运动物体位移及姿态参数的一种图像测量方法

利用散焦图像深度估计原理,给出了一种运动物体移动距离和姿态的测量方法,并对 图像特征点的获取和跟踪方法作了研究．该测量方法首先在物体上设置了四个明暗分明的圆 形特征点,然后根据物体运动过程中特征点图像边缘的模糊程度,测量计算物体沿摄像机光 轴的移动距离．当物体发生倾斜后,可由被测量的四个特征点沿光轴的移动距离值不同来计 算物体的倾斜角．该方法仅需一台摄像机,测量原理简单,计算量小,能满足实时性要求, 并具有一定的测量精度．     

单目变焦摄像机自运动的标定测量法

为了在单目摄像机变焦情况下测量其自运动参数,提出一种单目变焦摄像机自运动的参数标定测量法。在飞行平台着陆过程中,固连其上的单目俯视摄像机对包含已知世界坐标的特征点的静态着陆平面进行连续拍摄,该方法利用单帧图像可解算得到摄像机拍摄当时的等效焦距及其相对于着陆平面的6自由度位置,结合多帧信息即可对摄像机自运动的运动速度进行估计,进而转换为飞行平台的着陆运动参数。实验结果证明该方法可行有效。     

基于线结构光的三维坐标测量技术研究

传统的口腔修复体三维点云数据测量技术难以满足精度要求。为此,提出一种基于线结构光的三维坐标测量方法。在摄像机标定过程中,采用最小二乘法计算光平面方程,使用平移扫描和旋转扫描获取物体表面三维数据,以避免求解摄像机内外参数。实验结果表明,重建后的三维模型可以满足高精度近景三维测量的要求。     

三维仿真中高速物体的速度感表现方法研究

在拍摄战斗机等物体的高速飞行和旋转过程中,真实的拍摄受制于环境等因素一般为固定拍摄或跟踪拍摄,三维虚拟场景下的仿真高速运动和虚拟拍摄可以不受环境等因素影响,有更多的速度表现方式,但目前没有比较通用的速度感表现规律。基于人类对运动的视觉感知理论,将真实相机的拍摄方式应用于虚拟摄像机,研究不同的单镜头下如何通过虚拟摄像机的拍摄与取景将三维场景中仿真物体的高速运动更好地加以表现,实验过程中以战斗机直线飞行仿真动画及离心机旋转仿真动画为例,采用控制变量法与等级排列法,最终得到一系列较为实用的速度感表现方法。     

基于全局彩色摄像机的移动机器人定位

本文提出一种基于全局彩色摄像机的移动机器人定位方法。该方法首先利用全局彩色摄像机对移动机器人所在的运动平面拍摄图像并基于色调和饱和度信息进行图像分割获取目标物体在图像平面坐标系中的位置,然后利用多项式拟合的方法实现图像平面坐标系到移动机器人运动平面坐标系的映射,从而确定移动机器人在其运动平面坐标系中的位置,同时利用移动机器人的行驶轨线近似获得其方向角。实验结果表明了上述方法的有效性,具有一定的实用价值。     

一种重构直线运动轨迹的新方法

由于拍摄图象的摄像机可以是一个移动的摄像机 ,或是由空间中多个不同位置的摄像机组成的集合 ,因此开展由多幅图象上的测量值来重构物体在三维空间中运动轨迹的方法研究是一个热点问题 .Shashua等首先提出了一种 "轨迹三角形法 " .该方法是在关于运动轨迹的某些约束条件下 ,借助于 Grassmann- Carley代数和 Plücker坐标 ,再利用点与直线的相关性来求出 3D空间中的直线 (运动轨迹 ) ,但该方法较复杂 .为了快速简便地实现直线运动轨迹的重构 ,提出了一种基于“测量矩阵”秩的 2约束的新方法 .这种方法简单、直接 ,可在一般的射影坐标系下实现 .虽然该方法是针对直线运动轨迹提出的 ,但它可以方便地推广到高次多项式曲线运动轨迹的重构 .     

非接触目标相对姿态测量方法研究

针对空间中非接触目标相对位置、姿态角测量问题,采用双目摄像机、电控角位移台和电控旋转台建立物体相对姿态测量系统。提出了一种利用双目视觉结合物体刚体运动学原理,利用Harris算子提取物体特征角点进行相对姿态角解算。将卫星模型作为实验对象,运动过程中进行了非接触目标相对姿态测量方法的验证试验,实验结果表明姿态角测量误差小于±0.56°,证明了算法的有效性。     

用单数码相机实现物体表面的三维重建

根据由运动重建物体结构的原理,设计了一个简便易操作的三维重建系统,具体做法是:先用张氏标定法求得内参数矩阵,然后在两个不同的未知位置拍摄物体得到两幅图像,经立体匹配后,利用图像特征点的对应关系求解基本矩阵和本质矩阵,分解本质矩阵获得两个拍摄位置确定的摄像机运动参数(旋转矩阵和平移向量),进而求出相机在两个位置的投影矩阵,最后用三角法计算出物体表面特征点的三维坐标并在OpenGL中重建物体表面.和传统的立体视觉系统相比,本系统只需要一台数码相机和平面方格模板就可以实现三维重建,因此适用于普通相机用户.     

