Bounded multivariate generalized Gaussian mixture model using ICA and IVA

Pattern Analysis and Applications - A bounded multivariate generalized Gaussian mixture model with a full covariance matrix is proposed for modeling data in a bounded support region. For model...     

基于混合高斯模型的阴影去除算法

阴影去除是智能视频领域中运动目标识别的一项重要内容,其结果直接影响目标识别的准确性。针对当前基于纹理特征的阴影去除算法的不足,提出一种结合YCbCr颜色空间和混合高斯模型(GMM)的阴影去除算法。首先利用混合高斯模型提取出运动区域;然后通过分析运动区域的前景和背景在YCbCr颜色空间的差值统计特性,建立混合高斯阴影模型;最后根据高斯分布的概率分布规律,得到阴影分布特性,从而实现对阴影的去除。对于实验中的序列图像,所提算法有70%以上的阴影检测率。实验结果表明,所提方法能够在不同的场合快速有效地去除阴影,准确地提取运动目标。     

Random weighting estimation of parameters in generalized Gaussian distribution

This paper studies random weighting estimation of shape and scale parameters in generalized Gaussian distribution (GGD). An expression is established to describe the relationship between moments and parameters. The strong convergence for random weighting estimation of GGD parameters is also rigorously proved. Computational simulations and practical experiments are presented to demonstrate the efficacy for random weighting estimation of GGD parameters.     

新型背景混合高斯模型

针对背景减除法中经典混合高斯模型计算量过大的问题,提出一种新的背景混合高斯模型。该方法利用偏差均值作为判断模型是否与当前像素值匹配的阈值参数,有效减少了经典模型中由于开平方及指数运算带来的庞大计算量;同时引入持续平稳时间的概念,采用非线性权值更新方法,能够使较长时间停留在场景中的物体迅速成为背景。实验结果表明,该方法显著提高了背景模型的计算效率。     

Generating generalized inverse Gaussian random variates by fast inversion

The inversion method for generating non-uniformly distributed random variates is a crucial part in many applications of Monte Carlo techniques, e.g., when low discrepancy sequences or copula based models are used. Unfortunately, closed form expressions of quantile functions of important distributions are often not available. The (generalized) inverse Gaussian distribution is a prominent example. It is shown that algorithms that are based on polynomial approximation are well suited for this distribution. Their precision is close to machine precision and they are much faster than root finding methods like the bisection method that has been recently proposed.     

复杂条件下高斯混合模型的自适应背景更新

针对高斯混合模型背景更新中面临的光照突变和目标与背景相互转化的问题,提出一种分情况分区域的背景自适应更新算法。首先根据当前检测目标的面积大小判别是否发生光照突变情况,采取针对性更新策略,对于未发生光照突变情况再分背景区域和目标区域分别进行背景自适应更新。其中,重点讨论了目标区域的背景更新问题,提出根据目标尺寸、运动速度和匹配次数等特征参数来调整目标区域的背景更新速率。仿真结果表明,该算法在保证了目标检测完整性的同时,提高了模型对背景变化的适应能力。     

The Supervised Learning Gaussian Mixture Model

The traditional Gaussian Mixture Model(GMM)for pattern recognition is an unsupervised learning method.The parameters in the model are derived only by the training samples in one class without taking into account the effect of sample distributions of other classes,hence,its recognition accuracy is not ideal sometimes.This paper introduces an approach for estimating the parameters in GMM in a supervising way.The Supervised Learning Gaussian Mixture Model(SLGMM)improves the recognition accuracy of the GMM.An experimental example has shown its effectiveness.The experimental results have shown that the recognition accuracy derived by the approach is higher than those obtained by the Vector Quantization(VQ)approach,the Radial Basis Function (RBF) network model,the Learning Vector Quantization (LVQ) approach and the GMM.In addition,the training time of the approach is less than that of Multilayer Perceptrom(MLP).     

