Accurate 3D action recognition using learning on the Grassmann manifold

PATTERN RECOGNITION

卷:48

Article

Slama, Rim^1,2  Wannous, Hazem^1,2  Daoudi, Mohamed^2,3  Srivastava, Anuj⁴ 

[1] Univ Lille 1, F-59655 Villeneuve Dascq, France

[2] CNRS, UMR 8022, LIFL Lab, Villeneuve Dascq, France

[3] Inst Mines Telecom Telecom Lille, Villeneuve Dascq, France

[4] Florida State Univ, Dept Stat, Tallahassee, FL 32306 USA

关键词: Human action recognition;    Grassmann manifold;    Observational latency;    Depth images;    Skeleton;    Classification;   

DOI  :  10.1016/j.patcog.2014.08.011

来源: Elsevier

【 摘 要 】

In this paper we address the problem of modeling and analyzing human motion by focusing on 3D body skeletons. Particularly, our intent is to represent skeletal motion in a geometric and efficient way, leading to an accurate action-recognition system. Here an action is represented by a dynamical system whose observability matrix is characterized as an element of a Grassmann manifold. To formulate our learning algorithm, we propose two distinct ideas: (1) in the first one we perform classification using a Truncated Wrapped Gaussian model, one for each class in its own tangent space. (2) In the second one we propose a novel learning algorithm that uses a vector representation formed by concatenating local coordinates in tangent spaces associated with different classes and training a linear SVM. We evaluate our approaches on three public 3D action datasets: MSR-action 3D, UT-kinect and UCF-kinect datasets; these datasets represent different kinds of challenges and together help provide an exhaustive evaluation. The results show that our approaches either match or exceed state-of-the-art performance reaching 91.21% on MSR-action 3D, 97.91% on UCF-kinect, and 88.5% on UT-kinect. Finally, we evaluate the latency, i.e. the ability to recognize an action before its termination, of our approach and demonstrate improvements relative to other published approaches. (C)2014 Elsevier Ltd. All rights reserved.

【 授权许可】

Free