Research On Action Recognition Based On Pose Estimation

The human pose estimation is a very popular problem in computer vision. In this work, we consider the problem of pose estimation and action recognition on the static images and propose a new method to solve this matter. This is a challenging task due to the high degrees of freedom of body poses and lack of any motion cues. Specially, we build a pool of pose experts, each of which individually models a particular type of articulation for a group of human bodies with similar poses or semantics(actions). We investigate two ways to construct these pose experts and show that this method leads to improved pose estimation performance under difficult conditions. We test our model on two public datasets, our experiments on public datasets demonstrate the feasibility and effectiveness of the proposed methods.Furthermore, in contrast to previous wisdoms of combining the output of each pose expert for action recognition using such method as majority voting, we propose a flexible strategy which adaptively integrates them in a discriminative framework, allowing each pose expert to adjust their roles in action prediction according to their specificity when facing different action types. In particular, the spatial relationship between estimated part locations from each expert is encoded in a graph structure, capturing both the non-local and local spatial correlation of the body shape. Each graph is then treated as a separate group, on which an overall group sparse constraint is imposed to train the prediction model, with extra weight added according to the confidence of the corresponding expert. We show in our experiments on a challenging web data set with state of the art results that our method effectively improves the tolerance of our system to imperfect pose estimation.