线结构光传感器参数现场标定方法

为了精确、快速、高效地标定线结构光传感器参数,提出了一种线结构光传感器参数现场标定方法。根据摄像机标定方法,并结合L-M非线性优化算法对摄像机内外参数及镜头畸变系数进行标定。拍摄不同姿态下的平面靶标图像,利用靶标图像计算摄像机外参计算靶标上的圆点在摄像机坐标系下的三维坐标,并构建靶标平面方程。将激光线投射到不同姿态的靶标平面上,通过靶标平面方程计算出激光线上点在摄像机坐标系下的3D坐标,由不同位置重构出激光点在摄像机坐标系下的3D坐标来完成光平面参数标定。通过对摄像机参数、畸变系数和光平面参数的标定,重构目标物体进行测试。测量结果表明:该算法能够快速、准确地获取小车车体的三维坐标,并构造出车体的三维模型。该方法适用于大视场的工业现场标定。     

利用非高速摄像机测量转速的方法研究

对有些测量对象根本无法安装测量设备或者设备的主人不允许安装测量设备,比如测量乒乓球的旋转速度等情况;因此需要引进一种新的转速测量方法,即基于视频的角速度测量方法;本研究的目标就是利用两台价格低廉的普通摄像机取代价格昂贵的高速专业摄像机;通过两台低速摄像机同时对高速旋转对象进行采样,两台低速摄影机分别设置不同的采样频率;根据获得的采样图像,发现两组不同采样数据之间关系,建立相应的数学方程,计算出高速旋转对象的旋转角速度;通过实验,利用两台最高30帧/秒速度的摄像机,测量转速为100转/秒左右旋转对象,取得相当准确的精度的,因此,证明了该方法具有很好的实际应用价值.     

Low complexity-low power object tracking using dynamic quadtree pixelation and macroblock resizing

In this paper, a high speed, reliable, low memory demanding and precise object detection and tracking algorithm is proposed. The proposed work uses a macroblock of rectangular shape, which is placed in the very first frame of the video to detect and track a single moving object using monocular camera. The macroblocks are positioned in the field of view (FOV) of camera where the probability of occurrence of object is high. After placing macroblocks, a threshold value is examined to detect the presence of objects in the selected macroblocks. Afterwards, a quadtree approach is used to minimize the bounding box and to reduce the pixelation. A tracking algorithm is proposed which illustrates a unique method to find the moving directional vectors. The proposed method is based on macroblock resizing, which demonstrates an accuracy rate of 98.5% with low memory utilization.     

基于运动检测与运动搜索的多目标跟踪

提出一种新的单摄像机多目标跟踪方法,采用全局背景减法得到当前帧所有运动区域,利用kalman滤波器及局部背景减法得到已跟踪目标在当前帧的预测区域,根据全局减法运动区域及预测区域的位置及大小来判断是否有遮挡发生,并用不同匹配方法进行目标跟踪。实验表明,该方法能有效提高单摄像机跟踪对目标合并、遮挡等问题的处理能力。     

Correlation‐based visual odometry for ground vehicles

Reliable motion estimation is a key component for autonomous vehicles. We present a visual odometry method for ground vehicles using template matching. The method uses a downward‐facing camera perpendicular to the ground and estimates the motion of the vehicle by analyzing the image shift from frame to frame. Specifically, an image region (template) is selected, and using correlation we find the corresponding image region in the next frame. We introduce the use of multitemplate correlation matching and suggest template quality measures for estimating the suitability of a template for the purpose of correlation. Several aspects of the template choice are also presented. Through an extensive analysis, we derive the expected theoretical error rate of our system and show its dependence on the template window size and image noise. We also show how a linear forward prediction filter can be used to limit the search area to significantly increase the computation performance. Using a single camera and assuming an Ackerman‐steering model, the method has been implemented successfully on a large industrial forklift and a 4×4 vehicle. Over 6 km of field trials from our industrial test site, an off‐road area and an urban environment are presented illustrating the applicability of the method as an independent sensor for large vehicle motion estimation at practical velocities. © 2011 Wiley Periodicals, Inc.     

Integrating tracking with fine object segmentation

We present a novel method for on-line, joint object tracking and segmentation in a monocular video captured by a possibly moving camera. Our goal is to integrate tracking and fine segmentation of a single, previously unseen, potentially non-rigid object of unconstrained appearance, given its segmentation in the first frame of an image sequence as the only prior information. To this end, we tightly couple an existing kernel-based object tracking method with Random Walker-based image segmentation. Bayesian inference mediates between tracking and segmentation, enabling effective data fusion of pixel-wise spatial and color visual cues. The fine segmentation of an object at a certain frame provides tracking with reliable initialization for the next frame, closing the loop between the two building blocks of the proposed framework. The effectiveness of the proposed methodology is evaluated experimentally by comparing it to a large collection of state of the art tracking and video-based object segmentation methods on the basis of a data set consisting of several challenging image sequences for which ground truth data is available.     

