适用于旋转摄像下目标检测的图像补偿

目的 摄像机旋转扫描条件下的动目标检测研究中,传统的线性模型无法解决摄像机旋转扫描运动带来的图像间非线性变换问题,导致图像补偿不准确,在动目标检测时将引起较大误差,造成动目标虚假检测。为解决这一问题,提出了一种面阵摄像机旋转扫描条件下的图像补偿方法,其特点是能够同时实现背景运动补偿和图像非线性变换补偿,从而实现动目标的快速可靠检测。方法 首先进行图像匹配,然后建立摄像机旋转扫描非线性模型,通过参数空间变换将其转化为线性求解问题,采用Hough变换实现该方程参数的快速鲁棒估计。解决摄像机旋转扫描条件下获取的图像间非线性变换问题,从而实现图像准确补偿。在此基础上,可以利用帧间差分等方法检测出运动目标。结果 实验结果表明,在摄像机旋转扫描条件下,本文方法能够同时实现图像间的背景运动补偿和非线性变换补偿,可以去除大部分由于立体视差效应（parallax effects）产生的匹配错误。并且在实验中,本文方法处理速度可以达到50帧/s,满足实时性要求。结论 在面阵摄像机旋转扫描的条件下,相比于传统的基于线性模型的图像补偿方法,本文方法能够快速、准确地在背景补偿的基础上同时解决图像间非线性变换问题,从而更好地提取出运动目标,具有一定的实用价值。     

小型无人机地面目标跟踪系统机载云台自适应跟踪控制

本文针对小型无人机地面目标跟踪系统,提出了一种机载云台自适应跟踪控制算法.该算法在摄像机外参数未知的情况下,利用图像信息和机载传感器得到的无人机状态进行反馈,最终实现了对云台摄像机姿态的控制,使得无人机在跟踪目标飞行过程中,地面目标可以始终保持在摄像机的图像中心.为此,论文首先通过分析无人机、目标和摄像机三者的相对位姿关系,建立了目标点在图像平面的运动学模型.在此基础上,基于李雅普诺夫稳定性理论设计了自适应控制算法.理论分析与仿真结果表明本文所设计的摄像机姿态控制器在摄像机外参数未知的情况下,可以使被跟踪目标始终保持在图像中心.     

以目标为中心的MCRBR视点空间投影方法

三维目标的姿态随视点变化而不同,选择适当角度范围的多尺度投影图像为代表,建立三维目标的完备特征库,能够提高基于图像的三维目标识别率。以目标为观察中心,基于3ds MAX提出一种多摄像机旋转批量渲染的三维目标视点空间投影方法。首先建立目标的三维模型,设置目标模型位置和顶视图摄像机位置,然后利用max层级命令面板锁定其中一个轴向的角度,以等采样间隔复制摄像机,设置半球面运动路径,并约束到相应摄像机,最后设置投影图像的输出参数并建立批处理脚本,实现三维目标视点空间任意投影图像的自动保存。     

PTZ自主跟踪中的全景视频生成

提出了一种在单PTZ摄像机自主跟踪过程中生成全景视频的方法。该方法在自主跟踪目标的同时,生成目标在大场景上运动的全景视频,可应用于PTZ摄像机监控场所。该方 法将全景视频看作全景背景图像和当前目标图像的叠加：首先利用Mean Shift跟踪方法逐帧获取目标区域图像并保存;然后利用相邻两帧视频图像的竖直方向投影匹配和Harris角 点匹配结果合成全景背景,与传统的配准方法相比,大大降低了匹配运算的复杂度,使全景背景的生成能够实时进行,并记录每帧图像到背景图像的变换参数;最后逐帧将目标区 域图像变换到背景图像上得到全景视频。本文方法与传统的全景视频生成方法相比,无需人工控制摄像机的转动,也无需手工对齐视频帧,整个过程全部自动完成。     

