Real-time scene-based nonuniformity correction using feature pattern matching

Seong Gyo Seo; Jae Wook Jeon

doi:10.1109/IMCOM51814.2021.9377374

Real-time scene-based nonuniformity correction using feature pattern matching

Seong Gyo Seo
, Jae Wook Jeon

Department of Semiconductor Systems Engineering

Sungkyunkwan University

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

2 Scopus citations

Abstract

Infrared cameras require constant nonuniformity correction because image nonuniformity occurs with environmental changes. In this paper, we propose a nonuniformity correction algorithm using feature pattern matching that can correct nonuniformities in real time. The proposed algorithm consists of motion estimation and nonuniformity correction steps. The motion estimation algorithm consists of feature extraction, feature point simplification, and feature point pattern generation steps and is proposed to calculate the amount of motion between frames in real time using a field programmable gate array. The experimental results confirm that the proposed method is robust against ghost phenomenon, compared to a statistics-based nonuniformity correction, and improves the real-time performance while providing the same performance as the existing interframe registration-based nonuniformity correction algorithm.

Original language	English
Title of host publication	Proceedings of the 2021 15th International Conference on Ubiquitous Information Management and Communication, IMCOM 2021
Editors	Sukhan Lee, Hyunseung Choo, Roslan Ismail
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9780738105086
DOIs	https://doi.org/10.1109/IMCOM51814.2021.9377374
State	Published - 4 Jan 2021
Event	15th International Conference on Ubiquitous Information Management and Communication, IMCOM 2021 - Seoul, Korea, Republic of Duration: 4 Jan 2021 → 6 Jan 2021

Publication series

Name	Proceedings of the 2021 15th International Conference on Ubiquitous Information Management and Communication, IMCOM 2021

Conference

Conference	15th International Conference on Ubiquitous Information Management and Communication, IMCOM 2021
Country/Territory	Korea, Republic of
City	Seoul
Period	4/01/21 → 6/01/21

Keywords

Feature Pattern Matching
FPGA
Interframe Registration
Scene-based Nonuniformity Correction

Access to Document

10.1109/IMCOM51814.2021.9377374

Cite this

Seo, S. G., & Jeon, J. W. (2021). Real-time scene-based nonuniformity correction using feature pattern matching. In S. Lee, H. Choo, & R. Ismail (Eds.), Proceedings of the 2021 15th International Conference on Ubiquitous Information Management and Communication, IMCOM 2021 Article 9377374 (Proceedings of the 2021 15th International Conference on Ubiquitous Information Management and Communication, IMCOM 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IMCOM51814.2021.9377374

Seo, Seong Gyo ; Jeon, Jae Wook. / Real-time scene-based nonuniformity correction using feature pattern matching. Proceedings of the 2021 15th International Conference on Ubiquitous Information Management and Communication, IMCOM 2021. editor / Sukhan Lee ; Hyunseung Choo ; Roslan Ismail. Institute of Electrical and Electronics Engineers Inc., 2021. (Proceedings of the 2021 15th International Conference on Ubiquitous Information Management and Communication, IMCOM 2021).

@inproceedings{35240a9b0dcf4d8ba3dac11e8b6b1a99,

title = "Real-time scene-based nonuniformity correction using feature pattern matching",

abstract = "Infrared cameras require constant nonuniformity correction because image nonuniformity occurs with environmental changes. In this paper, we propose a nonuniformity correction algorithm using feature pattern matching that can correct nonuniformities in real time. The proposed algorithm consists of motion estimation and nonuniformity correction steps. The motion estimation algorithm consists of feature extraction, feature point simplification, and feature point pattern generation steps and is proposed to calculate the amount of motion between frames in real time using a field programmable gate array. The experimental results confirm that the proposed method is robust against ghost phenomenon, compared to a statistics-based nonuniformity correction, and improves the real-time performance while providing the same performance as the existing interframe registration-based nonuniformity correction algorithm.",

keywords = "Feature Pattern Matching, FPGA, Interframe Registration, Scene-based Nonuniformity Correction",

author = "Seo, \{Seong Gyo\} and Jeon, \{Jae Wook\}",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 15th International Conference on Ubiquitous Information Management and Communication, IMCOM 2021 ; Conference date: 04-01-2021 Through 06-01-2021",

year = "2021",

month = jan,

day = "4",

doi = "10.1109/IMCOM51814.2021.9377374",

language = "English",

series = "Proceedings of the 2021 15th International Conference on Ubiquitous Information Management and Communication, IMCOM 2021",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Sukhan Lee and Hyunseung Choo and Roslan Ismail",

booktitle = "Proceedings of the 2021 15th International Conference on Ubiquitous Information Management and Communication, IMCOM 2021",

