Graphics enhanced version of this site

Multimodal Data Collection
Heads: Jessica K Hodgins and Fernando De la Torre Frade
Contact: Jessica K Hodgins (jkh@cs.cmu.edu)

Mailing address:
Carnegie Mellon University
Robotics Institute
5000 Forbes Avenue
Pittsburgh, PA 15213

Associated lab/group: Human Sensing

The CMU Multi-Modal Activity Database (CMU-MMAC) database contains multimodal measures of the human activity of subjects performing the tasks involved in cooking and food preparation. The CMU-MMAC database was collected in Carnegie Mellon University's Motion Capture Lab. A kitchen was built, and, to date, five subjects have been recorded cooking five different recipes: brownies, pizza, sandwich, salad and scrambled eggs. The following modalities were recorded:

• Video: (A) Three high spatial resolution (1024x768) color video cameras at low temporal resolution (30 Hz). (B) Two low spatial resolution (640x480) color video cameras at high temporal resolution (60 Hz). (C) One wearable low spatial resolution (640x480) camera at low temporal resolution (12 Hz).
• Audio: (A) Five balanced microphones. (B) Wearable watch.
• Motion capture: A Vicon motion capture system with 12 infrared MX-40 cameras. Each camera records 4 megapixel resolution images at 120 Hz.
• Five 3-axis accelerometers and gyroscopes.

Name - Title <Email Address>
• [Home] Adam W Bargteil - Postdoctoral Fellow <adamwb@cs.cmu.edu>
• Josep Beltran - Visiting Scholar <jbeltran@andrew.cmu.edu>
• Alexandre Collado I Castells - Visiting Scholar <alexcolladocastells@gmail.com>
• [Home] Fernando De la Torre Frade - Research Scientist <ftorre@cs.cmu.edu>
• Jessica K Hodgins - Faculty, RI/CS <jkh@cs.cmu.edu>
• Justin C Macey - Research Associate III <jmacey@cs.cmu.edu>