Evasion of a moving object from detection by a system of observers: Sensor–maneuvering search means

Consideration was given to planning the optimal evasion trajectory of a moving object from the system of observers consisting of a sensor and initial and terminal points of the route. An optimization criterion was proposed. The optimal trajectory and the speed mode of the moving object were determined for sector and ring—the two zones of search for the maneuvering search means.     

Evasion from Detection by a System of Heterogenous Observers: One Sensor and a Group of Detectors

This paper considers the problem of moving object evasion from detection in the plane. Detection is performed by a system of heterogenous observers that consists of one sensor and a group of detectors. We establish the optimal evasion law in explicit form for the case when the level of transmitted signal has power-type dependence on the evader’s speed. The paths to evade the system of observers and penetrate through the system are constructed.     

Evasion of a moving object from detection by a system of heterogenous observers in the threat environment

This paper presents a formalization and the results of solution for the problem of moving object evasion from detection on a plane. Detection is performed by a system of heterogenous stationary observers by the last transmitted signals of the primary and reflected (secondary) fields in the passive and active modes, respectively. Simulation results are given.     

Evasion on plane from a single mobile observer in the conflict environment

Consideration was given to the problem of evasion of a mobile object from the moving observer in a conflict environment. A law of control of the mobile object speed was established. The optimal motion trajectory was constructed, and the time dependence of the accumulated signal was compared for other laws of control.     

Optimization of the law of moving object evasion from detection under constraints

Consideration was given to optimization of the laws of moving object evasion from detection under the coordinate and phase constraints.     

Analytical Method for Solution of the Game Problem of Soft Landing for Moving Objects

A game problem of pursuit of a controlled object moving in a horizontal plane, by another object, moving in a three-dimensional space, is treated. The dynamics of the players models motion in a medium characterized by friction. Initial phase states are described, and sufficient conditions on parameters of a conflict-controlled object are derived, for which the soft landing may be performed.     

Mobile object evasion from detection by a group of observers

Solution of the optimization problem of an open-loop evasion law is presented for mobile object which avoids detection by a group of observers. Control vector includes evasion path and speed law defined on the path.     

Estimating the kinematics and structure of a rigid object from asequence of monocular images

The problem considered involves the use of a sequence of noisy monocular images of a three-dimensional moving object to estimate both its structure and kinematics. The object is assumed to be rigid, and its motion is assumed to be smooth. A set of object match points is assumed to be available, consisting of fixed features on the object, the image plane coordinates of which have been extracted from successive images in the sequence. Structure is defined as the 3-D positions of these object feature points, relative to each other. Rotational motion occurs about the origin of an object-centered coordinate system, while translational motion is that of the origin of this coordinate system. In this work, which is a continuation of the research done by the authors and reported previously (ibid., vol.PAMI-8, p.90-9, Jan. 1986), results of an experiment with real imagery are presented, involving estimation of 28 unknown translational, rotational, and structural parameters, based on 12 images with seven feature points     

基于BRISK特征的动态背景下运动目标检测

针对动态背景下运动目标检测过程中对检测算法实时性和鲁棒性的要求,提出了一种基于二进制鲁棒不变尺度特征(BRISK)的运动目标检测算法.通过改进的BRISK算法检测特征点;为了保证匹配精度和速度,采用K最近邻(KNN)算法进行特征点匹配;运用基于随机抽样一致性(RANSAC)的全局运动参数估计法获取最优全局运动参数;采用帧间差分法进行运动目标检测.实验结果表明:改进的BRISK算法减少了49.8％的特征点数目,KNN算法去除了85.9％的特征点对;在各种场景下能够准确地检测出运动目标,与以往算法相比检测效果较好.     

一种光学式运动捕捉系统下的物体运动数据捕捉方法研究

多相机视觉运动捕捉系统能通过捕捉标记点的空间坐标来获得运动物体的运动学参数,文中提出了一种基于多相机运动捕捉系统下的通用物体运动数据捕捉方法;首先根据3个标记点组成固定模型获取物体运动过程中对应标记点的瞬时坐标,然后通过向量法求解出被测物体在运动过程中各采集点对应的物体位姿,然后通过卡尔曼滤波方法消除运动捕捉过程中的系统和环境误差的影响,获得平滑的物体位姿运动轨迹,并根据滤波数据计算出物体在各采集点对应的速度、加速度、角速度、角加速度;最后基于协作机器人进行物体的运动数据捕捉实验,验证了所提出物体运动数据捕捉方法的正确性。     

基于RBF神经网络的复杂背景下的运动目标检测

由于运动摄像机的存在使得复杂背蒂下的运动目标检测问题更加复杂,根据场景中目标与背景具有不同的运动、任意场景可以分成不同的运动区域这一基拳事实,提出一种新的基于RBF神经网络的运动目标检测算法。运动补偿后求参考帧与补偿后的当前帧之间的光流,联合当前像素坐标及其灰度值得到五雏特征向量作为RBF网络的输入,RBF网络学习算法通过最小化由Bayesian理论和能量最小化理论导出的损失函数实现。学习矢量量化方法修正网络的中心,收敛后网络的输出就是运动目标区域。试验结果证明了算法的有效性。     

基于移动机器人视觉系统的运动目标提取方法

提出了基于移动机器人视觉系统的运动目标提取方法。以视觉系统获取的视频作为研究对象,通过全局运动估计、目标背景的提取、三帧差技术和区域生长方法提取运动目标。采用邻域搜索运动补偿和带约束的区域生长的方法,降低了时间开销。实验结果表明,在时间开销和目标的提取上取得了较好的效果。     

