Entity

Time filter

Source Type


Fei Y.,Jilin University | Changjiu Z.,Jilin University | Changjiu Z.,Advanced Robotics and Intelligent Control Center | Yantao T.,Jilin University
International Journal of Security and its Applications | Year: 2016

To improve unconstrained iris recognition system performance in different environments, a performance improvement method of unconstrained iris recognition based on domain adaptation metric learning is proposed. A kernel matrix is calculated as the solution of domain adaptation metric learning. The known Hamming distance computing by intra-class and inter-class is used as the optimization learning constraints in the process of iris recognition. An optimal Mahalanobis matrix is computed for certain cross-environment system, then distance between two iris samples is redefined. The experimental results indicate that the proposed method can increase the accuracy of the unconstrained iris recognition in different circumstances, improving the classification ability of iris recognition system. © 2016 SERSC. Source


Yang T.,Advanced Robotics and Intelligent Control Center | Zhu C.,Nanyang Technological University | Fan X.,Southwest Jiaotong University | Peng Q.,Southwest Jiaotong University
Proceedings - IEEE International Conference on Multimedia and Expo | Year: 2012

Rate-distortion optimization (RDO) is widely employed to maximize coding efficiency in hybrid video coding. Due to an extensive use of spatial-temporal predictions in video coding, a global RDO problem becomes so complex that the processing of each coding unit (e.g. a macro block) is dependent and entangled each other. Usually the RDO is simply performed for each coding unit individually and independently, thus compromising the RDO performance significantly. In this paper, we examine temporal dependent RDO by developing a novel source distortion temporal propagation (SDTP) model, which takes into account the influence of a current coding macro block to future macro blocks in its temporal propagation chain. Accordingly estimations of the influence and the corresponding Lagrange multiplier for the proposed SDTP-based RDO are obtained. Experimental results show consistently a significant coding gain of the proposed scheme over H.264/AVC. © 2012 IEEE. Source


Zhang L.,Dalian Jiaotong University | Zhou C.,Advanced Robotics and Intelligent Control Center
2013 IEEE International Conference on Robotics and Biomimetics, ROBIO 2013 | Year: 2013

The state-of-the-art Kuka youBot is an open-source robot platform. In order to improve youBot arm manipulation performance, a novel robotic trajectory planning method based on geodesics is used for Kuka youBot arm shortest path trajectory planning in this paper. Geodesic is the necessary condition of the shortest length between two points on the Riemannian surface in which the covariant derivative of the geodesic's tangent vector is zero. The Riemannian metric is constructed according to the distance metric by arc length of the youBot arm trajectory to achieve shortest path. Once the Riemannian metric is obtained, the corresponding Riemannian surface is solely determined. Then the geodesic equations on this surface can be determined and calculated. For the given initial conditions of the trajectory, the geodesic equations can be solved and the results are the optimal trajectory of the youBot arm in the joint space for the given metric. The planned trajectories in the joint space can also be mapped into the workspace. A simple trajectory planning example on Kuka youBot arm from camera pose ready point to object grasping point is given to demonstrate the feasibility of the proposed approach. © 2013 IEEE. Source


Zhang L.,Advanced Robotics and Intelligent Control Center | Zhou C.,Advanced Robotics and Intelligent Control Center
Proceedings of the 2012 7th IEEE Conference on Industrial Electronics and Applications, ICIEA 2012 | Year: 2012

This paper presents a human and humanoid robot interaction method using 6-axis force/torque sensors. The Zero Moment Point (ZMP) can be calculated in real time when external forces from human act on the robot. Then the robot will perceive the human intention and walk along the direction where ZMP is moving. We develop a unified formulation of real-time ZMP detection system using 6-axis force/torque sensor in the framework of Lie group. Then the robot is controlled to walk along the ZMP moving direction. Experiment is conducted to verify the effectiveness of the proposed human-robot interaction control system. © 2012 IEEE. Source


Zhang L.,Advanced Robotics and Intelligent Control Center | Zhou C.,Advanced Robotics and Intelligent Control Center
Applied Bionics and Biomechanics | Year: 2012

A novel gait planning method using geodesics for humanoid robot is given in this paper. Both the linear inverted pendulum model and the exact Single Support Phase (SSP) are studied in our energy optimal gait planning based on geodesics. The kinetic energy of a 2-dimension linear inverted pendulum is obtained at first. We regard the kinetic energy as the Riemannian metric and the geodesic on this metric is studied and this is the shortest line between two points on the Riemannian surface. This geodesic is the optimal kinetic energy gait for the COG because the kinetic energy along geodesic is invariant according to the geometric property of geodesics and the walking is smooth and energy saving. Then the walking in Single Support Phase is studied and the energy optimal gait for the swing leg is obtained using our geodesics method. Finally, experiments using state-of-the-art method and using our geodesics optimization method are carried out respectively and the corresponding currents of the joint motors are recorded. With the currents comparing results, the feasibility of this new gait planning method is verified. © 2012 - IOS Press and the authors. All rights reserved. Source

Discover hidden collaborations