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

TL;DR

This paper introduces a unified Lie group-based framework for pose estimation, tracking, and action recognition of articulated objects from depth images, demonstrating competitive results across various biological and human applications.

Contribution

It presents a novel Lie group theory-based approach that simultaneously addresses multiple related problems in articulated object analysis, applicable to diverse objects.

Findings

Competitive results on lab animals and human hand datasets

Outperforms some deep learning and regression methods

Applicable to various articulated objects

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.