Automatic recognition and scoring of olympic rhythmic gymnastic movements.

We describe a conceptually simple algorithm for assigning judgement scores to rhythmic gymnastic movements, which could improve scoring objectivity and reduce judgemental bias during competitions. Our method, implemented as a real-time computer vision software, takes a video shot or a live performance video stream as input and extracts detailed velocity field information from body movements, transforming them into specialized spatio-temporal image templates. The collection of such images over time, when projected into a velocity covariance eigenspace, trace out unique but similar trajectories for a particular gymnastic movement type. By comparing separate executions of the same atomic gymnastic routine, our method assigns a quality judgement score that is related to the distance between the respective spatio-temporal trajectories. For several standard gymnastic movements, the method accurately assigns scores that are comparable to those assigned by expert judges. We also describe our rhythmic gymnastic video shot database, which we have made freely available to the human movement research community. The database can be obtained at http://www.milegroup.net/apps/gymdb/.

[1]  Lysann Damisch,et al.  Olympic medals as fruits of comparison? Assimilation and contrast in sequential performance judgments. , 2006, Journal of experimental psychology. Applied.

[2]  Ian D. Reid,et al.  Articulated Body Motion Capture by Stochastic Search , 2005, International Journal of Computer Vision.

[3]  Dolores Cabrera Suárez.  El perfil de las jueces de gimnasia rítmica , 1998 .

[4]  Marta Bobo-Arce.  El juicio deportivo en gimnasia rítmica : una propuesta de evaluación basada en indicadores de rendimiento , 2002 .

[5]  J. Gillis,et al.  Classical dynamics of particles and systems , 1965 .

[6]  Jackie Puhl,et al.  Use of Video Replay in Judging Gymnastics Vaults , 1980 .

[7]  D. Ste-Marie,et al.  Memory-Influenced Biases in Gymnastic Judging Occur across Different Prior Processing Conditions , 2001, Research quarterly for exercise and sport.

[8]  C. Ansorge,et al.  International Bias Detected in Judging Gymnastic Competition at the 1984 Olympic Games , 1988 .

[9]  B. Abernethy,et al.  The relationship between expertise and visual search strategy in a racquet sport , 1987 .

[10]  I. Čuk,et al.  Reliability and validity of judging in women's artistic gymnastics at University Games 2009 , 2012 .

[11]  Gunnar Farnebäck,et al.  Two-Frame Motion Estimation Based on Polynomial Expansion , 2003, SCIA.

[12]  N. Coffey,et al.  Common functional principal components analysis: a new approach to analyzing human movement data. , 2011, Human movement science.

[13]  M. Raab,et al.  Perceptual Judgments of Sports Officials are Influenced by their Motor and Visual Experience , 2012 .

[14]  Henning Plessner,et al.  Sports performance judgments from a social cognitive perspective , 2006 .

[15]  M. Nixon,et al.  Human gait recognition in canonical space using temporal templates , 1999 .

[16]  Martin Tomitsch,et al.  Be a judge!: wearable wireless motion sensors for audience participation , 2004, CHI EA '04.

[17]  Gianfranco Gambarelli,et al.  Anti-collusion indices and averages for the evaluation of performances and judges , 2012, Journal of sports sciences.

[18]  G Ferrigno,et al.  Robust recovery of human motion from video using Kalman filters and virtual humans. , 2003, Human movement science.

[19]  Stanislav Kovacic,et al.  Observation and analysis of large-scale human motion. , 2002, Human movement science.

[20]  Extreme judgments depend on the expectation of following judgments: A calibration analysis , 2012 .

[21]  G. Dallas,et al.  Influence of Angle of View on Judges' Evaluations of Inverted Cross in Men's Rings , 2011, Perceptual and motor skills.

[22]  Ronald Poppe,et al.  A survey on vision-based human action recognition , 2010, Image Vis. Comput..

[23]  Alexandra Pizzera.  Gymnastic Judges Benefit From Their Own Motor Experience as Gymnasts , 2012, Research quarterly for exercise and sport.

[24]  P. A. Richardson,et al.  Psychology of officiating , 1990 .

[25]  Bernhard Schölkopf,et al.  Kernel Principal Component Analysis , 1997, ICANN.

[26]  Mark S. Nixon,et al.  Recognising humans by gait via parametric canonical space , 1999, Artif. Intell. Eng..

[27]  Xosé Antón Vila-Sobrino,et al.  Eigenspace-based fall detection and activity recognition from motion templates and machine learning , 2012, Expert Syst. Appl..

[28]  D. Ste-Marie,et al.  Expertise in Women's Gymnastic Judging: An Observational Approach , 2000, Perceptual and motor skills.

[29]  The “coherent majority average” for juries’ evaluation processes , 2008, Journal of sports sciences.

[30]  Guillaume Rao,et al.  Regulation of pendulum length as a control mechanism in performing the backward giant circle in gymnastics. , 2009, Human movement science.

[31]  C. Ansorge,et al.  Judging Bias Induced by Viewing Contrived Videotapes: A Function of Selected Psychological Variables , 1983 .

[32]  Jianning Wu,et al.  Feature extraction via KPCA for classification of gait patterns. , 2007, Human movement science.

[33]  João Paulo Vilas-Boas,et al.  Individual profiles of spatio-temporal coordination in high intensity swimming. , 2012, Human movement science.

[34]  Keinosuke Fukunaga,et al.  Introduction to Statistical Pattern Recognition , 1972 .

[35]  H. Plessner,et al.  Judging the cross on rings: a matter of achieving shape constancy , 2005 .

[36]  Richard Szeliski,et al.  Computer Vision - Algorithms and Applications , 2011, Texts in Computer Science.

[37]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[38]  T. Heinen,et al.  MOTOR SKILL ACQUISITION INFLUENCES LEARNERS ‘ VISUAL PERCEPTION IN GYMNASTICS , 2013 .

[39]  Diane M. Ste-Marie,et al.  Expert-novice differences in gymnastic judging : An information-processing perspective , 1999 .

[40]  Tim Smits,et al.  Open feedback in gymnastic judging causes conformity bias based on informational influencing , 2008, Journal of sports sciences.