Abstract

In this paper we present a wide area tracking system based on consumer hardware and available motion capture modules and middleware. We are using multiple depth cameras for human pose tracking in order to increase the captured space. Commercially available cameras can capture human movements in a non-intrusive way, while associated software-modules produce pose information of a simplified skeleton model. We calibrate the cameras relatively to each other to seamlessly combine their tracking data. Our design allows an arbitrary number of sensors to be integrated and used in parallel over a local area network. This enables us to capture human movements in a large arbitrarily shaped area. In addition we can improve motion capture data in regions, where the field of view of multiple cameras overlaps, by mutually completing partly occluded poses. In various examples we demonstrate, how human pose data is being merged in order to cover a wide area and how this data can easily be used for character animation in a virtual environment.

Highlights

  • Today, human Motion Capture (MoCap) is a central element of games and entertainment products

  • A cell consists of a single sensor together with associated software components to derive human pose data from it

  • We have evaluated our system with different sensor placements to simulate situations that occur in wide area tracking

Read more

Summary

Introduction

Human Motion Capture (MoCap) is a central element of games and entertainment products. On the one hand it is used to animate virtual actors in movies and computer games using professional and costly setups. Recent developments in consumer hardware have made it possible to use MoCap - with and without a controller - as input to games and applications. Low-cost depth cameras enable consumers to capture human movements in an non-intrusive and stable way. Ready-to-use software modules and middleware, for retrieving sensor data and human pose information of a simplified skeleton model, has been distributed by sensor manufacturers [1, 2]. Ease of deployment and good usability makes them applicable in a home environment By moving control into the third dimension compelling experiences can be created and new ways of interaction established

Methods
Results
Conclusion
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