Human Action Recognition using Direction and Magnitude Models of Motion

This paper proposes an approach that uses direction and magnitude models to perform human action recognition from videos captured using monocular cameras. A mixture distribution is computed over the motion orientations and magnitudes of optical flow vectors at each spatial location of the video sequence. This mixture is estimated using an online k-means clustering algorithm. Thus, a sequence model which is composed of a direction model and a magnitude model is created by circular and non-circular clustering. Human actions are recognized via a metric based on the Bhattacharyya distance that compares the model of a query sequence with the models created from the training sequences. The proposed approach is validated using two public datasets in both indoor and outdoor environments with low and high resolution videos.

[1]  Aaron F. Bobick,et al.  Recognition of Visual Activities and Interactions by Stochastic Parsing , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Yassine Benabbas,et al.  Multi-Modal User Interactions in Controlled Environments , 2010 .

[3]  Xinghua Sun,et al.  Action recognition via local descriptors and holistic features , 2009, 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[4]  Christopher Leckie,et al.  Action recognition via multi-feature fusion and Gaussian process classification , 2009, 2009 Workshop on Applications of Computer Vision (WACV).

[5]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[6]  Luc Van Gool,et al.  An Efficient Dense and Scale-Invariant Spatio-Temporal Interest Point Detector , 2008, ECCV.

[7]  Sotirios P. Chatzis,et al.  A framework for robust visual behavior recognition based on holistic representations and multicamera information fusion , 2010 .

[8]  Thomas Mauthner,et al.  Instant Action Recognition , 2009, SCIA.

[9]  Ruzena Bajcsy,et al.  Recognition of Human Actions using an Optimal Control Based Motor Model , 2008, 2008 IEEE Workshop on Applications of Computer Vision.

[10]  Pierre Kornprobst,et al.  Action Recognition Using a Bio-Inspired Feedforward Spiking Network , 2009, International Journal of Computer Vision.

[11]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Shaogang Gong,et al.  Action categorization with modified hidden conditional random field , 2010, Pattern Recognit..

[13]  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.

[14]  Cordelia Schmid,et al.  Evaluation of Local Spatio-temporal Features for Action Recognition , 2009, BMVC.

[15]  Cordelia Schmid,et al.  A Spatio-Temporal Descriptor Based on 3D-Gradients , 2008, BMVC.

[16]  Ivan Laptev,et al.  Velocity adaptation of space-time interest points , 2004, ICPR 2004.

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

[18]  P. KaewTrakulPong,et al.  An Improved Adaptive Background Mixture Model for Real-time Tracking with Shadow Detection , 2002 .

[19]  Christopher Joseph Pal,et al.  Activity recognition using the velocity histories of tracked keypoints , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[20]  Wei Huang,et al.  Human action recognition using Recursive Self Organizing map and longest common subsequence matching , 2009, 2009 Workshop on Applications of Computer Vision (WACV).

[21]  Yang Wang,et al.  Efficient Human Action Detection Using a Transferable Distance Function , 2009, ACCV.

[22]  Cordelia Schmid,et al.  Learning realistic human actions from movies , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[23]  Greg Mori,et al.  Action recognition by learning mid-level motion features , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[24]  J.-Y. Bouguet,et al.  Pyramidal implementation of the lucas kanade feature tracker , 1999 .

[25]  Mubarak Shah,et al.  Human Action Recognition in Videos Using Kinematic Features and Multiple Instance Learning , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[27]  Rama Chellappa,et al.  Machine Recognition of Human Activities: A Survey , 2008, IEEE Transactions on Circuits and Systems for Video Technology.

[28]  Simone Calderara,et al.  Using circular statistics for trajectory shape analysis , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[29]  G. Jansson,et al.  Perceiving events and objects , 2013 .

[30]  Sotirios Chatzis,et al.  Robust Visual Behavior Recognition , 2010, IEEE Signal Processing Magazine.