Implementation of a Single Image Detection and Tracking System in Multiple Images

다중 이미지에서 단일 이미지 검출 및 추적 시스템 구현

  • Choi, Jaehak (Department of Electronic and Electronical Engineering, Dankook University) ;
  • Park, Inho (Department of Electronic and Electronical Engineering, Dankook University) ;
  • Kim, Seongyoon (Department of Electronic and Electronical Engineering, Dankook University) ;
  • Lee, Yonghwan (Department of Digital Contents Engineering, Wonkwang University) ;
  • Kim, Youngseop (Department of Electronic and Electronical Engineering, Dankook University)
  • 최재학 (단국대학교 전자전기공학과) ;
  • 박인호 (단국대학교 전자전기공학과) ;
  • 김성윤 (단국대학교 전자전기공학과) ;
  • 이용환 (원광대학교 디지털콘텐츠공학과) ;
  • 김영섭 (단국대학교 전자전기공학과)
  • Received : 2017.09.11
  • Accepted : 2017.09.24
  • Published : 2017.09.30


Augmented Reality(AR) is the core technology of the future knowledge service industry. It is expected to be used in various fields such as medical, education, entertainment etc. Briefly, augmented reality technology is a technique in which a mapped virtual object is augmented when a real-world object is viewed through a device after mapping a real-world object and a virtual object. In this paper, we implemented object detection and tracking system, which is a key technology of augmented reality. To speed up the object tracking, the ORB algorithm, which is a lightweight algorithm compared to the detection algorithm, is applied. In addition, KNN classifier, which is a machine learning algorithm, was applied to detect a single object by learning multiple images.



Grant : 360도 카메라와 스마트폰을 이용한 멀티미디어 집합 (.DTL파일 포맷) 저작 및 AR 기반 표출 기술 개발

Supported by : 정보통신기술진흥센터


  1. "Augmented Reality and Augmented Human", Korea Internet & Security Agency, Issue & Trend 2015, 8.
  2. Heejae Kim, "Authoring System using Panoramas of Real World", Sejong University, thesis for a degree, 2014.
  3. Sungpil Choi, "Scale-Invariant-Feature Transform (SIFT)", Department of Electrical and Electronic Engineering, KAIST, 2014.
  4. Taeryong Park, "Implementation of Real time based Multi-object recognition algorithm", Journal of IKEEE. Vol. 17, No. 1, pp. 051-056, March, 2013.
  5. Daejin Kim, Jaesik Yun and Insoo Kim. "Method and apparatus for recognizing an object using a covariance descriptor". Patent No. 10-14914461. 2015.
  7. Cui Yu, Beng Chin Ooi, Kian-Lee Tan, H.V. Jagadish "Indexing the Distance: An Effcient Method to KNN Processing". Department of Computer Science National University of Singapore, Proceedings of the 27th VLDB Conference, Roma, Italy, 2001