스케일 불변 특징을 이용한 이동 로봇의 위치 추정 및 매핑
Mobile Robot Localization and Mapping using Scale-Invariant Features
1
조회
0
다운로드
1
인용
0
참고문헌
초록
로봇이 자율주행을 하는데 있어 중요한 요소는 로봇 스스로 위치를 추정하고 동시에 주위 환경에 대한 지도를 작성하는 것이다. 본 논문에서는 스케일 불변 특징을 이용한 비전 기반 위치 추정 및 매핑 알고리즘을 제안한다.로봇에 어안렌즈가 부착된 카메라를 천정을 바라볼 수 있도록 부착하여 스케일 불변 특징을 갖는 고급의 영상 특징을 구하여 맵 빌딩과 위치 추정을 수행한다. 먼저, 전처리 과정으로 어안렌즈를 통해 입력된 영상을 카메라 보정을 행하여 축방향 왜곡을 제거하고 레이블링과 컨벡스헐을 적용하여 천정영역과 벽영역으로 분할한다. 최초 맵 빌딩시에는 분할된 영역에 대해 특징점을 구하고 맵 데이터베이스에 저장한다. 맵 빌딩이 종료될 때까지 연속하여 입력되는 영상에 대해 특징점들을 구하고 이미 작성된 맵과 매칭되는 점들을 찾고 매칭되지 않은 점들에 대해서는 기존의 맵에 추가하는 과정을 반복한다. 위치 추정은 맵 빌딩과정에서 매칭되는 점들을 찾을 때 동시에 수행되어 진다. 그리고 임의의 위치에서 기존의 작성된 맵과 매칭되는 점들을 찾음으로서 위치 추정이 행해지며 동시에 기존의 맵 데이터베이스의 특징점들을 갱신하게 된다.제안한 방법은 의 영역에 대해 맵 빌딩을 2분내에 수행할 수 있었으며, 위치의 정확도는 ±13cm, 위치에 대한 로봇의 자세(각도)는 ±3도의 오차를 갖는다.
Abstract
A key component of an autonomous mobile robot is to localize itself accurately and build a map of the environment simultaneously. In this paper, we propose a vision-based mobile robot localization and mapping algorithm using scale-invariant features.A camera with fisheye lens facing toward to ceiling is attached to the robot to acquire high-level features with scale invariance. These features are used in map building and localization process. As pre-processing, input images from fisheye lens are calibrated to remove radial distortion then labeling and convex hull techniques are used to segment ceiling region from wall region. At initial map building process, features are calculated for segmented regions and stored in map database. Features are continuously calculated from sequential input images and matched against existing map until map building process is finished. If features are not matched, they are added to the existing map. Localization is done simultaneously with feature matching at map building process. Localization is performed when features are matched with existing map and map building database is updated at same time.The proposed method can perform a map building in 2 minutes on area. The positioning accuracy is ±13cm, the average error on robot angle with the positioning is ±3 degree.
참고문헌 (26)
- J. Borenstein,L. Feng, "Measurement and correction of systematic odometry errors in mobile robots", pp.~5 (1996)
- J. Borenstein, "System and Techniques" (1996), Ltd
- Harris, "C. Geometry from visual motion", pp.264~284 (1992), MIT Press
- Thrun, "A probabilities approach to concurrent mapping and localization for mobile robots", 31-5, pp.1~25 (1998)
- Thrun, "A real-time algorithm for mobile robot mapping with applications to multi-robot and 3D mapping Conference on Robotics and Automation" (2000)
- Dellaert, "Using the condensation algorithm for robust In Proc. of IEEE Conference on Computer Vision and Pattern Recognition" (1999)
- O, "Experiments on augmenting condensation for mobile robot localization of the IEEE International Conference on Robotics and Automation" (2000)
- Sim, "Learning and evaluating visual features for pose estimation of the Seventh International Conference on Computer Vision" (1999)
- Smith, "A stochastic map for uncertain spatial relationships In 4th Int. Symposium on Robotics Research" (1987), MIT Press
- Leonard, "Simultaneous map building and localization for an autonomous mobile robot of IEEE", RSJ International Conference on Intelligent Robots and Systems, 1991., 1442~1447
- Castellanos, "Sensor influence in the performance of simultaneous localisation and map building In Proc. of 6th Int. Symposium an Experimental Robotics", pp.203~212 (1999)
- Williams,S.B.,Newman,P.,Dissanayake,G.,and Durrant-Whyte,H, "Autonomous underwater simultaneous localisation and map building", of int.
- Castellanos, "Simultaneous localisation and map building for mobile robots In Proc. of IEEE Int. Conference on Robotics and Automation" (2000)
- Leonard,J.J, "A computational efficient method for large-scale concurrent mapping and localization" (1999), Springer-Verlag
- Davison, "Dept. of Engineering Science Univ. of Oxford."
- Knight, "of IEEE", RSJ International Conference on Intelligent Robots and Systems, 2001., ~
- R. Tsai, "An efficient and accurate camera calibration technique for 3-D machine vision", pp.364~374 (1986)
- J. Weng,P. Cohen, "Camera calibration with distortion models and accuracy evaluation", 14 no. 10, pp.1992~
- P. Mansbach, "Calibration of a camera and light source by fitting to a physical model", graphics and image processing(35)
- Richard Hartley, "Multiple View Geometry in Computer Vision", pp.166~183 (2000), Cambridge University Press
- E. R. Davies, "Machine Vision Theory Algorithms Practices", pp.142~146 (1997), Academic Press
- K. Mikolajczyk, "A performance evaluation of local descriptors" (2003)
- D. G. Lowe, "Distinctive image features from scale invariant keypoints", 60(2), pp.91~110 (2004)
- D. G. Lowe, "Object recognition from local scale invariant features", pp.1150~1157 (1999)
- M. Brown, "10th International Conference on Computer Vision", recognizing pa(ramas), pp.1218~1225
- Niklas Karlsson, "Core Technologies for Sevice Robotics Proc. of Int. Conf. on IROS2004" (2004)