Robust digital image stabilization using the Kalman filter

Chuntao Wang; Jin Hyung Kim; Keun Yung Byun; Jiangqun Ni; Sung Jea Ko

doi:10.1109/TCE.2009.4814407

Robust digital image stabilization using the Kalman filter

Chuntao Wang, Jin Hyung Kim, Keun Yung Byun, Jiangqun Ni, Sung Jea Ko

Research output: Contribution to journal › Article › peer-review

95 Citations (Scopus)

Abstract

In this paper, we present a new digital image stabilization (DIS) algorithm based on feature point tracking. Feature points well tracked by the Kanade-Lucas-Tomasi (KLT) tracker are used to estimate the global motion between two consecutive image frames. The motion prediction with the Kalman filter (KF) is incorporated into the KLT tracker to further speed up the tracking process. Moreover, we develop an adaptive KF to better handle the intentional motion of the camera. In addition, a new scheme is also proposed to detect the scene change and automatically change the reference frame. Experimental simulation shows that the proposed DIS algorithm has the characteristics of high accuracy, good robustness to different irregular conditions.

Original language	English
Pages (from-to)	6-14
Number of pages	9
Journal	IEEE Transactions on Consumer Electronics
Volume	55
Issue number	1
DOIs	https://doi.org/10.1109/TCE.2009.4814407
Publication status	Published - 2009

Bibliographical note

Funding Information:
1This research was supported by Seoul Future Contents Convergence (SFCC) Cluster established by Seoul R&BD Program, NSFC under contract 60773200, and NSF of Guangdong under contract 7003722.

Keywords

Adaptive Kalman filter
Digital image stabilization (DIS)
Feature point tracking
KLT tracker
Scene change

ASJC Scopus subject areas

Media Technology
Electrical and Electronic Engineering

Access to Document

10.1109/TCE.2009.4814407

Cite this

@article{c1ef3280faa948c5ad539361418d3946,

title = "Robust digital image stabilization using the Kalman filter",

abstract = "In this paper, we present a new digital image stabilization (DIS) algorithm based on feature point tracking. Feature points well tracked by the Kanade-Lucas-Tomasi (KLT) tracker are used to estimate the global motion between two consecutive image frames. The motion prediction with the Kalman filter (KF) is incorporated into the KLT tracker to further speed up the tracking process. Moreover, we develop an adaptive KF to better handle the intentional motion of the camera. In addition, a new scheme is also proposed to detect the scene change and automatically change the reference frame. Experimental simulation shows that the proposed DIS algorithm has the characteristics of high accuracy, good robustness to different irregular conditions.",

keywords = "Adaptive Kalman filter, Digital image stabilization (DIS), Feature point tracking, KLT tracker, Scene change",

author = "Chuntao Wang and Kim, {Jin Hyung} and Byun, {Keun Yung} and Jiangqun Ni and Ko, {Sung Jea}",

note = "Funding Information: 1This research was supported by Seoul Future Contents Convergence (SFCC) Cluster established by Seoul R&BD Program, NSFC under contract 60773200, and NSF of Guangdong under contract 7003722.",

year = "2009",

doi = "10.1109/TCE.2009.4814407",

language = "English",

volume = "55",

pages = "6--14",

journal = "IEEE Transactions on Consumer Electronics",

issn = "0098-3063",

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

number = "1",

}

TY - JOUR

T1 - Robust digital image stabilization using the Kalman filter

AU - Wang, Chuntao

AU - Kim, Jin Hyung

AU - Byun, Keun Yung

AU - Ni, Jiangqun

AU - Ko, Sung Jea

N1 - Funding Information: 1This research was supported by Seoul Future Contents Convergence (SFCC) Cluster established by Seoul R&BD Program, NSFC under contract 60773200, and NSF of Guangdong under contract 7003722.

PY - 2009

Y1 - 2009

N2 - In this paper, we present a new digital image stabilization (DIS) algorithm based on feature point tracking. Feature points well tracked by the Kanade-Lucas-Tomasi (KLT) tracker are used to estimate the global motion between two consecutive image frames. The motion prediction with the Kalman filter (KF) is incorporated into the KLT tracker to further speed up the tracking process. Moreover, we develop an adaptive KF to better handle the intentional motion of the camera. In addition, a new scheme is also proposed to detect the scene change and automatically change the reference frame. Experimental simulation shows that the proposed DIS algorithm has the characteristics of high accuracy, good robustness to different irregular conditions.

AB - In this paper, we present a new digital image stabilization (DIS) algorithm based on feature point tracking. Feature points well tracked by the Kanade-Lucas-Tomasi (KLT) tracker are used to estimate the global motion between two consecutive image frames. The motion prediction with the Kalman filter (KF) is incorporated into the KLT tracker to further speed up the tracking process. Moreover, we develop an adaptive KF to better handle the intentional motion of the camera. In addition, a new scheme is also proposed to detect the scene change and automatically change the reference frame. Experimental simulation shows that the proposed DIS algorithm has the characteristics of high accuracy, good robustness to different irregular conditions.

KW - Adaptive Kalman filter

KW - Digital image stabilization (DIS)

KW - Feature point tracking

KW - KLT tracker

KW - Scene change

UR - http://www.scopus.com/inward/record.url?scp=65649124171&partnerID=8YFLogxK

U2 - 10.1109/TCE.2009.4814407

DO - 10.1109/TCE.2009.4814407

M3 - Article

AN - SCOPUS:65649124171

SN - 0098-3063

VL - 55

SP - 6

EP - 14

JO - IEEE Transactions on Consumer Electronics

JF - IEEE Transactions on Consumer Electronics

IS - 1

ER -

Robust digital image stabilization using the Kalman filter

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this