Abstract Common surveillance system is usually limited by the scope of observation, which may increase the probability of missing or misjudging suspicious targets. A wide-field monitoring system based on efficient ima...
详细信息
Abstract Common surveillance system is usually limited by the scope of observation, which may increase the probability of missing or misjudging suspicious targets. A wide-field monitoring system based on efficient image mosaicing algorithm is proposed in this paper. It can monitor a wide field for both short and long distance in real time and highlight the detected moving objects simultaneously. The image mosaicing is not only aimed at obtaining the wide field of view, but also utilized in motion detection for forming a wide-field motion mask. A simulation platform is developed to verify the performance of the system. The experiment results show that it satisfies the demands of high resolution and real-time implementation. The system is of high practical value to transportation surveillance or other applications.
Abstract The segmentation of the medical image faces the challenges of the existence of large number of diverse structures of human anatomy and inevitable artifacts induced from the imaging procedure. In this paper we...
详细信息
Abstract The segmentation of the medical image faces the challenges of the existence of large number of diverse structures of human anatomy and inevitable artifacts induced from the imaging procedure. In this paper we treat some structures and artifacts as general edge features, and introduce the edge information into the mean shift segmentation algorithm in both clustering and the fusion steps. Considering the medical images as two dimensional signals, the general edge can be detected and described with its local spatial frequency properties. The segmentation results show the improvement in preserving the completeness of details while sketching the overall structures.
Abstract Low-altitude penetration is one of the most important military applications of Unmanned Aerial Vehicles (UAVs). 3D route planning, which is a complex multi-objective optimization problem with multiple constra...
Abstract Low-altitude penetration is one of the most important military applications of Unmanned Aerial Vehicles (UAVs). 3D route planning, which is a complex multi-objective optimization problem with multiple constraints, is the key technology of UAV low altitude-penetration. A 3D route planning method based on Multi-Agent Genetic Algorithm (MAGA) is proposed in this paper. Specifically, a dynamic route representation form is proposed to improve the flight route accuracy. An efficient constraint handling method is used to simplify the treatment of multi-constraint and reduce the time-cost of planning computation. More importantly, details are presented to show how to apply MAGA to 3D route planning while some necessary improvements of MAGA are proposed to make it more efficient. Simulation and analysis illustrate the effectiveness of this method.
Abstract This paper presents a 3D online path planning algorithm for unmanned aerial vehicle (UAV) flying in partially known hostile environment. In order to provide a smooth fight route for UAV, the algorithm adopts ...
详细信息
Abstract This paper presents a 3D online path planning algorithm for unmanned aerial vehicle (UAV) flying in partially known hostile environment. In order to provide a smooth fight route for UAV, the algorithm adopts B-Spline curve to describe UAV's path whose control points are optimized by an improved differential evolution algorithm. The planner gradually produces a smooth path for UAV from starting location to its target. Regarding path planning performance, the proposed improved diferential evolution based planner is compared with its three competitors which are based on classical differential evolution, genetic algorithm and particle swarm optimization, respectively. Numerical simulation demonstrates that the proposed UAV path planner not only produces high-quality feasible flight routes for UAV, but also obviously outperforms its competitors.
This paper studies the loading coordinations for large-population autonomous individual (plug-in) electric vehicles (EVs) and a few controllable bulk loads, e.g. EV fleets, pumped storage hydro units, and so on. Due t...
详细信息
ISBN:
(纸本)9781612848006
This paper studies the loading coordinations for large-population autonomous individual (plug-in) electric vehicles (EVs) and a few controllable bulk loads, e.g. EV fleets, pumped storage hydro units, and so on. Due to the computational infeasibility of the centralized coordination methods to the underlying large-population systems, in this paper we develop a novel game-based decentralized coordination strategy. Following the proposed decentralized strategy update mechanism and under some mild conditions, the system may quickly converge to a nearly valley-fill Nash equilibrium. The results are illustrated with numerical examples.
