Multi-innovation Disturbance Rejection Filtering Algorithm forCoordination on Face Pose
WU Huajing1, LI Jiatian1, LIN Yan2, ZHANG Wenjing2, WANG Congcong1, LI Jian1
1. Faculty of Land Resources Engineering, Kunming University of Science and Technology, Kunming 650093, China;
2. Institute of Information Technology and Cyber Security, People's Public Security University of China, Beijing 100038, China
Abstract：When the deflection angle is large, great noises are brought to the face pose measurement results because the saliency of facial feature points decreases. To solve the problem, a multi-innovation disturbance rejection filtering algorithm is proposed, in which the pose changes between the moving face and the standard face model are taken as filtering observations. (1) Multi-innovation is introduced to modify filtering estimation, and the states of the face pose changes are estimated by the time series of multi-group observations. (2) The convergence of filtering is judged in real time, and then the noise covariances in the observation and the process are estimated by multi-innovation in time to adjust the Kalman gain matrix. (3) The pose coordination model is established and then the camera motion parameters are calculated according to the changes about face pose after filtering, to realize the coordination between the camera and face pose. On the basis of the hardware structure of the test device, the proposed algorithm is compared with the adaptive Kalman filter (AKF) algorithm. The experimental result shows that the pose estimation error of the proposed algorithm is less than 10 mm and the time of camera coordination is about 25 ms for coordination on face pose. Compared with the AKF algorithm, the pose accuracy is improved by 23% and the coordination efficiency is improved by 30%. The influences of the noises from facial pose calculation in pose coordination can be effectively suppressed by the proposed algorithm. It can improve the stability of the system of coordination on face pose and ensure the real-time response.
[1] Jin Y, Soh W S, Motani M, et al. A robust indoor pedestrian tracking system with sparse infrastructure support[J]. IEEE Transactions on Mobile Computing, 2013, 12(7):1392-1403.
[2] Kim S G, Crassidis J L, Cheng Y, et al. Kalman filtering for relative spacecraft attitude and position estimation[J]. Journal of Guidance, Control, and Dynamics, 2007, 30(1):133-143.
[3] Filipe N, Kontitsis M, Tsiotras P. Extended Kalman filter for spacecraft pose estimation using dual quaternions[J]. Journal of Guidance, Control, and Dynamics, 2015, 38(9):1625-1641.
[4] Qiao B, Tang S R, Ma K X, et al. Relative position and attitude estimation of spacecrafts based on dual quaternion for rendezvous and docking[J]. Acta Astronautica, 2013, 91:237-244.
[5] Giannitrapani A, Ceccarelli N, Scortecci F, et al. Comparison of EKF and UKF for spacecraft localization via angle measurements[J]. IEEE Transactions on Aerospace and Electronic Systems, 2011, 47(1):75-84.
[6] Yuan L, Lei R. Target tracking based on amendatory Sage-Husa adaptive Kalman filtering[C]//International Conference on Electronic Science and Automation Control. Paris, France:Atlantis Press, 2015:91-94.
[7] Caceres M A, Sottile F, Spirito M A. Adaptive location tracking by Kalman filter in wireless sensor networks[C]//IEEE International Conference on Wireless and Mobile Computing, Networking and Communications. Piscataway, USA:IEEE, 2009:123-128.
[8] Zhang L, Trinkle J C. The application of particle filtering to grasping acquisition with visual occlusion and tactile sensing[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2012:3805-3812.
[9] Ibarguren A, Maria Martinez-Otzeta J, Maurtua I. Particle filtering for industrial 6DOF visual servoing[J]. Journal of Intelligent and Robotic Systems, 2014, 74(3-4):689-696.
[10] 余洪山,王耀南.基于粒子滤波器的移动机器人定位和地图创建研究进展[J].机器人,2007,29(3):281-289,297. Yu H S, Wang Y N. A review on mobile robot localization and map-building algorithms based on particle filters[J]. Robot, 2007, 29(3):281-289,297.
[11] Mikami D, Otsuka K, Yamato J. Memory-based particle filter for face pose tracking robust under complex dynamics[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, USA:IEEE, 2009:999-1006.
[12] Wang X, Wang S, Ma J J. An improved particle filter for target tracking in sensor systems[J]. Sensors, 2007, 7(1):144-156.
[13] Ji Q. 3D face pose estimation and tracking from a monocular camera[J]. Image and Vision Computing, 2002, 20(7):499-511.
[14] Levine S, Pastor P, Krizhevsky A, et al. Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection[J]. International Journal of Robotics Research, 2018, 37(4-5):421-436.
[15] 厉茂海,洪炳镕,罗荣华,等.基于单目视觉的移动机器人全局定位[J].机器人,2007,29(2):140-144,178. Li M H, Hong B R, Luo R H, et al. Monocular-vision-based mobile robot global localization[J]. Robot, 2005, 27(3):140-144, 178.
[16] 赵天云,郭雷,张利川.基于单目视觉的空间定位算法[J].西北工业大学学报,2009,27(1):47-51. Zhao T Y, Guo L, Zhang L C. A new algorithm of spatial positioning based on mono-vision[J]. Journal of Northwestern Polytechnical University, 2009, 27(1):47-51.
[17] Featherstone R. Rigid body dynamics algorithms[M]. Berlin, Germany:Springer, 2008.
[18] Valenti R G, Dryanovski I, Xiao J Z. A linear Kalman filter for MARG orientation estimation using the algebraic quaternion algorithm[J]. IEEE Transactions on Instrumentation and Measurement, 2016, 65(2):467-481.
[19] Lu P, Zhao L, Chen Z. Improved Sage-Husa adaptive filtering and its application[J]. Journal of System Simulation, 2007, 19(15):3503-3505.
[20] 鲍水达,张安,毕文豪.快速强跟踪UKF算法及其在机动目标跟踪中的应用[J].系统工程与电子技术,2018,40(6):1189-1196.Bao S D, Zhang A, Bi W H. Speedy strong tracking unscented Kalman filter and its application in maneuvering target tracking[J]. Systems Engineering and Electronics, 2018, 40(6):1189-1196.
[21] Cressie N, Wikle C K. Space-time Kalman filter[M]//Encyclopedia of Environmetrics. Hoboken, USA:John Wiley & Sons, 2006. DOI:10.1002/9780470057339.vas037.
