序列图像中运动目标的自动提取方法

针对目标检测与跟踪领域中的运动目标自动提取问题,提出了一种新的运动目标自动提取方法.利用已有的图像帧滤波后初始化背景,并在运动目标检测过程中,利用检测结果,不断地自动更新背景.使用背景差法检测运动区域,并对差分图像进行动态阈值分割,以及边缘链接,使其边缘处于基本连续状态.在得到的二值图上,提取轮廓,并根据目标大小选择面积阈值,剔除由于噪音或者背景提取不干净造成的虚假轮廓,将得到的轮廓掩模图像与原图像做逻辑与运算,提取出目标.实验结果表明,该方法可以有效地提取出刚体或非刚体运动目标.     

分布式网络信息数据防篡改方法研究

为在足球视频中有效的检测与跟踪运动目标,需要对足球比赛视频中目标检测与跟踪算法进行研究。当前采用的算法,在动态场景中,存在运动目标检测与跟踪效果不佳的问题。为此,提出一种基于OpenCV的足球比赛视频中目标检测与跟踪算法。该算法结合平均背景算法将足球比赛视频中目标图像分割为前景区与背景区,计算足球比赛视频每一帧目标图像和背景图像之间差值的绝对差值,同时计算每一个目标图像中像素点的平均值与标准值来建立目标图像背景统计模型,利用TMHI算法对足球比赛视频中目标初始图像进行阈值分割,得到初始分割图像,对分割图像进行中值滤波和闭运算,再使用卡尔曼滤波对分割后的目标图像进行处理,得到镜头中目标的质心位置和目标外界矩形框,然后对足球比赛视频中目标进行跟踪。实验证明,该算法有效的检测与跟踪足球视频中运动目标。     

基于差分图像的运动目标跟踪与分割方法的应用研究

提出了一种基于差分图像运动检测和轮廓提取的跟踪与分割图像的方法。该方法首先从初始图像中提取目标的轮廓,然后利用相邻帧之间的差分图像初步确定目标在每帧图像中的粗略位置,最后把从上一帧图像中得到的目标轮廓置于该位置,并作为轮廓提取的初始值,由此可得到对目标的准确分割。     

动态背景下运动目标检测与跟踪研究

主要研究动态背景下的运动目标检测和跟踪问题。背景补偿差分法是一种常用的动态背景下运动目标检测算法,但检测到的目标轮廓要比其真实轮廓大,检测结果不准确且算法复杂度较高。主动轮廓模型在图像分割和目标提取过程中具有拓扑结构变化灵活性,对数值计算方案的设计更加方便、有效,据此提出一种基于改进C-V模型和卡尔曼滤波的算法,用来检测和跟踪动态背景下的运动目标。提出的算法利用C-V模型曲线演化检测和跟踪目标,使C-V模型在目标的边缘处收敛。结合卡尔曼滤波预测运动目标下一帧位置,从而实现对运动目标轮廓的跟踪。实验结果表明,该方法可以对动态背景下运动目标进行精确的检测与跟踪。     

基于分形几何边界提取的图像跟踪方法

为了满足现代武器装备对图像跟踪系统的实时性和跟踪可靠性的双重要求，针对武器装备所跟踪目标的特点，将基于分形几何的边界提取方法用于图像跟踪系统，提出了一种基于运动区域和边界图像的目标跟踪方案。文中的边界提取方法不仅能提取出目标的轮廓，还能较好地保留其内部细节，这样通过模板匹配得到的最佳匹配位置更加可靠。同时，基于运动区域的边界提取，尤其是对于远景的目标跟踪大大减少了计算量。此外，在利用边界图像进行匹配的基础上，采用了自适应模板更新策略，目的是尽可能地克服形变、光照等影响，使跟踪过程准确可靠。仿真实验表明，该方法运算量小，能满足武器装备实时性要求。     

基于轮廓跟踪的车载红外视频彩色化方法

 提出一种车载红外视频快速彩色化方法,利用轮廓特征点跟踪获取每帧物体类别的轮廓区域,采用类别特征色彩对各区域传递色彩。构建各景物样本特征色彩集,以各类景物在自然彩色图像中表现出来的特征色彩作为红外图像中对应景物的色彩;利用改进的高效K Means方法对红外关键帧进行聚类,得到分割区域,提取轮廓特征点;通过KLT算法跟踪特征点,得到其在下一帧中的位置并同时修正,采用B样条插值进行轮廓复原,得到该帧的各类别轮廓区域;最后将特征色彩按类别赋予各区域,从而给各帧图像着上合适的颜色,实现红外视频序列的快速彩色化。实验结果表明, 该方法与基于运动估计的算法相比可提高近5倍的处理速度,并且能够得到与自然景物色彩较接近的彩色化视觉效果。     