图像小波系数的高斯混合模型研究

图像小波系数的统计分布具有非高斯特性,可以用高斯混合模型进行描述。提出了一种随像素自适应调整的混合高斯模型,每个系数建模为两个均值为零、方差不同的正态分布之和,利用局部贝叶斯阈值对小波系数进行分类,通过当前系数邻域窗中两类系数的信息,得到大、小方差以及有关概率的模型参数估计。将此模型应用于图像去噪,根据贝叶斯后验均值估计理论设计了Wiener滤波器。通过与三种代表性去噪算法的比较实验,表明了这种基于模型的滤波算法的有效性。     

基于高斯混合模型的自动图像标注方法

为了进一步完善自动图像标注方法,提出基于高斯混合模型的自动图像标注方法。该方法通过建立每个关键词唯一的高斯混合模型(GMM),准确地描述关键词的语义内容,进而提高自动图像标注的精确性。最后,通过采用COREL图像数据集与不同方法的比较,从平均查准率、平均查全率的实验结果验证了该方法的有效性。     

基于混合高斯模型和空间模糊度的支持向量机算法研究

在提升支持向量机分类算法精度的问题上,提出了一种基于混合高斯模型和空间模糊度的支持向量机算法。该算法通过采用多维混合高斯模型的求带分布密度概率函数的二次规划问题的最优解,减少不同的输入样本数据对分类超平面造成的影响,引入了优化后的空间模糊度因子和空间模糊度函数。在实验仿真上,采用了人工选择的样本数据集和 UCI 机器学习数据库中的样本数据集进行多次实验,最后通过对比分析的方法突出了算法在分类精度上的优势。     

改进的自适应混合高斯前景检测方法

针对混合高斯背景模型计算量大、存在阴影和鬼影的不足,提出一种基于混合高斯模型的改进前景检测算法。通过分析背景的稳定性来选择连续或隔帧更新方式对背景模型中的参数进行更新,提高算法的运算速度。在背景更新方面,让更新率与权值相关联从而使更新率随权值改变并且对目标移动后显露的背景像素给予更大的更新率,提高背景的稳定性并解决鬼影现象及前景与背景转化的问题。对检测出的目标,用适应性更高的RGB颜色空间畸变模型进行阴影检测和消除,并进行高斯金字塔滤波和形态学滤波处理,以得到更好的前景目标。实验结果表明,该方法能提高算法的计算效率且准确地分割前景目标。     

Image thresholding based on the EM algorithm and the generalized Gaussian distribution

In this paper, a novel parametric and global image histogram thresholding method is presented. It is based on the estimation of the statistical parameters of “object” and “background” classes by the expectation-maximization (EM) algorithm, under the assumption that these two classes follow a generalized Gaussian (GG) distribution. The adoption of such a statistical model as an alternative to the more common Gaussian model is motivated by its attractive capability to approximate a broad variety of statistical behaviors with a small number of parameters. Since the quality of the solution provided by the iterative EM algorithm is strongly affected by initial conditions (which, if inappropriately set, may lead to unreliable estimation), a robust initialization strategy based on genetic algorithms (GAs) is proposed. Experimental results obtained on simulated and real images confirm the effectiveness of the proposed method.     

Finite asymmetric generalized Gaussian mixture models learning for infrared object detection

The interest in automatic surveillance and monitoring systems has been growing over the last years due to increasing demands for security and law enforcement applications. Although, automatic surveillance systems have reached a significant level of maturity with some practical success, it still remains a challenging problem due to large variation in illumination conditions. Recognition based only on the visual spectrum remains limited in uncontrolled operating environments such as outdoor situations and low illumination conditions. In the last years, as a result of the development of low-cost infrared cameras, night vision systems have gained more and more interest, making infrared (IR) imagery as a viable alternative to visible imaging in the search for a robust and practical identification system. Recently, some researchers have proposed the fusion of data recorded by an IR sensor and a visible camera in order to produce information otherwise not obtainable by viewing the sensor outputs separately. In this article, we propose the application of finite mixtures of multidimensional asymmetric generalized Gaussian distributions for different challenging tasks involving IR images. The advantage of the considered model is that it has the required flexibility to fit different shapes of observed non-Gaussian and asymmetric data. In particular, we present a highly efficient expectation–maximization (EM) algorithm, based on minimum message length (MML) formulation, for the unsupervised learning of the proposed model’s parameters. In addition, we study its performance in two interesting applications namely pedestrian detection and multiple target tracking. Furthermore, we examine whether fusion of visual and thermal images can increase the overall performance of surveillance systems.     

