraan dinamik yang terbaik, tetapi tahap keselarasan yang sangat tinggi mungkin dalam algoritma menjadikannya sesuai untuk pelaksanaan dengan pemproses selari. Keputusan eksperimen mengesahkan prestasi kaedah ini dan ralat pemadanan didapati merosot secara anggun dalam bentuk eksponen berkenaan dengan hingar.
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
Hong JEONG, Yuns OH, "Fast Stereo Matching Using Constraints in Discrete Space" in IEICE TRANSACTIONS on Information,
vol. E83-D, no. 7, pp. 1592-1600, July 2000, doi: .
Abstract: We present a new basis for discrete representation of stereo correspondence. This center referenced basis permits a more natural, complete and concise representation of constraints in stereo matching. In this context a MAP formulation for disparity estimation is derived and reduced to unconstrained minimization of an energy function. Incorporating natural constraints, the problem is simplified to the shortest path problem in a sparsely connected trellis structure which is performed by an efficient dynamic programing algorithm. The computational complexity is the same as the best of other dynamic programming methods, but a very high degree of concurrency is possible in the algorithm making it suitable for implementation with parallel procesors. Experimental results confirm the performance of this method and matching errors are found to degrade gracefully in exponential form with respect to noise.
URL: https://global.ieice.org/en_transactions/information/10.1587/e83-d_7_1592/_p
Salinan
@ARTICLE{e83-d_7_1592,
author={Hong JEONG, Yuns OH, },
journal={IEICE TRANSACTIONS on Information},
title={Fast Stereo Matching Using Constraints in Discrete Space},
year={2000},
volume={E83-D},
number={7},
pages={1592-1600},
abstract={We present a new basis for discrete representation of stereo correspondence. This center referenced basis permits a more natural, complete and concise representation of constraints in stereo matching. In this context a MAP formulation for disparity estimation is derived and reduced to unconstrained minimization of an energy function. Incorporating natural constraints, the problem is simplified to the shortest path problem in a sparsely connected trellis structure which is performed by an efficient dynamic programing algorithm. The computational complexity is the same as the best of other dynamic programming methods, but a very high degree of concurrency is possible in the algorithm making it suitable for implementation with parallel procesors. Experimental results confirm the performance of this method and matching errors are found to degrade gracefully in exponential form with respect to noise.},
keywords={},
doi={},
ISSN={},
month={July},}
Salinan
TY - JOUR
TI - Fast Stereo Matching Using Constraints in Discrete Space
T2 - IEICE TRANSACTIONS on Information
SP - 1592
EP - 1600
AU - Hong JEONG
AU - Yuns OH
PY - 2000
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E83-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2000
AB - We present a new basis for discrete representation of stereo correspondence. This center referenced basis permits a more natural, complete and concise representation of constraints in stereo matching. In this context a MAP formulation for disparity estimation is derived and reduced to unconstrained minimization of an energy function. Incorporating natural constraints, the problem is simplified to the shortest path problem in a sparsely connected trellis structure which is performed by an efficient dynamic programing algorithm. The computational complexity is the same as the best of other dynamic programming methods, but a very high degree of concurrency is possible in the algorithm making it suitable for implementation with parallel procesors. Experimental results confirm the performance of this method and matching errors are found to degrade gracefully in exponential form with respect to noise.
ER -