ActiveMoCap: Optimized Viewpoint Selection for Active Human Motion Capture

TL;DR

This paper presents ActiveMoCap, an algorithm that optimizes camera viewpoints in real-time to enhance the accuracy of monocular 3D human pose estimation from video sequences.

Contribution

It introduces a novel method to predict optimal future viewpoints by estimating uncertainty in 3D pose estimates, improving accuracy over existing approaches.

Findings

Outperforms existing person-following and orbiting methods.

Effectively estimates uncertainty from deep learning regressors.

Enhances 3D pose accuracy through viewpoint optimization.

Abstract

The accuracy of monocular 3D human pose estimation depends on the viewpoint from which the image is captured. While freely moving cameras, such as on drones, provide control over this viewpoint, automatically positioning them at the location which will yield the highest accuracy remains an open problem. This is the problem that we address in this paper. Specifically, given a short video sequence, we introduce an algorithm that predicts which viewpoints should be chosen to capture future frames so as to maximize 3D human pose estimation accuracy. The key idea underlying our approach is a method to estimate the uncertainty of the 3D body pose estimates. We integrate several sources of uncertainty, originating from deep learning based regressors and temporal smoothness. Our motion planner yields improved 3D body pose estimates and outperforms or matches existing ones that are based on person following and orbiting.