动态场景的自适应高斯混合模型的研究

混合高斯模型能够拟合像素颜色值分布、跟踪复杂的场景变化,基于它的算法已经成为对视频序列实施背景减法时的一个标准背景建模方法。分析了GMM算法的理论框架,提出了算法改进的两个方面：模型参数更新和BG/FG分类决策。在综述各种已有的算法的基础上,从学习因子控制、模态个数调节、算法评价以及算法初始化等几个方面展开分析。这些分析结果将为后续研究提供思路和方向。     

自适应混合高斯背景模型的改进

对自适应混合高斯背景模型进行了改进，将背景重构和前景消融时间控制机制整合到传统自适应混合高斯背景模型中，以提高运动分割的质量。背景重构算法从含有运动物体的动态场景视频序列中重构静态背景图像，然后用重构的静态背景图像初始化自适应混合高斯背景模型；而前景消融时间控制机制则使运动物体停止时的前景消融时间独立于背景模型的学习速率，从而可以根据需要调节前景消融的持续时间。实验结果表明了算法的有效性。     

基于帧差分块的混合高斯背景模型

针对混合高斯背景模型计算量过大、对复杂场景的适应能力较差等问题,提出了一种基于帧差分块和自适应学习率的混合高斯背景模型改进算法。引入分块模型思想,有效结合了像素的空域信息;根据帧间差分结果,判断可疑前景区域和背景区域,提高了检测灵敏度;针对前景可疑区域采用复杂模型,保证运动目标检测的精度,反之采用简单模型降低计算量;通过自适应学习率,加速背景的形成与消退。实验结果证明该算法较好地兼顾了检测精度和计算代价。     

A multi-manifold semi-supervised Gaussian mixture model for pattern classification

Semi-supervised Gaussian mixture model (SGMM) has been successfully applied to a wide range of engineering and scientific fields, including text classification, image retrieval, and biometric identification. Recently, many studies have shown that naturally occurring data may reside on or near manifold structures in ambient space. In this paper, we study the use of SGMM for data sets containing multiple separated or intersecting manifold structures. We propose a new multi-manifold regularized, semi-supervised Gaussian mixture model (M2SGMM) for classifying multiple manifolds. Specifically, we model the data manifold using a similarity graph with local and geometrical consistency properties. The geometrical similarity is measured by a novel application of local tangent space. We regularize the model parameters of the SGMM by incorporating the enhanced Laplacian of the graph. Experiments demonstrate the effectiveness of the proposed approach.     

融合密度峰值的高斯混合模型聚类算法

针对高斯混合模型（GMM）聚类算法对初始值敏感且容易陷入局部极小值的问题,利用密度峰值（DP）算法全局搜索能力强的优势,对GMM算法的初始聚类中心进行优化,提出了一种融合DP的GMM聚类算法（DP-GMMC）。首先,基于DP算法寻找聚类中心,得到混合模型的初始参数;其次,采用最大期望（EM）算法迭代估计混合模型的参数;最后,根据贝叶斯后验概率准则实现数据点的聚类。在Iris数据集下,DP-GMMC聚类准确率可达到96.67%,与传统GMM算法相比提高了33.6个百分点,解决了对初始聚类中心依赖的问题。实验结果表明,DP-GMMC对低维数据集有较好的聚类效果。     

基于高斯混合模型和AdaBoost的夜间车辆检测

针对夜间车辆检测精度相对不高的问题,提出通过构建车头灯对空间几何关系的高斯混合模型（GMM）和采用逆投影车辆样本的AdaBoost分类器准确检测夜间车辆的方法。首先,在交通场景中根据车头灯对的空间位置关系设置逆投影面,通过图像预处理粗定位车灯区域;其次,在逆投影图像下利用车头灯对的空间几何关系构建车灯对的高斯混合模型,初步匹配车头灯对;最后,采用逆投影车辆样本,利用AdaBoost分类器进一步准确检测车辆。实验在3个交通场景的检测结果表明,与原始图像下的AdaBoost方法相比,所提方法的检测率提高了1.93%,漏检率降低了17.83%,误检率降低了27.61%;与D-S （Dempster-Shafer）证据理论方法相比,检测率提高了2.03%,漏检率降低了7.58%,误检率降低了47.51%。所提方法提高了相对检测精度,减少了地面反光和影子等的干扰,满足交通场景中夜间车辆检测的可靠性和准确性的要求。     

混合高斯模型的自适应前景提取

复杂场景下的运动前景提取是计算机视觉研究领域的研究重点。为解决复杂场景中的前景目标提取问题,本文提出一种应用于复杂变化场景中的基于混合高斯模型的自适应前景提取方法。本方法可以对视频帧中每个像素的高斯分布数进行动态控制,并且通过在线EM算法对高斯分布的各参数进行学习,此外每个像素的权值更新速率可根据策略进行调整。实验结果表明本方法对复杂变化场景具有较好的适应性,可有效、快速地提取前景目标,提取结果具有较好的查准率和查全率。