Monocular Vision Based Localization System using Hybrid Features from Ceiling Images for Robot Navigation in an Indoor Environment
1
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
This paper presents a localization system using ceiling images in a large indoor environment. For a system with low cost and complexity, we propose a single camera based system that utilizes ceiling images acquired from a camera installed to point upwards. For reliable operation, we propose a method using hybrid features which include natural landmarks in a natural scene and artificial landmarks observable in an infrared ray domain. Compared with previous works utilizing only infrared based features, our method reduces the required number of artificial features as we exploit both natural and artificial features. In addition, compared with previous works using only natural scene, our method has an advantage in the convergence speed and robustness as an observation of an artificial feature provides a crucial clue for robot pose estimation. In an experiment with challenging situations in a real environment, our method was performed impressively in terms of the robustness and accuracy. To our knowledge, our method is the first ceiling vision based localization method using features from both visible and infrared rays domains. Our system can be easily utilized with a variety of service robot applications in a large indoor environment.
Abstract
This paper presents a localization system using ceiling images in a large indoor environment. For a system with low cost and complexity, we propose a single camera based system that utilizes ceiling images acquired from a camera installed to point upwards. For reliable operation, we propose a method using hybrid features which include natural landmarks in a natural scene and artificial landmarks observable in an infrared ray domain. Compared with previous works utilizing only infrared based features, our method reduces the required number of artificial features as we exploit both natural and artificial features. In addition, compared with previous works using only natural scene, our method has an advantage in the convergence speed and robustness as an observation of an artificial feature provides a crucial clue for robot pose estimation. In an experiment with challenging situations in a real environment, our method was performed impressively in terms of the robustness and accuracy. To our knowledge, our method is the first ceiling vision based localization method using features from both visible and infrared rays domains. Our system can be easily utilized with a variety of service robot applications in a large indoor environment.
참고문헌 (21)
- R. Sim, "Vision-based SLAM using the Rao-Blackwellised Particle Filter", IJCAI Workshop on Reasoning with Uncertainty in Robotics (2005)
- A. J. Davison, "Real-Time Simultaneous Localisation and Mapping with a Single Camera", International Conference on Computer Vision (ICCV)}, pp.1403~1410 (2003)
- P. Jensfelt, "A Framework for Vision based Bearing Only 3D SLAM", IEEE International Conference on Robotics and Automation, pp.1944~1950 (2006)
- W. Y. Jeong, "CV-SLAM: A new Ceiling Vision-based SLAM technique", IEEE, 2005, 3195~3200
- W. Y. Jeong, "Visual SLAM with Line nd Corner Features" (2006), IROS
- Seo-Yeon Hwang, "Monocular Vision-Based SLAM in Indoor Environment Using Corner, Lamp, and Door Features from Upward-Looking Camera", IEEE Transactions on Industrial Electronics (2011)
- S. Thrun, "Robust Monte Carlo localization for mobile robots", Artificial Intelligence, 128, pp.99~141 (2001)
- Y. Nakazato, "A Localization System Using Invisible Retroreflective Markers", IAPR Conference on Machine Vision Applications, pp.140~143 (2005)
- 이수용, "Mobile Robot Localization using Infrared Light Reflecting Landmarks", International Conference on Control, Automation and Systems 2007, pp.674~677 (2007), ICCAS
- "StarGazerTM"[URL]
- A. Haro, "Detecting and Tracking Eyes By Using Their Physiological Properties, Dynamics, and Appearance", Proceedings of IEEE Conference on Computer Vision and Pattern Recognition(CVPR), pp.163~168 (2000)
- D.H. Yoo, "A Novel Nonintrusive Eye Gaze Estimation System using Cross-ratio under Large Head Motion", Computer Vision and Image Understanding, 98(1), pp.25~51 (2005)
- H. Kato, "Marker Tracking and HMD Calibration for a Video-based Augmented Reality Conferencing System", Proceedings of the 2nd IEEE, 1999, 85~94
- D. G. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints", International Journal of Computer Vision, 60(2), pp.91~110 (2004)
- H. Bay, "SURF: Speeded Up Robust Features", Computer Vision and Image Understanding, 110(3), pp.346~359 (2008)
- J. Shi, "Good Features to Track", IEEE Conference on Computer Vision and Pattern Recognition(CVPR), pp.593~600 (1994)
- M. Montemerlo, "FastSLAM: A factored solution to the simultaneous localization and mapping problem", Proceedings of the AAAI National Conference on Artificial Intelligence, pp.593~598 (2002)
- S. Thrun, "Probabilistic Robotics" (2005), MIT Press
- J. Civera, "Inverse Depth Parametrization for Monocular SLAM", IEEE Transactions on Robotics, 24(5), pp.932~945 (2008)
- Detection and tracking of point features, "C. Tomasi", Carnegie Mellon Univ, ~, pp.CMU-CS- 91-132 (1991)
- J. Kang, "Ceiling Vision Based Autonomous Navigation of a Mobile Robot using Hybrid Visual Features in a Large Indoor Environment", The 7th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI 2010), pp.653~ (2010)