사각형 특징 기반 Visual SLAM을 위한 자세 추정 방법
A Camera Pose Estimation Method for Rectangle Feature based Visual SLAM
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
In this paper, we propose a method for estimating the pose of the camera using a rectangle feature utilized for the visual SLAM. A warped rectangle feature as a quadrilateral in the image by the perspective transformation is reconstructed by the Coupled Line Camera algorithm. In order to fully reconstruct a rectangle in the real world coordinate, the distance between the features and the camera is needed. The distance in the real world coordinate can be measured by using a stereo camera. Using properties of the line camera, the physical size of the rectangle feature can be induced from the distance. The correspondence between the quadrilateral in the image and the rectangle in the real world coordinate can restore the relative pose between the camera and the feature through obtaining the homography. In order to evaluate the performance, we analyzed the result of proposed method with its reference pose in Gazebo robot simulator.
Abstract
In this paper, we propose a method for estimating the pose of the camera using a rectangle feature utilized for the visual SLAM. A warped rectangle feature as a quadrilateral in the image by the perspective transformation is reconstructed by the Coupled Line Camera algorithm. In order to fully reconstruct a rectangle in the real world coordinate, the distance between the features and the camera is needed. The distance in the real world coordinate can be measured by using a stereo camera. Using properties of the line camera, the physical size of the rectangle feature can be induced from the distance. The correspondence between the quadrilateral in the image and the rectangle in the real world coordinate can restore the relative pose between the camera and the feature through obtaining the homography. In order to evaluate the performance, we analyzed the result of proposed method with its reference pose in Gazebo robot simulator.
참고문헌 (17)
- G.N. DeSouza, "Vision for mobile robot navigation: A survey", IEEE Trans. Pattern Analysis and Machine Intelligence, 24(2), pp.237~267 (2002)
- 허환, "천장 영상지도 기반의 전역 위치추정", 로봇학회 논문지, 9(3), pp.170~177 (2014), 한국로봇학회
- H. Lategahn, "Visual SLAM for autonomous ground vehicles", IEEE Int’l Conf. on Robotics and Automation, pp.1732~1737 (2011)
- H. Strasdat, "Real-time monocular SLAM : Why filter?", IEEE Int’l Conf. on Robotics and Automation, pp.2657~2664 (2010)
- A.J. Davison, "MonoSLAM : Real-time single camera SLAM", IEEE Trans. Pattern Analysis and Machine Intelligence, 29(6), pp.1052~1067 (2007)
- G. Klein, "Parallel tracking and mapping for small AR workspaces", 6th IEEE and ACM Int’l Symposium on Mixed and Augmented Reality (2007)
- 홍성훈, "국소 집단 최적화 기법을 적용한 비정형 해저면 환경에서의 비주얼 SLAM", 로봇학회 논문지, 9(4), pp.197~205 (2014), 한국로봇학회[DOI]
- S. Takezawa, "SLAMin indoor environments with stereo vision", IEEE, 2004, 1866~1871
- J.P. Tardif, "Monocular visual odometry in urban environments using an omnidirectional camera", IEEE, 2008, 22~26
- C. Kerl, "Dense visual SLAM for RGB-D camera", IEEE, 2013, 2100~2106
- D. Nistér, "Preemptive RANSAC for live structure and motion estimation", Machine Vision and Applications, 16(5), pp.321~329 (2005)
- G. Silveira, "An Efficient Direct Approach to Visual SLAM", IEEE Trans. Robotics, 24(5), pp.969~979 (2008)
- J. Engel, "LSD-SLAM : Large-Scale Direct Monocular SLAM", European Conf. on Computer Vision, pp.1~16 (2014)
- Y. Lu, "High Level Landmark-Based Visual Navigation Using Unsupervised Geometric Constraints in Local Bundle Adjustment", IEEE Int’l Conf. on Robotics and Automation, pp.1540~1545 (2014)
- J. Lee, "Camera calibration from a single image based on coupled line cameras and rectangle constraint", 21st Int’l Conf. on Pattern Recognition, pp.758~762 (2012)
- R. Hartley, "Multiple View Geometry in Computer Vision" (2003), Cambridge University Press
- J. Lee, "New Geometric Interpretation and Analytic Solution for Quadrilateral Reconstruction", 22nd Int’l Conf. on Pattern Recognition, pp.4015~4020 (2014)