首页 | 本学科首页   官方微博 | 高级检索  
     检索      


Accurate 3D action recognition using learning on the Grassmann manifold
Authors:Rim Slama  Hazem Wannous  Mohamed Daoudi  Anuj Srivastava
Institution:1. University of Lille 1, Villeneuve d?Ascq, France;2. LIFL Laboratory/UMR CNRS 8022, Villeneuve d?Ascq, France;3. Institut Mines-Telecom/Telecom Lille, Villeneuve d?Ascq, France;4. Florida State University, Department of Statistics, Tallahassee, USA
Abstract: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.
Keywords:Human action recognition  Grassmann manifold  Observational latency  Depth images  Skeleton  Classification
本文献已被 ScienceDirect 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号