Lie-X : Depth Image Based Articulated Object Pose Estimation, Tracking, and Action Recognition on Lie Groups
作者: Chi XuLakshmi Narasimhan GovindarajanYu ZhangLi Cheng
作者单位: 1Bioinformatics Institute, A*STAR
2National University of Singapore
刊名: International Journal of Computer Vision, 2017, Vol.123 (3), pp.454-478
来源数据库: Springer Nature Journal
DOI: 10.1007/s11263-017-0998-6
关键词: Depth imagesPose estimationFishMouseHuman handLie group
英文摘要: Pose estimation, tracking, and action recognition of articulated objects from depth images are important and challenging problems, which are normally considered separately. In this paper, a unified paradigm based on Lie group theory is proposed, which enables us to collectively address these related problems. Our approach is also applicable to a wide range of articulated objects. Empirically it is evaluated on lab animals including mouse and fish, as well as on human hand. On these applications, it is shown to deliver competitive results compared to the state-of-the-arts, and non-trivial baselines including convolutional neural networks and regression forest methods. Moreover, new sets of annotated depth data of articulated objects are created which, together with our code, are made...
原始语种摘要: Pose estimation, tracking, and action recognition of articulated objects from depth images are important and challenging problems, which are normally considered separately. In this paper, a unified paradigm based on Lie group theory is proposed, which enables us to collectively address these related problems. Our approach is also applicable to a wide range of articulated objects. Empirically it is evaluated on lab animals including mouse and fish, as well as on human hand. On these applications, it is shown to deliver competitive results compared to the state-of-the-arts, and non-trivial baselines including convolutional neural networks and regression forest methods. Moreover, new sets of annotated depth data of articulated objects are created which, together with our code, are made...
全文获取路径: Springer Nature  (合作)
分享到:
来源刊物:
影响因子:3.623 (2012)

×
关键词翻译
关键词翻译
  • Tracking 追踪
  • Recognition 识别
  • Action 
  • articulated 铰链的
  • recognition 识别
  • estimation 估计
  • convolutional 卷积
  • action 行为
  • unified 统一
  • separately 个别的