一种复杂背景下的运动目标提取算法

本文首先概述了目标提取的诸多算法,然后针对复杂背景下的运动目标提取,重点研究了帧间图像差分算法,设计了一种目标提取算法模型,最后提出了一种基于对象的目标提取方法并进行了仿真实验。     

Stabilization of a Linear Object by Frequency-Modulated Pulsed Signals

A control system consisting of an unstable continuous linear part and a pulse-frequency modulator in the feedback circuit is studied. Conditions for the boundedness of the solutions of the system under any initial data are determined.     

一种大目标去除的图像修复方法

提出了一种新的大目标去除的图像修复方法,即先采用结构传播,再采用相关的纹理传播来完成修复工作.该方法要求人为指出少量的曲线来表示缺损结构从已知区域向未知区域的传播情况.然后,在这些曲线周围的已知区域中选择适当的样本块,作为未知区域内合成这些曲线的目标块.这样,就可以使用这些获得的目标块来完成图像中缺损结构的修复.对于图像中未知区域内的其它部分的修复,可以使用纹理传播来完成.实验结果表明这种方法对于跳跃性结构的修复是非常有效的.     

一种大目标去除的图像修复方法

提出了一种新的大目标去除的图像修复方法,即先采用结构传播,再采用相关的纹理传播来完成修复工作。该方法要求人为指出少量的曲线来表示缺损结构从已知区域向未知区域的传播情况。然后,在这些曲线周围的已知区域中选择适当的样本块．作为未知区域内合成这些曲线的目标块。这样．就可以使用这些获得的目标块来完成图像中缺损结构的修复。对于图像中未知区域内的其它部分的修复,可以使用纹理传播来完成。实验结果表明这种方法对于跳跃性结构的修复是非常有效的。     

运动目标的检测与跟踪的研究

提出了一个基于TMS320C6201的DSP系统下的运动目标检测方法,主要应用于反坦克导弹系统.首先进行滤波,然后根据自适应梯度算法(边缘检测)计算出运动目标的位置,利用相关跟踪算法和记忆外推跟踪算法相结合实现复杂背景中运动目标的实时跟踪.给出运动目标检测和跟踪的实验结果.     

Stabilization of a Linear Discrete System: A Modification of the Problem

A method of constructing the minimal stabilizing sequence for an interval linear system over the field of real numbers is designed. The problem is shown to be reducible to an interval system of linear algebraic equations.     

On a Stabilization Problem of Nonlinear Programming Neural Networks

Intrinsically, Lagrange multipliers in nonlinear programming algorithms play a regulating role in the process of searching optimal solution of constrained optimization problems. Hence, they can be regarded as the counterpart of control input variables in control systems. From this perspective, it is demonstrated that constructing nonlinear programming neural networks may be formulated into solving servomechanism problems with unknown equilibrium point which coincides with optimal solution. In this paper, under second-order sufficient assumption of nonlinear programming problems, a dynamic output feedback control law analogous to that of nonlinear servomechanism problems is proposed to stabilize the corresponding nonlinear programming neural networks. Moreover, the asymptotical stability is shown by Lyapunov First Approximation Principle.     

视频序列图像中运动对象分割综述*

视频分割技术作为多媒体技术应用的一个主要方面, 在视频编码、检索、多媒体交互中存在着广阔的前景, 而且在计算机视觉中也有着极为重要的应用; 但是由于视频图像内容复杂, 还没有一个通用的分割方法, 视频分割算法还面临着挑战。主要介绍视频分割中采用的一些算法, 并对各种算法和性能进行了比较和讨论。     

Optimal Representative Blocks for the Efficient Tracking of a Moving Object

Optimal representative blocks are proposed for an efficient tracking of a moving object and it is verified experimentally by using a mobile robot with a pan‐tilt camera. The key idea comes from the fact that when the image size of a moving object is shrunk in an image frame according to the distance between the camera of mobile robot and the moving object, the tracking performance of a moving object can be improved by shrinking the size of representative blocks according to the object image size. Motion estimation using edge detection (ED) and block‐matching algorithm (BMA) are often used in the case of moving object tracking by vision sensors. However, these methods often miss the real‐time vision data since these schemes suffer from the heavy computational load. To overcome this problem and to improve the tracking performance, the optimal representative block that can reduce a lot of data to be computed is defined and optimized by changing the size of the representative block according to the size of object in the image frame. The proposed algorithm is verified experimentally by using a mobile robot with a two degree‐of‐freedom active camera. © 2004 Wiley Periodicals, Inc.     

基于新的码书模型检测动态背景下的运动目标

为了能有效解决动态背景下运动目标的检侧问题,给出了一种结合HSV颜色空间和图像分块思想的码书模型方法.这种方法可以分为三步:首先根据视频图像大小,合理确定其分块的大小;然后根据HSV颜色空间下的亮度和颜色扭曲度信息构造块码书模型;最后利用得到的块码书模型检测运动目标,并且同时更新此码书模型.实验结果证实:对存在动态因素的背景视频,提出的方法不仅能有效抑制伪目标的出现,而且能准确、实时地检测出真实的运动目标.     

