The Online Gait Measurement for Characteristic Gait Animation Synthesis

This paper presents a method to measure online the gait features from the gait silhouette images and to synthesize characteristic gait animation for an audience-participant digital entertainment. First, both static and dynamic gait features are extracted from the silhouette images captured by an online gait measurement system. Then, key motion data for various gaits are captured and a new motion data is synthesized by blending key motion data. Finally, blend ratios of the key motion data are estimated to minimize gait feature errors between the blended model and the online measurement. In experiments, the effectiveness of gait feature extraction were confirmed by using 100 subjects from OU-ISIR Gait Database and characteristic gait animations were created based on the measured gait features.

[1]  Kirsi Helkala,et al.  Biometric Gait Authentication Using Accelerometer Sensor , 2006, J. Comput..

[2]  Sudeep Sarkar,et al.  The humanID gait challenge problem: data sets, performance, and analysis , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Lucas Kovar,et al.  Flexible automatic motion blending with registration curves , 2003, SCA '03.

[4]  Liu Ming,et al.  A Wearable Acceleration Sensor System for Gait Recognition , 2007, 2007 2nd IEEE Conference on Industrial Electronics and Applications.

[5]  Yasushi Makihara,et al.  Gait Recognition Using a View Transformation Model in the Frequency Domain , 2006, ECCV.

[6]  Mark S. Nixon,et al.  Extended Model-Based Automatic Gait Recognition of Walking and Running , 2001, AVBPA.

[7]  Einar Snekkenes,et al.  Improved Gait Recognition Performance Using Cycle Matching , 2010, 2010 IEEE 24th International Conference on Advanced Information Networking and Applications Workshops.

[8]  Shigeo Morishima,et al.  Future Cast System , 2005, SIGGRAPH '05.

[9]  Bir Bhanu,et al.  Individual recognition using gait energy image , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Rama Chellappa,et al.  Combining multiple evidences for gait recognition , 2003, 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698).

[11]  Liu Ming,et al.  Identification of Individual Walking Patterns Using Gait Acceleration , 2007, 2007 1st International Conference on Bioinformatics and Biomedical Engineering.

[12]  Antti Oulasvirta,et al.  Computer Vision – ECCV 2006 , 2006, Lecture Notes in Computer Science.

[13]  Satoshi Nakamura,et al.  Instant Movie Casting with Personality: Dive into the Movie System , 2011, HCI.