基于局部轮廓特征的无人机头部检测跟踪算法

针对无人机的结构特点,提出了一种基于目标轮廓提取、轮廓自动分段、头部定位以及头部模板匹配四个模块的目标头部检测跟踪算法.首先对第一帧图像提取目标轮廓,并通过计算轮廓点的变化率,对轮廓进行自动分段,得到目标的4个局部轮廓点列,进而根据头部轮廓点列的特点,完成头部轮廓筛选,然后利用基于目标中轴的二次曲线拟合,实现头部顶点的...     

基于运动检测的多车辆跟踪方法研究

针对交通监控场景中多目标粘连造成跟踪上的困难和前后两帧车辆关联困难,提出了区域运动相似性分割方法和相似度关联矩阵的解决方案；在运动目标检测过程中, 首先使用背景差分法提取运动区域,经过消除缺口、空洞和分离等处理,在运动区域所在范围内进行块匹配搜索和局部光流计算区域运动矢量,然后使用模糊聚类方法对运动矢量区域融合,完整的分割出粘连运动目标；在目标跟踪部分,目标跟踪建立在目标关联的基础上,提出建立连续两帧目标间距离和局部二元模式相似度关联矩阵的方法进行运动目标标定,从而实现多目标关联；使用公共视频库的图像序列进行测试,所提算法都能实现连续的跟踪和准确的运动目标分割,且处理速度快,表明了算法具有鲁棒性和适用性。     

视觉注意驱动的测地线主动轮廓模型及其应用

针对前视红外时间序列图像,提出一种运动目标自动检测方法。利用三维(3D)时空纹理向量的变化度量运动特征,在视觉注意框架下,给出了运动目标的显著性定义。采用光流累加法校验并提取显著性运动区域作为视觉注意区域,将注意区域边界视作测地线主动轮廓的吸引力驱动可变形轮廓收敛于显著性运动目标,并利用目标梯度边缘作为收敛条件。实验结果表明,所提方法是合理、有效的。与传统运动检测方法相比,所提方法能够辨别冗余运动信息,对速率较快和较慢的运动对象以及噪声具有良好的稳健性。利用基于水平集的曲线演化计算能够同时给出多目标的边界定位,可为后续的识别跟踪以及3D重建与表示提供可靠依据。     

基于生物视觉特征和视觉心理学的视频显著性检测算法

提出了一种空域和时域相结合的视频显著性检测算法.对单帧图像，受视觉皮层层次化感知特性和Gestalt视觉心理学的启发，提出了一种层次化的静态显著图检测方法.在底层，通过符合生物视觉特性的特征图像（双对立颜色特征及亮度特征图像）的非线性简化模型来合成特征图像，形成多个候选显著区域；在中层，根据矩阵的最小Frobenius-范数（F-范数）性质选取竞争力最强的候选显著区域作为局部显著区域；在高层，利用Gestalt视觉心理学的核心理论，对在中层得到的局部显著区域进行整合，得到具有整体感知的空域显著图.对序列帧图像，基于运动目标在位置、运动幅度和运动方向一致性的假设，对Lucas-Kanade算法检测出的光流点进行二分类，排除噪声点的干扰，并利用光流点的运动幅度来衡量运动目标运动显著性.最后，基于人类视觉对动态信息与静态信息敏感度的差异提出了一种空域和时域显著图融合的通用模型.实验结果表明，该方法能够抑制视频背景中的噪声并且解决了运动目标稀疏等问题，能够较好地从复杂场景中检测出视频中的显著区域.     

Infrared moving object detection based on local saliency and sparse representation

The key issue of infrared object detection is to locate moving object in image sequence. In order to improve detection precision, an infrared object detection method based on local saliency and sparse representation is proposed in this paper. Motion information, such as velocity, acceleration components are added into the eigenvectors to build local saliency model. And the approximate position of the infrared target is located based on the local saliency. To accurately extract the infrared object, sparse representation is used to capture complete edge of the object. Experiments show that the proposed method can accurately detect infrared moving objects, and has good robustness to external disturbances and dynamic background.     

