一种非刚体运动图象序列的特征点对应方法

提出了一种非刚体图象序列特征点对应的新方法 ,首先根据图象序列帧间的时间间隔很小这一特点 ,指出特征点在图象帧间的运动具有平滑性 ,进而提出了一种特征点运动平滑的代价函数。然后将目标跟踪技术应用于特征点的跟踪 ,利用两个一维卡尔曼滤波器分别对特征点的两个坐标进行预测跟踪。在图象帧间的特征点对应过程中 ,该文综合考虑了特征点的预测位置与实际位置之间的距离以及特征点的平滑代价函数等因素 ,从而使特征点的运动轨迹得到正确的延续。特征点的遮挡问题可以通过特征点跟踪过程中对特征点位置的预测得到解决。实验证明 ,该文方法能建立非刚体运动特征点的正确对应 ,并能解决特征点的遮挡问题。     

一种非刚体运动图象序列的特征点对应方法

提出了一种非刚体图象序列特征点对应的新方法,首先根据图象序列帧间的时间间隔很小这一特点,指出特征点在图象帧间的运动具有平滑性,进而提出了一种特征点运动平滑的代价函数。然后将目标跟踪技术应用于特征点的跟踪,利用两个一维卡尔曼滤波器分别对特征点的两个坐标进行预测跟踪。     

图象序列运动目标特征点对应的极指数栅格方法

目前的图象序列特征点对应方法是建立在相邻图象间的特征点在运动形式上变化不大 ,即相邻两帧图象间的时间间隔较小这样的一个假设之上的 ,但当相邻图象间的时间间隔较大时 ,则这些方法很难找到对应的特征点 .为此 ,提出了一个由粗到细解决图象序列特征点对应的新方法 ,该方法首先进行粗定位 ,即利用极指数栅格方法来得到运动后目标特征点的大致范围 ;然后通过细定位来得到对应的特征点 .为了使人们对该方法有一全面了解 ,还介绍了该方法的原理 ,并给出了实验结果 .实验证明 ,该方法可以很好地解决时间间隔较大的两帧图象间的特征点对应问题 ,其最大的优点是比通常的方法简单有效 .     

基于神经网络的图象序列特征点匹配

利用神经网络优化技术解决图象序列的特征点匹配问题，将特征点匹配归结为一个带约束的优化问题，并用2D Hopfield网络实现，在Hopfield网络的能量函数的设计中，综合考虑了特征点的预测结果、特征点的遮挡等情况，从而克服了现有的多数方法所存在的误匹配现象，对于特征点的跟踪，头3帧图象的正确匹配是十分关键的。本文提出了一种3D Hopfield网络用以解决头3帧图象的特征点匹配，并提出了一个运动平滑性的代价函数用以构造3D Hopfield网络的能量函数，实际图象序列的实验结果证明了本方法的有效性。     

基于Harris角点与改进Hu矩的电子稳像算法

为提高抖动视频电子稳陣系统的稳陣雙果,提出一种基于 Harris 角点和改进 Hu 几何不变矩的电子稳陣算法。该算法检测视频每帧图陣的 Harris 角点为特征点,并计算其邻域图陣改进的 Hu 矩作为对应特征除量,以仿射变换为模型,通过特征点匹配计算前后帧的陒对运动参数,从而计算出图陣序列的运动轨迹,加以陒应的运动平滑补偿,得到保留镜头正常运动信息稳定的视频图陣序列。实验结果表明,在视频图陣帧间存在旋转、平移和轻微缩放的情况下,该算法能有雙降低特征匹配的计算量,且保持良好的匹配雙果。     

基于动态图像序列的下肢运动参数测量

针对人体下肢运动参数的检测问题，提出了基于动态图像序列的下肢运动测量方法。首先对成像系统进行了分析，然后根据所得的图像序列，提出了图像帧间特征点的对应、下肢的运动及结构参数估计等问题的处理方法，实验结果反映了该方法的有效性。     

获取视频特征的一种方法

根据目前的技术水平,在建立多层次分段模型的基础上,识别出现视频流中的镜头,利用光流图象序列分析技术处理镜头中的代表帧及其邻接帧,获取视频数据流中镜头的运动特征。所提出的方法既能获取镜砂的平移运动特征,也能获取镜头的旋转运动特征。     

