Human Motion Tracking with Less Constraint of Initial Posture from a Single RGB-D Sensor.

Chen Liu,Anna Wang,Wenhui Wang,Haijing Sun,Chunguang Bu

doi:10.3390/s21093029

Abstract

High-quality and complete human motion 4D reconstruction is of great significance for immersive VR and even human operation. However, it has inevitable self-scanning constraints, and tracking under monocular settings also has strict restrictions. In this paper, we propose a human motion capture system combined with human priors and performance capture that only uses a single RGB-D sensor. To break the self-scanning constraint, we generated a complete mesh only using the front view input to initialize the geometric capture. In order to construct a correct warping field, most previous methods initialize their systems in a strict way. To maintain high fidelity while increasing the easiness of the system, we updated the model while capturing motion. Additionally, we blended in human priors in order to improve the reliability of model warping. Extensive experiments demonstrated that our method can be used more comfortably while maintaining credible geometric warping and remaining free of self-scanning constraints.

Highlights

College of Information Science and Engineering, Northeastern University, Shenyang 110819, China; State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China
The recent volume measurement method eliminated the dependence on the pre-scan model by using an RGB-D sensor and high-performance GPU to capture the human body and maintain high efficiency
We propose a method using a single RGB-D sensor to capture a complete human surface with less constraint of initial posture

Summary

Introduction

High-quality and complete human motion 4D reconstruction is of great significance for immersive VR and even human operation It has inevitable self-scanning constraints, and tracking under monocular settings has strict restrictions. Since we live in three-dimensional space, 3D representations of real-world objects are more comfortable for humans to understand This leads to the challenging task of are pioneers in consumer-level sensor reconstruction static scenes. The recent volume measurement method eliminated the dependence on the pre-scan model by using an RGB-D sensor and high-performance GPU to capture the human body and maintain high efficiency. Researchers have made full use of the advantages of RGB-D sensors through multi-view settings [6,12,13,14,15,16], but the high fidelity of the model requires a strict working environment.

Methods

Discussion

Conclusion