A genetic algorithm approach to human motion capture data segmentation
Authors:
- 23 May 2014
- journal article
- research article
- Published by Wiley in Computer Animation and Virtual Worlds
- Vol. 25 (3-4) , 281-290
Abstract
In this paper, we propose a novel genetic algorithm approach to human motion capture (MoCap) data segmentation. For a given MoCap sequence, it constructs a symbolic representation through unsupervised sparse learning, detects the candidate segmenting points to the sequence, models the selection/deselection of each candidate with a gene, and employs the genetic algorithm to find the optimal solution. To the best of our knowledge, we for the first time introduce the genetic algorithm and the sparse learning technique to the problem of MoCap data segmentation, leading to excellent segmentation performance as experimentally demonstrated. Copyright © 2014 John Wiley & Sons, Ltd.Keywords
Funding Information
- National Natural Science Foundation of China (61303083)
- National Natural Science Foundation of China (61173079)
- National Natural Science Foundation of China (U1035004)
- National Natural Science Foundation of China (U1201258)
- Excellent Middle-Aged and Youth Scientists of Shandong Province of China (BS2011DX017)
- Program for New Century Excellent Talents in University in China
- Shandong Province Natural Science Foundation,China (ZR2011FZ003)
- Shandong Province Natural Science Foundation,China (ZR2011FZ004)
This publication has 13 references indexed in Scilit:
- Hierarchical Aligned Cluster Analysis for Temporal Clustering of Human MotionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Semantic Segmentation of Motion Capture Using Laban Movement Analysis2007
- Segmentation and recognition of motion capture data stream by classificationMultimedia Tools and Applications, 2007
- $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse RepresentationIEEE Transactions on Signal Processing, 2006
- Using nonlinear dimensionality reduction in 3D figure animation2005
- Acquiring and validating motion qualities from live limb gesturesGraphical Models, 2005
- Manifold clustering2005
- Automated Derivation of Primitives for Movement ClassificationAutonomous Robots, 2002
- Adaptive greedy approximationsConstructive Approximation, 1997
- Matching pursuits with time-frequency dictionariesIEEE Transactions on Signal Processing, 1993