Efficient Human Motion Retrieval via Temporal Adjacent Bag of Words and Discriminative Neighborhood Preserving Dictionary Learning
- 23 March 2017
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Human-Machine Systems
- Vol. 47 (6) , 763-776
Abstract
Human motion retrieval from motion capture data forms the fundamental basis for computer animation. In this paper, the authors propose an efficient human motion retrieval approach via temporal adjacent bag of words (TA-BoW) and discriminative neighborhood preserving dictionary learning (DNP-DL). The retrieval process includes two phases: offline training and online retrieval. In the first phase, the original skeleton model is first simplified and then pairwise joint distances are computed to characterize each motion frame. Then, a novel motion descriptor, namely TABoW, is proposed to discriminatively code the motion appearances, through which the articulated complexity and spatiotemporal dimensionality can be greatly reduced. Subsequently, by considering the neighborhood relationships of intraclass structure and the advantage of Fisher criterion, a DNP-DL method is exploited through which each human action can be discriminatively and sparsely represented by a linear combination of such dictionary atoms. In the second phase, a hierarchical retrieval mechanism is used by incorporating the sparse classification and chi-square ranking, whereby the searching range is significantly reduced. The experimental results show that the proposed human motion retrieval approach performs better than the state-of-the-art competing approaches.Keywords
Funding Information
- National Science Foundation of China (61673185, 61272366, 61672444)
- Science and Technology Research and Development Fund of Shenzhen (JCYJ20160531194006833)
- National Science Foundation of Fujian Province (2015J01656, 2017J01112)
- Promotion Program for Young and Middle-Aged Teacher in Science and Technology Research (ZQN-PY309)
- HKBU (FRG2/14-15/075, FRG2/15-16/049)
- Research Grants of University of Macau (MYRG2015-00050-FST)
- Macau-China Joint Project (008-2014-AMJ)
This publication has 35 references indexed in Scilit:
- 3D skeleton-based human action classification: A surveyPattern Recognition, 2016
- Efficient Pose-Based Action Recognition2015
- Activity-based methods for person recognition in motion capture sequencesPattern Recognition Letters, 2014
- Correlation-optimized time warping for motionThe Visual Computer, 2014
- Sparse Representation Based Fisher Discrimination Dictionary Learning for Image ClassificationInternational Journal of Computer Vision, 2014
- Spatial temporal pyramid matching using temporal sparse representation for human motion retrievalThe Visual Computer, 2014
- A semantic feature for human motion retrievalComputer Animation and Virtual Worlds, 2013
- Isotonic CCA for sequence alignment and activity recognition2011
- Motion classification using Dynamic Time Warping2008
- Derivative Dynamic Time Warping2001