Stereo-based reconstruction uncertainty and ego-motion estimation

被引：0

作者：

Du, Y. ^{[1
,2
]}

Sun, J. ^{[1
,2
]}

Han, J. ^{[1
]}

Tang, Y. ^{[1
]}

机构：

[1] State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Science

[2] Graduate School of the Chinese Academy of Science

来源：

International Journal of Robotics and Automation | 2009年 / 24卷 / 03期

关键词：

Motion estimation; Reconstruction; Robot; Uncertainty;

D O I：

10.2316/Journal.206.2009.3.206-3268

中图分类号：

学科分类号：

摘要：

Based on the analysis of reconstruction uncertainty, an ego-motion estimation method using the uncertainty to reduce error propagation is proposed. In our method, Harris corners are matched and tracked by an improved MNCC algorithm which is proposed and utilized to reduce illumination effect. The matched and tracked corners are reconstructed by Least-Squares method, and the reconstruction uncertainty is described by covariance matrices. Least-Squares method and Sparse Levenberg-Marquardt method combining the reconstruction uncertainty are utilized to estimate the motion of mobile robot roughly and more accurately, respectively. Simulation results showed that our method can estimate the motion of mobile robot accurately and reduce the error propagation efficiently. Practical experiment results in both outdoor and indoor environments demonstrate the actual validity of our method.

引用

页码：177 / 184

页数：7

共 26 条

[1]

Heimick D.M., Cheng Y., Roumeliotis S.I., Clouse D., Matthies L., Path following using visual odometry for a Mars rover in high-slip environments, Proc. IEEE Aerospace Conference, Big Sky, MT, pp. 1-17, (2004)

[2]

Olson C.F., Matthies L.H., Schoppers M., Maimone M.W., Rover navigation using stereo ego-motion, Robotics and Autonomous Systems, 43, pp. 215-229, (2003)

[3]

Zhu Z.W., Oskiper T., Naroditsky O., Samarasekera S., Sawhney H.S., Kumar R., An improved stereo-based visual odometry system, Proc. Performance Metrics for Intelligent Systems, pp. 149-156, (2006)

[4]

Garcia-Garcia R.G., Sotelo M.A., Parra I., Fernandez D., Gavilan M., 3D visual odometry for GPS navigation assistance, Proc. IEEE Intelligent Vehicles Symposium, Istanbul, Turkey, pp. 444-449, (2007)

[5]

Comport A.I., Malis E., Rives P., Accurate quadrifocal tracking for robust 3D visual odometry, Proc. IEEE International Conf. on Robotics and Automation, pp. 40-115, (2007)

[6]

Kelly J., Sukhatme G., An experimental study of aerial stereo visual odometry, Proc. 6th IFAC Symposium on Intelligent Autonomous Vehicles, (2007)

[7]

Ready B.B., Taylor C.N., Improving accuracy of MAV pose estimation using visual odometry, Proc. American Control Conference, pp. 3721-3726, (2007)

[8]

Ni K., Dellaert F., Stereo tracking and three-point/one-point algorithms: A robust approach in visual odometry, Proc. IEEE International Conf. on Image Processing, pp. 2777-2780, (2006)

[9]

Cheng Y., Matthies L., Two years of visual odometry on the mars exploration rovers, Journal of Field Robotics, 24, pp. 169-186, (2007)

[10]

Lappe M., Frenz H., Buehrmann T., Kolesnik M., Virtual odometry from visual flow, Proc. SPIE/IS&T Conf. on Human Vision and Electronic Imaging X, (2005)

← 1 2 3 →