一种适用于动态场景的运动目标提取新算法

在动态场景中提取运动目标是开展视频分析的关键问题,也是当前计算机视觉与图像处理技术领域中的热门课题。本文提出了一种适用于动态场景的运动目标提取新算法,算法先根据摄像机全局运动模型计算全局运动参数,再利用三帧差分法得到分割的前景。将分割为背景的像素点映射到邻近帧,求得各帧的像素点为背景时其高斯模型的均值及方差。最后利用粒子滤波预测出下一帧前景区域,计算各像素点为前景的概率,获得运动目标的视频分割结果。实验表明,本文算法有效地克服了由于全局运动模型参数估算偏差而导致的累积误差,能以更高精度实现跳水运动视频中的目标分割。     

基于时空背景差的运动目标检测算法

假定图像序列的背景图像已经获得,提出一种基于时空背景差的运动目标检测算法.该算法融合背景差分、基于时间信息的帧间差分及基于空间信息的背景差分信息,得到真实运动物体的运动种子点,认为背景差分图像中包含运动种子点的连通区域为真实的前景目标,从而可以检测出正确而完整的前景目标.仿真实验表明,该算法可以避免背景模型对场景的表征不足及背景更新阶段造成的错误检测,即使在场景中存在微小运动的复杂环境下,仍能实现准确的运动分割.     

基于背景建模的动态场景目标检测

背景建模一直是运动目标检测中的一个重要课题。该文提出一个适用于动态背景的基于非参数估计的前景背景对比模型。模型通过核函数估计的方法模拟了像素点五维特征向量(彩色灰度值,图像坐标)的概率分布,并在图像序列中滚动更新。对于每一个新入帧通过马尔可夫随机场最大后验概率判决框架将前景背景全局分割问题转化为最大流最小切求解。实验证明,上述算法能够在一般目标检测,特别是动态场景(摇动树枝等)的检测中取得较好的效果。     

一种运动背景下移动目标的检测方法

针对全局运动视频序列中的目标检测,提出了改进的灰度投影算法.通过对灰度投影相关曲线的分析,根据其单峰性特征,提出了三点局域自适应搜索算法,该方法能够快速的估计出前后两帧之间的运动矢量.然后以参考帧图像背景为参照,映射当前帧的背景信息,以此补偿全局运动矢量,将连续几帧图像的相同背景稳定在同一幅图像的相同位置上,从而能够利用改进的连续三帧差分法准确地检测出运动目标,并根据目标的特征进行分类识别.实验结果表明,该方法能够有效地从视频序列中提取和识别出运动目标.     

动态阈值的Vibe运动目标检测

Vibe算法是一种高效的像素级背景建模算法,但是它同混合高斯模型一样,不能适应光线突变的问题,在对Vibe算法的基础上提出了一种在静态场景下对光照变化鲁棒的运动目标检测方法。该方法首先利用Vibe模型建立背景样本集,并利用Vibe模型对判别为背景的像素对背景帧进行更新。其次视频当前图像帧与背景帧差分,并采用Otsu算法计算图像的分割阈值来检测运动目标。实验结果表明,改进的方法能够很好地消除由于环境光照变化引起的“曝光”现象,提高了运动目标检测的精确度,并且改进的算法对室内场景下的阴影也有较好的抑制作用。     

基于帧间差分的自适应运动目标检测方法*

本文提出了一种基于帧间差分的自适应运动目标检测算法。算法利用直方图统计各像素点处最大概率灰度的方法提取出连续视频的背景图像;相邻帧利用帧差法得到运动区域图像;利用运动区域图像与背景图像差分的方法提取出运动目标。实验结果表明,该算法能在多个不确定性因素的序列视频中较好的提取背景图像,能及时响应实际场景变化,提高运动目标检测的质量。     

一种基于多层背景模型的前景检测算法

动态场景中的前景检测是后继处理的基础和制约整个智能视频监控系统稳定性、可靠性的关键。为了在保证运动目标检测的基础上,进一步检测出前景中的静止目标并消除"鬼影(Ghost)",提出了一种基于多层背景模型的前景检测算法。该算法将背景分为参考背景和动态背景两层,分别采用单高斯和混合高斯模型进行背景建模。在线检测时,采用动态背景提取变化前景,用动态背景与参考背景之间高斯分布的差异提取静止前景,同时,通过逐层分析,比较输入像素与两层背景模型分布的相互关系,快速消除Ghost,降低虚警。实验结果表明,多层背景模型具有良好的检测性能和实时性,为后继跟踪、分类等处理提供了坚实的基础。目前,以该算法为核心构建了一个实时目标检测、跟踪系统,对图像大小为320×240的视频序列的平均处理速度达到15帧/s。     

信息视频图像人脸检测算法研究

本文首先采用运动信息检测算法,根据帧图像中是否包含运动信息判断图像中是否包含人脸区域,决定是否对该帧进行肤色分割,然后依据非线性的YCbCr肤色模型对需要检测的帧进行分割,进一步确定人脸区域的大致位置,并进行了仿真实验,实验结果表明该算法能够对视频图像序列中的人脸进行检测,具有良好的性能和一定的研究参考价值。     

混合高斯模型和差分法相融合的运动目标检测

提出运动目标检测中背景动态建模和OTSU局部递归分割的一种方法,该方法在自适应混合高斯背景模型基础上,为每个像素构建混合高斯背景模型,通过帧间差分把每帧中的图像区分为背景区域和运动区域,背景区域中像素点将以特定的更新率更新背景模型,物体运动区不再构建新的高斯分布加入到混合高斯分布模型中.实验结果表明,在有诸多不确定性因素的序列视频中构建的背景有较好的自适应性,能迅速响应实际场景的变化.     

复杂场景中运动目标的检测

由于检测场景的复杂性,传统的运动目标的提取常常采用自适应背景更新及自适应阈值分割方法,以去除噪声干扰,提高检测准确性。针对这种情况,提出在背景减除法的基础上通过改进的背景掩膜算法进行背景更新,利用场景的复杂性及系统中运动目标出现在障碍物边缘的特点,进行检测区域及非检测区域的划分,并采用阈值伪图的方法对整个视频序列图像进行自适应阈值分割。实验结果表明,该方法能够有效去除由于光线变化产生的噪声,以及由于相机抖动引起的背景与当前检测帧之间由位置偏差而产生的噪声,并避免了阈值分割时运动目标本身会出现空洞的问题,为后续运动目标的识别与跟踪奠定基础。     

运动显著性概率图提取及目标检测

目的 动态场景图像中所存在的静态目标、背景纹理等静态噪声,以及背景运动、相机抖动等动态噪声,极易导致运动目标检测误检或漏检。针对这一问题,本文提出了一种基于运动显著性概率图的目标检测方法。方法 该方法首先在时间尺度上构建包含短期运动信息和长期运动信息的构建时间序列组;然后利用TFT（temporal Fourier transform）方法计算显著性值。基于此,得到条件运动显著性概率图。接着在全概率公式指导下得到运动显著性概率图,确定前景候选像素,突出运动目标的显著性,而对背景的显著性进行抑制;最后以此为基础,对像素的空间信息进行建模,进而检测运动目标。结果 对提出的方法在3种典型的动态场景中与9种运动目标检测方法进行了性能评价。3种典型的动态场景包括静态噪声场景、动态噪声场景及动静态噪声场景。实验结果表明,在静态噪声场景中,F_score提高到92.91%,准确率提高到96.47%,假正率低至0.02%。在动态噪声场景中,F_score提高至95.52%,准确率提高到95.15%,假正率低至0.002%。而在这两种场景中,召回率指标没有取得最好的性能的原因是,本文所提方法在较好的包络目标区域的同时,在部分情况下易将部分目标区域误判为背景区域的,尤其当目标区域较小时,这种误判的比率更为明显。但是,误判的比率一直维持在较低的水平,且召回率的指标也保持在较高的值,完全能够满足于实际应用的需要,不能抵消整体性能的显著提高。另外,在动静态噪声场景中,4种指标均取得了最优的性能。因此,本文方法能有效地消除静态目标干扰,抑制背景运动和相机抖动等动态噪声,准确地检测出视频序列中的运动目标。结论 本文方法可以更好地抑制静态背景噪声和由背景变化（水波荡漾、相机抖动等）引起的动态噪声,在复杂的噪声背景下准确地检测出运动目标,提高了运动目标检测的鲁棒性和普适性。     