Detecting moving objects using the rigidity constraint

A method for visually detecting moving objects from a moving camera using point correspondences in two orthographic views is described. The method applies a simple structure-from-motion analysis and then identifies those points inconsistent with the interpretation of the scene as a single rigid object. It is effective even when the actual motion parameters cannot be recovered. Demonstrations are presented using point correspondences automatically determined from real image sequences     

Choosing the sequence of approach of a nonlinear object to a group of moving points

The problem of the fastest sequential approach of a controlled object, described by a nonlinear third-order system, to a group of points is considered. The necessary condition of the approach sequence optimality is obtained. Examples are given.     

鱼眼相机与PTZ相机相结合的主从目标监控系统

提出了一种将鱼眼相机和PTZ相机相结合的主从目标监控系统,充分利用鱼眼相机单镜头半球空间成像以及PTZ相机指向性高分辨率成像的优点,实现了单系统半球空间运动目标的高分辨率成像监控。首先采用运动点团模式实现鱼眼图像中运动目标的检测;然后在鱼眼图像空间计算目标的相对方位角P′、俯仰角T′和距离Z′;最后通过参数映射将其映射到PTZ图像空间,输出PTZ控制信号给相机进行指向性成像。PTZ图像空间中的P参数和T参数结合鱼眼镜头畸变系数进行校正计算,Z参数根据目标在鱼眼图像中的相对尺寸及PTZ图像中需要的尺寸进行计算。通过对PTZ参数的多次实验测量,其结果的误差均在系统要求范围之内。系统实际的户外测试结果表明,系统能准确检测出鱼眼图像中的运动目标,在PTZ参数的控制下,PTZ相机能准确指向目标进行二次高分辨率成像,目标在PTZ图像中的位置和大小合适,达到预期的设计目标。     

Optimal servicing strategy design problems for stationary objects in a one-dimensional working zone of a processor

We introduce a model of one-stage service for a group of stationary objects located along a one-dimensional working zone of a moving processor. For the servicing, the processor sequentially performs two passes between boundary points of the working zone: the direct pass, servicing some of the objects, and the reverse pass, servicing all remaining objects of a group. With each object, we associate an individual penalty function that increases monotonely with the time of finishing its servicing. We formulate design problems for optimal servicing strategies, give algorithms of their solutions, and study the issues of computational complexity.     

Reflectance and Shape from Images Using a Collinear Light Source

In this paper, a novel technique, called the photogeometric technique, is presented for surface reflectance extraction and surface recovery from an image sequence of a rotating object illuminated under a collinear light source (where the illuminant direction of the light source lies on or near the viewing direction of the camera). The rotation of the object is precisely controlled. The object surface is assumed to be smooth and uniform. The technique first computes the 3D locations of some surface points which give singular brightness values and builds the surface reflectance function by extracting the brightness values of these surface points from the image sequence. Then the technique uses the surface reflectance function and two images of the surface to recover surface depth and orientation simultaneously. The technique has been tested on real images of surfaces with different reflectance properties and geometric structures. The experimental results and comprehensive analysis show that the proposed technique is efficient and robust.     

动摄像机下基于SIFT特征匹配和MHI的目标检测

摄像机的运动使得复杂背景下动目标的检测复杂化。为了应对动态变化的背景,本文提出基于SIFT特征匹配和运动历史图的目标检测算法。首先用SIFT算法提取特征点,采用RANSAC方法求得仿射变换模型参数并实现图像的全局运动补偿,最后利用运动历史图的方法检测出动目标。SIFT特征点匹配的准确性和RANSAC方法去除异常点的有效性使得仿射变换模型参数计算准确,运动历史图则给出了动目标清晰的轮廓,并指明了动目标的运动方向。与Ninad Thakoor实验结果对比说明:该算法能够准确地检测出动目标,并且显示了动目标的运动方向。     

视频序列的全景图拼接技术

提出了一种对视频序列进行全景图拼接的方法。主要讨论了有大面积的非刚性运动物体出现的序列，不过此方法也同样适用于无运动物体的纯背景序列。为计算各帧间的投影关系，用仿射模型来描述摄像机运动，并用特征点匹配的方法计算出模型中各参数的值。由于用相关法计算的匹配结果准确率比较低，所以用RANSAC（Random Sampling Consensus）对匹配结果进行了筛选，可以准确求出摄像机运动参数。利用运动参数进行投影，然后用多帧相减并求交集，估计出每帧图像中运动物体存在的区域，最后计算得到了全景图。该方法的结果与前人得到的结果进行了比较，证明用此方法能获得质量较高的全景图。     

运动物体的头戴式视线追踪控制系统设计

设计了一种基于嵌入式的头戴式视线追踪控制系统.它将实际运动物体作为控制对象,以人眼为控制源,采用图像处理算法和坐标映射模型,实现视线追踪技术.通过质心检测和椭圆拟合算法的比较与优化,系统定位瞳孔中心的角度误差精确到1.4°以内,再利用最小二乘法进行视线空间坐标变换,最终控制运动对象移动到注视点.实验结果表明,人眼距离被控对象2 m内时,被控对象的定点误差在5 cm内,系统响应时间在0.3 s内,满足用户日常操作要求.