Zero-Effort Camera-Assisted Calibration Techniques for Wearable Motion Sensors. Conference Paper uri icon

abstract

  • Activity recognition using wearable motion sensors plays an important role in pervasive wellness and healthcare monitoring applications. The activity recognition algorithms are often designed to work with a known orientation of sensors on the body. In the case of accidental displacement of the motion sensors, it is important to identify the new sensor location and orientation. This step, often called calibration or recalibration, requires extra effort from the user to either perform a set of known movements, or enter information about the placement of the sensors manually. In this paper, we propose a camera-assisted calibration approach that does not require any extra effort from the user. The calibration is done seamlessly when the user appears in front of the camera (in our case, a Kinect camera) and performs an arbitrary activity of choice (e.g., walking in front of the camera). We provide experimental results supporting the effectiveness of our approach.

name of conference

  • Proceedings of the Wireless Health 2014 on National Institutes of Health

published proceedings

  • Proc Wirel Health

author list (cited authors)

  • Wu, J., & Jafari, R.

citation count

  • 3

complete list of authors

  • Wu, Jian||Jafari, Roozbeh

publication date

  • October 2014