基于贝叶斯学习的视频图像分割

如果背景中光线变化,那么视频图像分割将会变得比较困难。为了对光线变化的图像进行顺利侵害,提出了一种利用贝叶斯学习方法来进行视频图像分割的算法,即先在每个像素点处对不断变化的背景建模,同时计算每个像素点处的颜色直方图,再用这些直方图来表示该像素点处特征向量的概率分布,然后用贝叶斯学习方法来进行判断,以确定在光线缓慢或者突然变化的时候,每个像素点是属于前景还是属于背景。     

一种基于混合概率模型的视频分割方法

该文提出一种新的基于混合概率模型视频分割方法。这个方法主要利用两个概率模型：隐马尔可夫模型和概率图模型建立一个混合的贝叶斯网概率模型,对视频输入中背景变化的时间和空间局部相关性（同现性）进行学习。在建立正确模型参数的基础上,贝叶斯信念传播算法根据图像输入预测当前背景状态的后验分布。并根据预测得到的背景状态对输入图像进行分割,实验结果显示方法的有效性和在复杂背景变化下的鲁棒性。     

基于时域统计变化检测实时分割头肩视频序列

分析了头肩视频序列的特点，提出了基于时域统计变化检测、利用多帧运动信息实时分割视频对象的方法。先选取包括当前帧在内的前连续2N帧图像，将奇数帧与偶数帧图像作差值，形成长度为Ⅳ的帧差图像序列；对每个象素点时域上的Ⅳ个帧差样本值进行分布显著性检验，判断象素点是否发生了变化；对得到的二值图像进行形态学处理，得到完整的分割结果。试验结果表明，该算法能够自动实时的分割视频对象。     

基于同态滤波抑制光照变化的视频分割算法

针对光照变化较大时基于颜色差分直方图的视频分割算法不能有效更新背景,导致后续输入图像前景目标分割失效的问题,提出一种基于同态滤波抑制光照变化的视频分割算法。首先利用同态滤波算法对输入和背景图像(RGB)在HSV空间中亮度分量进行同参矫正,然后将矫正后图像转换到RGB空间,最后利用颜色差分直方图算法进行视频分割。文中算法有效解决颜色差分直方图算法无法将受光照变化影响较大区域更新到背景中的问题,实现背景的实时有效更新,保证稳健地从后续输入图像分割前景目标。3组视频仿真结果表明该算法与高斯混合和Codebook算法相比具有运算速度快,对光照变化鲁棒的优点。     

基于混合概率背景模型的视频分割方法

提出一种新的基于混合概率模型的背景建模方法,用于视频中前景物体的检测与分割。主要利用两个概率模型：隐马尔可夫模型和概率图模型建立一个混合的贝叶斯网概率模型,对视频输入中背景变化的时间和空间局部相关性(同现性)进行学习。在建立正确模型参数的基础上,贝叶斯信念传播算法根据图像输入预测当前背景状态的后验分布,并根据预测得到的背景状态对输入图像进行分割。实验结果验证了该方法的有效性和在复杂背景变化下的鲁棒性。     

基于非归一化直方图的GrabCut图像分割算法改进

针对GrabCut算法在图像分割中存在迭代求解耗时长、分割结果欠分割的问题,提出了一种基于非归一化直方图改进的GrabCut算法。在保留GrabCut第一次分割结果的基础上,通过非归一化直方图计算像素点属于前景或背景的方法来代替高斯混合模型迭代学习的过程;在构图过程中引入一类新的节点Bin进行构图以提高分割精度。选取MSRA1000数据集中部分图片进行实验验证,结果表明该算法在分割效果和效率上都有明显的提升,在进行背景复杂图像的分割时改进算法优势更加明显。     

视频图像的邻域统计直方图均衡化增强算法

针对视频监控图像相邻帧之间场景变化小的特点,提出一种适用于视频图像的邻域统计直方图均衡化算法来提升图像的对比度。根据相邻视频帧的场景相关性,对图像当前帧进行邻域信息统计,利用Laplace算子得到前一帧图像中的背景和细节信息,从而选择合适的增强参数,生成视频图像的优化直方图。使用优化后直方图的均值点将其分割成2个部分得到各自的变换函数,对视频图像进行直方图均衡化操作。实验结果表明,该算法能够提升视频图像的对比度,保持图像的平均亮度,减弱过增强现象,保留视频中兴趣区域的细节信息。可以获得的最小绝对平均亮度误差值为1.4741,最大熵值为7.0993,最大峰值信噪比值为20.6710。     

复杂背景下的阈值插值方法

图像分割是进行图像处理的关键步骤。目前很多图像分割的技术都需要人工干预，而且是针对单纯的图像背景才能达到目标。为了解决有复杂背景的图像的分割问题，采用自适应阈值(阈值插值)的方法，并对其加以改进，用迭代阈值判断子图像的直方图是否是双峰分布，同时确定直方图有双峰的子图像的阈值；用双线性插值的方法确定直方图非双峰分布的予图像的阈值，使这种算法在实际中可行。实验证明这种方法适用于复杂背景的图像分割，且通用性比较好。     

视频序列中运动目标自动提取的研究

本文提出了一种从彩色视频序列中,有效分割运动目标的算法。首先将当前帧图像和背景参考图像在YUV彩色空间中进行距离差分得到距离差分图像,然后根据差分图像直方图的单峰聚集特性,提出了基于直方图的自适应聚类分割算法;对分割后的二值图像采用图像形态学方法去除无用的噪声斑点,并根据得到运动模板,提出了背景参考图像的更新策略。实验结果表明这是一种简单、有效的运动目标提取方法。     

基于均值—梯度共生矩阵模型的最大熵多阈值算法

为解决噪声显微细胞图像的多阈值分割问题,该文提出基于均值和梯度共生矩阵模型的最大熵多阈值算法。选用象素点的邻域灰度均值和梯度值构成二维灰度直方图。因为对象素点取均值可以平滑噪声,取梯度值可以锐化边缘,所以该算法能够改善图像的分割质量。考虑显微细胞图像多阈值分割的要求,该算法对二维灰度直方图采用改进的区域划分方式。通过优化传统的求熵算法,来减少运算时间,使之更加适合于擅长矩阵运算的MATLAB编程语言,从而提高运算速度。实验证明,该算法去除了噪声干扰,实现了显微细胞图像的多阈值分割,运算速度较快。     

Visual information fusion for object-based video image segmentation using unsupervised Bayesian online learning

An algorithm using the unsupervised Bayesian online learning process is proposed for the segmentation of object-based video images. The video image segmentation is solved using a classification method. First, different visual features (the spatial location, colour and optical-flow vectors) are fused in a probability framework for image pixel clustering. The appropriate modelling of the probability distribution function (PDF) for each feature-cluster is obtained through a Gaussian distribution. The image pixel is then assigned a cluster number in a maximum a posteriori probability framework. Different from the previous segmentation methods, the unsupervised Bayesian online learning algorithm has been developed to understand a cluster's PDF parameters through the image sequence. This online learning process uses the pixels of the previous clustered image and information from the feature-cluster to update the PDF parameters for segmentation of the current image. The unsupervised Bayesian online learning algorithm has shown satisfactory experimental results on different video sequences.     

基于CHMM的背景差算法

为了解决背景差算法在前景提取的过程中对光照变化的敏感性和提取的前景中容易产生椒盐噪声的问题,提出了一种基于耦合隐马尔科夫模型的背景差方法.对像素的马尔科夫性进行了分析,并对像素建立耦合隐马尔科夫模型,通过时间统计的方法统计了像素隐含状态的转移概率,通过实验的方法选取了合适的前景标准差和背景标准差,利用Viterbi算法来求解耦合隐马尔科夫模型的最优隐含状态问题,运用该算法对一段交通监控视频进行分析,表明了该算法能够有效的抑制光照变化的影响,并且能够在一定程度上抑制前景噪声的出现.     

