Random-forest-based initializer for solving inverse problem in 3D motion tracking systems

Ryo Sugawara, Jiawei Huang, Kazuki Takashima, Taku Komura, Yoshifumi Kitarmura

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Many motion tracking systems require solving inverse problem to compute the tracking result from original sensor measurements. For real-time motion tracking, such typical solutions as the Gauss-Newton method for solving their inverse problems need an initial value to optimize the cost function through iterations. A powerful initializer is crucial to generate a proper initial value for every time instance and, for achieving continuous accurate tracking without errors and rapid tracking recovery even when it is temporally interrupted. An improper initial value easily causes optimization divergence, and cannot always lead to reasonable solutions. Therefore, we propose a new initializer based on random-forest to obtain proper initial values for efficient real-time inverse problem computation. Our method trains a random-forest model with varied massive inputs and corresponding outputs and uses it as an initializer for runtime optimization. As an instance, we apply our initializer to IM3D[1], which is a real-time magnetic 3D motion tracking system with multiple tiny, identifiable, wireless, occlusion-free passive markers (LC coils).

Original languageEnglish
Title of host publicationProceedings - VRST 2018
Subtitle of host publication24th ACM Symposium on Virtual Reality Software and Technology
EditorsStephen N. Spencer
PublisherAssociation for Computing Machinery
ISBN (Electronic)9781450360869
DOIs
Publication statusPublished - 2018 Nov 28
Event24th ACM Symposium on Virtual Reality Software and Technology, VRST 2018 - Tokyo, Japan
Duration: 2018 Nov 282018 Dec 1

Publication series

NameProceedings of the ACM Symposium on Virtual Reality Software and Technology, VRST

Other

Other24th ACM Symposium on Virtual Reality Software and Technology, VRST 2018
CountryJapan
CityTokyo
Period18/11/2818/12/1

Keywords

  • Inverse problem
  • Machine learning
  • Sensor

ASJC Scopus subject areas

  • Software

Fingerprint Dive into the research topics of 'Random-forest-based initializer for solving inverse problem in 3D motion tracking systems'. Together they form a unique fingerprint.

Cite this