Video Matching
Author(s)
Sand, Peter; Teller, Seth
DownloadMIT-CSAIL-TR-2004-029.ps (22.56Mb)
Additional downloads
Other Contributors
Computer Graphics
Metadata
Show full item recordAbstract
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.
Date issued
2004-05-11Other identifiers
MIT-CSAIL-TR-2004-029
MIT-LCS-TR-947
Series/Report no.
Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory