Charles, J, Pfister, T, Magee, D et al. (2 more authors) (2014) Upper body pose estimation with temporal sequential forests. In: Proceedings of the British Machine Vision Conference 2014. 2014 British Machine Vision Conference, 01-05 Sep 2014, Nottingham, UK. BMVA Press , 1 - 12.
Abstract
Our objective is to efficiently and accurately estimate human upper body pose in gesture videos. To this end, we build on the recent successful applications of random forests (RF) classifiers and regressors, and develop a pose estimation model with the following novelties: (i) the joints are estimated sequentially, taking account of the human kinematic chain. This means that we don't have to make the simplifying assumption of most previous RF methods - that the joints are estimated independently; (ii) by combining both classifiers (as a mixture of experts) and regressors, we show that the learning problem is tractable and that more context can be taken into account; and (iii) dense optical flow is used to align multiple expert joint position proposals from nearby frames, and thereby improve the robustness of the estimates. The resulting method is computationally efficient and can overcome a number of the errors (e.g. confusing left/right hands) made by RF pose estimators that infer their locations independently. We show that we improve over the state of the art on upper body pose estimation for two public datasets: the BBC TV Signing dataset and the ChaLearn Gesture Recognition dataset.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2014, The Authors. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms. |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Computing (Leeds) > Artificial Intelligence & Biological Systems (Leeds) |
Depositing User: | Symplectic Publications |
Date Deposited: | 27 Mar 2015 11:26 |
Last Modified: | 21 Feb 2024 14:09 |
Published Version: | http://www.bmva.org/bmvc/2014/papers/paper026/inde... |
Status: | Published |
Publisher: | BMVA Press |
Identification Number: | 10.5244/c.28.54 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:83898 |