Full Text Views
35
This paper presents a fast and accurate volume correspondence matching method using 3D Phase-Only Correlation (POC). The proposed method employs (i) a coarse-to-fine strategy using multi-scale volume pyramids for correspondence search and (ii) high-accuracy POC-based local block matching for finding dense volume correspondence with sub-voxel displacement accuracy. This paper also proposes its GPU implementation to achieve fast and practical computation of volume registration. Experimental evaluation shows that the proposed approach exhibits higher accuracy and lower computational cost compared with conventional method. We also demonstrate that the GPU implementation of the proposed method can align two volume data in several seconds, which is suitable for practical use in the image-guided radiation therapy.
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.
Copy
Yuichiro TAJIMA, Kinya FUDANO, Koichi ITO, Takafumi AOKI, "Fast and Robust 3D Correspondence Matching and Its Application to Volume Registration" in IEICE TRANSACTIONS on Information,
vol. E96-D, no. 4, pp. 826-835, April 2013, doi: 10.1587/transinf.E96.D.826.
Abstract: This paper presents a fast and accurate volume correspondence matching method using 3D Phase-Only Correlation (POC). The proposed method employs (i) a coarse-to-fine strategy using multi-scale volume pyramids for correspondence search and (ii) high-accuracy POC-based local block matching for finding dense volume correspondence with sub-voxel displacement accuracy. This paper also proposes its GPU implementation to achieve fast and practical computation of volume registration. Experimental evaluation shows that the proposed approach exhibits higher accuracy and lower computational cost compared with conventional method. We also demonstrate that the GPU implementation of the proposed method can align two volume data in several seconds, which is suitable for practical use in the image-guided radiation therapy.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E96.D.826/_p
Copy
@ARTICLE{e96-d_4_826,
author={Yuichiro TAJIMA, Kinya FUDANO, Koichi ITO, Takafumi AOKI, },
journal={IEICE TRANSACTIONS on Information},
title={Fast and Robust 3D Correspondence Matching and Its Application to Volume Registration},
year={2013},
volume={E96-D},
number={4},
pages={826-835},
abstract={This paper presents a fast and accurate volume correspondence matching method using 3D Phase-Only Correlation (POC). The proposed method employs (i) a coarse-to-fine strategy using multi-scale volume pyramids for correspondence search and (ii) high-accuracy POC-based local block matching for finding dense volume correspondence with sub-voxel displacement accuracy. This paper also proposes its GPU implementation to achieve fast and practical computation of volume registration. Experimental evaluation shows that the proposed approach exhibits higher accuracy and lower computational cost compared with conventional method. We also demonstrate that the GPU implementation of the proposed method can align two volume data in several seconds, which is suitable for practical use in the image-guided radiation therapy.},
keywords={},
doi={10.1587/transinf.E96.D.826},
ISSN={1745-1361},
month={April},}
Copy
TY - JOUR
TI - Fast and Robust 3D Correspondence Matching and Its Application to Volume Registration
T2 - IEICE TRANSACTIONS on Information
SP - 826
EP - 835
AU - Yuichiro TAJIMA
AU - Kinya FUDANO
AU - Koichi ITO
AU - Takafumi AOKI
PY - 2013
DO - 10.1587/transinf.E96.D.826
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E96-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2013
AB - This paper presents a fast and accurate volume correspondence matching method using 3D Phase-Only Correlation (POC). The proposed method employs (i) a coarse-to-fine strategy using multi-scale volume pyramids for correspondence search and (ii) high-accuracy POC-based local block matching for finding dense volume correspondence with sub-voxel displacement accuracy. This paper also proposes its GPU implementation to achieve fast and practical computation of volume registration. Experimental evaluation shows that the proposed approach exhibits higher accuracy and lower computational cost compared with conventional method. We also demonstrate that the GPU implementation of the proposed method can align two volume data in several seconds, which is suitable for practical use in the image-guided radiation therapy.
ER -