Fast image registration for multisensor fusion using graphics hardware

Seung H. Yoo, Tae Dong Lee, Ki Young Choi, Chang-Sung Jeong

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper presents a fast image registration using graphics hardware for image fusion of high resolution aerial images taken by different sensors. The GPU (Graphics Processing Unit) provides high-performance compared to its price and executes rapid computation by supporting parallel architectures. Fast image registration should be gone ahead to execute high-speed fusion of high resolution aerial images. Our approach is based on clustering techniques using parameter space, but we estimate the number of feature consensus pairs in the feature space according to change of parameter values instead of conversion over the parameter space. To extract feature points, we modified the filter which has been used for TNO fusion method based on image information and frequency. Furthermore, we reduce the search range of mapping parameters, and utilize multi-resolution methods to alleviate high computational cost.We implemented all processes for automatic image registration on programmable graphics hardware, the speed of GPU-based registration increased double compared to CPU's.

Original languageEnglish
Title of host publicationIEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems
Pages321-325
Number of pages5
DOIs
Publication statusPublished - 2008 Dec 1
Event2008 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI - Seoul, Korea, Republic of
Duration: 2008 Aug 202008 Aug 22

Other

Other2008 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI
CountryKorea, Republic of
CitySeoul
Period08/8/2008/8/22

Fingerprint

Sensor data fusion
Image registration
Hardware
Antennas
Image fusion
Parallel architectures
Program processors
Sensors
Costs
Graphics processing unit

ASJC Scopus subject areas

  • Computer Science Applications
  • Software
  • Control and Systems Engineering

Cite this

Yoo, S. H., Lee, T. D., Choi, K. Y., & Jeong, C-S. (2008). Fast image registration for multisensor fusion using graphics hardware. In IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (pp. 321-325). [4648085] https://doi.org/10.1109/MFI.2008.4648085

Fast image registration for multisensor fusion using graphics hardware. / Yoo, Seung H.; Lee, Tae Dong; Choi, Ki Young; Jeong, Chang-Sung.

IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems. 2008. p. 321-325 4648085.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yoo, SH, Lee, TD, Choi, KY & Jeong, C-S 2008, Fast image registration for multisensor fusion using graphics hardware. in IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems., 4648085, pp. 321-325, 2008 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI, Seoul, Korea, Republic of, 08/8/20. https://doi.org/10.1109/MFI.2008.4648085
Yoo SH, Lee TD, Choi KY, Jeong C-S. Fast image registration for multisensor fusion using graphics hardware. In IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems. 2008. p. 321-325. 4648085 https://doi.org/10.1109/MFI.2008.4648085
Yoo, Seung H. ; Lee, Tae Dong ; Choi, Ki Young ; Jeong, Chang-Sung. / Fast image registration for multisensor fusion using graphics hardware. IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems. 2008. pp. 321-325
@inproceedings{002793fc33a84b8395dc77f654d0bd43,
title = "Fast image registration for multisensor fusion using graphics hardware",
abstract = "This paper presents a fast image registration using graphics hardware for image fusion of high resolution aerial images taken by different sensors. The GPU (Graphics Processing Unit) provides high-performance compared to its price and executes rapid computation by supporting parallel architectures. Fast image registration should be gone ahead to execute high-speed fusion of high resolution aerial images. Our approach is based on clustering techniques using parameter space, but we estimate the number of feature consensus pairs in the feature space according to change of parameter values instead of conversion over the parameter space. To extract feature points, we modified the filter which has been used for TNO fusion method based on image information and frequency. Furthermore, we reduce the search range of mapping parameters, and utilize multi-resolution methods to alleviate high computational cost.We implemented all processes for automatic image registration on programmable graphics hardware, the speed of GPU-based registration increased double compared to CPU's.",
author = "Yoo, {Seung H.} and Lee, {Tae Dong} and Choi, {Ki Young} and Chang-Sung Jeong",
year = "2008",
month = "12",
day = "1",
doi = "10.1109/MFI.2008.4648085",
language = "English",
pages = "321--325",
booktitle = "IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems",

}

TY - GEN

T1 - Fast image registration for multisensor fusion using graphics hardware

AU - Yoo, Seung H.

AU - Lee, Tae Dong

AU - Choi, Ki Young

AU - Jeong, Chang-Sung

PY - 2008/12/1

Y1 - 2008/12/1

N2 - This paper presents a fast image registration using graphics hardware for image fusion of high resolution aerial images taken by different sensors. The GPU (Graphics Processing Unit) provides high-performance compared to its price and executes rapid computation by supporting parallel architectures. Fast image registration should be gone ahead to execute high-speed fusion of high resolution aerial images. Our approach is based on clustering techniques using parameter space, but we estimate the number of feature consensus pairs in the feature space according to change of parameter values instead of conversion over the parameter space. To extract feature points, we modified the filter which has been used for TNO fusion method based on image information and frequency. Furthermore, we reduce the search range of mapping parameters, and utilize multi-resolution methods to alleviate high computational cost.We implemented all processes for automatic image registration on programmable graphics hardware, the speed of GPU-based registration increased double compared to CPU's.

AB - This paper presents a fast image registration using graphics hardware for image fusion of high resolution aerial images taken by different sensors. The GPU (Graphics Processing Unit) provides high-performance compared to its price and executes rapid computation by supporting parallel architectures. Fast image registration should be gone ahead to execute high-speed fusion of high resolution aerial images. Our approach is based on clustering techniques using parameter space, but we estimate the number of feature consensus pairs in the feature space according to change of parameter values instead of conversion over the parameter space. To extract feature points, we modified the filter which has been used for TNO fusion method based on image information and frequency. Furthermore, we reduce the search range of mapping parameters, and utilize multi-resolution methods to alleviate high computational cost.We implemented all processes for automatic image registration on programmable graphics hardware, the speed of GPU-based registration increased double compared to CPU's.

UR - http://www.scopus.com/inward/record.url?scp=67650548497&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67650548497&partnerID=8YFLogxK

U2 - 10.1109/MFI.2008.4648085

DO - 10.1109/MFI.2008.4648085

M3 - Conference contribution

AN - SCOPUS:67650548497

SP - 321

EP - 325

BT - IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems

ER -