• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neural Networks and Learning Systems, IEEE Transactions on >Learning a Tracking and Estimation Integrated Graphical Model for Human Pose Tracking
【24h】

Learning a Tracking and Estimation Integrated Graphical Model for Human Pose Tracking

机译：学习用于人体姿势跟踪的跟踪和估计集成图形模型

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

We investigate the tracking of 2-D human poses in a video stream to determine the spatial configuration of body parts in each frame, but this is not a trivial task because people may wear different kinds of clothing and may move very quickly and unpredictably. The technology of pose estimation is typically applied, but it ignores the temporal context and cannot provide smooth, reliable tracking results. Therefore, we develop a tracking and estimation integrated model (TEIM) to fully exploit temporal information by integrating pose estimation with visual tracking. However, joint parsing of multiple articulated parts over time is difficult, because a full model with edges capturing all pairwise relationships within and between frames is loopy and intractable. In previous models, approximate inference was usually resorted to, but it cannot promise good results and the computational cost is large. We overcome these problems by exploring the idea of divide and conquer, which decomposes the full model into two much simpler tractable submodels. In addition, a novel two-step iteration strategy is proposed to efficiently conquer the joint parsing problem. Algorithmically, we design TEIM very carefully so that: 1) it enables pose estimation and visual tracking to compensate for each other to achieve desirable tracking results; 2) it is able to deal with the problem of tracking loss; and 3) it only needs past information and is capable of tracking online. Experiments are conducted on two public data sets in the wild with ground truth layout annotations, and the experimental results indicate the effectiveness of the proposed TEIM framework.
机译：我们调查了视频流中二维人体姿势的跟踪以确定每个帧中身体部位的空间配置，但这并不是一件容易的事，因为人们可能穿着不同种类的衣服，并且移动得非常迅速且无法预测。姿态估计技术通常被应用，但是它忽略了时间上下文并且不能提供平滑，可靠的跟踪结果。因此，我们开发了一种跟踪和估计集成模型（TEIM），通过将姿势估计与视觉跟踪相集成来充分利用时间信息。但是，随着时间的推移，多个关节部分的联合解析是困难的，因为具有捕获帧内和帧之间所有成对关系的边缘的完整模型是有环且难处理的。在以前的模型中，通常采用近似推理，但是它不能保证良好的结果，并且计算量很大。我们通过探索分而治之的思想克服了这些问题，该思想将整个模型分解为两个更简单易处理的子模型。此外，提出了一种新颖的两步迭代策略来有效地克服联合解析问题。在算法上，我们非常仔细地设计TEIM，以便：1）它使姿势估计和视觉跟踪能够相互补偿，以实现理想的跟踪结果； 2）能够处理跟踪损耗的问题； 3）它只需要过去的信息，并且能够在线跟踪。在野外使用地面实况布局注释对两个公共数据集进行了实验，实验结果表明了所提出的TEIM框架的有效性。

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