Stereo-based markerless human motion capture for humanoid robot systems

被引:22
作者
Azad, Pedram [1 ]
Ude, Ales [2 ]
Asfour, Tamim [1 ]
Dillmann, Ruediger [1 ]
机构
[1] Univ Karlsruhe TH, Inst Comp Sci & Engn, Karlsruhe, Germany
[2] Jozef Stefan Inst, Ljubljana, Slovenia
来源
PROCEEDINGS OF THE 2007 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-10 | 2007年
关键词
D O I
10.1109/ROBOT.2007.364085
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In this paper, we present an image-based markerless human motion capture system, intended for humanoid robot systems. The restrictions set by this ambitious goal are numerous. The input of the system is a sequence of stereo image pairs only, captured by cameras positioned at approximately eye distance. No artificial markers can be used to simplify the estimation problem. Furthermore, the complexity of all algorithms incorporated must be suitable for real-time application, which is maybe the biggest problem when considering the high dimensionality of the search space. Finally, the system must not depend on a static camera setup and has to find the initial configuration automatically. We present a system, which tackles these problems by combining multiple cues within a particle filter framework, allowing the system to recover from wrong estimations in a natural way. We make extensive use of the benefit of having calibrated stereo setup. To reduce search space implicitly, we use the 3D positions of the hands and the head, computed by a separate hand and head tracker using a linear motion model for each entity to be tracked. With stereo input image sequences at a resolution of 320 x 240 pixels, the processing rate of our system is 15 Hz on a 3 GHz CPU. Experimental results documenting the performance of our system are available in form of several videos.
引用
收藏
页码:3951 / +
页数:2
相关论文
共 50 条
[41]   Stereo-based human head detection from crowd scenes [J].
Huang, XY ;
Li, LY ;
Sim, T .
ICIP: 2004 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1- 5, 2004, :1353-1356
[42]   Morphological approach of stereo camera based human motion capture system [J].
Jun, Sewoong ;
Park, Joongeon ;
Park, Changwoo ;
Jung, Il-Kyun ;
Kim, Yong-Ouk ;
Kim, Bongseok .
2007 INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND SYSTEMS, VOLS 1-6, 2007, :1056-1059
[43]   Human machine interface by using stereo-based depth extraction [J].
Liao, Chao-Kang ;
Wu, Chi-Hao ;
Lin, Hsueh-Yi ;
Chang, Ting-Ting ;
Lin, Tung-Yang ;
Huang, Po-Kuan .
THREE-DIMENSIONAL IMAGE PROCESSING, MEASUREMENT (3DIPM), AND APPLICATIONS 2014, 2014, 9013
[44]   Motion capture-based wearable interaction system and its application to a humanoid robot, AMIO [J].
Seo, Yong-Ho ;
Jeong, Il-Woong ;
Yang, Hyun S. .
ADVANCED ROBOTICS, 2007, 21 (15) :1725-1741
[45]   The evolution of methods for the capture of human movement leading to markerless motion capture for biomechanical applications [J].
Lars Mündermann ;
Stefano Corazza ;
Thomas P Andriacchi .
Journal of NeuroEngineering and Rehabilitation, 3
[46]   Markerless Human Motion Capture from Voxel Reconstruction with Simple Human Model [J].
Takahashi, Kazuhiko ;
Nagasawa, Yusuke ;
Hashimoto, Masafumi .
JOURNAL OF ADVANCED MECHANICAL DESIGN SYSTEMS AND MANUFACTURING, 2008, 2 (06) :985-997
[47]   Teleoperation Control of Baxter Robot based on Human Motion Capture [J].
Peng, Guangzhu ;
Yang, Chenguang ;
Jiang, Yiming ;
Cheng, Long ;
Liang, Peidong .
2016 IEEE INTERNATIONAL CONFERENCE ON INFORMATION AND AUTOMATION (ICIA), 2016, :1026-1031
[48]   Markerless motion capture systems for tracking of persons in forensic biomechanics: an overview [J].
Yang, Sylvia X. M. ;
Christiansen, Martin S. ;
Larsen, Peter K. ;
Alkjaer, Tine ;
Moeslund, Thomas B. ;
Simonsen, Erik B. ;
Lynnerup, Niels .
COMPUTER METHODS IN BIOMECHANICS AND BIOMEDICAL ENGINEERING-IMAGING AND VISUALIZATION, 2014, 2 (01) :46-65
[49]   Stereo-based preprocessing for human shape localization in unstructured environments [J].
Broggi, A ;
Fascioli, A ;
Fedriga, I ;
Tibaldi, A ;
Del Rose, M .
IEEE IV2003: INTELLIGENT VEHICLES SYMPOSIUM, PROCEEDINGS, 2003, :410-415
[50]   Human motion oriented control method for humanoid robot [J].
Imai, H ;
Nozawa, M ;
Kawamura, Y ;
Sankai, Y .
IEEE ROMAN 2002, PROCEEDINGS, 2002, :211-216