Key frame extraction method for human animation based on pose saliency

A technology of human animation and extraction method, which is applied in the field of image processing, and can solve the problems that the number of key frames cannot be adaptively given, and the user is inconvenient to use, etc.

Active Publication Date: 2021-07-20
NANCHANG UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, most of the existing key frame extraction methods cannot adaptively give the number of key frames to be extracted, and need to manually set various thresholds that are difficult to determine, which causes inconvenience to users.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Key frame extraction method for human animation based on pose saliency
  • Key frame extraction method for human animation based on pose saliency
  • Key frame extraction method for human animation based on pose saliency

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments. figure 1 Be flow chart of the present invention, its concrete implementation comprises the following steps:

[0043] S1: Filter feature components. According to the variance, some motion components are selected as the feature components of human motion, and the weights of the feature components are calculated. The implementation steps are as follows:

[0044] From the human skeleton model, 8 joints including wrist joint, elbow joint, ankle joint and knee joint of limbs, 2 joints of hip joint and thoracic joint of trunk and 1 joint of head are selected as the motion feature representation. Compute the variance ar(c i ), i=1...62, choose The motion component of is the feature component, and its weight is calculated

[0045] S2: Compute pose saliency. Calculate the multi-scale saliency of feature components, weighted and fitted int...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a method for extracting key frames of human body animation based on posture saliency, the steps of which are: screening part of motion components according to variance as feature components of human body motion; calculating multi-scale salience of feature components, and weighting and fitting into human body animation pose saliency; extract the local maximum point of the pose saliency curve as the initial keyframe, and determine the number of keyframes according to the ratio of the optimal reconstruction error to the number of keyframes; select the initial keyframe with a large reconstruction error according to the number of keyframes The frame is a candidate key frame, and the frame with the minimum reconstruction error is extracted from the neighborhood of the candidate key frame by using the reconstruction error optimization algorithm as the final key frame. The invention can self-adaptively determine the optimal number of key frames, extract the key frames with the minimum reconstruction error, and meet the requirement of real-time compression of motion capture data.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for extracting key frames of human animation based on gesture salience. Background technique [0002] Keyframe refers to the partial pose sequence in the human animation sequence that can best represent the animation content, and it provides an important basis for the compression, retrieval, preview and reuse of motion capture data. Equal interval sampling can be regarded as a simple key frame extraction method, but its essence is equivalent to reducing the sampling frequency of motion capture, and there are data redundancy when the motion is slow and loss of details when the motion is severe. To overcome this problem, researchers have proposed many adaptive keyframe extraction methods, which can be roughly divided into methods based on curve simplification, methods based on clustering and methods based on optimization. [0003] The method based on curve simpli...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00
CPCG06V40/10G06V40/20G06V20/46
Inventor 刘云根张俊
Owner NANCHANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap