We propose a Bayesian higher-order probability logic reasoning approach with interval probability parameters to the problem of making inference from conditional knowledge, which combines weak conditional probability a...
详细信息
The identification of the correspondences of points of views is an important task. A new feature matching algorithm for weakly calibrated stereo images of curved scenes is proposed, based on mere geometric constraints...
详细信息
The identification of the correspondences of points of views is an important task. A new feature matching algorithm for weakly calibrated stereo images of curved scenes is proposed, based on mere geometric constraints. After initial correspondences are built via the epipolar constraint, many point-to-point image mappings called homographies are set up to predict the matching position for feature points. To refine the predictions and reject false correspondences, four schemes are proposed. Extensive experiments on simulated data as well as on real images of scenes of variant dept.s show that the proposed method is effective and robust.
This paper introduces kernels on attributed pointsets, which are sets of vectors embedded in an euclidean space. The embedding gives the notion of neighborhood, which is used to define positive semidefinite kernels on...
详细信息
ISBN:
(纸本)160560352X
This paper introduces kernels on attributed pointsets, which are sets of vectors embedded in an euclidean space. The embedding gives the notion of neighborhood, which is used to define positive semidefinite kernels on pointsets. Two novel kernels on neighborhoods are proposed, one evaluating the attribute similarity and the other evaluating shape similarity. Shape similarity function is motivated from spectral graph matching techniques. The kernels are tested on three real life applications: face recognition, photo album tagging, and shot annotation in video sequences, with encouraging results.
The diode laser welding process is a typical nonlinear system with disturbances and noises. To obtain unbiased estimates for unknown parameters, an identification method based on correlation functions is preferred. In...
详细信息
The main factors of influencing the crack change of concrete dams can be reduced to three parts of water pressure, temperature and aging, but it is very difficult to get the effects of this three parts respectively. T...
详细信息
ISBN:
(纸本)9780784409886
The main factors of influencing the crack change of concrete dams can be reduced to three parts of water pressure, temperature and aging, but it is very difficult to get the effects of this three parts respectively. The nonlinear time-varying relationship between the crack change and its influencing factors is very strong. Using the unique ability of data analysis and learning of artificial neural network, and through the intercrossing of dam construction knowledge, then a good approach to solve these problems can be offered. In this paper, based on in-situ monitoring data of concrete dams, from the angle of machine learning, the time varying analysis model for causality of cracks of concrete dams is introduced, and the evolution law of load cracks with the change of time and load is analyzed and forecasted. The example indicates that the model can finely describe and forecast the time varying characteristic of cracks causality in concrete dams, and can give each factor's contribution to crack opening.
Feature extraction is the key process in any pattern recognition issues. There is no exception in analog circuit fault diagnosis, because fault diagnosis is equivalent to pattern recognition issue in nature. In this p...
详细信息
This paper presents a robust stability analysis approach to stochastic genetic regulatory networks with time-varying delays. By utilizing a Lyapunov functional and conducting stochastic analysis, we show that the addr...
详细信息
The field of Unmanned Aerial Vehicles (UAV) has gained great significance in the R&D activities of several institutions, and numerous realizations have been constructed. Controlling the movement of a UAV is one of...
详细信息
ISBN:
(纸本)9789633130117
The field of Unmanned Aerial Vehicles (UAV) has gained great significance in the R&D activities of several institutions, and numerous realizations have been constructed. Controlling the movement of a UAV is one of the most significant tasks in the hierarchical control system that should be realized in order to successfully manage UAVs in several missions. Precise control of the movement requires accurate mathematical models of the aircraft that correspond to the several control schemes that are intended to apply, including linearised, LPV, and nonlinear ones. The source of mathematical models includes the physical model constructed on the basis of the Newtonian equations and the rules of aerodynamics, as well as the use of empirical observations, measurements. The methodology of system identification offers the tools that can be used to manage this field. The Systems and Control Laboratory of the computer and automation Research Institute in cooperation with University of Minnesota and Budapest University of Technology and Economics has built - as a part of a more general framework established to solve complex UAV control problems - small UAVs, equipped with on-board sensors and embedded computer with the purpose of obtaining an adequate test platform for the aircraft experiments. Based on on-board measurements acquired during the flight tests performed with the UAVs, the opportunity has been given to test several system identification approaches corresponding to the control tasks to be solved. This paper gives an outline of the system identification and modelling methods that have successfully been applied, and also analyzes the problems encountered in the data-acquisition - signal processing - computing chain.
Cell manufacturing is widely introduced to cope with the dynamically changing market demands. This study considers a scheduling method for a cell assembly system for the products that are characterized by the type and...
详细信息
Dynamic singularities make it difficult to plan the Cartesian path of free-floating robot. In order to avoid its effect, the direct kinematic equations are used for path planning in the paper. Here, the joint position...
详细信息
Dynamic singularities make it difficult to plan the Cartesian path of free-floating robot. In order to avoid its effect, the direct kinematic equations are used for path planning in the paper. Here, the joint position, rate and acceleration are bounded. Firstly, the joint trajectories are parameterized by polynomial or sinusoidal functions. And the two parametric functions are compared in details. It is the first contribution of the paper that polynomial functions can be used when the joint angles are limited (In the similar work of other researchers, only sinusoidla functions could be used). Secondly, the joint functions are normalized and the system of equations about the parameters is established by integrating the differential kinematics equations. Normalization is another contribution of the paper. After normalization, the boundary of the parameters is determined beforehand, and the general criterion to assign the initial guess of the unknown parameters is supplied. The criterion is independent on the planning conditions such as the total time tf. Finally, the parametes are solved by the iterative Newtonian method. Modification of tf may not result in the recalculation of the parameters. Simulation results verify the path planning method.
暂无评论