IEICE Transactions on Information and Systems
Online ISSN : 1745-1361
Print ISSN : 0916-8532
Regular Section
Pose Estimation with Action Classification Using Global-and-Pose Features and Fine-Grained Action-Specific Pose Models
Norimichi UKITA
Author information

2018 Volume E101.D Issue 3 Pages 758-766


This paper proposes an iterative scheme between human action classification and pose estimation in still images. Initial action classification is achieved only by global image features that consist of the responses of various object filters. The classification likelihood of each action weights human poses estimated by the pose models of multiple sub-action classes. Such fine-grained action-specific pose models allow us to robustly identify the pose of a target person under the assumption that similar poses are observed in each action. From the estimated pose, pose features are extracted and used with global image features for action re-classification. This iterative scheme can mutually improve action classification and pose estimation. Experimental results with a public dataset demonstrate the effectiveness of the proposed method both for action classification and pose estimation.

Information related to the author
© 2018 The Institute of Electronics, Information and Communication Engineers
Previous article Next article