DOI QR코드

DOI QR Code

A Precise Tracking System for Dynamic Object using IR sensor for Spatial Augmented Reality

공간증강현실 구현을 위한 적외선 센서 기반 동적 물체 정밀 추적 시스템

  • Oh, JiSoo (Global School of Media, Soongsil University) ;
  • Park, Jinho (Global School of Media, Soongsil University)
  • 오지수 (숭실대학교 글로벌미디어학부) ;
  • 박진호 (숭실대학교 글로벌미디어학부)
  • Received : 2017.06.24
  • Accepted : 2017.07.06
  • Published : 2017.07.14

Abstract

As the era of the fourth industrial revolution began, augmented reality showed infinite possibilities throughout society. However, current augmented reality systems such as head-mount display and hand-held display systems suffer from various problems such as weariness and nausea, and thus space-augmented reality, which is a projector-based augmented reality technology, is attracting attention. Spacial augmented reality requires precise tracking of dynamic objects to project virtual images in order to increase realism of augmented reality and induce user 's immersion. The infrared sensor-based precision tracking algorithm developed in this paper demonstrates very robust tracking performance with an average error rate of less than 1.5% and technically opens the way towards advanced augmented reality technologies such as tracking for arbitrary objects, and Socially, by easy-to-use tracking algorithms for non-specialists, it allows designers, students, and children to easily create and enjoy their own augmented reality content.

4 차 산업혁명 시대로 접어들면서 증강현실은 사회 전반에 걸쳐 무한한 가능성을 보여주고 있다. 하지만 현재의 헤드-마운트 디스플레이, 핸드-헬드 디스플레이 방식의 증강현실은 착용의 번거로움, 멀미 등의 여러 문제점이 있고 이에 따라 프로젝터 기반의 증강현실 기술인 공간증강현실이 각광받고 있다. 공간증강현실은 증강현실의 실재감을 높이고 사용자의 몰입을 유도하기 위해 가상 영상을 투영할 움직이는 물체에 대한 정밀한 추적이 필수적이다. 본 논문에서 개발한 적외선 센서 기반의 정밀 추적 알고리즘은 평균 오차율 1.5% 이내의 매우 견고한 추적 성능을 통해 기술적으로는 임의의 물체에 대한 추적과 같은 진보된 증강현실 기술을 향한 길을 열었고, 사회적으로는 비전문가도 사용하기 쉬운 추적 알고리즘을 통해 디자이너, 학생, 어린이들이 쉽게 자신만의 증강현실 콘텐츠를 제작, 즐길 수 있게 하였다.

Keywords

References

  1. G. Narita, Y. Watanabe, and M. Ishikawa, "Dynamic projection mapping onto deforming non-rigid surface using deformable dot cluster marker," IEEE Transactions on visualization and computer graphics, pp. 1235-1248, 2017.
  2. Y. Zhou, S. Xiao, N. Tang, Z. Wei, and X. Chen, "Pmomo: projection mapping on movable 3D object," ACM Conference on Human Factors in Computing Systems, pp. 781-790, 2016.
  3. C. Resch, P. Keitler, and G. Klinker, "Sticky projections-a new approach to interactive shader lamp tracking," IEEE International Symposium on Mixed and Augmented Reality, pp. 151-156, 2014.
  4. T. Sueishi, H. Oku, and M. Ishikawa, "Lumipen 2: Dynamic Projection Mapping with Mirror-Based Robust High-Speed Tracking against Illumination Changes," PRESENCE: Teleoperators and Virtual Environments, 2017.
  5. B. Drost, M. Ulrich, N. Navab, and S. Ilic, "Model globally, match locally: Efficient and robust 3D object recognition," IEEE Computer Vision and Pattern Recognition, pp. 998-1005, 2010.
  6. A.-J. Trevor, S. Gedikli, R.-B. Rusu, and H.-I. Christensen, "Efficient organized point cloud segmentation with connected components," Semantic Perception Mapping and Exploration, 2013.
  7. R.-B. Rusu, N. Blodow, and M. Beetz, "Fast point feature histograms (FPFH) for 3D registration," IEEE International Conference on Robotics and Automation, pp. 3212-3217, 2009.
  8. R.-B. Rusu, Z.-C. Marton, N. Blodow, and M. Beetz, "Learning informative point classes for the acquisition of object model maps," IEEE Control, Automation, Robotics and Vision, pp. 640-650, 2008.
  9. S. Izadi, D. Kim, O. Hilliges, D. Molyneaux, R. Newcombe, P. Kohli, and A. Fitzgibbon, "KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera," ACM Proceedings of the 24th annual ACM symposium on User interface software and technology, pp. 559-568, 2011.
  10. C. Siegl, M. Colaianni, L. Thies, J. Thies, M. Zollhofer, S. Izadi, and F. Bauer, "Real-time pixel luminance optimization for dynamic multi-projection mapping," ACM Transactions on Graphics, 34(6), 2015.