...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neural processing letters >A Review of Dynamic Maps for 3D Human Motion Recognition Using ConvNets and Its Improvement
【24h】

A Review of Dynamic Maps for 3D Human Motion Recognition Using ConvNets and Its Improvement

机译：探讨与改进的3D人体运动识别动态地图述评

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

RGB-D based action recognition is attracting more and more attention in both the research and industrial communities. However, due to the lack of training data, pre-training based methods are popular in this field. This paper presents a review of the concept of dynamic maps for RGB-D based human motion recognition using pretrained models in image domain. The dynamic maps recursively encode the spatial, temporal and structural information contained in the video sequence into dynamic motion images simultaneously. They enable the usage of Convolutional Neural Network and its pretained models on ImageNet for 3D human motion recognition. This simple, compact and effective representation achieves state-of-the-art results on various gesture/action/activities recognition datasets. Based on the review of previous methods using this concept upon different modalities (depth, skeleton or RGB-D data), a novel encoding scheme is developed and presented in this paper. The improved method generates effective flow-guided dynamic maps, and they could select the high motion window and distinguish the order among the frames with small motion. The improved flow-guided dynamic maps achieve state-of-the-art results on the large Chalearn LAP IsoGD and NTU RGB+D datasets.
机译：基于RGB-D的动作识别在研究和工业社区中吸引了越来越多的关注。但是，由于缺乏培训数据，基于预先训练的方法在该领域很受欢迎。本文在图像域中使用预读模型，对基于RGB-D基于人的运动识别的动态地图的概念进行了审查。动态映射同时递归地将视频序列中包含的空间，时间和结构信息进行编码为动态运动图像。它们能够使用卷积神经网络及其预防模型的3D人体运动识别。这种简单，紧凑且有效的表示实现了各种手势/动作/活动识别数据集的最先进结果。基于使用此概念在不同模式（深度，骨架或RGB-D数据）上使用此概念的审查，本文开发并介绍了一种新颖的编码方案。改进的方法产生有效的流动引导的动态图，并且它们可以选择高运动窗口并区分具有小运动的帧中的顺序。改进的流动引导的动态图在大Chalearn LAP ISOGD和NTU RGB + D数据集上实现最先进的结果。

著录项

  • 来源
    《Neural processing letters》 |2020年第2期|1501-1515|共15页
  • 作者

    Zhimin Gao; Pichao Wang; Huogen Wang; Mingliang Xu; Wanqing Li;

  • 作者单位

    School of Information Engineering Zhengzhou University Zhengzhou. China;

    Alibaba Group (U.S.) Inc. Bellevue WA USA;

    School of Electrical and Information Engineer Tianjin University Tianjin China;

    School of Information Engineering Zhengzhou University Zhengzhou. China;

    Advanced Multimedia Research Lab University of Wollongong Wollongong Australia;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Dynamic maps; 3D human motion recognition; ConvNets;

    机译：动态地图;3D人类运动识别;Convnets.;

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