面向多种场景的视频对象自动分割算法

针对当前应用于视频对象分割的图割方法容易在复杂环境、镜头移动、光照不稳定等场景下鲁棒性不佳的问题,提出了结合光流和图割的视频对象分割算法.主要思路是通过分析前景对象的运动信息,得到单帧图像上前景区域的先验知识,从而改善分割结果.论文首先通过光流场采集视频中动作信息,并提取出前景对象先验区域,然后结合前景和背景先验区域建立图割模型,实现前景对象分割.最后为提高算法在不同场景下的鲁棒性,本文改进了传统的测地显著性模型,并基于视频本征的时域平滑性,提出了基于混合高斯模型的动态位置模型优化机制.在两个标准数据集上的实验结果表明,所提算法与当前其他视频对象分割算法相比,降低了分割结果的错误率,有效提高了在多种场景下的鲁棒性.     

基于运动优化语义分割的变分光流计算方法

针对光照变化和大位移运动等复杂场景下图像序列变分光流计算的边缘模糊与过度分割问题,文中提出基于运动优化语义分割的变分光流计算方法.首先,根据图像局部区域的去均值归一化匹配模型,构建变分光流计算能量泛函.然后,利用去均值归一化互相关光流估计结果,获取图像运动边界信息,优化语义分割,设计运动约束语义分割的变分光流计算模型.最后,融合图像不同标签区域光流,获得光流计算结果.在Middlebury、UCF101数据库上的实验表明,文中方法的光流估计精度与鲁棒性较高,尤其对光照变化、弱纹理和大位移运动等复杂场景的边缘保护效果较优.     

基于马尔可夫随机场模型的运动对象分割算法

提出了一种基于马尔可夫随机场(MRF)模型的运动分割算法,仅使用了压缩流中的运动矢量和块编码模式信息,可以在复杂场景下对运动对象有很好的分割效果.利用运动矢量量化的方法来对运动矢量进行预处理,对运动矢量进行马尔可夫建模,利用能量最小函数进行优化得到运动对象分割的效果.实验表明:与现有的方法相比,该方法可从复杂场景中更准确地对运动对象进行分割.     

一种新的基于吉布斯随机场的视频运动对象分割算法

与现有的视频运动对象分割算法不同, 本文提出一种新的基于吉布斯 (Gibbs) 随机场模型的视频运动对象的分割算法, 该算法将运动对象的运动场作为主分割信息, 空间像素值的一致性作为次要分割信息. 该算法首先对运动矢量场进行累加和滤波处理；然后在 Gibbs 运动场模型的势能函数的定义中引入空间相关影响因子, 采用最大后验概率的方法进行分割；最后细化运动对象边缘. 对多个视频序列的测试, 实验结果表明该算法比现有基于光流的分割算法更准确的分割运动对象.     

基于光流场的动态目标分割

采用光流法结合基于小波变换的像素级图像融合算法,研究了一种动态目标分割方法。光流场可以看作是带有灰度的像素点在图像平面运动产生的瞬时速度场,算法先以光流法计算出的动态目标瞬时速度场的水平速度分量和垂直速度分量作为初始信息,再利用基于小波变换的融合算法获得动态目标的初始分割,最后对初始分割结果进行图像去噪和图像增强,并最终获得清楚的分割图。实验证明,该方法能够产生良好的目标分割效果。     

基于熵能的H.264压缩域运动对象分割

提出了一种基于熵能选取自适应阈值的时空域运动对象分割方法。首先对H.264压缩码流中提取的原始运动矢量场进行连续多帧的累加来增强运动信息,并对累积运动矢量场进行相似性判断,初步获得运动块;然后提取压缩码流中4×4块残差编码位数,并基于熵能自动选取自适应局部阈值,获取运动区域的轮廓信息;最后结合运动块和轮廓信息按照一定的规则对边界进行校正。对多个视频序列进行了实验,结果表明,该算法能快速取得较好的分割结果。     

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.     

