ActiveMoCap: Optimized Viewpoint Selection for Active Human Motion Capture
Authors:
- 1 June 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 100-109
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.Keywords
All Related Versions
This publication has 34 references indexed in Scilit:
- INFORMATION-DRIVEN AUTONOMOUS EXPLORATION FOR A VISION-BASED MAVISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2017
- Real-time planning for automated multi-view drone cinematographyACM Transactions on Graphics, 2017
- LCR-Net: Localization-Classification-Regression for Human Pose2017
- Learning to gather information via imitation2017
- Designing a camera placement assistance system for human motion capture based on a guided genetic algorithmVirtual Reality, 2017
- An Adaptable, Probabilistic, Next-Best View Algorithm for Reconstruction of Unknown 3-D ObjectsIEEE Robotics and Automation Letters, 2017
- Optimal Camera Placement for Motion Capture SystemsIEEE Transactions on Visualization and Computer Graphics, 2016
- An information gain formulation for active volumetric 3D reconstruction2016
- Recurrent Network Models for Human Dynamics2015
- MonoSLAM: Real-Time Single Camera SLAMIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007