基于视频处理的视线稳定技术

针对既有摄像机运动又有前景物体运动的图像稳定问题,提出了一种快速算法。该算法首先利用改进的 Harries 算子提取特征点,根据三级匹配策略实现特征点的三级匹配,并且利用基于块的去噪声点方法检测出前景区域,剔除存在于前景区域的角点;然后建立当前帧与参考帧的映射关系,利用最小二乘法求解出全局运动参数;最后利用 Kalman 滤波平滑运动参数,依据平滑后的参数对图像进行补偿。     

加权最小二乘法与卡尔曼滤波实时稳像技术

无人机和车辆行驶等情况下拍摄的视频受外界影响会造成视频抖动。通过对比现有的电子稳像技术,提出了利用FAST获取特征点的位置信息,再通过光流法结合NCC匹配得到参考帧特征点在当前帧的位置信息,在此基础上,结合RANSAC算法剔除错误匹配的特征点对的改进算法。为了提高运动矢量估计的精度,应用加权最小二乘法得到相邻帧间的刚性变换矩阵,并经过卡尔曼滤波进行运动平滑得到扫描运动矢量并补偿,最终得到实时的稳定视频。实验表明,视频序列稳像后的帧间变换保真度有所提高,并且能够达到实时处理速度。     

一种基于光流场重建三维运动和结构的新方法

提出了一种基于稀疏光流场计算三维运动和结构的线性新方法 ,该方法综合视觉运动分析中的两类处理方法 ,选取图象中的角点作为特征点 ;并检测和跟踪图象序列中的角点 .记录检测到的角点在图象序列中的位移 ,在理论上证明了时变图象的光流场可以近似地用角点的位移场代替 ,从而得到时变图象的稀疏光流场 ;通过光流运动模型的建立 ,推导出由稀疏光流场重建三维物体运动和结构的线性方法 .通过用真实图象序列验证该算法 ,表明该算法取得了较好的效果     

基于Hausdorff距离图象配准方法研究

图象配准是图象融合的一个重要步骤，为此提出了一种自动图象配准算法，该算法从两幅待配准的图象中分别抽取特征点，然后选用Hausdorff距离对两特征点集进行匹配，得到点集间的仿射变换，从而实现图象的自动配准，此算法以特征点而不是物体边缘计算仿射变换，大大降低了计算Hausdorff距离的运算量；同时，基于Hausdorff距离的图象匹配只需要点集之间的对应，而无须点与点的对应，因而可以使用于存在较大物体形变的情况，即完成两幅差异较大图象的配准，实验结果证明了算法的有效性。     

A heuristic search-based motion correspondence algorithm using fuzzy clustering

Motion correspondence problem between many feature points of consecutive frames is computationally explosive. We present a heuristic algorithm for finding out the most probable motion correspondence of points in consecutive frames, based on fuzzy confidence degrees. The proposed algorithm consists of three stages: (i) reduction of the search space for candidate points of association, (ii) pairwise association cost estimation and (iii) complete association of every feature point between the consecutive frames. In the first stage, all the points in a frame, frame t-1 are grouped into several groups by using fuzzy clustering. This is done with a Euclidean distance as a similarity measure between the points. The points in the following frame, frame t are also clustered into the same number of groups with respect to the cluster centers of the previous frame. The association between the points of the consecutive frames is allowed only for the points that belong to the same group in each frame. In the second stage, the cost of each association of a point in frame t-1 with a point in frame t is estimated by using motion constraints that are based on the velocity vector and the orientation angle of each point. The cost is measured as a fuzzy confidence degree of each head point, i.e., a point in frame t-1, belonging to each measurement, i.e., a point in frame t. In the final stage, we search for the most likely associations among all the possible mappings between the feature points in the consecutive frames. A search tree is constructed in such a way that an ith level node represents an association of ith node in frame t-1 with a node in frame t. We devise a heuristic function of an admissible A* algorithm by using the pairwise association cost developed in the second stage. Experimental results show an accuracy of more than 98%.     

