직선기반 SLAM에서의 루프결합
Loop Closure in a Line-based SLAM
1
조회
0
다운로드
5
인용
0
참고문헌
키워드
초록
The loop closure problem is one of the most challenging issues in the vision-based simultaneous localization and mapping community. It requires the robot to recognize a previously visited place from current camera measurements. While the loop closure often relies on visual bag-of-words based on point features in the previous works, however, in this paper we propose a line-based method to solve the loop closure in the corridor environments. We used both the floor line and the anchored vanishing point as the loop closing feature, and a two-step loop closure algorithm was devised to detect a known place and perform the global pose correction. We propose an anchored vanishing point as a novel loop closure feature, as it includes position information and represents the vanishing points in bi-direction. In our system, the accumulated heading error is reduced using an observation of a previously registered anchored vanishing points firstly, and the observation of known floor lines allows for further pose correction. Experimental results show that our method is very efficient in a structured indoor environment as a suitable loop closure solution.
Abstract
The loop closure problem is one of the most challenging issues in the vision-based simultaneous localization and mapping community. It requires the robot to recognize a previously visited place from current camera measurements. While the loop closure often relies on visual bag-of-words based on point features in the previous works, however, in this paper we propose a line-based method to solve the loop closure in the corridor environments. We used both the floor line and the anchored vanishing point as the loop closing feature, and a two-step loop closure algorithm was devised to detect a known place and perform the global pose correction. We propose an anchored vanishing point as a novel loop closure feature, as it includes position information and represents the vanishing points in bi-direction. In our system, the accumulated heading error is reduced using an observation of a previously registered anchored vanishing points firstly, and the observation of known floor lines allows for further pose correction. Experimental results show that our method is very efficient in a structured indoor environment as a suitable loop closure solution.
참고문헌 (17)
- A. Angeli, "Fast and incremental method for loop-closure detection using bags of visual words", IEEE Transactions on Robotics, 24(5), pp.1027~1037 (2008)
- M. Cummins, "Highly scalable appearance-only SLAM - FAB-MAP 2.0", In Proceedings of Robotics: Science and Systems (RSS) (2009)
- P. Smith, "Real-time monocular SLAM with straight lines", in British Machine Vision Conference, 1, pp.17~26 (2006)
- A. P. Gee, "Real-Time Model-Based SLAM Using Line Segments", in 2nd International Symposium on Visual Computing (2006)
- T. Lemaire, "Monocular-vision based SLAM using line segments", in Proc. of IEEE International Conference on Robotics and Automation, pp.2791~2796 (2007)
- J. Solà, "Undelayed initialization of line segments inmonocular SLAM", in Proc. of The IEEE, 2009, 11~15
- M. Bosse, "Vanishing Points and 3D Lines fromOmnidirectional Video", in Proc. of IEEE IntlConf. Image Processing (2002)
- Y. H. Lee, "Doh, In VPass: Algorithmic Compass using Vanishing Points in Indoor Environments", in Proc. Of IEEE, 2009, ~
- Y. B. Park, "Visual Recognition of Types of Structural Corridor Landmarks Using Vanishing Points Detection and Hidden Markov Models", Proc. of the International Conference on Pattern Recognition (2010)
- G. Zhang, "A Vertical and Floor Line-based Monocular SLAM System for Corridor Environments", International Journal of Control, Automation, and Systems, 10(3) (2012)
- J. Civera, "Inverse depth parametrization for monocularSLAM", IEEE Transactions on Robotics, 24(5) (2008)
- G. Zhang, "Building a Partial 3D Line-based Map using a Monocular SLAM", in Proc. of The IEEE International Conference on Robotics and Automation (2011)
- G. Zhang, "SoF-SLAM: Segments-on-Floor-based Monocular SLAM", in Proc. of The IEEE, 2010, ~
- R. I. Hartley, "Multiple View Geometry in Computer Vision 2nd Edition", pp.213~ (2004), Cambridge University Press
- G. Zhang, "Loop Closure Through Vanishing Points in a Line-based Monocular SLAM", Accepted for The IEEE International Conference on Robotics and Automation (2012)
- H. Durrant-Whyte, "Simultaneous localization and mapping: Part I", IEEE Robotics & Automation Magazine, 13(2), pp.99~110 (2006)
- P. V. C. Hough, "Method and Means for Recognizing Complex Patterns", U.S. Patent 3,069,654, ~ (1962)