首页> 外文期刊>IEEE Transactions on Image Processing >Tangent Fisher Vector on Matrix Manifolds for Action Recognition
【24h】

Tangent Fisher Vector on Matrix Manifolds for Action Recognition

机译:在矩阵歧管的切线fisher传染媒介行动识别的

获取原文
获取原文并翻译 | 示例

摘要

In this paper, we address the problem of representing and recognizing human actions from videos on matrix manifolds. For this purpose, we propose a new vector representation method, named tangent Fisher vector, to describe video sequences in the Fisher kernel framework. We first extract dense curved spatio-temporal cuboids from each video sequence. Compared with the traditional 'straight cuboids', the dense curved spatio-temporal cuboids contain much more local motion information. Each cuboid is then described using a linear dynamical system (LDS) to simultaneously capture the local appearance and dynamics. Furthermore, a simple yet efficient algorithm is proposed to learn the LDS parameters and approximate the observability matrix at the same time. Each video sequence is thus represented by a set of LDSs. Considering that each LDS can be viewed as a point in a Grassmann manifold, we propose to learn an intrinsic GMM on the manifold to cluster the LDS points. Finally a tangent Fisher vector is computed by first accumulating all the tangent vectors in each Gaussian component, and then concatenating the normalized results across all the Gaussian components. A kernel is defined to measure the similarity between tangent Fisher vectors for classification and recognition of a video sequence. This approach is evaluated on the state-of-the-art human action benchmark datasets. The recognition performance is competitive when compared with current state-of-the-art results.
机译:在本文中,我们解决了代表和识别矩阵歧管上的视频的问题。为此目的,我们提出了一种新的向量表示方法,命名为切线Fisher载体,以描述Fisher内核框架中的视频序列。我们首先从每个视频序列中提取密集的弯曲时空立方体。与传统的“直立方体”相比,密集的弯曲时空颞骨码包含更多的本地运动信息。然后使用线性动力系统(LDS)来描述每个长方体,以同时捕获本地外观和动态。此外,提出了一种简单而有效的算法来学习LDS参数并同时近似观察性矩阵。因此,每个视频序列由一组LDS表示。考虑到每个LD可以被视为基层歧管中的一个点,我们建议学习歧管上的内在GMM以聚类LDS点。最后,通过首先在每个高斯组件中累积所有切线矢量来计算切线Fisher载体,然后在所有高斯组件上连接标准化结果。定义内核以测量切线Fish载体之间的相似性,用于对视频序列进行分类和识别。在最先进的人类行动基准数据集上评估这种方法。与当前最先进的结果相比,识别性能是竞争力的。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号