Maximum a posteriori multimodal 3D object localization with a depth sensor and stereo microphones

  • Authors:
  • Bowon Lee;Kar-Han Tan

  • Affiliations:
  • Hewlett-Packard Laboratories, Palo Alto, CA;Hewlett-Packard Laboratories, Palo Alto, CA

  • Venue:
  • Proceedings of the 2nd International Conference on Immersive Telecommunications
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

We propose an algorithm for multimodal object localization with a depth sensor and stereo microphones. For this we formulate a joint probability distribution of object locations conditioned upon depth and acoustic observations. Then we use the maximum a posteriori estimation for object localization. For multimodal fusion, we map likelihood of acoustic observation given time difference of arrival information to that given object location in a three dimensional space. Our method offers a principled way to fuse information from microphones and depth sensors, and experimentally we find that it reliably locates the object without requiring careful calibration of the sensors.