Detecting moving objects from a video taken by a moving camera using sequential inference of background images

This paper proposes a method of detecting moving objects using sequential inference of the background in a video taken with a moving camera. In the video taken using a moving camera, all positions of pixels change every frame. The positions of the background pixels in the image frame T are not the same as the positions of the background pixels in the image frame T + 1. 2D projective transform can be used to find changes in the pixel position every frame. Bilinear interpolation with four nearest pixels around the pixel in image frame T which corresponds to a pixel in the image frame T+1 can be used for creating a background model at T + 1. Having obtained the background model, a pixel in image frame T + 1 can be determined if it is a background pixel or a foreground pixel. The detection results of the proposed method are compared with the ground truth to determine the effectiveness of the proposed method.     

营区扫描式监控中的运动目标检测

为解决部队营区监控中运动目标检测问题,提出了基于扫描式的运动目标检测法。对通过云台采集的背景帧提取边缘特性生成特征图,搜索与实时视频帧特征图相似度最大的背景帧。采用一种基于非规则形状的K值模板匹配进行运动补偿,并提出一种基于分块的前景连通法。实验结果表明,该背景搜索法降低了计算维度,算法快速;匹配算法对图像噪声、局部光照变化具有很好的鲁棒性;前景连通算法具有很好的检测效果,且可行有效。     

Matching wire frame objects from their two dimensional perspective projections

A wire frame object consists of a set of three dimensional arcs, each arc being a sequence of conics and line segments lying in the same plane, with different arcs being allowed to lie on different planes. Given a picture taken by a camera focusing on one wire frame object, we show how to determine what the object is and where it is situated relative to the camera when the camera viewing parameters are unknown.

To accomplish the object identification, we begin with a segmented picture. Then we construct a ray from the lens to each point on the boundary of every region. For each region, the collection of its associated rays is a cone. We show that by constructing cones, the two-dimensional to three-dimensional matching problem is transformed into an equivalent three-dimensional to three-dimensional matching problem.

This matching problem is expressed as a nonlinear optimization search procedure on the 6 camera viewing parameters: the 3 translation parameters and the 3 rotation parameters. A solution is found when a viewing position and optical axis is determined which is consistent with the world knowledge we have of possible curves and the observed image data.     

People tracking using a network-based PTZ camera

In this paper, we propose a method for online upper body tracking using an IP PTZ camera. This type of camera uses a built-in Web server resulting in variable response times when sending control commands. Furthermore, communicating with a Web server involves network delays. Thus, because the camera is inside a control loop, the effective frame rate that can be processed by a computer vision method is irregular and in general low (2–6 fps). Our tracking method has been specifically designed to perform in such conditions. It detects, at every frame, candidate blobs using motion detection, region sampling, and region color appearance. The target is detected among candidate blobs using a fuzzy classifier. Then, a movement command is sent to the camera using the target position and speed. The proposed method can cope with low frame rate, and thus with large motion of the target, even in the case of a fast walk. Results show that our system has a good target detection precision (>88%) and low track fragmentation, and the target is almost always localized within 1/6th of the image diagonal from the image center.     

基于模糊逻辑的多相机非重叠场景的物体匹配

An approach based on fuzzy logic for matching both articulated and non-articulated objects across multiple non-overlapping field of views (FoVs) from multiple cameras is proposed. We call it fuzzy logic matching algorithm (FLMA). The approach uses the information of object motion, shape and camera topology for matching objects across camera views. The motion and shape information of targets are obtained by tracking them using a combination of ConDensation and CAMShift tracking algorithms. The information of camera topology is obtained and used by calculating the projective transformation of each view with the common ground plane. The algorithm is suitable for tracking non-rigid objects with both linear and non-linear motion. We show videos of tracking objects across multiple cameras based on FLMA. From our experiments, the system is able to correctly match the targets across views with a high accuracy.     

相机抖动场景中数据驱动的背景图像更新算法

视频序列中的运动目标检测是计算机视觉领域的重要研究课题.背景减除是运动目标检测的有效方法,但相机抖动会对背景提取带来极大干扰,从而可能造成传统基于模型的图像处理方法模型失真.本文提出了相机抖动场景下前景图像提取的数据驱动背景图像更新控制算法.首先利用Harris特征检测进行背景补偿以消除抖动干扰.然后利用无模型自适应控制方法,建立单入单出控制系统来表示背景图像并进行实时更新.最后运用背景减除法提取运动目标前景图像.本文方法与传统基于模型方法进行了不同视频序列的对比仿真.实验结果表明,本文方法可以有效处理相机抖动场景下的运动目标检测问题,目标前景图像分离效果更加接近真实场景.