基于二维透射变换的视频全景图拼接算法

视频序列全景图拼接技术是视频图像分析的关键技术之一。针对帧间运动模型为二维投影变换的常见视频序列,提出了一种全景图拼接算法.该算法首先采用改进的基于RANSAC的特征点匹配算法对相邻帧的运动参数进行估计,接着采用直接法对各帧与全景图间的运动参数进行精确调整,最后运用自适应中值滤波绘制出全景图。实验结果表明,该方法能够生成较高质量的全景图,基本能实现无缝连接。     

体育视频全景图合成技术

研究了面向体育视频的全景图合成技术，提出了通过计算前景区域模板和α混合进行前景合成的方法．首先采用MPEG-4校验模型中的Konrad算法和基于Fisher线性判别准则的外点过滤算法进行全局运动参数估计，并用中值法合成背景全景图；然后将前景帧进行仿射投影后与背景求差值，并用中值滤波和形态学方法处理差值图像，得到前景区域模板；最后采用α混合生成前景序列的全景图，并叠加到背景上．由此得到的全景图能同时展现运动的场景和运动员的动作过程．     

利用数字视频技术测量旋转速度的研究

基于视频的测量系统,具有非接触,安装维护简捷而且费用低等特点;本研究的目标就是利用摄像机对测量对象进行视频采集,然后提取相邻两帧图像;当运动对象进行简单的单轴旋转时,利用Hough变换(或Rando变换)技术进行直线的角度检测;计算出相邻帧的角度差,根据间隔时间,计算出角速度;当球体进行多轴旋转时,根据球体标志投影,结合三维空间刚体运动模型,利用一组特征点坐标,采用两步迭代交替估计运动参数,求得运动物体相对三维空间各个轴的角速度;并对特殊已知结构参数的运动物体给出了简化的计算方法,通过实验表明本方法测量结果满足要求.     

PanoVideo:摄像机运动建模及从视频估计摄像机运动参数的一种方法

通过给摄像机平移、旋转与变焦等运动建模，并把运动模型与基于象素点亮度变化的方法相结合来估计 摄像机运动参数。用得到的运动参数可以把视频构造成一幅全景图，全景图可广泛应用于视频压缩与检索。实验表 明，该方法可成功地应用于视频会议系统中的视频压缩与视频检索。     

Pano Video:摄像机运动建模及从视频估计摄像机运动参数的一种方法

通过给摄像机平移、旋转与变焦等运动建模，并把运动模型与基于象素点亮度变化的方法相结合来估计摄像机运动参数。用得到的运动参数可以把视频构造成一幅全景图，全景图可广泛应用于视频压缩与检索。实验表明，该方法可成功地应用于视频会议系统中的视频压缩与视频检索。     

一种基于压缩域的视频拼接算法

提出了一种基于压缩域的双摄像机视频拼接算法。首先利用相位相关法估算输入视频的对应第一帧重叠区域，并在重叠区域进行SIFT角点检测和匹配，加快角点匹配速度，提高匹配稳健性，使用RANSAC算法去除外点，采用奇异值分解法配合LM非线性优化方法求解变换参数，得到首帧的对应投影矩阵；对于非首帧的配准，利用压缩视频中的当前帧与前帧的运动矢量，获得全局运动矢量，然后结合对应前帧的投影矩阵，获得相应的当前帧的投影矩阵;最后使用多频带融合算法进行图像混合以改善线性加权融合算法带来的高频细节模糊。与传统算法相比，由于省去了特征提取和匹配方法，从而减少了大量的计算步骤和时间，提高了速度，增加了实用性。实验结果表明该算法具有较好的实用价值。     

利用直线对应计算纯旋转运动参数的一种线性方法

从单镜头序列图象确定运动刚体的3维运动参数是计算机视觉中一个重要的问题.本文提出了一个利用直线对应计算纯旋转运动参数的线性方法.在该算法中,仅用图象中直线的两个不变量.假设两帧图象中已经抽取和匹配出4对以上的对应直线,则可以唯一地确定旋转运动参数,该算法适用予旋转轴过投影中心的情况.本文同时给出了实验结果.     

基于鲁棒背景运动补偿的运动目标检测算法*

提出一种用仿射参数模型来近似场景中摄像机的复杂运动,采用参数化的多分辨率估计方法鲁棒地估计出仿射参数;然后在当前帧与运动补偿后的帧之间求光流场,得到目标轮廓的初始分割;最后通过聚类和搜索填充算法分割出完整的目标.试验结果表明,该运动补偿算法能有效消除摄像机运动引起的背景运动,在摄像机运动情况下得到完整的目标.     

