제어로봇시스템학회논문지 (Journal of Institute of Control, Robotics and Systems)

  • 제22권10호
  • /
  • Pages.833-838
  • /
  • 2016
  • /
  • 1976-5622(pISSN)
  • /
  • 2233-4335(eISSN)
제어로봇시스템학회 (Institute of Control, Robotics and Systems)
권호 표지
DOI QR코드

DOI QR Code

전방 모노카메라 기반 SLAM 을 위한 다양한 특징점 초기화 알고리즘의 성능 시뮬레이션

Performance Simulation of Various Feature-Initialization Algorithms for Forward-Viewing Mono-Camera-Based SLAM

  • 이훈 (서울대학교 전기정보공학부, 자동화시 스템공동연구소) ;
  • 김철홍 (서울대학교 전기정보공학부, 자동화시 스템공동연구소) ;
  • 이태재 (서울대학교 전기정보공학부, 자동화시 스템공동연구소) ;
  • 조동일 (서울대학교 전기정보공학부, 자동화시 스템공동연구소)
  • Lee, Hun (School of Electrical and Computer Engineering, Seoul National University Automation and Systems Research Institute (ASRI), Seoul National University) ;
  • Kim, Chul Hong (School of Electrical and Computer Engineering, Seoul National University Automation and Systems Research Institute (ASRI), Seoul National University) ;
  • Lee, Tae-Jae (School of Electrical and Computer Engineering, Seoul National University Automation and Systems Research Institute (ASRI), Seoul National University) ;
  • Cho, Dong-Il Dan (School of Electrical and Computer Engineering, Seoul National University Automation and Systems Research Institute (ASRI), Seoul National University)
  • 투고 : 2016.04.19
  • 심사 : 2016.08.23
  • 발행 : 2016.10.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

This paper presents a performance evaluation of various feature-initialization algorithms for forward-viewing mono-camera based simultaneous localization and mapping (SLAM), specifically in indoor environments. For mono-camera based SLAM, the position of feature points cannot be known from a single view; therefore, it should be estimated from a feature initialization method using multiple viewpoint measurements. The accuracy of the feature initialization method directly affects the accuracy of the SLAM system. In this study, four different feature initialization algorithms are evaluated in simulations, including linear triangulation; depth parameterized, linear triangulation; weighted nearest point triangulation; and particle filter based depth estimation algorithms. In the simulation, the virtual feature positions are estimated when the virtual robot, containing a virtual forward-viewing mono-camera, moves forward. The results show that the linear triangulation method provides the best results in terms of feature-position estimation accuracy and computational speed.

키워드

참고문헌

  1. H. Lee, C. H. Kim, T. J. Lee, and D. I. Cho, "Performance evaluation of various feature-initialization methods for forward viewing mono-camera based SLAM in indoor environments," Proc. of 31th ICROS Annual Conference 2016, Seoul, Korea, pp. 367-368, 2016.
  2. V. D. Hoang and K. H. Jo, "Automatic calibration of camera and LRF based on morphological pattern and optimal angular back-projection error," International Journal of Control, Automation and Systems, vol. 13, no. 6, pp. 1436-1445, 2015. https://doi.org/10.1007/s12555-014-0287-x
  3. T. J. Lee, B. M. Jang, and D. I. Cho, "A non-iterative pose-graph optimization algorithm for fast 2D SLAM," Proc. of IEEE International Conference on Robotics and Biomimetics, pp. 1596-1601, Bali, Indonesia, Dec. 2014.
  4. W. S. Moon, J. W. Jang, H. S. Kim, and K. R. Baek, "Virtual pheromone map building and a utilization method for a multi-purpose swarm robot system," International Journal of Control, Automation and Systems, vol. 13, no. 6, pp. 1446-1453, 2015. https://doi.org/10.1007/s12555-013-0431-z
  5. H. Xiao, Z. Li, C. Yang, W. Yuan, and L. Wang, "RGB-D sensor-based visual target detection and tracking for an intelligent wheelchair robot in indoors environments," International Journal of Control, Automation and Systems, vol. 13, no. 3, pp. 521-529, 2015. https://doi.org/10.1007/s12555-014-0353-4
  6. http://www.lge.co.kr/lgekor/product/household-appliances/vacuum/productList.do?cateId=6110
  7. http://www.samsung.com/sec/consumer/living-appliances/vacuumcleaners
  8. T. J. Lee, B. M. Jang, and D. I. Cho, "A novel method for estimating the heading angle for a home service robot using a forward-viewing mono-camera and motion sensors," International Journal of Control, Automation and Systems, vol. 13, no. 3, pp. 709-717, 2015. https://doi.org/10.1007/s12555-014-9111-x
  9. T. J. Lee, W. Bahn, B. M. Jang, H. J. Song, and D. I. Cho, "A new localization method for mobile robot by data fusion of vision sensor data and motion sensor data," Proc. of IEEE International Conference on Robotics and Biomimetics, pp. 723-728, Guangzhou, China, Dec. 2012.
  10. C. H. Lee, J. H. Park, W. Bahn, T. I. Kim, T. J. Lee, M. M. Shaikh, K. S. Kim, and D. I. Cho, "Vision tracking of a moving robot from a second moving robot using both relative and absolute position referencing methods," Proc. of the 37th Annual Conference of IEEE Industrial Electronics, pp. 278-283, Melbourne, Australia, Nov. 2011.
  11. R. I. Hartley and A. Zisserman, Multiple view geometry in Multiple view geometry in computer vision, 2nd Ed., Cambridge University Press, UK, 2003.
  12. H. W. Chae, C. S. Park, and J. B. Song, "Sliding window based landmark extraction for indoor 2D SLAM," Proc. of International Conference on Control Automation and Systems, pp. 336-341, Busan, Korea, Oct. 2015.
  13. M. Pitt and N. Shephard, "Filtering via simulation: Auxiliary particle filters," Journal of the American Statistical Association, vol. 94, no. 446, pp. 590-599, 1999. https://doi.org/10.1080/01621459.1999.10474153
  14. D. H. Won, S. H. Chun, S. K. Sung, Y. J. Lee, J. H. Cho, J. M. Joo, and J. K. Park, "INS/vSLAM system using distributed particle filter," International Journal of Control, Automation and Systems, vol. 8, no. 6, pp. 1232-1240, 2010. https://doi.org/10.1007/s12555-010-0608-7