作者:
Gong KunDeng FangMa TaoGong Kun is with School of Automation
Beijing Institute of Technology and Key Laboratory of Advanced Control of Iron and Steel Process (Ministry of Education) Beijing China Deng Fang is with School of Automation
Beijing Institute of Technology and Key Laboratory of Advanced Control of Iron and Steel Process (Ministry of Education) Beijing China Ma Tao is with School of Automation
Beijing Institute of Technology and Key Laboratory of Complex System Intelligent Control and Decision Ministry of Education Beijing China
In order to improve the precision of the azimuth measured by mobile robot's electronic compass, this paper proposes a new calibration method based on Fourier Neural Network trained by Modified Particle Swarm Optim...
详细信息
In order to improve the precision of the azimuth measured by mobile robot's electronic compass, this paper proposes a new calibration method based on Fourier Neural Network trained by Modified Particle Swarm Optimization (MPSO-FNN). This method makes use of Fourier Neural Network (FNN) to establish the error compensation model of electronic compass's azimuth, and introduces Modified Particle Swarm Optimization (MPSO) algorithm to optimize the weights of neural network. Thus the comparatively accurate error model of azimuth is obtained to compensate the output of electronic compass. This method not only has strong nonlinear approximation capability, but also overcomes the neural networks' shortcomings which are too slow convergence speed, oscillation, and easy to fall into local optimum and sensitive to the initial values. Experimental results demonstrate that after calibrated by this method, the range of azimuth error reduces to -0.35°~0.70° from -3.4°~25.2°, and the average value of absolute error is only 0.30°.
The present work considers a scenario that a multi-actuator-sensor network neutralizes poisonous gas and tracks the pollution sources in a bounded area. A novel algorithm is proposed to minimize the system information...
详细信息
The present work considers a scenario that a multi-actuator-sensor network neutralizes poisonous gas and tracks the pollution sources in a bounded area. A novel algorithm is proposed to minimize the system information uncertainty while reaching balance on the workload of actuators. The method combines the centroidal Voronoi tessellations (CVT) with a consensus strategy. The CVT of the region insures a local optimal position configuration of the actuators, thus the sensing uncertainty can be minimized. The consensus algorithm utilizes the connection information among actuators, and helps them to reach a common workload. The consensus component will be terminated or suppressed when the workload is averaged. The consensus component may postpone the realization of CVT configuration. But it could be viewed as a perturbation that helps the actuators jump out of the local optimal CVT configuration. As a result, the information uncertainty may be further reduced. Comparison is drawn between the pure CVT algorithm and the method with consensus strategy. Simulations validated the proposed approach.
An adaptive sliding mode control scheme for electromechanical actuator has been presented. The adaptive control strategy can estimate the uncertain parameters and adaptively compensate the modeled dynamical uncertaint...
详细信息
An adaptive sliding mode control scheme for electromechanical actuator has been presented. The adaptive control strategy can estimate the uncertain parameters and adaptively compensate the modeled dynamical uncertainties, while the sliding mode control method overcomes the unmodelled dynamics. In the adaptive law an equivalent output injection of the sliding mode observer which contains the parameter estimation error is used, and estimates of parameters can approximate the true values without prediction-error that is typically used in compositive adaptive law. Due to the improved estimation of uncertain parameters, the sliding mode law can robustifies the design against model uncertainties with a small swithcing gain. Stability of the system with the proposed approach has been proved and it has also been shown that the system states can reach the sliding mode in finite time. Finally, the effectiveness of the proposed control scheme has been exhibited via simulation examples.
Based on the comparison of several common methods of electronic compass error compensation, this paper presents a new error compensation method based on Adaptive Differential Evolution-Fourier Neural Networks (ADE-FNN...
详细信息
In order to solve the multi-UAV cooperative path planning problem of low-altitude penetration, the paper proposes an improved Multi-agent Coevolutionary Algorithm (IMACEA), which introduces co-evolution mechanism base...
详细信息
暂无评论