}

Seo, SG & Jeon, JW 2021, Real-time scene-based nonuniformity correction using feature pattern matching. in S Lee, H Choo & R Ismail (eds), Proceedings of the 2021 15th International Conference on Ubiquitous Information Management and Communication, IMCOM 2021., 9377374, Proceedings of the 2021 15th International Conference on Ubiquitous Information Management and Communication, IMCOM 2021, Institute of Electrical and Electronics Engineers Inc., 15th International Conference on Ubiquitous Information Management and Communication, IMCOM 2021, Seoul, Korea, Republic of, 4/01/21. https://doi.org/10.1109/IMCOM51814.2021.9377374

Real-time scene-based nonuniformity correction using feature pattern matching. / Seo, Seong Gyo; Jeon, Jae Wook.
Proceedings of the 2021 15th International Conference on Ubiquitous Information Management and Communication, IMCOM 2021. ed. / Sukhan Lee; Hyunseung Choo; Roslan Ismail. Institute of Electrical and Electronics Engineers Inc., 2021. 9377374 (Proceedings of the 2021 15th International Conference on Ubiquitous Information Management and Communication, IMCOM 2021).

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

TY - GEN

T1 - Real-time scene-based nonuniformity correction using feature pattern matching

AU - Seo, Seong Gyo

AU - Jeon, Jae Wook

PY - 2021/1/4

Y1 - 2021/1/4

N2 - Infrared cameras require constant nonuniformity correction because image nonuniformity occurs with environmental changes. In this paper, we propose a nonuniformity correction algorithm using feature pattern matching that can correct nonuniformities in real time. The proposed algorithm consists of motion estimation and nonuniformity correction steps. The motion estimation algorithm consists of feature extraction, feature point simplification, and feature point pattern generation steps and is proposed to calculate the amount of motion between frames in real time using a field programmable gate array. The experimental results confirm that the proposed method is robust against ghost phenomenon, compared to a statistics-based nonuniformity correction, and improves the real-time performance while providing the same performance as the existing interframe registration-based nonuniformity correction algorithm.

AB - Infrared cameras require constant nonuniformity correction because image nonuniformity occurs with environmental changes. In this paper, we propose a nonuniformity correction algorithm using feature pattern matching that can correct nonuniformities in real time. The proposed algorithm consists of motion estimation and nonuniformity correction steps. The motion estimation algorithm consists of feature extraction, feature point simplification, and feature point pattern generation steps and is proposed to calculate the amount of motion between frames in real time using a field programmable gate array. The experimental results confirm that the proposed method is robust against ghost phenomenon, compared to a statistics-based nonuniformity correction, and improves the real-time performance while providing the same performance as the existing interframe registration-based nonuniformity correction algorithm.

KW - Feature Pattern Matching

KW - FPGA

KW - Interframe Registration

KW - Scene-based Nonuniformity Correction

UR - https://www.scopus.com/pages/publications/85103742724

U2 - 10.1109/IMCOM51814.2021.9377374

DO - 10.1109/IMCOM51814.2021.9377374

M3 - Conference contribution

AN - SCOPUS:85103742724

T3 - Proceedings of the 2021 15th International Conference on Ubiquitous Information Management and Communication, IMCOM 2021

BT - Proceedings of the 2021 15th International Conference on Ubiquitous Information Management and Communication, IMCOM 2021

A2 - Lee, Sukhan

A2 - Choo, Hyunseung

A2 - Ismail, Roslan

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 15th International Conference on Ubiquitous Information Management and Communication, IMCOM 2021

Y2 - 4 January 2021 through 6 January 2021

ER -

Seo SG, Jeon JW. Real-time scene-based nonuniformity correction using feature pattern matching. In Lee S, Choo H, Ismail R, editors, Proceedings of the 2021 15th International Conference on Ubiquitous Information Management and Communication, IMCOM 2021. Institute of Electrical and Electronics Engineers Inc. 2021. 9377374. (Proceedings of the 2021 15th International Conference on Ubiquitous Information Management and Communication, IMCOM 2021). doi: 10.1109/IMCOM51814.2021.9377374

Real-time scene-based nonuniformity correction using feature pattern matching

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this