Shooting a smooth video with a shaky camera

Authors:
Zoran Duric;Azriel Rosenfeld
Affiliations:
Department of Computer Science, George Mason University, Fairfax, VA;Center for Automation Research University of Maryland College Park, MD
Venue:
Machine Vision and Applications
Year:
2003

Citing 6
Cited 4

Solid shape

Solid shape
Estimating the heading direction using normal flow

International Journal of Computer Vision
Egomotion analysis based on the Frenet-Serret motion model

International Journal of Computer Vision - Special issue: image understanding research at the University of Maryland
Image sequence stabilization in real time

Real-Time Imaging
The Applicability of Green‘s Theorem to Computation of Rate of Approach

International Journal of Computer Vision
Fast structure from motion recovery applied to 3D image stabilization

ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 06

Fixation as a Mechanism for Stabilization of Short Image Sequences

International Journal of Computer Vision
Embedding of a Real Time Image Stabilization Algorithm on SoPC Platform, a Chip Multi-processor Approach

ACIVS '08 Proceedings of the 10th International Conference on Advanced Concepts for Intelligent Vision Systems
Optic flow from unstable sequences through local velocity constancy maximization

Image and Vision Computing
Embedding of a real time image stabilization algorithm on a parameterizable SoPC architecture a chip multi-processor approach

Journal of Real-Time Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The image sequence in a video taken by a moving camera may suffer from irregular perturbations because of irregularities in the motion of the person or vehicle carrying the camera. We show how to use information in the image sequence to correct the effects of these irregularities so that the sequence is smoothed, i.e., is approximately the same as the sequence that would have been obtained if the motion of the camera had been smooth. Our method is based on the fact that the irregular motion is almost entirely rotational, and that the rotational image motion can be detected and corrected if a distant object, such as the horizon, is visible.