一种时空信息联合的运动对象分割算法

提出了一种在通用视频序列中联合时空信息分割运动对象的算法。首先,提出匹配加权的全局运动估计补偿算法,以消除动态场景中背景运动对运动对象分割的影响。其次,时域信息提取中,使用基于直方图拟合的显著性检测及对称差分法获得运动对象模板,以克服依据经验设定阂值的缺点并且提高运动对象模板的准确性;空域信息提取中,提出基于粘性形态学梯度修正和相部区域边缘强度合并的改进分水岭分割算法,以较好地解决分水岭算法的过分割问题,获得有效空间区域分割。最后,利用双阂值比重算法将时域和空域信息结合,提取出运动对象。实验表明,该算法分割结果准确,有效地解决了背景运动、时域信息不准确、空域过分割以及时空信息难以有效结合的问题。     

一种新型的实效运动目标检测方法

提出一种新型的帧间差分光流的运动目标检测方法.该方法通过改进七帧差分和改进背景减除消除运动目标检测时出现的"空洞"和虚假目标;通过在光流计算方程加入权函数和引入通用动态图像模型建立新的光流约束条件,以解决常用光流场计算耗时长和亮度变化引起的约束方程不成立的问题,同时获取运动准确信息;最后通过阈值分割和形态学处理完成对目标的分割.实验对比分析表明,该方法能实现运动目标的准确快速检测与分割.     

结合高斯混合模型与多通道双边滤波的RGBD场景流计算方法

针对现有RGBD场景流计算方法在大位移、运动遮挡等复杂运动场景中存在计算准确性与可靠性较低的问题，文中提出结合高斯混合模型与多通道双边滤波的RGBD场景流计算方法.首先，构造基于高斯混合模型的光流聚类分割模型，从光流中提取目标运动信息，逐层优化深度图分层分割结果，获取高置信度的深度运动分层分割信息.然后，在场景流计算中引入多通道双边滤波优化，建立结合高斯混合模型与多通道双边滤波的RGBD场景流计算模型，克服场景流计算边缘模糊问题.最后，在Middlebury、MPI-Sintel数据集上的实验表明，文中方法在大位移、运动遮挡等复杂运动场景下具有较高的场景流计算准确性和鲁棒性，特别在边缘区域具有较好的保护效果.     

基于水平集的多运动目标时空分割与跟踪

针对背景运动时的运动目标分割问题,提出了一种对视频序列中的多个运动目标进行分割和跟踪的新方法。该方法着眼于运动的且较为复杂的背景,首先利用光流约束方程和背景运动模型建立一个基于时空域的能量函数,然后用该函数进行背景运动速度的估算和运动目标的分割和跟踪。而时空域中的运动目标的最佳分割,乃是通过使该能量函数最小化来驱动时空曲面演化实现。时空曲面的演化采用了水平集PDEs(Partial Differential Equations)方法。实验中,用实际的图像序列验证了该算法及其数值实现。实验表明,该方法能够同时进行背景运动速度的估算、运动目标的分割和跟踪。     

Joint segmentation of collectively moving objects using a bag-of-words model and level set evolution

In scenes with collectively moving objects, to disregard the individual objects and take the entire group into consideration for motion characterization is a promising approach with wide application prospects. In contrast to studies on the segmentation of independently moving objects, our purpose is to construct a segmentation of these objects to characterize their motions at a macroscopic level. In general, the collectively moving objects in a group have very similar motion behavior with their neighbors and appear as a kind of global collective motion. This paper presents a joint segmentation approach for these collectively moving objects. In our model, we extract these macroscopic movement patterns based on optical flow field sequences. Specifically, a group of collectively moving objects correspond to a region where the optical flow field has high magnitude and high local direction coherence. As a result, our problem can be addressed by identifying these coherent optical flow field regions. The segmentation is performed through the minimization of a variational energy functional derived from the Bayes classification rule. Specifically, we use a bag-of-words model to generate a codebook as a collection of prototypical optical flow patterns, and the class-conditional probability density functions for different regions are determined based on these patterns. Finally, the minimization of our proposed energy functional results in the gradient descent evolution of segmentation boundaries which are implicitly represented through level sets. The application of our proposed approach is to segment and track multiple groups of collectively moving objects in a large variety of real-world scenes.     

Improvement of the precision of the gradient method and object tracking using optical flow

In this study, the spatial local optimization method was improved to obtain high precision of optical flow for cases in which the object movement changes substantially and a method to trace the loci of moving objects was considered. In the spatial local optimization method, the precision of the optical flow when the object movement changes substantially becomes a problem. Therefore, to make the object movement relatively small, we obtained flow vectors from the image sequence to drop the resolution of the original input image sequence to half the initial resolution. flow vectors were then obtained from the original input image sequence that were smaller than the threshold value. We show that the precision of the optical flow when the object movement changes substantially is improved by this method. Method used to trace the loci of moving objects was demonstrated. We obtained clusters from histograms of flow vectors and pursued each cluster. We show that it is possible to trace moving objects by this method. This work was presented, in part, at the 7th International Symposium on Artificial Life and Robotics, Oita, Japan, January 16–18, 2002     

Motion estimation and segmentation

In the general structure-from-motion (SFM) problem involving several moving objects in a scene, the essential first step is to segment moving objects independently. We attempt to deal with the problem of optical flow estimation and motion segmentation over a pair of images. We apply a mean field technique to determine optical flow and motion boundaries and present a deterministic algorithm. Since motion discontinuities represented by line process are embedded in the estimation of the optical flow, our algorithm provides accurate estimates of optical flow especially along motion boundaries and handles occlusion and multiple motions. We show that the proposed algorithm outperforms other well-known algorithms in terms of estimation accuracy and timing.     

