Digital video stabilization in static and dynamic scenes

Margarita Favorskaya, Lakhmi JAIN, Vladimir Buryachenko

Research output: A Conference proceeding or a Chapter in BookChapter

6 Citations (Scopus)
1 Downloads (Pure)

Abstract

The digital video stabilization is oriented on the removal of unintentional motions from video sequences caused by camera vibrations under external conditions, motion of robots stabilized platforms in a rugged landscape, a sea, oceans, or jitters during a non-professional hand-held shooting. The approaches for digital video stabilization in static and dynamic scenes are similar. However, objectively the analysis of dynamic scenes is needed in advanced intelligent methods. Several sequential stages include the choice of the key frames, the local and global motion estimations, the jitters compensation algorithm, the inpainting of frames boundaries, and the blurred frames restoration, for which the novel methods and algorithms were developed. The proposed application of fuzzy logic operators improves the separation results between the unwanted motion and the real motion of rigid objects. The corrective algorithm compensates the unwanted motion in frames; thereby the scene is aligned. The quality of stabilization in test video sequences was estimated by Peak Signal to Noise Ratio (PSNR) and Interframe Transformation Fidelity (ITF) metrics. During experiments, the PSNR and ITF estimations were received for six video sequences received from the static camera and eight video sequences received from the moving camera. The ITF estimations increase up on 3–4 dB or 15–20% relative to the original video sequences.
Original languageEnglish
Title of host publicationComputer Vision in Control Systems-1
Subtitle of host publicationMathematical Theory
EditorsMargarita N. Favorskaya, Lakhmi C. Jain
Place of PublicationNew York
PublisherSpringer
Chapter9
Pages261-309
Number of pages49
Volume73
Edition1
ISBN (Electronic)9783319106533
ISBN (Print)9783319106526
DOIs
Publication statusPublished - 2015

Publication series

NameIntelligent Systems Reference Library
PublisherSpringer
Volume73
ISSN (Print)1868-4394
ISSN (Electronic)1868-4408

Fingerprint

Stabilization
Cameras
Jitter
Signal to noise ratio
Motion estimation
Fuzzy logic
Restoration
Robots
Experiments
Compensation and Redress

Cite this

Favorskaya, M., JAIN, L., & Buryachenko, V. (2015). Digital video stabilization in static and dynamic scenes. In M. N. Favorskaya, & L. C. Jain (Eds.), Computer Vision in Control Systems-1: Mathematical Theory (1 ed., Vol. 73, pp. 261-309). (Intelligent Systems Reference Library; Vol. 73). New York: Springer. Intelligent Systems Reference Library https://doi.org/10.1007/978-3-319-10653-3_9
Favorskaya, Margarita ; JAIN, Lakhmi ; Buryachenko, Vladimir. / Digital video stabilization in static and dynamic scenes. Computer Vision in Control Systems-1: Mathematical Theory. editor / Margarita N. Favorskaya ; Lakhmi C. Jain. Vol. 73 1. ed. New York : Springer, 2015. pp. 261-309 (Intelligent Systems Reference Library). (Intelligent Systems Reference Library).
@inbook{eb1efb90076c4263bc523acc9c4167be,
title = "Digital video stabilization in static and dynamic scenes",
abstract = "The digital video stabilization is oriented on the removal of unintentional motions from video sequences caused by camera vibrations under external conditions, motion of robots stabilized platforms in a rugged landscape, a sea, oceans, or jitters during a non-professional hand-held shooting. The approaches for digital video stabilization in static and dynamic scenes are similar. However, objectively the analysis of dynamic scenes is needed in advanced intelligent methods. Several sequential stages include the choice of the key frames, the local and global motion estimations, the jitters compensation algorithm, the inpainting of frames boundaries, and the blurred frames restoration, for which the novel methods and algorithms were developed. The proposed application of fuzzy logic operators improves the separation results between the unwanted motion and the real motion of rigid objects. The corrective algorithm compensates the unwanted motion in frames; thereby the scene is aligned. The quality of stabilization in test video sequences was estimated by Peak Signal to Noise Ratio (PSNR) and Interframe Transformation Fidelity (ITF) metrics. During experiments, the PSNR and ITF estimations were received for six video sequences received from the static camera and eight video sequences received from the moving camera. The ITF estimations increase up on 3–4 dB or 15–20{\%} relative to the original video sequences.",
keywords = "digital-video-stabilization, static-dynamic-scenes, Fuzzy logic, Video sequence, Motion estimation, Frame deblurring, Robust detectors, Video stabilization, Motion inpainting",
author = "Margarita Favorskaya and Lakhmi JAIN and Vladimir Buryachenko",
year = "2015",
doi = "10.1007/978-3-319-10653-3_9",
language = "English",
isbn = "9783319106526",
volume = "73",
series = "Intelligent Systems Reference Library",
publisher = "Springer",
pages = "261--309",
editor = "Favorskaya, {Margarita N.} and Jain, {Lakhmi C.}",
booktitle = "Computer Vision in Control Systems-1",
address = "Netherlands",
edition = "1",

}

Favorskaya, M, JAIN, L & Buryachenko, V 2015, Digital video stabilization in static and dynamic scenes. in MN Favorskaya & LC Jain (eds), Computer Vision in Control Systems-1: Mathematical Theory. 1 edn, vol. 73, Intelligent Systems Reference Library, vol. 73, Springer, New York, Intelligent Systems Reference Library, pp. 261-309. https://doi.org/10.1007/978-3-319-10653-3_9

Digital video stabilization in static and dynamic scenes. / Favorskaya, Margarita; JAIN, Lakhmi; Buryachenko, Vladimir.

Computer Vision in Control Systems-1: Mathematical Theory. ed. / Margarita N. Favorskaya; Lakhmi C. Jain. Vol. 73 1. ed. New York : Springer, 2015. p. 261-309 (Intelligent Systems Reference Library; Vol. 73), (Intelligent Systems Reference Library).

Research output: A Conference proceeding or a Chapter in BookChapter

TY - CHAP

T1 - Digital video stabilization in static and dynamic scenes

AU - Favorskaya, Margarita

AU - JAIN, Lakhmi

AU - Buryachenko, Vladimir

PY - 2015

Y1 - 2015

N2 - The digital video stabilization is oriented on the removal of unintentional motions from video sequences caused by camera vibrations under external conditions, motion of robots stabilized platforms in a rugged landscape, a sea, oceans, or jitters during a non-professional hand-held shooting. The approaches for digital video stabilization in static and dynamic scenes are similar. However, objectively the analysis of dynamic scenes is needed in advanced intelligent methods. Several sequential stages include the choice of the key frames, the local and global motion estimations, the jitters compensation algorithm, the inpainting of frames boundaries, and the blurred frames restoration, for which the novel methods and algorithms were developed. The proposed application of fuzzy logic operators improves the separation results between the unwanted motion and the real motion of rigid objects. The corrective algorithm compensates the unwanted motion in frames; thereby the scene is aligned. The quality of stabilization in test video sequences was estimated by Peak Signal to Noise Ratio (PSNR) and Interframe Transformation Fidelity (ITF) metrics. During experiments, the PSNR and ITF estimations were received for six video sequences received from the static camera and eight video sequences received from the moving camera. The ITF estimations increase up on 3–4 dB or 15–20% relative to the original video sequences.

AB - The digital video stabilization is oriented on the removal of unintentional motions from video sequences caused by camera vibrations under external conditions, motion of robots stabilized platforms in a rugged landscape, a sea, oceans, or jitters during a non-professional hand-held shooting. The approaches for digital video stabilization in static and dynamic scenes are similar. However, objectively the analysis of dynamic scenes is needed in advanced intelligent methods. Several sequential stages include the choice of the key frames, the local and global motion estimations, the jitters compensation algorithm, the inpainting of frames boundaries, and the blurred frames restoration, for which the novel methods and algorithms were developed. The proposed application of fuzzy logic operators improves the separation results between the unwanted motion and the real motion of rigid objects. The corrective algorithm compensates the unwanted motion in frames; thereby the scene is aligned. The quality of stabilization in test video sequences was estimated by Peak Signal to Noise Ratio (PSNR) and Interframe Transformation Fidelity (ITF) metrics. During experiments, the PSNR and ITF estimations were received for six video sequences received from the static camera and eight video sequences received from the moving camera. The ITF estimations increase up on 3–4 dB or 15–20% relative to the original video sequences.

KW - digital-video-stabilization

KW - static-dynamic-scenes

KW - Fuzzy logic

KW - Video sequence

KW - Motion estimation

KW - Frame deblurring

KW - Robust detectors

KW - Video stabilization

KW - Motion inpainting

UR - http://www.scopus.com/inward/record.url?scp=84921328692&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-10653-3_9

DO - 10.1007/978-3-319-10653-3_9

M3 - Chapter

SN - 9783319106526

VL - 73

T3 - Intelligent Systems Reference Library

SP - 261

EP - 309

BT - Computer Vision in Control Systems-1

A2 - Favorskaya, Margarita N.

A2 - Jain, Lakhmi C.

PB - Springer

CY - New York

ER -

Favorskaya M, JAIN L, Buryachenko V. Digital video stabilization in static and dynamic scenes. In Favorskaya MN, Jain LC, editors, Computer Vision in Control Systems-1: Mathematical Theory. 1 ed. Vol. 73. New York: Springer. 2015. p. 261-309. (Intelligent Systems Reference Library). (Intelligent Systems Reference Library). https://doi.org/10.1007/978-3-319-10653-3_9