scispace - formally typeset
Search or ask a question
Topic

Residual frame

About: Residual frame is a research topic. Over the lifetime, 4443 publications have been published within this topic receiving 68784 citations.


Papers
More filters
Patent
Ling Shao1
14 Apr 2010
TL;DR: In this article, a method of extracting a key frame from a sequence of frames constituting a shot, each frame being constituted by a matrix of pixels, comprises: computing (1) the optical flow of the frame compared to the following frame as a matrix, and (2) a motion entropy measure based on the optical flows of the frames.
Abstract: A method of extracting a key frame from a sequence of frames constituting a shot, each frame being constituted by a matrix of pixels, comprises: for each frame of the sequence of frames: computing (3) the optical flow of the frame compared to the following frame as a matrix of displacement of each pixel from the frame to the following frame; computing (5) a motion entropy measure based on the optical flow of the frame; selecting (7) as key frame the frame of the sequence of frames having the maximum motion entropy measure.

28 citations

Patent
31 Jul 2007
TL;DR: In this paper, an interpolation frame generating method performs motion detection processing using two blocks having different sizes, and adopts a motion vector detected by a smaller block under normal conditions.
Abstract: An interpolation frame generating method performs motion detection processing using two blocks having different sizes, and adopts a motion vector detected by a smaller block under normal conditions (Block 104). When a plurality of reliable motion vector candidates are detected in vector detection using the smaller block (YES of Block 103), a vector detected by a larger block is referred to (Block 105), and a motion vector which is closest to the motion vector detected with the larger block among the motion vectors detected with the smaller block is adopted as a motion vector of the block to be used for generating an interpolation frame (Block 106).

28 citations

Patent
Boyce Jill M1
05 Nov 1991
TL;DR: In this article, the mean absolute difference between each block in the reference frame and identically located blocks in adjacent frames is calculated by making a search for a block in adjacent frame that matches the block in reference frame.
Abstract: A method for reducing noise in a reference frame of video information by determining the mean absolute difference, MAD o , between each block in the reference frame and identically located blocks in adjacent frames. If MAD o is A, a search is made for a block in the adjacent frame that matches the block in the reference frame. This is labelled MAD min . If MAD o for the block in the adjacent frame is

28 citations

Patent
18 Jan 2000
TL;DR: In this article, an optical flow calculator is configured for generating an image motion vector field by iteratively comparing a predicted image with the second image frame, where the predicted image is generated according to a current motion estimate in proximity to an observation point.
Abstract: An apparatus for generating an image motion vector field which describes a motion of individual image components of a first image frame and corresponding image components of a second image frame in a sequence of image frames. The apparatus comprises a first frame memory for receiving said first image frame, a second frame memory for receiving a second image frame, and an optical flow calculator. The optical flow calculator is configured for generating an image motion vector field by iteratively comparing a predicted image with the second image frame. The predicted image is generated according to a current motion estimate in proximity to an observation point, wherein the observation point migrates according to a previous motion estimate and is implemented by the calculator to generate a current motion estimate.

28 citations

Patent
20 Dec 2004
TL;DR: A motion vector estimation method and an encoding mode determining method for converting an input moving picture into a compressed moving picture image suitable for a desired frame rate by re-determining a motion vector and a motion-compensated block type when the frame rate of the image needs to be reduced is discussed in this paper.
Abstract: A motion vector estimation method and an encoding mode determining method for converting an input moving picture image into a compressed moving picture image suitable for a desired frame rate by re-determining a motion vector and a motion-compensated block type when the frame rate of the input moving picture image needs to be reduced. A method of estimating a motion vector of a motion vector of a macroblock of a current frame in a transcoder includes determining whether the motion vector of the macroblock of the current frame is created with reference to a macroblock of a dropped frame and estimating the motion vector of the macroblock of the current frame by tracing back a reference frame until an undropped frame is found, if the motion vector of the macroblock of the current frame is created with reference to the macroblock of the dropped frame.

27 citations


Network Information
Related Topics (5)
Feature (computer vision)
128.2K papers, 1.7M citations
81% related
Feature extraction
111.8K papers, 2.1M citations
80% related
Image segmentation
79.6K papers, 1.8M citations
80% related
Image processing
229.9K papers, 3.5M citations
78% related
Pixel
136.5K papers, 1.5M citations
78% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
202313
202223
20217
20204
20196
201811