摄像机图像序列的全景图拼接

全景图是虚拟现实和计算机视觉中一种重要的场景表示方法 .通常获得高质量的全景图需要使用昂贵的专用设备 ,而且拍摄时需要精确地校准摄像机 .从普通摄像机图像拼接是获得全景图的一种低成本而且比较灵活的方法 .文中提出一种新的摄像机图像拼接算法 ,利用摄像机绕垂直轴旋转 36 0°依次拍摄的照片序列 ,拼接圆柱面全景图 .该算法不要求校准摄像机 ,对相邻帧之间摄像机的转角也没有严格的限制 ,而且不受帧间光照强度剧烈变化的影响 .从实验结果看 ,该算法获得了理想的拼接效果     

基于SURF算法的全景图拼接技术研究与实现

针对云台网络摄像机监控系统,提出一种基于摄像机视频流的全景图生成算法,以构建更大的监控场景。根据帧间重叠区域的大小选取关键帧,进行柱面投影,利用计算性能优越的SURF(Speeded Up Robust Features,加速鲁棒性特征)算法对所选取的关键帧进行特征点提取,使用基于哈希映射的特征点匹配算法加快特征点的匹配,并结合RANSAC(RANdom SAmple Consensus,随机抽样一致)算法剔除误匹配,估计关键帧之间的变换关系。实验结果表明,该方法能较好实现视频序列的快速拼接,鲁棒性强,具有较高的实用价值。     

基于SIFT特征匹配和动态更新背景模型的运动目标检测算法

运动摄像机情况下的运动目标检测是视频监控中的难点和热点问题。为了能够有效地检测出运动目标,提出了一个基于SIFT（Scale Invariant Feature Transform）特征匹配和动态背景建模的背景差算法。首先利用SIFT算法提取特征点,采用RANSAC（Random Sample Consensus）方法求得仿射变换模型参数并实现图像的全局运动补偿,然后用背景差方法实现运动目标的检测,同时进行阴影和鬼影的去除。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,动态更新背景模型的背景差则完整地检测出了前景目标。与Ninad Thakoor实验结果对比说明：该算法能够准确地检测出运动目标,并且保持了前景目标的完整性。     

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。     

分裂合并运动分割的多运动视觉里程计方法

目的 视觉里程计（visual odometry,VO）仅需要普通相机即可实现精度可观的自主定位,已经成为计算机视觉和机器人领域的研究热点,但是当前研究及应用大多基于场景为静态的假设,即场景中只有相机运动这一个运动模型,无法处理多个运动模型,因此本文提出一种基于分裂合并运动分割的多运动视觉里程计方法,获得场景中除相机运动外多个运动目标的运动状态。方法 基于传统的视觉里程计框架,引入多模型拟合的方法分割出动态场景中的多个运动模型,采用RANSAC（random sample consensus）方法估计出多个运动模型的运动参数实例;接着将相机运动信息以及各个运动目标的运动信息转换到统一的坐标系中,获得相机的视觉里程计结果,以及场景中各个运动目标对应各个时刻的位姿信息;最后采用局部窗口光束法平差直接对相机的姿态以及计算出来的相机相对于各个运动目标的姿态进行校正,利用相机运动模型的内点和各个时刻获得的相机相对于运动目标的运动参数,对多个运动模型的轨迹进行优化。结果 本文所构建的连续帧运动分割方法能够达到较好的分割结果,具有较好的鲁棒性,连续帧的分割精度均能达到近100%,充分保证后续估计各个运动模型参数的准确性。本文方法不仅能够有效估计出相机的位姿,还能估计出场景中存在的显著移动目标的位姿,在各个分段路径中相机自定位与移动目标的定位结果位置平均误差均小于6%。结论 本文方法能够同时分割出动态场景中的相机自身运动模型和不同运动的动态物体运动模型,进而同时估计出相机和各个动态物体的绝对运动轨迹,构建出多运动视觉里程计过程。     

A fast and accurate moving object tracker in active camera model

Detecting and tracking moving objects within a scene is an essential step for high-level machine vision applications such as video content analysis. In this paper, we propose a fast and accurate method for tracking an object of interest in a dynamic environment (active camera model). First, we manually select the region of the object of interest and extract three statistical features, namely the mean, the variance and the range of intensity values of the feature points lying inside the selected region. Then, using the motion information of the background’s feature points and k-means clustering algorithm, we calculate camera motion transformation matrix. Based on this matrix, the previous frame is transformed to the current frame’s coordinate system to compensate the impact of camera motion. Afterwards, we detect the regions of moving objects within the scene using our introduced frame difference algorithm. Subsequently, utilizing DBSCAN clustering algorithm, we cluster the feature points of the extracted regions in order to find the distinct moving objects. Finally, we use the same statistical features (the mean, the variance and the range of intensity values) as a template to identify and track the moving object of interest among the detected moving objects. Our approach is simple and straightforward yet robust, accurate and time efficient. Experimental results on various videos show an acceptable performance of our tracker method compared to complex competitors.     

