Fitting, Comparison, and Alignment of Trajectories on Positive Semi-Definite Matrices with Application to Action Recognition
This is an incremental improvement for action recognition in computer vision, focusing on skeleton-based methods.
The paper tackles action recognition using body skeletons by representing video frames as trajectories on the Riemannian manifold of positive-semidefinite matrices with a new metric and algorithms for curve fitting and temporal alignment. The results show competitive performance with state-of-the-art methods on three datasets (UTKinect-Action3D, KTH-Action, UAV-Gesture), using only skeleton data.
In this paper, we tackle the problem of action recognition using body skeletons extracted from video sequences. Our approach lies in the continuity of recent works representing video frames by Gramian matrices that describe a trajectory on the Riemannian manifold of positive-semidefinite matrices of fixed rank. In comparison with previous works, the manifold of fixed-rank positive-semidefinite matrices is here endowed with a different metric, and we resort to different algorithms for the curve fitting and temporal alignment steps. We evaluated our approach on three publicly available datasets (UTKinect-Action3D, KTH-Action and UAV-Gesture). The results of the proposed approach are competitive with respect to state-of-the-art methods, while only involving body skeletons.