融合摄像机位姿信息的模板匹配跟踪算法

针对图像制导目标跟踪系统在跟踪过程中,由于图像旋转、成像视角和目标尺度的变化带来的跟踪漂移问题,提出一种利用摄像机的位姿信息的匹配模板校正和更新方法。根据摄像机与目标的相对位姿信息,建立目标透视成像模型以及不同摄像机位姿情况下的模板校正方程;将校正方程分解为实时图像旋转和模板仿射变换两部分减小模板变换的误差;通过设计与相关系数和距离信息相关的模板更新策略达到适应跟踪系统逐渐接近目标过程中目标的变化。采用基于视景仿真软件Vega Prime产生的模拟飞行视频对算法进行了验证。实验表明所提算法能够适应图像制导跟踪系统在跟踪过程中目标尺度、成像视角以及图像旋转的变化,减小跟踪漂移。     

SoftPOSIT方法在PNP问题中的应用

本文针对PNP问题(N>6且不共面)提出了一种基于SoftPOSIT方法的技术方案,内容包括:1)以一长方体为目标物体,建立目标物体坐标系,确定目标物体坐标系下角点的空间坐标;2)建立包含透镜畸变分析的摄像机针孔成像模型,采集目标物体图像;3)获取物体角点的图像坐标,在目标物体角点的物点和像点对应关系未知的情况下,利用SoftPOSIT方法迭代出摄像机在目标物体坐标系下的全局最优位姿参数;4)根据得到的摄像机在目标物体坐标系下的位姿参数,计算目标物体角点在摄像机坐标系下的坐标。本文的研究结果表明,该方法为解决PNP问题(N>6)提供了一个理论上可行且有效的方法。     

双摄像机系统对移动目标的跟踪

提出了一种由一个静止摄像机加上一个动态摄像机组成的双摄像机实时跟踪系统．该系统利用两种形式摄像机各自的优点,克服它们自身的不足,实现了对运动目标的实时跟踪．文中给出了双摄像机系统的组成以及功能划分．利用由近似的摄像机投影模型导出的单应性关系,实现两个摄像机图像之间的目标匹配．系统在静态摄像机的图像平面上建立目标的2D运动模型,采用卡尔曼滤波实现目标位置的预测,由单应性关系求出动态摄像机图像平面上对应目标的预测位置,然后计算摄像机动态平台的旋转角度,实现对动态平台的伺服控制．     

一种基于特征匹配的目标入侵检测方法

视频监控中常用云台摄像机监控视场较大的区域.对于云台摄像机跟随拍摄的情况,提出了一种基于特征匹配的目标入侵检测方法.通过提取的尺度不变特征变换(SIFT)特征点对,将当前图像和全景图像进行匹配,从而得到当前图像和全景图像投影关系,再将当前图像的坐标系变换到全景图像下,最后运用差分法,找到入侵目标.实验结果表明,即使当前图像与全景图像存在尺度、缩放、形变等差异,通过本方法也可正确地检测出入侵目标.     

基于图像重投影的视图合成

针对摄像机绕光心旋转的情形,讨论了在这种特殊情形下单应矩阵具有的性质。然后根据这些性质结合三维图像变换技术给出了一种摄像机绕光心旋转时新视图的合成方法。该方法首先利用单应矩阵的性质生成目标图像的一部分,并采用逆向映射的方法以避免产生空洞;接着利用三维图像变换生成目标图像的剩余部分;最后对由三维图像变换生成的部分进行空洞填补。实验结果表明,该方法能够生成质量较好的新视图。     

高速公路动态环境下的摄像机自标定

提出一种动态环境下高速公路监控系统摄像机的自标定方法.首先利用混合高斯背景建模方法从动态视频图像中获取背景图像和目标频繁出现的目标区域;然后利用不同的直线检测算法检测和估计出目标区域内高速公路上大量存在的各种标志线和虚标志线以及水平线,基于这些线状特征计算出摄像机的灭点;最后根据灭点和线特征之间的几何关系计算出摄像机的内外参数,从而实现摄像机自标定.真实场景的实验结果表明,该算法非常合适于各种高速公路监控系统中摄像机的实时自标定,且精度高、稳定性好.     

