3D Human Action Recognition Using Spatio-temporal Motion Templates

• Published in: Computer Vision in Human-Computer Interaction pp. 120 - 130
• Main Authors: Lv, Fengjun, Nevatia, Ramakant, Lee, Mun Wai
• Format: Book Chapter Conference Proceeding
• Language: English
• Published: Berlin, Heidelberg Springer Berlin Heidelberg 2005; Springer
• Series: Lecture Notes in Computer Science
• Subjects: Action Recognition; Applied sciences; Artificial intelligence; Computer science; control theory; systems; Computer systems and distributed systems. User interface; Exact sciences and technology; False Alarm Rate; Human Action Recognition; Pattern recognition. Digital image processing. Computational geometry; Software; Template Match; Training Sample; Computer vision; Dimensionality; Neyman Pearson detection; Motion estimation; Human body; User interface; Body movement; Large displacement; Automatic recognition; Spatial variation; Measurement error
• ISBN: 9783540296201; 3540296204
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/11573425_12

Our goal is automatic recognition of basic human actions, such as stand, sit and wave hands, to aid in natural communication between a human and a computer. Human actions are inferred from human body joint motions, but such data has high dimensionality and large spatial and temporal variations may occur in executing the same action. We present a learning-based approach for the representation and recognition of 3D human action. Each action is represented by a template consisting of a set of channels with weights. Each channel corresponds to the evolution of one 3D joint coordinate and its weight is learned according to the Neyman-Pearson criterion. We use the learned templates to recognize actions based on χ2 error measurement. Results of recognizing 22 actions on a large set of motion capture sequences as well as several annotated and automatically tracked sequences show the effectiveness of the proposed algorithm.