交通视频图像中运动目标的提取

主要阐述交通视频检测中背景模型的建立,在普通均值法提取背景的基础上,提出改进的均值提取法,并通过实验验证和对比。论证改进的均值法在提取背景图像方面,可以减少背景中的车辆幻影,得到效果比较好的背景图,进而对视频中运动目标的提取作介绍,并通过实验得到所需的前景图,即运动目标,为后续的车流量计数工作做好基础准备。     

视频运动对象分割技术的研究

随着视频标准MPEG-4和MPEG-7的出现，视频运动对象的分割显得极其重要．详细分析了几种典型的视频运动对象分割技术，并对视频运动对象分割技术的发展趋势进行了展望。     

虚拟场景中有宽度物体移动路径的优化方法

提出一种虚拟场景中有宽度物体移动路径的优化方法,在地图掩码数据经过寻路算法搜索后,得到一组连续路径节点组成的节点集,从起始节点出发,沿着路径节点找出离起始节点最远且没有障碍物遮挡的可见节点,作为下一个起点,循环往复直至节点集的终止节点,并顺序连接这些可见节点,即可得到优化路径。通过合并节点集中的多余节点,使路径更平滑,从而减少物体移动过程中改变方向的次数,解决有宽度物体无法通过狭窄通道后,须重新计算路径的问题,达到了更好的用户体验效果。     

Optimization of a Data Dependence Graph for the Local Microcode Compaction Problem. Part 1: Problem Statement

A traditional approach to solving the problem of local compaction of a horizontal microcode is described. In accordance with this approach any linear segment of the source microcode is made to correspond to a unique data dependence graph. A notion of the data exchange between the microoperations is introduced. Based on this notion, a model is developed that demonstrates that a given linear segment is, generally, associated with a set of semantically equivalent data dependence graphs, which differ from one another by the order of the execution of the exchanges on shared static resources. An optimization combinatorial problem on the permutation of the exchanges of a linear segment is formulated. Conditions for the existence of an admissible solution are studied, and a method for finding it is developed. A new space of solutions for the local compaction problem is obtained through the use of a new data dependence graph, which is, in a sense, better than the original one.     

Exponential Set-Point Stabilization of Underactuated Vehicles Moving in Three-Dimensional Space

This paper investigates the stabilization of underactuated vehicles moving in a three-dimensional vector space.The vehicle’s model is established on the matrix Lie group SE(3),which describes the configuration of rigid bodies globally and uniquely.We focus on the kinematic model of the underactuated vehicle,which features an underactuation form that has no sway and heave velocity.To compensate for the lack of these two velocities,we construct additional rotation matrices to generate a motion of rotation coupled with translation.Then,the state feedback is designed with the help of the logarithmic map,and we prove that the proposed control law can exponentially stabilize the underactuated vehicle to the identity group element with an almost global domain of attraction.Later,the presented control strategy is extended to set-point stabilization in the sense that the underactuated vehicle can be stabilized to an arbitrary desired configuration specified in advance.Finally,simulation examples are provided to verify the effectiveness of the stabilization controller.     

一类缺乏明确平衡点的不确定系统的部分变量镇定

针对一类缺乏明确平衡点的不确定系统,研究了系统部分变量的稳定性问题. 提出了将一致最终有界和渐近稳定相结合的系统稳定性模式,并给出了该系统稳定性模式的条件. 基于该稳定性模式,提出了阻尼配置控制方案,使系统部分变量在不同阶段稳定于给定运行区域和原点. 所开展的研究工作拓展了不确定系统的稳定性研究,解决了工业应用中普遍存在的一类缺乏明确平衡点的不确定系统的部分变量控制问题. 永磁同步电机的仿真验证了研究结果的有效性和实用性.     

Some Problems of Robust Control of a Stochastic Object

Studies are made of a problem of constructing a robust system according to an averaged performance criterion of a stochastic control system. Cases of the parametric and the structural uncertainty are considered. The relation of the notion of the stochastic robustness to the classical definition of deterministic systems is shown. A comparative analysis of the suggested method of developing a robust system and some other approaches is carried out.     

视频序列中运动目标自动提取的研究

本文提出了一种从彩色视频序列中,有效分割运动目标的算法。首先将当前帧图像和背景参考图像在YUV彩色空间中进行距离差分得到距离差分图像,然后根据差分图像直方图的单峰聚集特性,提出了基于直方图的自适应聚类分割算法;对分割后的二值图像采用图像形态学方法去除无用的噪声斑点,并根据得到运动模板,提出了背景参考图像的更新策略。实验结果表明这是一种简单、有效的运动目标提取方法。     

视频中运动目标检测方法的研究与应用

介绍了一种在视频中运用序列图像检测运动目标的方法。采用累积差分图像的策略,突出目标、消除干扰,去除背景并降低平均噪声;将图像序列分为两个阶段。分别求取差分图像的累积图像,以便消除背景中周期性的运动;结合形态学分析方法去除噪声、斑点,求取目标的运动轨迹和定位目标。     

视频图像序列中运动目标区域检测算法研究

文章针对视频图像的特点,提出一种基于背景差分法的运动目标区域检测算法。该算法利用当前图像与背景图像作差分,并采用一阶Kalman滤波实现动态背景图像的更新,接着采用自适应阈值法进行运动区域分割,经过滤波处理即可得到运动目标区域。实验结果表明所提出的算法具有较理想的效果。