• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Arabian Journal for Science and Engineering. Section A, Sciences >Multiple Batches of Motion History Images (MB-MHIs) for Multi-view Human Action Recognition
【24h】

Multiple Batches of Motion History Images (MB-MHIs) for Multi-view Human Action Recognition

机译：多批次的运动历史图像（MB-MHI），用于多视图人类行动识别

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The recognition of human actions recorded in a multi-camera environment faces the challenging issue of viewpoint variation. Multi-view methods employ videos from different views to generate a compact view-invariant representation of human actions. This paper proposes a novel multi-view human action recognition approach that uses multiple low-dimensional temporal templates and a reconstruction-based encoding scheme. The proposed approach is based upon the extraction of multiple 2D motion history images (MHIs) of human action videos over non-overlapping temporal windows, constructing multiple batches of motion history images (MB-MHIs). Then, two kinds of descriptions are computed for these MHIs batches based on (1) a deep residual network (ResNet) and (2) histogram of oriented gradients (HOG) to effectively quantify a change in gradient. ResNet descriptions are average pooled at each batch. HOG descriptions are processed independently at each batch to learn a class-based dictionary using a K-spectral value decomposition algorithm. Later, the sparse codes of feature descriptions are obtained using an orthogonal matching pursuit approach. These sparse codes are average pooled to extract encoded feature vectors. Then, encoded feature vectors at each batch are fused to form a final view-invariant feature representation. Finally, a linear support vector machine classifier is trained for action recognition. Experimental results are given on three versions of a multi-view dataset:MuHAVi-8, MuHAVi-14, and MuHAVi-uncut. The proposed approach shows promising results when tested for a novel camera. Results on deep features indicate that action representation by MB-MHIs is more view-invariant than single MHIs.
机译：识别在多相机环境中记录的人类行为面临着挑战性的观点变化问题。多视图方法采用不同视图的视频，以生成人类动作的紧凑视图不变表示。本文提出了一种新颖的多视图人体行动识别方法，它使用多个低维时间模板和基于重建的编码方案。该方法基于在非重叠时间窗口上提取人类动作视频的多个2D运动历史图像（MHIS），构建多批次的运动历史图像（MB-MHI）。然后，基于（1）基于（1）的深度残余网络（Reset）和（2）的面向梯度（HOG）直方图来计算两种描述，以有效地量化梯度的变化。 Reset描述是每个批处理池的平均值。在每个批处理上独立地处理生猪描述，以学习基于类的字典，使用k光谱值分解算法。稍后，使用正交匹配的追踪方法获得特征描述的稀疏代码。这些稀疏代码是平均池，以提取编码的特征向量。然后，每个批处理的编码特征向量被融合以形成最终视图不变特征表示。最后，接受线性支持向量机分类器进行动作识别。实验结果给出了三种版本的多视图数据集：Muhavi-8，Muhavi-14和Muhavi-Uncut。所提出的方法显示了在测试小型相机时的有希望的结果。深度特征的结果表明MB-MHI的动作表示比单个MHI更加视图。

著录项

  • 来源
  • 作者

    Hajra Binte Naeem; Fiza Murtaza; Muhammad Haroon Yousaf; Sergio A. Velastin;

  • 作者单位

    Department of Computer Engineering University of Engineering and Technology Taxila 47080 Pakistan;

    Department of Computer Engineering University of Engineering and Technology Taxila 47080 Pakistan;

    Department of Computer Engineering University of Engineering and Technology Taxila 47080 Pakistan Swarm Robotics Lab National Centre for Robotics and Automation University of Engineering and Technology Taxila Pakistan;

    School of Electronic Engineering and Computer Science Queen Mary University of London London E1 4NS UK Zebra Technologies Corp. London SE1 9LQ UK Department of Computer Science and Engineering University Carlos Ⅲ de Madrid 28270 Colmenarejo Spain;

  • 收录信息 美国《科学引文索引》(SCI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Human action recognition; Motion history images; Sparse coding; MuHAVi; Multi-view;

    机译：人类行动认可;运动历史图像;稀疏编码;穆罕默德;多视图;

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