1. Fast Optical Flow Extraction From Compressed Video.
- Author
-
Young, Sean I., Girod, Bernd, and Taubman, David
- Subjects
- *
OPTICAL flow , *VIDEOS , *VIDEO coding , *PROBLEM solving , *LIGHT filters , *VIDEO surveillance - Abstract
We propose the fast optical flow extractor, a filtering method that recovers artifact-free optical flow fields from HEVC-compressed video. To extract accurate optical flow fields, we form a regularized optimization problem that considers the smoothness of the solution and the pixelwise confidence weights of an artifact- ridden HEVC motion field. Solving such an optimization problem is slow, so we first convert the problem into a confidence-weighted filtering task. By leveraging the already-available HEVC motion parameters, we achieve a 100-fold speed-up in the running times compared to similar methods, while producing subpixel-accurate flow estimates. The fast optical flow extractor is useful when video frames are already available in coded formats. Our method is not specific to a coder, and works with motion fields from video coders such as H.264/AVC and HEVC. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF