期刊
IMAGE AND VISION COMPUTING
卷 55, 期 -, 页码 149-157出版社
ELSEVIER
DOI: 10.1016/j.imavis.2016.04.010
关键词
Human action recognition; Classifier combination; Dempster-Shafer evidence theory; Rejection; Actionlet; HON4D
In this paper, we propose a comprehensive solution to 3D human action recognition including feature extraction, classification, and multiple classifier combination. We effectively present two feature extraction methods, four different types of well-known classifiers, and four multiple classifier combination strategies including a specially designed belief based method. In order to enhance the recognition accuracy, we propose a new rejection criterion based on the conflict from the information sources: the classifier outputs. We test our method on the MSRAction 3D dataset. Discarding examples using the conflict based criterion shows superior results than other combination approaches. Moreover this criterion allows choosing a tradeoff between the performance and rejection rate. (C) 2016 Elsevier B.V. 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