A Catadioptric and Pan-Tilt-Zoom Camera Pair Object Tracking System for UAVs

Unmanned aerial vehicles (UAVs) are seeing widespread use in military, scientific, and civilian sectors in recent years. As the mission demands increase, these systems are becoming more complicated. Omnidirectional camera is a vision sensor that can captures 360° view in a single frame. In recent years omnidirectional camera usage has experienced a remarkable increase in many fields, where many innovative research has been done. Although, it is very promising, employment of omnidirectional cameras in UAVs is quite new. In this paper, an innovative sensory system is proposed, that has an omnidirectional imaging device and a pan tilt zoom (PTZ) camera. Such a system combines the advantages of both of the camera systems. The system can track any moving object within its 360° field of view and provide detailed images of it. The detection of the moving object has been accomplished by an adaptive background subtraction method implemented on the lowered resolution images of the catadioptric camera. A novel algorithm has also been developed to estimate the relative distance of the object with respect to the UAV, using tracking information of both of the cameras. The algorithms are implemented on an experimental system to validate the approach.     

基于一维标定物的多摄像机标定

一维标定物是由三个或三个以上彼此距离已知的共线点构成的. 现有文献指出只有当一维标定物做平面运动或者绕固定点转动时，才能实现摄像机的标定. 本文的研究结果表明，当多个摄像机同时观察作任意刚体运动的一维标定物时，则该摄像机组能被线性地标定. 本文给出一种线性标定算法，并使用最大似然准则对线性算法结果进行精化. 模拟实验和真实图像实验都表明本文的算法是有效可行的.     

Camera calibration using one-dimensional information and its applications in both controlled and uncontrolled environments

Camera model and its calibration are required in many applications for coordinate conversions between the two-dimensional image and the real three-dimensional world. Self-calibration method is usually chosen for camera calibration in uncontrolled environments because the scene geometry could be unknown. However when no reliable feature correspondences can be established or when the camera is static in relation to the majority of the scene, self-calibration method fails to work. On the other hand, object-based calibration methods are more reliable than self-calibration methods due to the existence of the object with known geometry. However, most object-based calibration methods are unable to work in uncontrolled environments because they require the geometric knowledge on calibration objects. Though in the past few years the simplest geometry required for a calibration object has been reduced to a 1D object with at least three points, it is still not easy to find such an object in an uncontrolled environment, not to mention the additional metric/motion requirement in the existing methods. Meanwhile, it is very easy to find a 1D object with two end points in most scenes. Thus, it would be very worthwhile to investigate an object-based method based on such a simple object so that it would still be possible to calibrate a camera when both self-calibration and existing object-based calibration fail to work. We propose a new camera calibration method which requires only an object with two end points, the simplest geometry that can be extracted from many real-life objects. Through observations of such a 1D object at different positions/orientations on a plane which is fixed in relation to the camera, both intrinsic (focal length) and extrinsic (rotation angles and translations) camera parameters can be calibrated using the proposed method. The proposed method has been tested on simulated data and real data from both controlled and uncontrolled environments, including situations where no explicit 1D calibration objects are available, e.g. from a human walking sequence. Very accurate camera calibration results have been achieved using the proposed method.     

掌纹拍摄距离与图像清晰度的关系研究

研究了物距(即手掌与镜头之间的移动范围)与成像清晰度的关系,从而可以根据掌纹识别精度确定在超出景深范围情况下的手掌与镜头之间的可移动范围。通过三种基于梯度的清晰度与物距实验结果发现,三种清晰度评价值与物距均成单调单值非线性关系且曲线靠近。以此可以推论,各种梯度清晰度评价函数在与物距的关系表述上没有明显差异。     

Tracking in 3D: Image Variability Decomposition for Recovering Object Pose and Illumination

As an object moves through space, it changes its orientation relative to the viewing camera and relative to light sources which illuminate it. As a consequence, the images of the object produced by the viewing camera may change dramatically. Thus, to successfully track a moving object, image changes due to varying pose and illumination must be accounted for. In this paper, we develop a method for object tracking that can not only accommodate large changes in object pose and illumination, but can recover these parameters as well. To do this, we separately model the image variation of the object produced by changes in pose and illumination. To track the object through each image in the sequences, we then locally search the models to find the best match, recovering the object’s orientation and illumination in the process. Throughout, we present experimental results, achieved in real-time, demonstrating the effectiveness of our methods. Received: 9 December 1998?Received in revised form: 23 December 1998?Accepted: 23 December 1998     

一种简易的线结构光投影三维形状获取方法

利用普通的LCD投影仪和数码相机获得物体的三维形状.投影仪作为光源,投射线结构光在物体表面,从数码相机拍摄的照片序列中,恢复物体的形状.提出了根据已经标定好的相机参数,继续对投影仪进行标定的方法;同时,针对物体表面颜色/纹理较为复杂的情况,提出了一次投射三色线结构光的改进方法,克服了不易恢复此类物体形状的困难.实验结果表明,该方法可以获得物体的稠密点云用于进一步的重建,适于组建一个廉价但却保持相对精度的扫描系统.     

一种采用高斯模型的步态轮廓分割算法

步态识别中大多采用步态轮廓作为识别特征,因此提取完整封闭的运动人体轮廓以准确表达步态特征是正确识别的前提。本文提出一种采用高斯模型的步态轮廓分割算法。在人的运动方向与摄像机成像面平行和摄像机静止的条件下,假设序列图像所有帧中对应像素点背景时刻的灰度值在时间轴上是高斯分布,而目标时刻不满足这种分布,采用统计推断的方法分割出运动目标轮廓。实验结果表明,本文算法不仅能够提取出完整的人体轮廓,并且能有效地去除噪声,对阴影抑制也有一定效果,能够提高步态识别率。算法直接在RGB空间或灰度空间进行,无需进行颜色空间转换,也无需建立单独的背景图像,计算量小,处理实时性高。     

基于运动显著性的移动镜头下的运动目标检测

针对移动镜头下的运动目标检测中的背景建模复杂、计算量大等问题,提出一种基于运动显著性的移动镜头下的运动目标检测方法,在避免复杂的背景建模的同时实现准确的运动目标检测。该方法通过模拟人类视觉系统的注意机制,分析相机平动时场景中背景和前景的运动特点,计算视频场景的显著性,实现动态场景中运动目标检测。首先,采用光流法提取目标的运动特征,用二维高斯卷积方法抑制背景的运动纹理;然后采用直方图统计衡量运动特征的全局显著性,根据得到的运动显著图提取前景与背景的颜色信息;最后,结合贝叶斯方法对运动显著图进行处理,得到显著运动目标。通用数据库视频上的实验结果表明,所提方法能够在抑制背景运动噪声的同时,突出并准确地检测出场景中的运动目标。     

一种基于随动视觉的排爆机器人自主抓取系统

在传统基于固定视觉的排爆机器人抓取系统中,相机视觉易被遮挡且不能保证拍摄清晰度。基于随动视觉技术,提出一种将深度相机置于机械手末端并随机械手运动的排爆机器人自主抓取系统。利用深度相机计算目标物体的三维坐标,采用坐标转换方法将目标物体的位置坐标信息实时转换至机器人全局坐标系,并研究相机坐标系、机器人全局坐标系与末端执行器手爪工具坐标系三者的动态映射关系,实现排爆机器人的自主抓取。实验结果表明,与传统固定视觉方法相比,随动视觉方法可在误差2cm内,使得机器人机械手爪准确到达目标物体所在位置,且当机器人距离目标物体100cm~150cm时,抓取效果最佳。     

Acoustic and video sensor integration for object recognition

Through our studies of methods for measuring the shapes of objects in three-dimensional object recognition, we have developed a method for constructing detailed solid object images that employs the fusion of the data from acoustic sensors and a charge-coupled device (CCD) camera. This method uses a matrix of ultrasonic sensors to obtain data on the position and height of the object. These data are used to automatically extract the two-dimensional images of the object from gray-scale camera images. By combining the results with distance information, a detailed solid image of the object is obtained. This method produces markedly better resolution than using acoustic data alone. Thus, by using it in combination with a neural network recognition mechanism, it is possible to automatically recognize small objects that are difficult to distinguish by means of acoustic sensing alone, even if they can be detected. This paper reports the newly developed sensor fusion mechanism, presents the results of experiments on an experimental system, and discusses the features of the method.