基于自适应特征融合的粒子滤波目标跟踪算法

提出了一种基于自适应特征融合的粒子滤波跟踪算法,用于解决传统的粒子滤波跟踪方法在复杂背景下容易跟踪失败的问题。该算法选取颜色特征和边缘特征来描述目标,并通过粒子滤波进行特征融合,根据可靠性因子调整各特征的权值系数;在跟踪过程中,随着目标自身形变,自适应更新目标模板。实验结果表明,在复杂背景下以及受到遮挡时,本算法能够准确稳健地跟踪目标。     

基于分布式聚类的有向传感器网络移动目标跟踪算法研究

针对有向传感器网络DSN（Directional Sensor Networks）中,传感器节点部署数量对目标跟踪精度、网络寿命和能效问题的影响方面,提出了一个分布式聚类算法,该算法在优化活跃传感器和节点的直接通信过程中,由分布式集群来负责协调成员间的节点,通过传输给Sink的定位信息及从多个节点聚集的传感数据来准确定位目标的位置。基于该理论的目标跟踪机制,提高了目标跟踪精度、增加了网络寿命和网络剩余能量。并进行了仿真验证,结果表明该方法能实现更高的跟踪性能。     

结构尺寸对LNG低温螺旋波纹钢管弯曲性能的影响分析

基于ANSYS三维壳模型,依据结构几何尺寸对LNG低温螺旋波纹钢管进行参数化有限元建模.考虑低温环境下材料力学性能的改变和结构几何非线性因素,对弯曲载荷作用下低温螺旋波纹钢管结构力学性能进行数值模拟;分析管体弯曲失效模式和力学行为特点.改变结构几何尺寸,分析比较波峰和波谷极值应力以及管道整体力学性能,发现尺寸参数对低温波纹钢管力学性能的影响显著,分析相应的灵敏度规律,最后给出合理的截面尺寸参数.分析结果可以为低温柔性管道的结构设计提供参考.     

Joint underwater target detection and tracking with the Bernoulli filter using an acoustic vector sensor

In this paper, we study the problem of joint underwater target detection and tracking using an acoustic vector sensor (AVS). For this challenging problem, first a realistic frequency domain simulation is set up. The outputs of this simulation generate the two dimensional FRequency–AZimuth (FRAZ) image. On this image, the random finite set (RFS) framework is employed to characterize the target state and sensor measurements. We propose to use the Bernoulli filter, which is the optimal Bayes filter emerged from the RFS framework for randomly on/off switching single dynamic systems. Moreover, to increase the performance of detection and azimuth tracking in low signal-to-noise ratio (SNR) scenarios, a track-before-detect (TBD) measurement model for AVS is proposed to be used with the Bernoulli filter. Sequential Monte Carlo (SMC) implementation is preferred for the Bernoulli filter recursions. Extensive simulation results prove the performance gain obtained by the proposed approach both in estimation accuracy and detection range of the system.     

Robust Adaptive Neural Control for a Class of Time‐Varying Delay Systems with Backlash‐like Hysteresis Input

This paper proposes a robust adaptive dynamic surface control (DSC) scheme for a class of time‐varying delay systems with backlash‐like hysteresis input. The main features of the proposed DSC method are that 1) by using a transformation function, the prescribed transient performance of the tracking error can be guaranteed; 2) by estimating the norm of the unknown weighted vector of the neural network, the computational burden can be greatly reduced; 3) by using the DSC method, the explosion of complexity problem is eliminated. It is proved that the proposed scheme guarantees all the closed‐loop signals being uniformly ultimately bounded. The simulation results show the validity of the proposed control scheme.     

基于深度图像的人体运动姿态跟踪和识别算法

由于人体运动的复杂性,现有基于低质量深度图像的三维立体姿态跟踪和识别 方法的准确性较低、鲁棒性较差。针对低质量深度图像的人体运动姿态和识别问题,本文设 计了一种基于三步搜索算法的人体运动姿态的跟踪和识别方法。该方法首先对获取的深度信 息进行分析,从而判定人体轮廓;然后通过基于深度图像的骨骼跟踪方法跟踪特定骨骼点, 并采用三步搜索算法进行运动估计,跟踪获取人体运动轨迹;最后利用获取的骨骼点坐标实 现人体运动姿态的识别。实验结果表明,该算法克服光照影响的鲁棒性较强,且能有效地提 高人体运动姿态跟踪与识别的准确性。     

机载跟踪器的逃逸目标图像快速识别模型仿真

机载跟踪器进行逃逸目标识别跟踪的过程中,目标往往是高速移动的,为了逃逸跟踪,运动的速度和方向具有较大的突变性,与跟踪器之间会形成较大的跟踪距离差.传统的视觉方法为了弥补这种距离差,通过减少采集图像的样本,以提高跟踪的准确性,但是一旦样本数量过少,将会导致识别跟踪的准确性降低.提出基于高斯分布的动态逃逸目标识别跟踪方法.对跟踪目标图像进行归一化处理,获取与数据库中的样本图像具有同样的尺寸和分辨率的图像.计算动态目标图像的形心,根据高斯分布原理建立动态目标的识别跟踪模型,并对模型中的相关参数进行及时更新,保证了动态目标识别跟踪的及时性和准确性.实验结果表明,利用改进算法能够有效提高动态目标识别跟踪的准确性,缩短了识别跟踪的时间.     

A Saturating Extension of an Output Feedback Controller for Internally Damped Euler‐Lagrange Systems

In this research, a novel extension of the passivity‐based output feedback trajectory tracking controller is developed for internally damped Euler‐Lagrange systems with input saturation. Compared with the previous output feedback controllers, this new design of a combined adaptive controller‐observer system will reduce the risk of actuator saturation effectively via generalized saturation functions. Semi‐global uniform ultimate boundedness stability of the tracking errors and state estimation errors is guaranteed by Lyapunov stability analysis. An application of the proposed saturated output feedback controller is the stabilization of a nonholonomic wheeled mobile robot with saturated actuators towards desired trajectories. Simulation results are provided to illustrate the efficiency of the proposed controller in dealing with the actuator saturation.     

基于分层光流的煤矿井下运动目标跟踪算法

针对煤矿井下视频序列高噪声、运动目标繁多、目标交错等特点,提出了一种基于分层光流法的矿井运动目标跟踪算法。首先对相邻两帧视频序列采用帧差法确定多个初始目标跟踪模版;然后采用SUSAN角点检测提取模版内的特征点;最后运用改进的分层光流法进行目标检测和跟踪,并在跟踪过程中对模版进行更新。该算法实现了煤矿井下多目标运动物体的稳定跟踪,并能解决目标部分遮挡问题。实验和仿真结果证实了该算法的有效性。     

一种智能寻迹与搬运机器人的控制系统设计

提出寻迹与搬运机器人的一种智能控制系统设计;该系统主要由单片机、传感器和执行舵机组成;通过分析直行、弯道与取物等工作模式,建立相应的舵机驱动控制;传感器将检测到的路线和工件信号传送给单片机进行处理;按照不同的优先级别,由单片机发出脉冲信号,控制舵机的速度与方向,完成抓取、转运工件的任务;实验结果表明:多路传感器的信息融合能有效识别寻迹路径,确定优先级别的控制;舵机的驱动控制能满足寻迹与搬运的要求;系统设计简单,实用可靠,具有良好的开放性与扩展性.