Video matching
Authors:
Open Access
- 1 August 2004
- conference paper
- Published by Association for Computing Machinery (ACM)
- Vol. 23 (3) , 592-599
Abstract
This paper describes a method for bringing two videos (recorded at different times) into spatiotemporal alignment, then comparing and combining corresponding pixels for applications such as background subtraction, compositing, and increasing dynamic range. We align a pair of videos by searching for frames that best match according to a robust image registration process. This process uses locally weighted regression to interpolate and extrapolate high-likelihood image correspondences, allowing new correspondences to be discovered and refined. Image regions that cannot be matched are detected and ignored, providing robustness to changes in scene content and lighting, which allows a variety of new applications.Keywords
This publication has 18 references indexed in Scilit:
- Interactive digital photomontageACM Transactions on Graphics, 2004
- High dynamic range videoACM Transactions on Graphics, 2003
- A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence AlgorithmsInternational Journal of Computer Vision, 2002
- Video textures2000
- A pixel dissimilarity measure that is insensitive to image samplingIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- Effective Corner Matching1998
- The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow FieldsComputer Vision and Image Understanding, 1996
- The computation of optical flowACM Computing Surveys, 1995
- A Combined Corner and Edge Detector1988
- Random sample consensusCommunications of the ACM, 1981