ICPR2012-CR.pdf (1.64 MB)
Download fileObject localisation via action recognition
conference contribution
posted on 2016-02-10, 11:35 authored by John Darby, Baihua LiBaihua Li, Ryan Cunningham, Nicholas CostenThe aim of this paper is to track objects during their use by humans. The task is difficult because these objects are small, fast-moving and often occluded by the user. We present a novel solution based on cascade action recognition, a learned mapping between body-and object-poses, and a hierarchical extension of importance sampling. During tracking, body pose estimates from a Kinect sensor are classified between action classes by a Support Vector Machine and converted to discriminative object pose hypotheses using a {body, object} pose mapping. They are then mixed with generative hypotheses by the importance sampler and evaluated against the image. The approach out-performs a state of the art adaptive tracker for localisation of 14/15 test implements and additionally gives object classifications and 3D object pose estimates.
History
School
- Science
Department
- Computer Science