Skip to main content

KeyFrame extraction for human motion capture data via multiple binomial fitting.

Xu, C., Yu, W., Li, Y., Lu, X., Wang, M. and Yang, X., 2020. KeyFrame extraction for human motion capture data via multiple binomial fitting. Computer Animation and Virtual Worlds, e1976. (In Press)

Full text available as:

[img] PDF
KeyFrame+Extraction+for+Human+Motion+Capture.pdf - Accepted Version
Restricted to Repository staff only until 14 December 2021.
Available under License Creative Commons Attribution Non-commercial.

8MB

DOI: 10.1002/cav.1976

Abstract

In this paper, we make two contributions. The first is to propose a new keyframe extraction algorithm, which reduces the keyframe redundancy and reduces the motion sequence reconstruction error. Secondly, a new motion sequence reconstruction method is proposed, which further reduces the error of motion sequence reconstruction. Specifically, we treated the input motion sequence as curves, then the binomial fitting was extended to obtain the points where the slope changes dramatically in the vicinity. Then we took these points as inputs to obtain keyframes by density clustering. Finally, the motion curves were segmented by keyframes and the segmented curves were fitted by binomial formula again to obtain the binomial parameters for motion reconstruction. Experiments show that our methods outperform existing techniques, in terms of reconstruction error.

Item Type:Article
ISSN:1546-4261
Additional Information:Funding information: Key Laboratory of Agricultural Internet of Things, Ministry of Agriculture and Rural Affairs, China, (2018AIOT‐09); Key Research and Development Program of Shaanxi Province, (2018NY‐127); Shaanx‐i Key Industrial Innovation Chain Project in Agricultural Domain, (2019ZDLNY02‐05)
Uncontrolled Keywords:computer animation; curve simplification; keyframe extraction; motion capture
Group:Faculty of Media & Communication
ID Code:35006
Deposited By: Unnamed user with email symplectic@symplectic
Deposited On:04 Jan 2021 15:25
Last Modified:04 Jan 2021 15:25

Downloads

Downloads per month over past year

More statistics for this item...
Repository Staff Only -