Reconstruction of a Scene with Multiple Linearly Moving Objects

In this paper we describe an algorithm to recover the scene structure, the trajectories of the moving objects and the camera motion simultaneously given a monocular image sequence. The number of the moving objects is automatically detected without prior motion segmentation. Assuming that the objects are moving linearly with constant speeds, we propose a unified geometrical representation of the static scene and the moving objects. This representation enables the embedding of the motion constraints into the scene structure, which leads to a factorization-based algorithm. We also discuss solutions to the degenerate cases which can be automatically detected by the algorithm. Extension of the algorithm to weak perspective projections is presented as well. Experimental results on synthetic and real images show that the algorithm is reliable under noise.     

利用运动线索的单目深度测量

目的 传统的单目视觉深度测量方法具有设备简单、价格低廉、运算速度快等优点,但需要对相机进行复杂标定,并且只在特定的场景条件下适用。为此,提出基于运动视差线索的物体深度测量方法,从图像中提取特征点,利用特征点与图像深度的关系得到测量结果。方法 对两幅图像进行分割,获取被测量物体所在区域;然后采用本文提出的改进的尺度不变特征变换SIFT（scale-invariant feature transtorm）算法对两幅图像进行匹配,结合图像匹配和图像分割的结果获取被测量物体的匹配结果;用Graham扫描法求得匹配后特征点的凸包,获取凸包上最长线段的长度;最后利用相机成像的基本原理和三角几何知识求出图像深度。结果 实验结果表明,本文方法在测量精度和实时性两方面都有所提升。当图像中的物体不被遮挡时,实际距离与测量距离之间的误差为2.60%,测量距离的时间消耗为1.577 s;当图像中的物体存在部分遮挡时,该方法也获得了较好的测量结果,实际距离与测量距离之间的误差为3.19%,测量距离所需时间为1.689 s。结论 利用两幅图像上的特征点来估计图像深度,对图像中物体存在部分遮挡情况具有良好的鲁棒性,同时避免了复杂的摄像机标定过程,具有实际应用价值。     

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。     

Structure from Motion: Beyond the Epipolar Constraint

The classic approach to structure from motion entails a clear separation between motion estimation and structure estimation and between two-dimensional (2D) and three-dimensional (3D) information. For the recovery of the rigid transformation between different views only 2D image measurements are used. To have available enough information, most existing techniques are based on the intermediate computation of optical flow which, however, poses a problem at the locations of depth discontinuities. If we knew where depth discontinuities were, we could (using a multitude of approaches based on smoothness constraints) accurately estimate flow values for image patches corresponding to smooth scene patches; but to know the discontinuities requires solving the structure from motion problem first. This paper introduces a novel approach to structure from motion which addresses the processes of smoothing, 3D motion and structure estimation in a synergistic manner. It provides an algorithm for estimating the transformation between two views obtained by either a calibrated or uncalibrated camera. The results of the estimation are then utilized to perform a reconstruction of the scene from a short sequence of images.The technique is based on constraints on image derivatives which involve the 3D motion and shape of the scene, leading to a geometric and statistical estimation problem. The interaction between 3D motion and shape allows us to estimate the 3D motion while at the same time segmenting the scene. If we use a wrong 3D motion estimate to compute depth, we obtain a distorted version of the depth function. The distortion, however, is such that the worse the motion estimate, the more likely we are to obtain depth estimates that vary locally more than the correct ones. Since local variability of depth is due either to the existence of a discontinuity or to a wrong 3D motion estimate, being able to differentiate between these two cases provides the correct motion, which yields the least varying estimated depth as well as the image locations of scene discontinuities. We analyze the new constraints, show their relationship to the minimization of the epipolar constraint, and present experimental results using real image sequences that indicate the robustness of the method.     

