首页 | 本学科首页   官方微博 | 高级检索  
     


Human activity recognition using multi-features and multiple kernel learning
Authors:Salah Althloothi  Mohammad H. Mahoor  Xiao Zhang  Richard M. Voyles
Affiliation:1. Department of Electrical and Computer Engineering, University of Denver, CO 80208, USA;2. College of Technology, Purdue University, West Lafayette, IN 47907, USA
Abstract:This paper presents two sets of features, shape representation and kinematic structure, for human activity recognition using a sequence of RGB-D images. The shape features are extracted using the depth information in the frequency domain via spherical harmonics representation. The other features include the motion of the 3D joint positions (i.e. the end points of the distal limb segments) in the human body. Both sets of features are fused using the Multiple Kernel Learning (MKL) technique at the kernel level for human activity recognition. Our experiments on three publicly available datasets demonstrate that the proposed features are robust for human activity recognition and particularly when there are similarities among the actions.
Keywords:Human activity recognition   Multiple kernel learning   Spherical harmonics coefficients   Distal limb segments   Support vector machines
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