A Motion Retargeting Method for Topologically Different Characters

Lu, Wenyu; Liu, Yan; Sun, Jizhou; Sun, Libo

doi:10.1109/cgiv.2009.53

Cited by 10 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The related topic of motion retargeting, i.e. motion adaptation from one character to another with different kinematic structures, has been considered in computer vision and animation [20], [35], [26], [30], [8], [22].…”

Section: Related Workmentioning

confidence: 99%

Arm gesture recognition and humanoid imitation using functional principal component analysis

Aleotti

Cionini

Fontanili

et al. 2013

2013 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

A method is proposed for gesture recognition and humanoid imitation based on Functional Principal Component Analysis (FPCA). FPCA is a statistical technique of functional data analysis that has never been applied before for humanoid imitation. In functional data analysis data (e.g. gestures) are functions that can be considered as observations of a random variable on a functional space. FPCA is an extension of multivariate PCA that provides functional principal components which describe the modes of variation in the data. In the proposed approach FPCA is used for both unsupervised clustering of training data and gesture recognition.In this work we focus on arm gesture recognition. Human hand paths in Cartesian space are reconstructed from inertial sensors. Recognized gestures are reproduced by a small humanoid robot. The FPCA algorithm has also been compared to a state of the art algorithm for gesture classification based on Dynamic Time Warping (DTW). Results indicate that, in this domain, the FPCA algorithm achieves a comparable recognition rate while it outperforms DTW in terms of efficiency in execution time.

show abstract

Section: Related Workmentioning

confidence: 99%

Arm gesture recognition and humanoid imitation using functional principal component analysis

Aleotti

Cionini

Fontanili

et al. 2013

2013 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

show abstract

“…The related topic of motion retargeting, i.e., adjusting the motion from one character to another with di®erent kinematic structures, has been considered in computer vision and animation. [39][40][41][42][43][44][45] In particular, Pollard et al 42 investigated the problem of adaptation of human motion to a humanoid robot with joint and velocity limits.…”

Section: State Of the Artmentioning

confidence: 99%

Functional Principal Component Analysis for Recognition of Arm Gestures and Humanoid Imitation

Aleotti

Caselli

2013

Int. J. Human. Robot.

View full text Add to dashboard Cite

This paper investigates the use of functional principal component analysis (FPCA) for automatic recognition of dynamic human arm gestures and robot imitation. FPCA is a statistical technique of functional data analysis that generalizes standard multivariate principal component analysis. Functional data analysis signals (e.g., gestures) are functions that are considered as observations of a random variable on a functional space. In particular, FPCA reduces the dimensionality of the input data by projecting them onto a¯nite-dimensional space spanned by a few prominent eigenfunctions. The main contribution of this work is the proposal of a novel technique for unsupervised clustering of training data and dynamic gesture recognition based on FPCA. FPCA has not been considered in previous studies on humanoid learning. The proposed approach has been evaluated in two experimental settings for motion capture. In the¯rst setup single arm gestures are recognized from inertial sensors attached to the arm of the user. In the second setup the method is extended to two-arm gestures acquired from a range sensor. Recognized gestures are reproduced by a small humanoid robot. The FPCA method has also been compared to a high performance algorithm for gesture classi¯cation based on dynamic time warping (DTW). The FPCA algorithm achieves comparable results in both recognition rate and robustness to missing data, while it outperforms DTW in terms of e±ciency in execution time.

show abstract

“…Recently, a computational human motion study has drawn much warranted attention; and is a part of the development of motion capture techniques, which in turn have resulted in a growth in many applications such as animation, film, interactive games, virtual world, etc. In terms of animation, motion capture can be used for different aspects such as [41] and [42], they have been used in character animation and motion retarget; and have the lot of interest in the methods of using and re-using of mocap data [21][22][23][24]. In [46] describes the optical or magnetic sensors are attached to the human body joints to record their activities, which can be used to recognize the daily home activities such as eating meals, using bathroom, teeth cleaning, and washing face in a smart home.…”

Section: Introductionmentioning

confidence: 99%

Human Identification Using Sensors Data Based on 3D Gait Area

Ali

Zhou

et al. 2014

2014 International Conference on Cyberworlds

View full text Add to dashboard Cite

Surveillance means is a system that monitors the behavior, activities, or other changing information; usually it is used to recognize the people for the purpose of security issues in society. This paper aims to propose a novel approach based on sensor data acquired by an optical system for the purpose of human identification. Three joints of the human body, such as the hip, knee, and ankle joint have been selected by the amount of gait movement in this algorithm. By extracting suitable 3D static and dynamic joints feature from data. The method applies the PBC (Parametric Bézier Curve) technique on the extracted features in order to derive the strong correlation between joint movements. The curve control points are used to construct the triangles of each walking pose of human. The geometric function and statistical methods on the triangles are used here to compute the gait signature and analysis of this signature and find the maximum unique relationship among the human gait during the walk, and use it as to classify the human identification. The experimental results demonstrate that this method is more accurate and reliable.

show abstract

A Motion Retargeting Method for Topologically Different Characters

Cited by 10 publications

References 11 publications

Arm gesture recognition and humanoid imitation using functional principal component analysis

Arm gesture recognition and humanoid imitation using functional principal component analysis

Functional Principal Component Analysis for Recognition of Arm Gestures and Humanoid Imitation

Human Identification Using Sensors Data Based on 3D Gait Area

Contact Info

Product

Resources

About