FG08-HMM_APF-mono.pdf (1.43 MB)
Download fileTracking a walking person using activity-guided annealed particle filtering
conference contribution
posted on 2016-02-09, 14:35 authored by John Darby, Baihua LiBaihua Li, Nicholas CostenTracking human pose using observations from less than three cameras is a challenging task due to ambiguity in the available image evidence. This work presents a method for tracking using a pre-trained model of activity to guidesampling within an Annealed Particle Filtering framework. The approach is an example of model-based analysis-by-synthesis and is capable of robust tracking from less than 3 cameras with reduced numbers of samples. We test the scheme on a common dataset containing ground truth mo-tion capture data and compare against quantitative results for standard Annealed Particle Filtering. We find lower ab-solute and relative error scores for both monocular and 2-camera sequences using 80% fewer particles. © 2008 IEEE.
History
School
- Science
Department
- Computer Science