GPU implementation of phase-based stereo correspondence and its application

Mamoru Miura; Kinya Fudano; Koichi Ito; Takafumi Aoki; Hiroyuki Takizawa; Hiroaki Kobayashi

doi:10.1109/ICIP.2012.6467205

GPU implementation of phase-based stereo correspondence and its application

Mamoru Miura, Kinya Fudano, Koichi Ito, Takafumi Aoki, Hiroyuki Takizawa, Hiroaki Kobayashi

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

8 Citations (Scopus)

Abstract

This paper proposes a Graphics Processing Unit (GPU) implementation of the stereo correspondence matching using Phase-Only Correlation (POC). The use of high-accuracy stereo correspondence matching based on POC makes it possible to measure accurate 3D shape of the object using stereo vision, while the drawback of POC-based approach is its high computational cost. Addressing this problem, we propose a GPU implementation of POC-based correspondence matching. Through a set of experiments using a variety of GPUs, we demonstrate that the proposed implementation is high-speed and high-efficiency compared with the CPU implementation. We also apply the proposed approach to a real-time 3D measurement system.

Original language	English
Title of host publication	2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings
Pages	1697-1700
Number of pages	4
DOIs	https://doi.org/10.1109/ICIP.2012.6467205
Publication status	Published - 2012 Dec 1
Event	2012 19th IEEE International Conference on Image Processing, ICIP 2012 - Lake Buena Vista, FL, United States Duration: 2012 Sep 30 → 2012 Oct 3

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
ISSN (Print)	1522-4880

Other

Other	2012 19th IEEE International Conference on Image Processing, ICIP 2012
Country	United States
City	Lake Buena Vista, FL
Period	12/9/30 → 12/10/3

Keywords

GPU
phaseonly correlation
real-time 3D measurement
stereo correspondence
stereo vision

ASJC Scopus subject areas

Computer Networks and Communications
Information Systems

Access to Document

10.1109/ICIP.2012.6467205

Fingerprint Dive into the research topics of 'GPU implementation of phase-based stereo correspondence and its application'. Together they form a unique fingerprint.

Cite this

Miura, M., Fudano, K., Ito, K., Aoki, T., Takizawa, H., & Kobayashi, H. (2012). GPU implementation of phase-based stereo correspondence and its application. In 2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings (pp. 1697-1700). [6467205] (Proceedings - International Conference on Image Processing, ICIP). https://doi.org/10.1109/ICIP.2012.6467205

GPU implementation of phase-based stereo correspondence and its application. / Miura, Mamoru; Fudano, Kinya; Ito, Koichi ; Aoki, Takafumi ; Takizawa, Hiroyuki ; Kobayashi, Hiroaki.

2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings. 2012. p. 1697-1700 6467205 (Proceedings - International Conference on Image Processing, ICIP).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Miura, M, Fudano, K, Ito, K , Aoki, T , Takizawa, H & Kobayashi, H 2012, GPU implementation of phase-based stereo correspondence and its application. in 2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings., 6467205, Proceedings - International Conference on Image Processing, ICIP, pp. 1697-1700, 2012 19th IEEE International Conference on Image Processing, ICIP 2012, Lake Buena Vista, FL, United States, 12/9/30. https://doi.org/10.1109/ICIP.2012.6467205

@inproceedings{bd622c54dd0748beb2eb963715d5d678,

title = "GPU implementation of phase-based stereo correspondence and its application",

abstract = "This paper proposes a Graphics Processing Unit (GPU) implementation of the stereo correspondence matching using Phase-Only Correlation (POC). The use of high-accuracy stereo correspondence matching based on POC makes it possible to measure accurate 3D shape of the object using stereo vision, while the drawback of POC-based approach is its high computational cost. Addressing this problem, we propose a GPU implementation of POC-based correspondence matching. Through a set of experiments using a variety of GPUs, we demonstrate that the proposed implementation is high-speed and high-efficiency compared with the CPU implementation. We also apply the proposed approach to a real-time 3D measurement system.",

keywords = "GPU, phaseonly correlation, real-time 3D measurement, stereo correspondence, stereo vision",

author = "Mamoru Miura and Kinya Fudano and Koichi Ito and Takafumi Aoki and Hiroyuki Takizawa and Hiroaki Kobayashi",

year = "2012",

month = dec,

day = "1",

doi = "10.1109/ICIP.2012.6467205",

language = "English",

isbn = "9781467325332",

series = "Proceedings - International Conference on Image Processing, ICIP",

pages = "1697--1700",

booktitle = "2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings",

note = "2012 19th IEEE International Conference on Image Processing, ICIP 2012 ; Conference date: 30-09-2012 Through 03-10-2012",

}

TY - GEN

T1 - GPU implementation of phase-based stereo correspondence and its application

AU - Miura, Mamoru

AU - Fudano, Kinya

AU - Ito, Koichi

AU - Aoki, Takafumi

AU - Takizawa, Hiroyuki

AU - Kobayashi, Hiroaki

PY - 2012/12/1

Y1 - 2012/12/1

N2 - This paper proposes a Graphics Processing Unit (GPU) implementation of the stereo correspondence matching using Phase-Only Correlation (POC). The use of high-accuracy stereo correspondence matching based on POC makes it possible to measure accurate 3D shape of the object using stereo vision, while the drawback of POC-based approach is its high computational cost. Addressing this problem, we propose a GPU implementation of POC-based correspondence matching. Through a set of experiments using a variety of GPUs, we demonstrate that the proposed implementation is high-speed and high-efficiency compared with the CPU implementation. We also apply the proposed approach to a real-time 3D measurement system.

AB - This paper proposes a Graphics Processing Unit (GPU) implementation of the stereo correspondence matching using Phase-Only Correlation (POC). The use of high-accuracy stereo correspondence matching based on POC makes it possible to measure accurate 3D shape of the object using stereo vision, while the drawback of POC-based approach is its high computational cost. Addressing this problem, we propose a GPU implementation of POC-based correspondence matching. Through a set of experiments using a variety of GPUs, we demonstrate that the proposed implementation is high-speed and high-efficiency compared with the CPU implementation. We also apply the proposed approach to a real-time 3D measurement system.

KW - GPU

KW - phaseonly correlation

KW - real-time 3D measurement

KW - stereo correspondence

KW - stereo vision

UR - http://www.scopus.com/inward/record.url?scp=84875855295&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875855295&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2012.6467205

DO - 10.1109/ICIP.2012.6467205

M3 - Conference contribution

AN - SCOPUS:84875855295

SN - 9781467325332

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 1697

EP - 1700

BT - 2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings

T2 - 2012 19th IEEE International Conference on Image Processing, ICIP 2012

Y2 - 30 September 2012 through 3 October 2012

ER -