Modified homogeneous parameterization for monocular SLAM
Modified homogeneous parameterization for monocular SLAM
摘要
Feature initialization is an important issue in the monocular simultaneous locahzation ana mapping (SLAM) literature as the feature depth can not be obtained at one observation. In this paper, we present a new feature initialization method named modified homogeneous parameterization (MHP), which allows undelayed initialization with scale invariant representation of point features located at various depths. The linearization error of the measurement equation is quantified using a depth estimation model and the feature initialization process is described. In order to verify the performance of the proposed method, the simulation is carried out. Results show that with the proposed method, the SLAM algorithm can achieve better consistency as compared with the existing inverse depth parameterization (IDP) method.
参考文献19
-
1Davison A J. Real-time simultaneous localization and mapping with a single camera. In: Proceedings of the International Conference on Computer Vision, Nice, France, 2003. 1052-1067.
-
2Eade E, Drummond T. Scalable monocular SLAM. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York, USA, 2006. 469-476.
-
3Davison A J, Reid I D, Mohon N D, et al. Monoslam real-time single camera slam. IEEE Transactions on Pat tern Analysis and Machine Intelligence, 2007, 29 (6) 1052-1067.
-
4Holmes S A, Klein G, Murray D W. An 0 (N2) square root unscented Kalman filter for visual simultaneous lo- calization and mapping. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31 (7) : 1251- 1263.
-
5Lemaire T, Lacroix S, Sola J. A practical 3D bearing-on- ly SLAM algorithm. In: Proceedings of the International Conference on Intelligent Robots and Systems, Edmon- ton, Canada, 2005. 2449-2454.
-
6Sola J, Monin A, Devy M, et al. Undelayed initialization in bearing only SLAM. In: Proceedings of the Interna- tional Conference on Intelligent Robots and Systems, Ed- monton, Canada, 2005. 2499-2504.
-
7Ngai M K, Quang P H, Shoudong H, et al. Mobile robotlocalization and mapping using a Gaussian sum filter. In- ternational Journal of Control, Automation, and Sys- tems, 2007, 5(3):251-268.
-
8Montiel J M M, Civera J, Davison A J. Unified inverse depth parameterization for monocular SLAM. In: Pro- ceedings of the Robotics : Science and Systems, Philade- phia, USA, 2006. doi: 10.1.97. 2675.
-
9Pinies P, Lupton T, Sukkarieh S, et al. Inertial aiding of inverse depth SLAM using a monocular camera. In: Pro- ceedings of the International Conference on Robotics and Automation, San Diego, USA, 2007. 2797-2802.
-
10Pinies P, Tardos J D.-Large Scale SLAM building condi- tionally independent local maps: Application to monocu- lar vision. IEEE Transactions on Robotics, 2008, 24 (5) :1094-1106.
-
1Wei Liu,Nanning Zheng,Zejian Yuan,Pengju Ren,Tao Wang.Robust monocular SLAM towards motion disturbance[J].Chinese Science Bulletin,2014,59(17):2050-2056. 被引量:3
-
2顾照鹏,刘宏.单目视觉同步定位与地图创建方法综述[J].智能系统学报,2015,10(4):499-507. 被引量:21
-
3杨秀华,陈涛,王延风,吉桐伯.光电跟踪目标的非线性滤波算法研究[J].仪器仪表学报,2004,25(z1):810-812. 被引量:14
-
4陈世辉.机械CAD制图的初始化与国家标准应用[J].机械工业标准化与质量,2002(7):4-7. 被引量:4
-
5姚妮,李红婵.基于混合蝙蝠算法的多目标柔性作业车间调度问题[J].微电子学与计算机,2017,34(3):25-29. 被引量:1
-
6Jun-jie CAO Zhi-xun SU Xiu-ping LIU Hai-chuan BI.Measured boundary parameterization based on Poisson's equation[J].Journal of Zhejiang University-Science C(Computers and Electronics),2010,11(3):187-198.
-
7王首珏.UV-260可见紫外分光光度计开机故障排除二则[J].上海生物医学工程,1999,20(2):64-64.
-
8王淇胜,李华军.纯方位目标跟踪—直角坐标卡尔曼滤波算法[J].青岛海洋大学学报(自然科学版),2000,30(2):352-356. 被引量:10
-
9刘磊,吴谦,曹育,吕苏荷.某电控式空氧混合器的线性化讨论[J].中国高新技术企业,2015(1):91-93. 被引量:2
-
10姜文雪,周凯.基于干扰观测器的磁悬浮系统精确反馈线性化[J].清华大学学报(自然科学版),2015,55(10):1067-1071. 被引量:5