Deakin University
Browse
venkatesh-robustrecognition-2005.pdf (1.14 MB)

Robust recognition and segmentation of human actions using HMMs with missing observations

Download (1.14 MB)
journal contribution
posted on 2005-08-01, 00:00 authored by P Peursum, H Bui, Svetha VenkateshSvetha Venkatesh, G West
This paper describes the integration of missing observation data with hidden Markov models to create a framework that is able to segment and classify individual actions from a stream of human motion using an incomplete 3D human pose estimation. Based on this framework, a model is trained to automatically segment and classify an activity sequence into its constituent subactions during inferencing. This is achieved by introducing action labels into the observation vector and setting these labels as missing data during inferencing, thus forcing the system to infer the probability of each action label. Additionally, missing data provides recognition-level support for occlusions and imperfect silhouette segmentation, permitting the use of a fast (real-time) pose estimation that delegates the burden of handling undetected limbs onto the action recognition system. Findings show that the use of missing data to segment activities is an accurate and elegant approach. Furthermore, action recognition can be accurate even when almost half of the pose feature data is missing due to occlusions, since not all of the pose data is important all of the time.

History

Journal

EURASIP journal on applied signal processing

Volume

2005

Pagination

2110 - 2126

Location

Heidelberg, Germany

Open access

  • Yes

ISSN

1687-6172

eISSN

1687-6180

Language

eng

Notes

Reproduced with the kind permission of the copyright owner

Publication classification

C1.1 Refereed article in a scholarly journal

Copyright notice

2005, Hindawi Publishing Corporation