期刊
EXPERT SYSTEMS WITH APPLICATIONS
卷 135, 期 -, 页码 194-200出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.eswa.2019.05.055
关键词
Dynamic textures; Randomized neural network; Dynamic texture analysis method
类别
资金
- CNPq (National Council for Scientific and Technological Development, Brazil) [302183/2017-5]
- Sao Paulo Research Foundation (FAPESP) [2016/23763-8]
- CNPq [307797/2014-7, 484312/2013-8]
- FAPESP [14/08026-1, 2016/18809-9]
- Fundacao de Amparo a Pesquisa do Estado de Sao Paulo (FAPESP) [16/23763-8, 14/08026-1] Funding Source: FAPESP
Dynamic texture analysis has been the focus of intensive research in recent years. Thus, this paper presents an innovative and highly discriminative dynamic texture analysis method, whose signature is composed of the weights of the output layer of a randomized neural network after a training procedure. This training is performed by using the pixels of slices of each orthogonal plane of the video (XY, YT, and XT) as input feature vectors and corresponding output labels. The obtained video signature provided an accuracy of 97.05%, 98.54%, 97.74% and 96.51% on the UCLA-50 classes, UCLA-9 classes, UCLA-8 classes and Dyntex++, respectively. These results, when compared to other dynamic texture analysis methods, demonstrate that our descriptors are very effective and that our proposed approach can contribute significantly to the field of dynamic texture analysis. (C) 2019 Elsevier Ltd. 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