基于灰度信息的动场景视频序列中运动对象的提取

提出了一种基于视频序列灰度信息的运动对象提取方法。该方法采用改进的Sobel算子提取边缘图像,依据边缘信息将视频图像分割为不同的灰度连续区域。在各灰度连续区域中,选取特征点进行匹配获得特征点对。根据特征点对合并灰度连续区域,获得全局运动参数。采用具有自适应帧间隔的帧差交集法,获得图像中运动对象区域。结合灰度信息和运动信息,分割出运动对象。实验结果表明,该算法可以有效地将运动对象从视频序列中提取出来。     

基于区域增长的图像跟踪算法的研究

为了提高序列图像的跟踪精度,提出了基于区域增长的特征量提取方法。这种方法可捕获图像中所有单连通域,并能准确地提取其特征量,然后依据所提取的特征量设计分类器,实现对图像中所有单连通域进行分类识别并加以跟踪的目的。此算法有效地解决了一般传统识别算法难以区分目标和其近邻区域的干扰,而导致跟踪目标特征量提取不准确的问题。在目标特征提取识别算法的基础上,还提出了阈值预测分割算法,并应用在序列图像的跟踪中,取得了较好效果。     

Surface profile inspection of a moving object by using dual-frequency Fourier transform profilometry

The 2π phase ambiguity caused by surface isolations and large height step can be solved by dual-frequency projection grating profilometry. However, in the Fourier transform profilometry (FTP) of a moving object, only one single deformed fringe pattern can be obtained. In order to introduce the dual-frequency technique into the FTP of moving object, a novel experimental system is designed to capture two fringe patterns with different frequency at the same time. A grating structure comprising two regions with different frequencies is projected upon the surface of the detected object. Two line-scan CCD cameras are used to capture the surface images encoded by the two kinds of patterns, respectively. By getting the corresponding image intensity at the same point of the object surface in the two acquired images, the dual-frequency technique is applied to extract the real phase without phase ambiguity. The surface profile of a specimen with a large height step is measured to prove the feasibility of the proposed method. The experimental results show that the proposed method can solve the 2π phase ambiguity problem successfully in the surface profile inspection of a moving object.     

Human detection based on motion object extraction and head–shoulder feature

Aimed at the shortcomings of the traditional video monitoring system, human detection method in intelligent video monitoring system was researched. This paper proposed a human detection method based on motion object extraction and head–shoulder feature to complete human detection and statistics in video image sequences. Firstly, background subtraction based on adaptive threshold was used to extract foreground moving object information, then image erosion and image dilation were used to bypass the object shade and remove false object in order to optimize the results of motion object extraction. And finally, for realizing human moving object detection, we proposed the object discrimination algorithm based on human head–shoulder feature to complete human detection and statistics. Experimental results show that the method can successfully realize human detection and statistics. The method is highly accurate and has good real-time and extensive applications. The identification rate is 86% through human video sequences to test. This method can detect human automatically and provide the theoretical and technological base for object detection in the intelligent surveillance system.     

Projection-type moiré topography with frequency modulation technique using liquid crystal digital gratings

A projection-type moiré topography that uses a frequency modulation technique with two liquid crystal digital gratings (LCDGs) is proposed. In this method, moiré contours are filtered to remove the image of the original grating from the moiré contours by moving the image created by the LCDGs. The frequency modulation technique can be used to analyze the fringe of step heights or other separate areas by modulating the fringe interval. The experimental results showed the possibility of measuring three-dimensional shapes and step heights.     

Moving object detection based on improved VIBE and graph cut optimization

Extracting foreground moving objects from video sequences is an important task and also a hot topic in computer vision and image processing. Segmentation results can be used in many object-based video applications such as object-based video coding, content-based video retrieval, intelligent video surveillance and video-based human–computer interaction. In this paper, we present a novel moving object detection method based on improved VIBE and graph cut method from monocular video sequences. Firstly, perform moving object detection for the current frame based on improved VIBE method to extract the background and foreground information; then obtain the clusters of foreground and background respectively using mean shift clustering on the background and foreground information; Third, initialize the S/T Network with corresponding image pixels as nodes (except S/T node); calculate the data and smoothness term of graph; finally, use max flow/minimum cut to segmentation S/T network to extract the motion objects. Experimental results on indoor and outdoor videos demonstrate the efficiency of our proposed method.     

Precise speed measurement using an interlaced scan image

In this paper, we propose a novel scheme for speed measurement of a moving object with translational motion. First, this scheme uses one interlaced scan CCD camera to obtain only one interlaced scan image of a moving object. The odd and even field images are extracted and resized. Second, image matte is applied in these two field images to extract the moving object’s silhouettes. The distance between two centroids in the two silhouettes is then computed. Finally, the object’s speed is calculated using the above distance and the camera imaging parameters. Simulation and real experiments prove that our scheme can fulfill the speed measurement for translational motion accurately.