A hierarchy of cameras for 3D photography

The view-independent visualization of 3D scenes is most often based on rendering accurate 3D models or utilizes image-based rendering techniques. To compute the 3D structure of a scene from a moving vision sensor or to use image-based rendering approaches, we need to be able to estimate the motion of the sensor from the recorded image information with high accuracy, a problem that has been well-studied. In this work, we investigate the relationship between camera design and our ability to perform accurate 3D photography, by examining the influence of camera design on the estimation of the motion and structure of a scene from video data. By relating the differential structure of the time varying plenoptic function to different known and new camera designs, we can establish a hierarchy of cameras based upon the stability and complexity of the computations necessary to estimate structure and motion. At the low end of this hierarchy is the standard planar pinhole camera for which the structure from motion problem is non-linear and ill-posed. At the high end is a camera, which we call the full field of view polydioptric camera, for which the motion estimation problem can be solved independently of the depth of the scene which leads to fast and robust algorithms for 3D Photography. In between are multiple view cameras with a large field of view which we have built, as well as omni-directional sensors.     

Efficient Fourier-Based Approach for Detecting Orientations and Occlusions in Epipolar Plane Images for 3D Scene Modeling

This paper presents a Fourier-based approach for automatically constructing a 3D panoramic model of a natural scene from a video sequence. The video sequences could be captured by an unstabilized camera mounted on a moving platform on a common road surface. As the input of the algorithms, seamles panoramic view images (PVIs) and epipolar plane images (EPIs) are generated after image stabilization if the camera is unstabilized. A novel panoramic EPI analysis method is proposed that combines the advantages of both PVIs and EPIs efficiently in three important steps: locus orientation detection in the Fourier frequency domain, motion boundary localization in the spatio-temporal domain, and occlusion/resolution recovery only at motion boundaries. The Fourier energy-based approaches in literature were usually for low-level local motion analysis and are therefore not accurate for 3D reconstruction and are also computationally expensive. Our panoramic EPI analysis approach is both accurate and efficient for 3D reconstruction. Examples of layered panoramic representations for large-scale 3D scenes from real world video sequences are given.     

由抖动图象序列建立自然环境三维真实感全景模型

由真实环境中的现场图象进行三维环境建模是目前国际上研究的热点问题。本文依据合理的运动模型，提出和实现了由包含抖动的摄像机运动下的图象序列建立３Ｄ环境全景模型的两步法。首先通过运动滤波和运动分解获得运动稳定的图象序列，然后采用无特征提取的时空纹理方向精确估计、深度边界确定和遮挡恢复算法，建立全局自然景物的真实感三维环境模型。提出了２种三维全景图象的表示方法，即非阵列方式深度分层区域表示和阵列方式的深度分层布景表示，可用于机器人全局定位的自然路标提取和真实环境虚拟再现的图象合成。该研究推广和结合了外极面图象的方法和全景图象的方法，放宽了对运动的要求，从而可使该种方法适用于室外颠簸的道路环境。和现有运动分层方法相比，避免了该类方法迭代过程中的局部最小化问题，并具有计算和存储效率高，适应性强，算法鲁棒性好的优点。     

基于全局运动补偿的多运动目标检测方法研究

提出了一种动态背景下的对多个运动目标检测的完整方法.利用基于宏块匹配的六参数全局运动估计方法进行全局运动补偿,有效地消除了摄像机在非稳定运动情况下对目标检测性能带来的不利影响.同时在宏块匹配前进行了预处理,通过预判提取纹理信息丰富的宏块,并在宏块匹配的过程中采用九点十字搜索算法取代传统的三步搜索算法,减少了匹配数据量....     

Self-calibration from one circular motion sequence and two images

This paper describes a new method for self-calibration of camera with constant internal parameters under circular motion, using one sequence and two images captured with different camera orientations. Unlike the previous method, in which three circular motion sequences are needed with known motion, the new method computes the rotation angles and the projective reconstructions of the sequence and the images with circular constraint enforced, which is called a circular projective reconstruction, using a factorization-based method. It is then shown that the images of the circular points of each circular projective reconstruction can be readily obtained. Subsequently, the image of the absolute conic and the calibration matrix of the camera can be determined. Experiments on both synthetic and real image sequence are given, showing the accuracy and robustness of the new algorithm.