For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Pose Estimation with Action Classification Using Global-and-Pose Features and Fine-Grained Action-Specific Pose Models
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2018/03/01
Online ISSN: 1745-1361
Type of Manuscript: PAPER
Category: Image Recognition, Computer Vision
human action classification, human pose estimation, action-specific pose models,
Full Text: PDF(2.1MB)
>>Buy this Article
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.