Real-time temporal stereo matching using iterative adaptive support weights

Jȩdrzej Kowalczuk; Eric T. Psota; Lance C. Pérez

doi:10.1109/EIT.2013.6632688

Real-time temporal stereo matching using iterative adaptive support weights

Jȩdrzej Kowalczuk, Eric T. Psota, Lance C. Pérez

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

9 Scopus citations

Abstract

Stereo matching algorithms are nearly always designed to find matches between a single pair of images. A method is presented that was specifically designed to operate on sequences of images. This method considers the cost of matching image points in both the spatial and temporal domain. To maintain real-time operation, a temporal cost aggregation method is used to evaluate the likelihood of matches that is invariant with respect to the number of prior images being considered. This method has been implemented on massively parallel GPU hardware, and the implementation ranks as one of the fastest and most accurate real-time stereo matching methods as measured by the Middlebury stereo performance benchmark.

Original language	English (US)
Title of host publication	2013 IEEE International Conference on Electro/Information Technology, EIT 2013
DOIs	https://doi.org/10.1109/EIT.2013.6632688
State	Published - 2013
Event	2013 IEEE International Conference on Electro/Information Technology, EIT 2013 - Rapid City, SD, United States Duration: May 9 2013 → May 11 2013

Publication series

Name	IEEE International Conference on Electro Information Technology
ISSN (Print)	2154-0357
ISSN (Electronic)	2154-0373

Other

Other	2013 IEEE International Conference on Electro/Information Technology, EIT 2013
Country/Territory	United States
City	Rapid City, SD
Period	5/9/13 → 5/11/13

ASJC Scopus subject areas

Computer Science Applications
Information Systems
Control and Systems Engineering
Electrical and Electronic Engineering

Access to Document

10.1109/EIT.2013.6632688

Cite this

Real-time temporal stereo matching using iterative adaptive support weights. / Kowalczuk, Jȩdrzej; Psota, Eric T.; Pérez, Lance C.
2013 IEEE International Conference on Electro/Information Technology, EIT 2013. 2013. 6632688 (IEEE International Conference on Electro Information Technology).

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

Kowalczuk, J, Psota, ET & Pérez, LC 2013, Real-time temporal stereo matching using iterative adaptive support weights. in 2013 IEEE International Conference on Electro/Information Technology, EIT 2013., 6632688, IEEE International Conference on Electro Information Technology, 2013 IEEE International Conference on Electro/Information Technology, EIT 2013, Rapid City, SD, United States, 5/9/13. https://doi.org/10.1109/EIT.2013.6632688

@inproceedings{cd571184d13f42f797dc8e85d13eeaf3,

title = "Real-time temporal stereo matching using iterative adaptive support weights",

abstract = "Stereo matching algorithms are nearly always designed to find matches between a single pair of images. A method is presented that was specifically designed to operate on sequences of images. This method considers the cost of matching image points in both the spatial and temporal domain. To maintain real-time operation, a temporal cost aggregation method is used to evaluate the likelihood of matches that is invariant with respect to the number of prior images being considered. This method has been implemented on massively parallel GPU hardware, and the implementation ranks as one of the fastest and most accurate real-time stereo matching methods as measured by the Middlebury stereo performance benchmark.",

author = "Jȩdrzej Kowalczuk and Psota, {Eric T.} and P{\'e}rez, {Lance C.}",

year = "2013",

doi = "10.1109/EIT.2013.6632688",

language = "English (US)",

isbn = "9781467352086",

series = "IEEE International Conference on Electro Information Technology",

booktitle = "2013 IEEE International Conference on Electro/Information Technology, EIT 2013",

note = "2013 IEEE International Conference on Electro/Information Technology, EIT 2013 ; Conference date: 09-05-2013 Through 11-05-2013",

}

TY - GEN

T1 - Real-time temporal stereo matching using iterative adaptive support weights

AU - Kowalczuk, Jȩdrzej

AU - Psota, Eric T.

AU - Pérez, Lance C.

PY - 2013

Y1 - 2013

N2 - Stereo matching algorithms are nearly always designed to find matches between a single pair of images. A method is presented that was specifically designed to operate on sequences of images. This method considers the cost of matching image points in both the spatial and temporal domain. To maintain real-time operation, a temporal cost aggregation method is used to evaluate the likelihood of matches that is invariant with respect to the number of prior images being considered. This method has been implemented on massively parallel GPU hardware, and the implementation ranks as one of the fastest and most accurate real-time stereo matching methods as measured by the Middlebury stereo performance benchmark.

AB - Stereo matching algorithms are nearly always designed to find matches between a single pair of images. A method is presented that was specifically designed to operate on sequences of images. This method considers the cost of matching image points in both the spatial and temporal domain. To maintain real-time operation, a temporal cost aggregation method is used to evaluate the likelihood of matches that is invariant with respect to the number of prior images being considered. This method has been implemented on massively parallel GPU hardware, and the implementation ranks as one of the fastest and most accurate real-time stereo matching methods as measured by the Middlebury stereo performance benchmark.

UR - http://www.scopus.com/inward/record.url?scp=84890075650&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84890075650&partnerID=8YFLogxK

U2 - 10.1109/EIT.2013.6632688

DO - 10.1109/EIT.2013.6632688

M3 - Conference contribution

AN - SCOPUS:84890075650

SN - 9781467352086

T3 - IEEE International Conference on Electro Information Technology

BT - 2013 IEEE International Conference on Electro/Information Technology, EIT 2013

T2 - 2013 IEEE International Conference on Electro/Information Technology, EIT 2013

Y2 - 9 May 2013 through 11 May 2013

ER -

Real-time temporal stereo matching using iterative adaptive support weights

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this