A Spatio-Temporal Descriptor Based on 3D-Gradients

A Spatio-Temporal Descriptor Based on 3D-Gradients
复制标题

DOI:
10.5244/c.22.99
复制
发表时间:
2008-09
期刊:
--
影响因子:
--
通讯作者:
Alexander Kläser;Marcin Marszalek;C. Schmid
Alexander Kläser;Marcin Marszalek;C. Schmid
中科院分区:
其他
文献类型:
--
作者:
Alexander Kläser;Marcin Marszalek;C. Schmid

文献摘要

被引文献

相似文献

在这项工作中,我们为视频序列提出了一种新颖的局部描述符。所提出的描述符基于有向3D时空梯度的直方图。我们的贡献有四个方面。(i)为了计算任意尺度的3D梯度,我们开发了一种基于积分视频的高效存储算法。(ii)我们提出了一种基于正多面体的通用3D方向量化方法。(iii)我们对所有描述符参数进行了深入评估,并针对动作识别对其进行了优化。(iv)我们将我们的描述符应用于各种动作数据集(KTH、魏茨曼、好莱坞),并表明我们的性能优于现有技术。
In this work, we present a novel local descriptor for video sequences. The proposed descriptor is based on histograms of oriented 3D spatio-temporal gradients. Our contribution is four-fold. (i) To compute 3D gradients for arbitrary scales, we develop a memory-efficient algorithm based on integral videos. (ii) We propose a generic 3D orientation quantization which is based on regular polyhedrons. (iii) We perform an in-depth evaluation of all descriptor parameters and optimize them for action recognition. (iv) We apply our descriptor to various action datasets (KTH, Weizmann, Hollywood) and show that we outperform the state-of-the-art.