Human Identification Based on Tensor Representation of the Gait Motion Capture Data

Josiński, Henryk; Świtoński, Adam; Jędrasiak, Karol; Kostrzewa, Daniel

doi:10.1142/9789814439084_0009

Cited by 8 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The classification is performed by using a nearest neighbor approach involving Euclidean distance. In [12], second-order tensor objects are used to represent mocap walking data. Multilinear principal component analysis (MPCA) is used to reduce the high-dimensionality of the tensor objects.…”

Section: Previous Workmentioning

confidence: 99%

Person identity recognition on motion capture data using multiple actions

Kapsouras

Nikolaidis

2015

Machine Vision and Applications

View full text Add to dashboard Cite

In this paper, we introduce a novel method for person identity recognition (identification) on skeleton animation/motion capture data representing persons performing various actions. The joints positions or orientation angles and the forward differences of these quantities are used to represent a motion capture sequence. First K-means clustering is applied on training data to discover the most representative patterns on joints positions or orientation angles (dynemes) and their forward differences (F-dynemes). Each frame is then assigned to one of these patterns and the frequency of occurrence histograms for each movement are constructed in a bag-of-words fashion. Person identity recognition is done through a nearest neighbor classifier. The proposed method is experimentally tested on a number of datasets of motion capture data, with very good results.

show abstract

Section: Previous Workmentioning

confidence: 99%

Person identity recognition on motion capture data using multiple actions

Kapsouras

Nikolaidis

2015

Machine Vision and Applications

View full text Add to dashboard Cite

show abstract

“…Activity-based person identification methods applied on skeletal animation or motion capture data are almost non existent, since research on mocap data focuses mainly on motion indexing and retrieval as well as activity recognition. Approaches that use mocap data for activity-based person recognition are very few and deal only with gait [2], [3], [4], [5]. The authors are aware of only two other approaches that perform activitybased person identification using skeletal animation / motion capture data.…”

Section: Introductionmentioning

confidence: 99%

Person identity recognition on motion capture data using label propagation

Nikolaidis

2017

2017 25th European Signal Processing Conference (EUSIPCO)

View full text Add to dashboard Cite

Abstract-Most activity-based person identity recognition methods operate on video data. Moreover, the vast majority of these methods focus on gait recognition. Obviously, recognition of a subject's identity using only gait imposes limitations to the applicability of the corresponding methods whereas a method capable of recognizing the subject's identity from various activities would be much more widely applicable. In this paper, a new method for activity-based identity recognition operating on motion capture data, that can recognize the subject's identity from a variety of activities is proposed. The method combines an existing approach for feature extraction from motion capture sequences with a label propagation algorithm for classification. The method and its variants (including a novel one, that takes advantage of the fact that, in certain cases, both activity and person identity labels might exist for the labeled sequences) have been tested in two different datasets. Experimental analysis proves that the proposed approach provides very good person identity recognition results, surpassing those obtained by two other methods.

show abstract

“…The MPCA reduction is also extended by LDA method. The application of MPCA to the classification of motion capture data by supervised learning can be found in [15]. In [12] mutlilinear ICA and in [14] uncorrelated MPCA are applied to face recognitions.…”

Section: Introductionmentioning

confidence: 99%

Gait Identification Based on MPCA Reduction of a Video Recordings Data

Michalczuk

Świtoński

Josiński

et al. 2012

Computer Vision and Graphics

Self Cite

View full text Add to dashboard Cite

Abstract. The scope of this article is gait identification of individuals on the basis of reduced sequences of video recordings data. The gait sequences are considered to be the 3rd-order tensors and its dimensionality is reduced by Multilinear Principal Component Analysis with different values of variation covered. Reduced gait descriptors are identified by the supervised classifiers: Naive Bayes and Nearest Neighbor. CASIA Gait Database 'dataset A' is chosen to verify the proposed method. The obtained results are promising. For the Naive Bayes and attributes discretization almost 99% of classification accuracy is achieved, which means only one misclassified gait out of eighty validated.

show abstract

Human Identification Based on Tensor Representation of the Gait Motion Capture Data

Cited by 8 publications

References 12 publications

Person identity recognition on motion capture data using multiple actions

Person identity recognition on motion capture data using multiple actions

Person identity recognition on motion capture data using label propagation

Gait Identification Based on MPCA Reduction of a Video Recordings Data

Contact Info

Product

Resources

About