A Unified Framework for 3D Hand Tracking

被引:0
|
作者
Poudel, Rudra P. K. [1 ]
Fonseca, Jose A. S. [1 ]
Zhang, Jian J. [1 ]
Nait-Charif, Hammadi [1 ]
机构
[1] Bournemouth Univ, Pool BH12 5BB, England
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Discriminative techniques are good for hand part detection, however they fail due to sensor noise and high inter-finger occlusion. Additionally, these techniques do not incorporate any kinematic or temporal constraints. Even though model-based descriptive (for example Markov Random Field) or generative (for example Hidden Markov Model) techniques utilize kinematic and temporal constraints well, they are computationally expensive and hardly recover from tracking failure. This paper presents a unified framework for 3D hand tracking, utilizing the best of both methodologies. Hand joints are detected using a regression forest, which uses an efficient voting technique for joint location prediction. The voting distributions are multimodal in nature; hence, rather than using the highest scoring mode of the voting distribution for each joint separately, we fit the five high scoring modes of each joint on a tree-structure Markovian model along with kinematic prior and temporal information. Experimentally, we observed that relying on discriminative technique (i.e. joints detection) produces better results. We therefore efficiently incorporate this observation in our framework by conditioning 50% low scoring joints modes with remaining high scoring joints mode. This strategy reduces the computational cost and produces good results for 3D hand tracking on RGB-D data.
引用
收藏
页码:129 / 139
页数:11
相关论文
共 50 条
  • [1] A Hand Tracking Framework Using the 3D Active Tracking Volume
    Kim, Kyung-Ho
    Jung, Da-Un
    Lee, Seok-Han
    Choi, Jong-Soo
    [J]. PROCEEDINGS OF THE 19TH KOREA-JAPAN JOINT WORKSHOP ON FRONTIERS OF COMPUTER VISION (FCV 2013), 2013, : 159 - 163
  • [2] Hand Tracking Guidance by 3D Printing
    Yu, Sunjin
    Choi, Kwontaeg
    [J]. ADVANCED SCIENCE LETTERS, 2018, 24 (03) : 2036 - 2040
  • [3] A framework for 3D hand tracking and gesture recognition using elements of genetic programming
    El-Sawah, Ayman
    Joslin, Chris
    Georganas, Nicolas D.
    Petriu, Emil M.
    [J]. FOURTH CANADIAN CONFERENCE ON COMPUTER AND ROBOT VISION, PROCEEDINGS, 2007, : 495 - +
  • [4] Tracking as recognition: A stable 3D tracking framework
    Leng, J
    Wang, H
    [J]. 2004 8TH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION, ROBOTICS AND VISION, VOLS 1-3, 2004, : 2303 - 2307
  • [5] AN UNIFIED FRAMEWORK FOR 3D FRAGMENTED OBJECT PATCHING
    Li, Jun-Bao
    Li, Meng
    Shi, Peng
    Pan, Jeng-Shyang
    [J]. INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL, 2010, 6 (12): : 5633 - 5644
  • [6] A Unified 3D Mapping Framework Using a 3D or 2D LiDAR
    Zhen, Weikun
    Scherer, Sebastian
    [J]. PROCEEDINGS OF THE 2018 INTERNATIONAL SYMPOSIUM ON EXPERIMENTAL ROBOTICS, 2020, 11 : 702 - 711
  • [7] A Framework for 3D Object Identification and Tracking
    Chliveros, Georgios
    Figueiredo, Rui P.
    Moreno, Plinio
    Pateraki, Maria
    Bernardino, Alexandre
    Santos-Victor, Jose
    Trahanias, Panos
    [J]. PROCEEDINGS OF THE 2014 9TH INTERNATIONAL CONFERENCE ON COMPUTER VISION, THEORY AND APPLICATIONS (VISAPP 2014), VOL 3, 2014, : 672 - 677
  • [8] 3D hand tracking for human computer interaction
    Prisacariu, Victor Adrian
    Reid, Ian
    [J]. IMAGE AND VISION COMPUTING, 2012, 30 (03) : 236 - 250
  • [9] 3D hand tracking in a Stochastic approximation setting
    Chik, Desmond
    Trumpf, Jochen
    Schraudolph, Nicol N.
    [J]. HUMAN MOTION - UNDERSTANDING, MODELING, CAPTURE AND ANIMATION, PROCEEDINGS, 2007, 4814 : 136 - +
  • [10] Hierarchical Particle Filtering for 3D Hand Tracking
    Makris, Alexandros
    Kyriazis, Nikolaos
    Argyros, Antonis A.
    [J]. 2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2015,