Online learning neural tracker

Object tracking is a fundamental computer vision problem and is required for many high-level tasks such as activity recognition, behavior analysis and surveillance. The main challenge in the object tracking problem is the dynamic change in object/background appearance, illumination, shape and occlusion. We present an online learning neural tracker (OLNT) to differentiate the object from the background and also adapt to changes in object/background dynamics. For target modeling and object tracking, a neural algorithm based on risk sensitive loss function is proposed to handle issues related to sample imbalance and dynamics of object. Region-based features like region-based color moments for larger mobile objects and color/texture features at pixel level for smaller mobile objects are used to discriminate the object from background. The proposed neural classifier automatically determines the number of neurons required to estimate the posterior probability map. In the online learning neural classifier, only one neuron parameter is updated per tracker to reduce the computational burden during online adaptation. The tracked object is represented using an estimated posterior probability map. The posterior probability map is used to adapt the bounding box to handle the scale change and improper initialization.For illustrating the advantage of the proposed OLNT under rapid illumination variation, change in appearance, scale/size change, and occlusion, we present results from benchmark video sequences. Finally, we also present the comparison with well-known trackers in the literature and highlight the advantage of the proposed tracker.     

Target tracking based on foreground probability

According to the mean shift tracking algorithm, weights are used to reduce the background interference. However, weights also weaken the representation of the target at the same time. In order to reduce of weakness for model representation brought by the weight, weighted fusion which is composed of target model, candidate model and the probability that the pixel belonging to foreground is proposed to enhance the difference between foreground and background. The purpose is to resist the affection brought by background pixels. Firstly, weak classifiers composed of color and texture features are deduced by Bayesian and update the weak classifiers by changing the parameters of the Gauss distribution. Projection vector to distinguish the foreground and background is found through iteration. Then the projection vector obtained by foreground probability map and weight in mean shift is fused. The projection vector that strengthens the difference between foreground and background is updated to adapt to the changes of illumination or background. Finally, the target center position, scale and rotation angle are determined to achieve the target tracking by the moment features based on the improved weight.     

基于贝叶斯生成对抗网络的背景消减算法

背景消减是计算机视觉和模式识别的关键技术之一.本文提出一种新的背景消减算法,该算法首先利用中值滤波算法进行背景数据的获取,然后基于贝叶斯生成对抗网络进行训练,利用生成对抗网络的特性,有效地对每个像素进行分类,解决了光照渐变和突变、非静止背景以及鬼影的问题.本文采用深度卷积神经网络,来构建贝叶斯生成对抗网络的生成器和判别器.实验结果表明,本文提出的算法性能在绝大多数情况下优于现有其他算法.本文的贡献在于首次将贝叶斯生成对抗网络应用于背景消减,并且取得了良好的实验效果.     

统计建模与对象更新机制相结合的背景减法

基于混合高斯模型（Gaussian Mixture Models,GMM）或码书模型（Codebook,CB）的传统背景建模算法和改进后的G-KDE算法被广泛地运用于运动目标检测中,但是在光照突变、非静止背景和运动目标短暂停留再运动的场景中不能正确地检测出运动目标。针对以上问题,提出了一种从静止摄像机的视频序列中检测运动目标的背景减算法。通过统计像素的经历作为时间序列,利用核密度估计判断背景像素是否受到运动目标干扰,使用K-均值聚类算法的两个连续阶段来确定可靠的背景区域,通过像素更新适应渐进的光照变化,提出一种基于对象的背景更新机制适应突然的光照变化以及非静止背景、鬼影等干扰。对实际摄取的视频进行了仿真实验,结果表明该算法比其他三种方法检测运动目标鲁棒性更好,准确性更高。     

An efficient estimation method for intensity factor of illumination changes

For intensity correction under illumination changes in video sequence, one of the main problems lies in the lack of adaptive technique for the classification of stationary and non-stationary pixels in the images. In this paper, we propose an efficient estimation approach for intensity factor of illumination changes in order to perform intensity correction for dynamic sequence images. Firstly, the ratio image is obtained, where the probability density function computed on pixel values can be considered as a mixture Gaussian model. Then the process of the parameter estimations is performed based on Expectation–maximization (EM) algorithm. Under the assumption of Gaussian distribution for the values of stationary pixels, the intensity factor can be estimated by using pixels adjacent to the mean value of Gaussian distribution related to the stationary class. Finally, two experiments are carried out to verify the proposed method.