Automatic feature point extraction and tracking in image sequences for arbitrary camera motion

An automatic egomotion compensation based point correspondence algorithm is presented. A basic problem in autonomous navigation and motion estimation is automatically detecting and tracking features in consecutive frames, a challenging problem when camera motion is significant. In general, feature displacements between consecutive frames can be approximately decomposed into two components: (i) displacements due to camera motion which can be approximately compensated by image rotation, scaling, and translation; (ii) displacements due to object motion and/or perspective projection. In this paper, we introduce a two-step approach: First, the motion of the camera is compensated using a computational vision based image registration algorithm. Then consecutive frames are transformed to the same coordinate system and the feature correspondence problem is solved as though tracking moving objects for a stationary camera. Methods of subpixel accuracy feature matching, tracking and error analysis are introduced. The approach results in a robust and efficient algorithm. Results on several real image sequences are presented.The support of the Advanced Research Projects Agency (ARPA Order No. 8459) and the U.S. Army Engineer Topographic Laboratories under Contract DACA 76-92-C-0009 is gratefully acknowledged.     

Image sequence analysis of real world human motion

Three fundamental problems of image sequence analysis are investigated for real world human motions. The first one is the modelling of body motion, which is approached by the methods of key frame sequence of stick figures and generalized cone approximation of body parts. The second problem is the correspondence of feature points in the consecutive frames, for which a method called “window code matching” is proposed. The last one is the analysis of occluding regions, which is studied on the bases of occlusion prediction by model and difference images.     

Performance evaluation of 1‐point‐RANSAC visual odometry

Monocular visual odometry is the process of computing the egomotion of a vehicle purely from images of a single camera. This process involves extracting salient points from consecutive image pairs, matching them, and computing the motion using standard algorithms. This paper analyzes one of the most important steps toward accurate motion computation, which is outlier removal. The random sample consensus (RANSAC) has been established as the standard method for model estimation in the presence of outliers. RANSAC is an iterative method, and the number of iterations necessary to find a correct solution is exponential in the minimum number of data points needed to estimate the model. It is therefore of utmost importance to find the minimal parameterization of the model to estimate. For unconstrained motion [six degrees of freedom (DoF)] of a calibrated camera, this would be five correspondences. In the case of planar motion, the motion model complexity is reduced (three DoF) and can be parameterized with two points. In this paper we show that when the camera is installed on a nonholonomic wheeled vehicle, the model complexity reduces to two DoF and therefore the motion can be parameterized with a single‐point correspondence. Using a single‐feature correspondence for motion estimation is the lowest model parameterization possible and results in the most efficient algorithm for removing outliers, which we call 1‐point RANSAC. To support our method, we run many experiments on both synthetic and real data and compare the performance with state‐of‐the‐art approaches and with different vehicles, both indoors and outdoors. © 2011 Wiley Periodicals, Inc.     

Recovery of the 3-D location and motion of a rigid object through camera image (An Extended Kalman Filter Approach)

This paper deals with the problem of locating a rigid object and estimating its motion in three dimensions. This involves determining the position and orientation of the object at each instant when an image is captured by a camera, and recovering the motion of the object between consecutive frames.In the implementation scheme used here, a sequence of camera images, digitized at the sample instants, is used as the initial input data. Measurements are made of the locations of certain features (e.g., maximum curvature points of an image contour, corners, edges, etc.) on the 2-D images. To measure the feature locations a matching algorithm is used, which produces correspondences between the features in the image and the object.Using the measured feature locations on the image, an algorithm is developed to solve the location and motion problem. The algorithm is an extended Kalman filter modeled for this application.Department of Electrical Engineering and Alberta Center for Machine Intelligence and Robotics, University of Alberta     

A fast robot homing approach using sparse image waypoints

This paper proposes a fast image sequence-based navigation approach for a flat route represented in sparse waypoints. Instead of purely optimizing the length of the path, this paper aims to speed up the navigation by lengthening the distance between consecutive waypoints. When local visual homing in a variable velocity is applied for robot navigation between two waypoints, the robot's speed changes according to the distance between waypoints. Because long distance implies large scale difference between the robot's view and the waypoint image, log-polar transform is introduced to find a correspondence between images and infer a less accurate motion vector. In order to maintain the navigation accuracy, our prior work on local visual homing with SIFT feature matching is adopted when the robot is relatively close to the waypoint. Experiments support the proposed navigation approach in a multiple-waypoint route. Compared to other prior work on visual homing with SIFT feature matching, the proposed navigation approach requires fewer waypoints and the navigation speed is improved without compromising the accuracy in navigation.