Title :
Action Recognition Using Sparse Representation on Covariance Manifolds of Optical Flow
Author :
Guo, Kai ; Ishwar, Prakash ; Konrad, Janusz
Author_Institution :
Dept. of Electr. & Comput. Eng., Boston Univ., Boston, MA, USA
fDate :
Aug. 29 2010-Sept. 1 2010
Abstract :
A novel approach to action recognition in video based on the analysis of optical flow is presented. Properties of optical flow useful for action recognition are captured using only the empirical covariance matrix of a bag of features such as flow velocity, gradient, and divergence. The feature covariance matrix is a low-dimensional representation of video dynamics that belongs to a Riemannian manifold. The Riemannian manifold of covariance matrices is transformed into the vector space of symmetric matrices under the matrix logarithm mapping. The log-covariance matrix of a test action segment is approximated by a sparse linear combination of the log-covariance matrices of training action segments using a linear program and the coefficients of the sparse linear representation are used to recognize actions. This approach based on the unique blend of a logcovariance-descriptor and a sparse linear representation is tested on the Weizmann and KTH datasets. The proposed approach attains leave-one-out cross validation scores of 94.4% correct classification rate for the Weizmann dataset and 98.5% for the KTH dataset. Furthermore, the method is computationally efficient and easy to implement.
Keywords :
covariance matrices; image recognition; linear programming; sparse matrices; video signal processing; KTH datasets; Riemannian manifold; Weizmann datasets; action recognition; covariance manifolds sparse representation; feature covariance matrix; flow velocity; linear programming; log-covariance matrix; matrix logarithm mapping; optical flow; sparse linear combination; test action segmentation; video dynamics; Covariance matrix; Feature extraction; Pixel; Sparse matrices; Symmetric matrices; Training; Vectors;
Conference_Titel :
Advanced Video and Signal Based Surveillance (AVSS), 2010 Seventh IEEE International Conference on
Conference_Location :
Boston, MA
Print_ISBN :
978-1-4244-8310-5
DOI :
10.1109/AVSS.2010.71