.png){kind=icon}
.png){kind=icon}
Return
Human activity recognition using multi-features and multiple kernel learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2013.11.032.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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. (C) 2013 Elsevier Ltd. All rights reserved.
Keywords:
Human activity recognition
Multiple kernel learning
Spherical harmonics coefficients
Distal limb segments
Support vector machines
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
