• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International symposium on multispectral image processing and pattern recognition >Improved Dense Trajectories for Action Recognition based on Random projection and Fisher vectors
【24h】

Improved Dense Trajectories for Action Recognition based on Random projection and Fisher vectors

机译：基于随机投影和Fisher向量的改进的密集轨迹用于动作识别

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

As an important application of intelligent monitoring system, the action recognition in video has become a very important research area of computer vision. In order to improve the accuracy rate of the action recognition in video with improved dense trajectories, one advanced vector method is introduced. Improved dense trajectories combine Fisher Vector with Random Projection. The method realizes the reduction of the characteristic trajectory though projecting the high-dimensional trajectory descriptor into the low-dimensional subspace based on defining and analyzing Gaussian mixture model by Random Projection. And a GMM-FV hybrid model is introduced to encode the trajectory feature vector and reduce dimension. The computational complexity is reduced by Random Projection which can drop Fisher coding vector. Finally, a Linear SVM is used to classifier to predict labels. We tested the algorithm in UCF101 dataset and KTH dataset. Compared with existed some others algorithm, the result showed that the method not only reduce the computational complexity but also improved the accuracy of action recognition.
机译：视频中的动作识别作为智能监控系统的重要应用，已经成为计算机视觉研究的重要领域。为了提高具有密集轨迹的视频中动作识别的准确率，提出了一种先进的矢量方法。改进的密集轨迹将Fisher向量与随机投影结合在一起。通过基于随机投影定义和分析高斯混合模型，该方法通过将高维轨迹描述符投影到低维子空间中来实现特征轨迹的减少。引入了GMM-FV混合模型对轨迹特征向量进行编码并减小维数。随机投影可以降低Fisher编码向量，从而降低了计算复杂度。最后，将线性SVM用于分类器以预测标签。我们在UCF101数据集和KTH数据集中测试了该算法。与已有算法相比，该方法不仅降低了运算量，而且提高了动作识别的准确性。

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