Fast moving object detection with non-stationary background

The detection of moving objects under a free-moving camera is a difficult problem because the camera and object motions are mixed together and the objects are often detected into the separated components. To tackle this problem, we propose a fast moving object detection method using optical flow clustering and Delaunay triangulation as follows. First, we extract the corner feature points using Harris corner detector and compute optical flow vectors at the extracted corner feature points. Second, we cluster the optical flow vectors using K-means clustering method and reject the outlier feature points using Random Sample Consensus algorithm. Third, we classify each cluster into the camera and object motion using its scatteredness of optical flow vectors. Fourth, we compensate the camera motion using the multi-resolution block-based motion propagation method and detect the objects using the background subtraction between the previous frame and the motion compensated current frame. Finally, we merge the separately detected objects using Delaunay triangulation. The experimental results using Carnegie Mellon University database show that the proposed moving object detection method outperforms the existing other methods in terms of detection accuracy and processing time.     

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.     

Motion segmentation using occlusions

We examine the key role of occlusions in finding independently moving objects instantaneously in a video obtained by a moving camera with a restricted field of view. In this problem, the image motion is caused by the combined effect of camera motion (egomotion), structure (depth), and the independent motion of scene entities. For a camera with a restricted field of view undergoing a small motion between frames, there exists, in general, a set of 3D camera motions compatible with the observed flow field even if only a small amount of noise is present, leading to ambiguous 3D motion estimates. If separable sets of solutions exist, motion-based clustering can detect one category of moving objects. Even if a single inseparable set of solutions is found, we show that occlusion information can be used to find ordinal depth, which is critical in identifying a new class of moving objects. In order to find ordinal depth, occlusions must not only be known, but they must also be filled (grouped) with optical flow from neighboring regions. We present a novel algorithm for filling occlusions and deducing ordinal depth under general circumstances. Finally, we describe another category of moving objects which is detected using cardinal comparisons between structure from motion and structure estimates from another source (e.g., stereo).     

Recording,processing, and analysis of digital high-speed sequences in glottography

A new high-speed system for recording, processing, and analyzing vocal fold vibrations has been developed. Results obtained with this system are discussed from the technical and the medical points of view. Laryngeal movement can be recorded with a digital high-speed camera, at a maximum speed of about 5 600 frames/s and the sequence can contain as many as 8 192 single frames. Application specific software for adaptive, semiautomatic, motion analysis is used to calculate and plot the glottograms for selected points on each vocal cord. From the data obtained, we can calculate speed, acceleration rates, the fundamental frequency, amplitudes, and perturbation parameters. This approach to laryngeal examination, based on the digital films, motion plots and characteristic statistics, is a practicable method that promotes the possibilities of quantitative and graphic analysis of the moving vocal folds and overcomes the disadvantages of the currently common examination methods.     

运动摄像机下多目标检测与跟踪

针对摄像机运动情况下多目标的检测与跟踪问题,提出一种将Global K均值与模板匹配相结合的方法.利用六参数仿射模型得到摄像机运动参数,对图像进行全局运动补偿,用GlobalK均值算法对前景点进行循环聚类,判断目标数目并进行跟踪,通过对目标区域进行模板匹配使跟踪结果更准确.实验结果表明,该方法能够在运动摄像机下稳定、实时地跟踪多个目标,对发生形变的目标基本也能稳定跟踪.     

OPTICS聚类与目标区域概率模型的多运动目标跟踪

目的 针对多运动目标在移动背景情况下跟踪性能下降和准确度不高的问题,本文提出了一种基于OPTICS聚类与目标区域概率模型的方法。方法 首先引入了Harris-Sift特征点检测,完成相邻帧特征点匹配,提高了特征点跟踪精度和鲁棒性;再根据各运动目标与背景运动向量不同这一点,引入了改进后的OPTICS加注算法,在构建的光流图上聚类,从而准确的分离出背景,得到各运动目标的估计区域;对每个运动目标建立一个独立的目标区域概率模型(OPM),随着检测帧数的迭代更新,以得到运动目标的准确区域。结果 多运动目标在移动背景情况下跟踪性能下降和准确度不高的问题通过本文方法得到了很好地解决,Harris-Sift特征点提取、匹配时间仅为Sift特征的17%。在室外复杂环境下,本文方法的平均准确率比传统背景补偿方法高出14%,本文方法能从移动背景中准确分离出运动目标。结论 实验结果表明,该算法能满足实时要求,能够准确分离出运动目标区域和背景区域,且对相机运动、旋转,场景亮度变化等影响因素具有较强的鲁棒性。