Data

Software for Ground-truthing Articulated Tracking via Virtual Markers

Curtin University
Patrick Peursum (Managed by)
Viewed: [[ro.stat.viewed]] Cited: [[ro.stat.cited]] Accessed: [[ro.stat.accessed]]
ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rfr_id=info%3Asid%2FANDS&rft_id=http://ddfe.curtin.edu.au/impca/gttrackvm/&rft.title=Software for Ground-truthing Articulated Tracking via Virtual Markers&rft.publisher=Curtin University&rft.description=This is a small Matlab GUI utility to ease the tedious task of defining the ground-truth 2D (x,y) location of body joints for articulated human body tracking in videos that have no associated motion capture data. The system partially automates the task of defining the 'virtual markers' by predicting a joint's (x,y) position in the next frame via template matching, and a human can correct the prediction interactively if necessary. For each joint, it takes 5-10 minutes to ground-truth 500 frames of video. Under Windows, any installed AVI codec is supported; under Unix Matlab only supports raw video.&rft.creator=Anonymous&rft.date=2013&rft.relation=http://dx.doi.org/10.1109/CVPR.2007.383130&rft.relation=http://dx.doi.org/10.1007/s11263-009-0205-5&rft_subject=Tracking&rft_subject=Computer Vision&rft_subject=INFORMATION AND COMPUTING SCIENCES&rft_subject=ARTIFICIAL INTELLIGENCE AND IMAGE PROCESSING&rft.type=dataset&rft.language=English Access the data
Cite Saved to MyRDA Save to MyRDA

Access:

Open view details

The software is provided freely for research-only purposes under GPL V2 license.


Brief description

This is a small Matlab GUI utility to ease the tedious task of defining the ground-truth 2D (x,y) location of body joints for articulated human body tracking in videos that have no associated motion capture data. The system partially automates the task of defining the 'virtual markers' by predicting a joint's (x,y) position in the next frame via template matching, and a human can correct the prediction interactively if necessary. For each joint, it takes 5-10 minutes to ground-truth 500 frames of video. Under Windows, any installed AVI codec is supported; under Unix Matlab only supports raw video.

Data time period: 2007 to 2009

This dataset is part of a larger collection

Click to explore relationships graph
Help

Related Publications

Related People

Related Grants and Projects

Subjects
Artificial Intelligence and Image Processing | Computer Vision | Information and Computing Sciences | Tracking |

User Contributed Tags    

Login to tag this record with meaningful keywords to make it easier to discover

Similar data you may be interested in: