Mutual Information Based Data Selection in Gaussian Processes for People Tracking

Publisher:
The ACRA 2012 Organising Committee
Publication Type:
Conference Proceeding
Citation:
Australasian Conference on Robotics and Automation 2012, 2012, pp. 1 - 6
Issue Date:
2012-01
Full metadata record
Files in This Item:
Filename Description Size
Thumbnail2012000641OK.pdf6.6 MB
Adobe PDF
It is the general perception that models describing human motion patterns enhance tracking even with long term occlusions. One effective way of learning such patterns is to use Gaussian Processes (GP). However, with the increase of the amount of training data with time, the GP becomes computationally intractable. In this work, we have proposed a Mutual Information (MI) based technique along with the Mahalanobis Distance (MD) measure to keep the most informative data while discarding the least informative data. The algorithm is tested with data collected in an office environment with a Segway robot equipped with a laser range finder. It leads to more than 80% data reduction while keeping the rms errors within the required bounds. We have also implemented a GP based Particle filter tracker for long term people tracking with occlusions. The comparison results with Extended Kalman Filter based tracker shows the superiority of the proposed approach.
Please use this identifier to cite or link to this item: