首页> 外文会议>IEEE/CVF Conference on Computer Vision and Pattern Recognition >You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactions
【24h】

You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactions

机译:You2Me:通过第一人称和第二人称互动推断自我中心视频中的身体姿势

获取原文

摘要

The body pose of a person wearing a camera is of great interest for applications in augmented reality, healthcare, and robotics, yet much of the person's body is out of view for a typical wearable camera. We propose a learning-based approach to estimate the camera wearer's 3D body pose from egocentric video sequences. Our key insight is to leverage interactions with another person---whose body pose we can directly observe---as a signal inherently linked to the body pose of the first-person subject. We show that since interactions between individuals often induce a well-ordered series of back-and-forth responses, it is possible to learn a temporal model of the interlinked poses even though one party is largely out of view. We demonstrate our idea on a variety of domains with dyadic interaction and show the substantial impact on egocentric body pose estimation, which improves the state of the art.
机译:佩戴相机的人的身体姿势对于增强现实,医疗保健和机器人技术中的应用非常感兴趣,但是对于典型的可佩戴式相机,该人的大部分身体视而不见。我们提出了一种基于学习的方法,可以从以自我为中心的视频序列中估算出相机佩戴者的3D身体姿势。我们的主要见解是利用与他人的互动-我们可以直接观察到的人体姿态-作为与第一人称主体的人体姿态固有相关的信号。我们表明,由于个人之间的交互通常会引起一系列有序的来回响应,因此即使一方不在很大程度上,也可以学习相互联系的姿势的时间模型。我们通过二元互动展示了我们在各种领域中的想法,并展示了对以自我为中心的人体姿势估计的重大影响,从而改善了现有技术。

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