Abstract

There is a growing interest in 3D content following the recent developments in 3D movies, 3D TVs and 3D smartphones. However, 3D content creation is still dominated by professionals, due to the high cost of 3D motion capture instruments. The availability of a low-cost motion capture system will promote 3D content generation by general users and accelerate the growth of the 3D market. In this paper, we describe the design and implementation of a real-time motion capture system based on a portable low-cost wireless camera sensor network. The proposed system performs motion capture based on the data-driven 3D human pose reconstruction method to reduce the computation time and to improve the 3D reconstruction accuracy. The system can reconstruct accurate 3D full-body poses at 16 frames per second using only eight markers on the subject's body. The performance of the motion capture system is evaluated extensively in experiments.

Highlights

  • We are witnessing rapidly-growing 3D industries, such as 3D movies, 3D TVs and 3D smartphones.It is expected that the consumption of 3D content will be further increased as more 3D products are introduced into the market

  • The proposed system is designed based on the method suggested by [15] in order to reduce the computation time and to improve the 3D reconstruction accuracy, such that motion capture can be performed in real-time using a low-cost wireless camera sensor network

  • An extensive set of experiments is performed to validate the performance of the Samba motion capture system

Read more

Summary

Introduction

We are witnessing rapidly-growing 3D industries, such as 3D movies, 3D TVs and 3D smartphones. The introduction of digital cameras has revolutionized the Internet, as the creation and sharing of photos and videos have been accelerated with help from social network sites, such as YouTube, Flickr and Facebook Based on these facts, it can be concluded that the success of the 3D market depends on the availability of an inexpensive tool, with which a common user can create 3D content. The present paper proposes a low-cost approach to 3D content generation Motion capture systems, such as the Vicon MX motion capture system [1], can provide the full 3D pose of a subject using a set of markers. The Samba motion capture system consists of a wireless camera sensor network, a server and an optional display.

Related Work
An Overview of the Samba Motion Capture System
Data-Driven Human Pose Estimation
Local Pose Space Method
Pseudo-Pose Generation
One-DOF Joints
Two-DOF Joints
Initial Values for Optimization
System Implementation
Camera Node
Samba Server
Human Pose Database
Marker Detection and Tracking
Experimental Results
CMU Motion Capture Database
Demonstration of the Samba Motion Capture System
A Comparison to Kinect under the Bright Lighting Condition
Conclusions
17. Levmar
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call