Browse views: by Year, by Function, by GLF, by Subfunction, by Conference, by Journal

Lie-X: Depth Image Based Articulated Object Pose Estimation, Tracking, and Action Recognition on Lie Groups

Xu, Chi and Govindarajan, Lakshmi Narasimha and Zhang, Yu and Stewart, James and Bichler, Zoë and Jesuthasan, Suresh and Claridge-Chang, Adam and Mathuru, Ajay Sriram and Tang, Wenlong and Zhu, Peixin and Cheng, Li (2017) Lie-X: Depth Image Based Articulated Object Pose Estimation, Tracking, and Action Recognition on Lie Groups. International journal of computer vision, 123 (3). pp. 454-478.

Abstract

Pose estimation, tracking, and action recognition of articulated objects from depth images are important and challenging problems, which are normally considered separately. In this paper, a unified paradigm based on Lie group theory is proposed, which enables us to collectively address these related problems. Our approach is also applicable to a wide range of articulated objects. Empirically it is evaluated on lab animals including mouse and fish, as well as on human hand. On these applications, it is shown to deliver competitive results compared to the state-of-the-arts, and non-trivial baselines including convolutional neural networks and regression forest methods. Moreover, new sets of annotated depth data of articulated objects are created which, together with our code, are made publicly available.

Item Type: Article
Keywords: Depth images Pose estimation Fish Mouse Human hand Lie group
Date Deposited: 04 Sep 2018 00:45
Last Modified: 04 Sep 2018 00:45
URI: https://oak.novartis.com/id/eprint/35977

Search

Email Alerts

Register with OAK to receive email alerts for saved searches.