UKF Algorithm Based on MEstimators and Its Application in Motion Estimation
ZHOU LuPing1, WANG ZhiLing1, CHEN ZongHai1,2
1.MDEMS Key Laboratory of Multimedia Calculation and Communication, Department of Automation, University of Science and Technology of China, Hefei, 230027 2.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100080
Abstract To solve the problems on nonlinear of motion model and robustness of motion estimation, a robust unscented kalman filter (UKF) method called MUKF is proposed, which is combined with the principle of the equivalent weight of Mestimate. In this method, the UKF is used to get the initial estimation of the parameters of motion. Then more accurate estimations are obtained by MUKE. The combination of Mestimators and UKF not only solves the nonlinear problems but also conquers the inflation of outliers, which has greatly improved the robustness of estimation. Finally, experimental results demonstrate the validity of the proposed method.
[1] Hou Feili, Zhu Feng. Kalman Filter for 3D Motion Estimation via Lagrange Interpolation and Numerical Integration // Proc of the IEEE International Conference on Robotics and Biomimetics. Shengyang, China, 2004: 693699 [2] Welch G, Bishop G. An Introduction to the Kalman Filter. Technical Report, 95041, Chapel Hill, USA: University of North Carolina. Department of Computer Science, 2004: 116 [3] Julier S J, Uhlmann J K. A New Extension of the Kalman Filter to Nonlinear Systems // Proc of the 11th International Symposium on Aerospace/Defense Sensing, Simulation and Control. Orlando, USA, 2000: 447482 [4] Wang Hua. Robust Motion Estimation in Video Coding at Low BitRate // Proc of the IEEE International Conference on Robotics, Intelligent Systems and Signal Processing. Changsha, China, 2003, Ⅱ: 794798 [5] Huber P J. Robust Estimation of a Location Parameter. Annals of Mathematical Statistics, 1964, 35(2): 73101 [6] Li Peihua, Zhang Tianwen, Ma Bo. Unscented Kalman Filter for Visual Curve Tracking. Image and Vision Computing, 2004, 22(2): 157164 [7] Chan S C, Zhang Z G, Tse K W. A New Robust Kalman Filter Algorithm under Outliers and System Uncertainties // Proc of the IEEE International Symposium on Circuits and Systems. Kobe, Japan, 2005, Ⅴ: 43174320 [8] Rousseeuw P J. Least Median of Squares Regression. Journal of the American Statistical Association, 1984, 79(6): 871880 [9] Huber P J. Robust Statistics: A Review. Annals of Mathematical Statistics, 1972, 43(4): 10411067 [10] Cheng Yijun, Sun Haiyan, Cheng Haibin. Robust Estimate of Kalman Filtering and Its Application in Adjustment of Dynamic Leveling Network. Engineering of Surveying and Mapping, 2004, 13(4): 5557,71 (in Chinese) (程义军,孙海燕,程海斌.抗差卡尔曼滤波及其在动态水准网差中的应用.测绘工程, 2004, 13(4): 5557,71) [11] Hu Yusuo, Chen Zonghai. Adaptive Image Smoothing Based on Robust Estimation. Journal of University of Science and Technology of China, 2006, 36(2): 153157 (in Chinese) (胡玉锁,陈宗海.一种基于鲁棒估计的自适应的图像平滑方法.中国科学技术大学学报, 2006, 36(2): 153157) [12] Voss H U, Timmer J, Kurths J. Nonlinear Dynamical Systems Identification from Uncertain and Indirect Measurements. International Journal of Bifurcation and Chaos, 2004, 14(6): 19051933 [13] Yao Yisheng, Chellappa R. Dynamic Feature Point Tracking in an Image Sequence. Pattern Recognition, 1994, 1(1): 654657
2007, Vol. 20 