一种基于帧间差分和光流技术结合的运动车辆检测和跟踪新算法

为了改进智能交通中的运动车辆检测和跟踪方法,提出一种基于改进的帧间差分和光流技术结合的运动车辆检测和跟踪的新方法。先用帧间差分法检测出运动物体的运动区域,再计算差值图中不为零处的光流,然后利用其光流场来实现运动目标的跟踪。为了减少计算量,提出一种基于最优估计的点匹配技术和光流均匀采样策略的光流场计算方法,并通过对灰度化后的光流场进行自适应阈值分割、形态学滤波等处理,实现了实时的运动目标检测和跟踪。     

融合多特征的运动一致性图像分割

目的:在彩色图像分割中,光流法能够得到运动区域,但难以获得运动目标准确的分割边界,而常用的算法往往会产生过分割。为了克服光流法的不足,在保留显著性区域的同时抑制过分割,从而获得具有运动一致性区域的分割结果,提出融合多特征的运动一致性图像分割算法。方法:首先通过Mean Shift算法获取图像的初始分割,然后利用空域信息（包括颜色、边缘和区域面积）对视觉感知上具有相似性的区域进行合并,再利用时域信息进行运动一致性区域合并,最终得到分割结果。结果:实验结果表明通过结合时空信息,该方法能够有效抑制过分割,不仅弥补了光流场不能准确提取目标边缘的不足,而且提高了分割目标的完整性。结论:与两种流行的彩色图像分割算法相比,所提方法获得了更加理想的结果。     

Optical flow 3D segmentation and interpretation: a variational method with active curve evolution and level sets

This study investigates a variational, active curve evolution method for dense three-dimensional (3D) segmentation and interpretation of optical flow in an image sequence of a scene containing moving rigid objects viewed by a possibly moving camera. This method jointly performs 3D motion segmentation, 3D interpretation (recovery of 3D structure and motion), and optical flow estimation. The objective functional contains two data terms for each segmentation region, one based on the motion-only equation which relates the essential parameters of 3D rigid body motion to optical flow, and the other on the Horn and Schunck optical flow constraint. It also contains two regularization terms for each region, one for optical flow, the other for the region boundary. The necessary conditions for a minimum of the functional result in concurrent 3D-motion segmentation, by active curve evolution via level sets, and linear estimation of each region essential parameters and optical flow. Subsequently, the screw of 3D motion and regularized relative depth are recovered analytically for each region from the estimated essential parameters and optical flow. Examples are provided which verify the method and its implementation     

Adaptive Grid Refinement Procedures for Efficient Optical Flow Computation

Two approaches are described that improve the efficiency of optical flow computation without incurring loss of accuracy. The first approach segments images into regions of moving objects. The method is based on a previously defined Galerkin finite element method on a triangular mesh combined with a multiresolution segmentation approach for object flow computation. Images are automatically segmented into subdomains of moving objects by an algorithm that employs a hierarchy of mesh coarseness for the flow computation, and these subdomains are reconstructed over a finer mesh on which to recompute flow more accurately. The second approach uses an adaptive mesh in which the resolution increases where motion is found to occur. Optical flow is computed over a reasonably coarse mesh, and this is used to construct an optimal adaptive mesh in a way that is different from the gradient methods reported in the literature. The finite element mesh facilitates a reduction in computational effort by enabling processing to focus on particular objects of interest in a scene (i.e. those areas where motion is detected). The proposed methods were tested on real and synthetic image sequences, and promising results are reported.     

A Neural Paradigm for Motion Understanding

The main aim of this paper is to propose a new neural algorithm to perform a segmentation of an observed scene in regions corresponding to different moving objects, by analysing a time-varying image sequence. The method consists of a classification step, where the motion of small patches is recovered through an optimisation approach, and a segmen-tation step merging neighbouring patches characterised by the same motion. Classification of motion is performed without optical flow computation. Three-dimensional motion parameter estimates are obtained directly from the spatial and temporal image gradients by minimising an appropriate energy function with a Hopfield-like neural network. Network convergence is accelerated by integrating the quantitative estimation of the motion parameters with a qualitative estimate of dominant motion using the geometric theory of differential equations.