期刊
OPTIK
卷 126, 期 9-10, 页码 882-887出版社
ELSEVIER GMBH
DOI: 10.1016/j.ijleo.2015.02.053
关键词
Compressive sensing; Dimensionality reduction; Action recognition
类别
资金
- NSAF [11176018]
- National Natural Science Foundation of China [61471248]
- Robot Technology Used for Special Environment Key Laboratory of Sichuan Province [14zxtk03]
- Promotive Research Fund for Young Middle-aged Scientists of Shandong Province [BS2014DX009]
We propose a new dimensionality reduction method called compressive sensing with Gaussian mixture random matrix (CS-GMRM), in which a novel measurement matrix using Gaussian mixture distribution is constructed and is proved to satisfy the restricted isometry property. The CS-GMRM method projects high-dimensional vector spaces into low-dimensional ones via a single matrix multiplication. In particular, the proposed method removes the need of a training process, preserves the metric information of the original vector space, and requires a low level of computational complexity. We apply our method to the problem of recognizing human action from video sequences. Experimental results show that the proposed method is simultaneously highly effective and highly efficient for action recognition, and outperforms the state-of-the-art dimensionality reduction methods. (C) 2015 Elsevier GmbH. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据