View-Invariant Action Recognition Based on Action Graphs

This paper proposes a weighted codebook vector representation and an action graph model for view-invariant human action recognition. A video is represented as a weighted codebook vector combining dynamic interest points and static shapes. This combined representation has strong noise robusticity and high classification performance on static actions. Several 3D key poses are extracted from the motion capture data or points cloud data, and a set of primitive motion segments are generated. A directed graph called Essential Graph is built of these segments according to self-link, forward-link and back-link. Action Graph is generated from the essential graph projected from a wide range of viewpoints. This paper uses Naive Bayes to train a statistical model for each node. Given an unlabeled video, Viterbi algorithm is used for computing the match score between the video and the action graph. The video is then labeled based on the maximum score. Finally, the algorithm is tested on the IXMAS dataset, and the CMU motion capture library. The experimental results demonstrate that this algorithm can recognize the

[1]  David A. Forsyth,et al.  Searching Video for Complex Activities with Finite State Models , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Ferdinand van der Heijden,et al.  Efficient adaptive density estimation per image pixel for the task of background subtraction , 2006, Pattern Recognit. Lett..

[3]  Dariu Gavrila,et al.  The Visual Analysis of Human Movement: A Survey , 1999, Comput. Vis. Image Underst..

[4]  Juan Carlos Niebles,et al.  Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words , 2006, BMVC.

[5]  David A. Forsyth,et al.  Automatic Annotation of Everyday Movements , 2003, NIPS.

[6]  Roberto Cipolla,et al.  Extracting Spatiotemporal Interest Points using Global Information , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[7]  Rémi Ronfard,et al.  Free viewpoint action recognition using motion history volumes , 2006, Comput. Vis. Image Underst..

[8]  Rama Chellappa,et al.  View Invariance for Human Action Recognition , 2005, International Journal of Computer Vision.

[9]  Xu Guang-You,et al.  Viewpoint Independent Action Recognition , 2008 .

[10]  Barbara Caputo,et al.  Recognizing human actions: a local SVM approach , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[11]  Mubarak Shah,et al.  Actions sketch: a novel action representation , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[12]  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.

[13]  Adrian Hilton,et al.  A survey of advances in vision-based human motion capture and analysis , 2006, Comput. Vis. Image Underst..

[14]  Mohiuddin Ahmad,et al.  Human action recognition using shape and CLG-motion flow from multi-view image sequences , 2008, Pattern Recognit..

[15]  I. Patras,et al.  Spatiotemporal salient points for visual recognition of human actions , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[16]  Rémi Ronfard,et al.  Automatic Discovery of Action Taxonomies from Multiple Views , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[17]  Yiannis Aloimonos,et al.  View-Invariant Modeling and Recognition of Human Actions Using Grammars , 2006, WDV.

[18]  Serge J. Belongie,et al.  Behavior recognition via sparse spatio-temporal features , 2005, 2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance.

[19]  Z. Zivkovic.  Improved adaptive Gaussian mixture model for background subtraction , 2004, ICPR 2004.

[20]  Rémi Ronfard,et al.  Action Recognition from Arbitrary Views using 3D Exemplars , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[21]  Jake K. Aggarwal,et al.  Human motion: modeling and recognition of actions and interactions , 2004, Proceedings. 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 2004. 3DPVT 2004..

[22]  James W. Davis,et al.  The Recognition of Human Movement Using Temporal Templates , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  Ivan Laptev,et al.  On Space-Time Interest Points , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[24]  Mohiuddin Ahmad,et al.  HMM-based Human Action Recognition Using Multiview Image Sequences , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[25]  Jitendra Malik,et al.  Recognizing action at a distance , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[26]  Tae-Kyun Kim,et al.  Learning Motion Categories using both Semantic and Structural Information , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[27]  Ronen Basri,et al.  Actions as space-time shapes , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[28]  Tieniu Tan,et al.  Recent developments in human motion analysis , 2003, Pattern Recognit..