Automatic Key Pose Selection for 3D Human Action Recognition

This article describes a novel approach to the modeling of human actions in 3D. The method we propose is based on a "bag of poses" model that represents human actions as histograms of key-pose occurrences over the course of a video sequence. Actions are first represented as 3D poses using a sequence of 36 direction cosines corresponding to the angles 12 joints form with the world coordinate frame in an articulated human body model. These pose representations are then projected to three-dimensional, action-specific principal eigenspaces which we refer to as aSpaces. We introduce a method for key-pose selection based on a local-motion energy optimization criterion and we show that this method is more stable and more resistant to noisy data than other key-poses selection criteria for action recognition.

[1]  Jordi Gonzàlez,et al.  Automatic learning of 3D pose variability in walking performances for gait analysis , 2008 .

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

[3]  Tido Röder,et al.  Efficient content-based retrieval of motion capture data , 2005, SIGGRAPH 2005.

[4]  Pietro Perona,et al.  A Bayesian hierarchical model for learning natural scene categories , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[5]  Michael J. Black,et al.  HumanEva: Synchronized Video and Motion Capture Dataset for Evaluation of Articulated Human Motion , 2006 .

[6]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[7]  Osama Masoud,et al.  A method for human action recognition , 2003, Image Vis. Comput..

[8]  Andrew Zisserman,et al.  Representing shape with a spatial pyramid kernel , 2007, CIVR '07.

[9]  Vladimir M. Zatsiorsky.  Kinematics of human motion , 1998 .

[10]  Vladimir M. Zatsiorsky,et al.  Kinetics of Human Motion , 2002 .

[11]  Michael Gleicher,et al.  Automated extraction and parameterization of motions in large data sets , 2004, SIGGRAPH 2004.

[12]  Xavier Varona,et al.  Analysis of Human Walking Based on aSpaces , 2004, AMDO.

[13]  Ramakant Nevatia,et al.  Single View Human Action Recognition using Key Pose Matching and Viterbi Path Searching , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  F. Xavier Roca,et al.  Action-specific motion prior for efficient Bayesian 3D human body tracking , 2009, Pattern Recognit..

[15]  Shyamsundar Rajaram,et al.  Human Activity Recognition Using Multidimensional Indexing , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Ramakant Nevatia,et al.  3D Human Action Recognition Using Spatio-temporal Motion Templates , 2005, ICCV-HCI.

[17]  Stefano Soatto,et al.  Flexible Dictionaries for Action Classification , 2008 .

[18]  Ramakant Nevatia,et al.  Recognition and Segmentation of 3-D Human Action Using HMM and Multi-class AdaBoost , 2006, ECCV.