Color-texture segmentation using JSEG based on Gaussian mixture modeling

An improved approach for J-value segmentation （JSEG） is presented for unsupervised color image segmentation. Instead of color quantization algorithm, an automatic classification method based on adaptive mean shift （AMS） based clustering is used for nonparametric clustering of image data set. The clustering results are used to construct Gaussian mixture modelling （GMM） of image data for the calculation of soft J value. The region growing algorithm used in JSEG is then applied in segmenting the image based on the multiscale soft J-images. Experiments show that the synergism of JSEG and the soft classification based on AMS based clustering and GMM overcomes the limitations of JSEG successfully and is more robust.

Research on Initialization on EM Algorithm Based on Gaussian Mixture Model

The EM algorithm is a very popular maximum likelihood estimation method, the iterative algorithm for solving the maximum likelihood estimator when the observation data is the incomplete data, but also is very effective algorithm to estimate the finite mixture model parameters. However, EM algorithm can not guarantee to find the global optimal solution, and often easy to fall into local optimal solution, so it is sensitive to the determination of initial value to iteration. Traditional EM algorithm select the initial value at random, we propose an improved method of selection of initial value. First, we use the k-nearest-neighbor method to delete outliers. Second, use the k-means to initialize the EM algorithm. Compare this method with the original random initial value method, numerical experiments show that the parameter estimation effect of the initialization of the EM algorithm is significantly better than the effect of the original EM algorithm.

A multi-target tracking algorithm based on Gaussian mixture model

Since the joint probabilistic data association(JPDA)algorithm results in calculation explosion with the increasing number of targets,a multi-target tracking algorithm based on Gaussian mixture model(GMM)clustering is proposed.The algorithm is used to cluster the measurements,and the association matrix between measurements and tracks is constructed by the posterior probability.Compared with the traditional data association algorithm,this algorithm has better tracking performance and less computational complexity.Simulation results demonstrate the effectiveness of the proposed algorithm.

An Improved Moving Object Detection Algorithm Based on Gaussian Mixture Models

Aiming at the problems that the classical Gaussian mixture model is unable to detect the complete moving object, and is sensitive to the light mutation scenes and so on, an improved algorithm is proposed for moving object detection based on Gaussian mixture model and three-frame difference method. In the process of extracting the moving region, the improved three-frame difference method uses the dynamic segmentation threshold and edge detection technology, and it is first used to solve the problems such as the illumination mutation and the discontinuity of the target edge. Then, a new adaptive selection strategy of the number of Gaussian distributions is introduced to reduce the processing time and improve accuracy of detection. Finally, HSV color space is used to remove shadow regions, and the whole moving object is detected. Experimental results show that the proposed algorithm can detect moving objects in various situations effectively.

Adaptive learning algorithm based on mixture Gaussian background

The key problem of the adaptive mixture background model is that the parameters can adaptively change according to the input data. To address the problem, a new method is proposed. Firstly, the recursive equations are inferred based on the maximum likelihood rule. Secondly, the forgetting factor and learning rate factor are redefined, and their still more general formulations are obtained by analyzing their practical functions. Lastly, the convergence of the proposed algorithm is proved to enable the estimation converge to a local maximum of the data likelihood function according to the stochastic approximation theory. The experiments show that the proposed learning algorithm excels the formers both in converging rate and accuracy.

An unsupervised clustering method for nuclear magnetic resonance transverse relaxation spectrums based on the Gaussian mixture model and its application

To make the quantitative results of nuclear magnetic resonance(NMR) transverse relaxation(T;) spectrums reflect the type and pore structure of reservoir more directly, an unsupervised clustering method was developed to obtain the quantitative pore structure information from the NMR T;spectrums based on the Gaussian mixture model(GMM). Firstly, We conducted the principal component analysis on T;spectrums in order to reduce the dimension data and the dependence of the original variables. Secondly, the dimension-reduced data was fitted using the GMM probability density function, and the model parameters and optimal clustering numbers were obtained according to the expectation-maximization algorithm and the change of the Akaike information criterion. Finally, the T;spectrum features and pore structure types of different clustering groups were analyzed and compared with T;geometric mean and T;arithmetic mean. The effectiveness of the algorithm has been verified by numerical simulation and field NMR logging data. The research shows that the clustering results based on GMM method have good correlations with the shape and distribution of the T;spectrum, pore structure, and petroleum productivity, providing a new means for quantitative identification of pore structure, reservoir grading, and oil and gas productivity evaluation.

An efficient approach for shadow detection based on Gaussian mixture model

An efficient approach was proposed for discriminating shadows from moving objects. In the background subtraction stage, moving objects were extracted. Then, the initial classification for moving shadow pixels and foreground object pixels was performed by using color invariant features. In the shadow model learning stage, instead of a single Gaussian distribution, it was assumed that the density function computed on the values of chromaticity difference or bright difference, can be modeled as a mixture of Gaussian consisting of two density functions. Meanwhile, the Gaussian parameter estimation was performed by using EM algorithm. The estimates were used to obtain shadow mask according to two constraints. Finally, experiments were carried out. The visual experiment results confirm the effectiveness of proposed method. Quantitative results in terms of the shadow detection rate and the shadow discrimination rate(the maximum values are 85.79% and 97.56%, respectively) show that the proposed approach achieves a satisfying result with post-processing step.

Predicting Precipitation Events Using Gaussian Mixture Model

In this paper, a Gaussian mixture model (GMM) based classifier is described to tell whether precipitation events will happen on a certain day at a certain time from historical meteorological data. The classifier deals with a two-class classification problem where one class represents precipitation events and the other represents non-precipitation events. The concept of ambiguity is introduced to represent cases where weather conditions between the two classes like drizzles, intermittent or overcast are more likely to happen. Six groups of experiments are carried out to evaluate the performance of the classifier using different configurations based on the observation data released by Shanghai Baoshan weather station. Specifically, a typical classification performance of about 75% accuracy, 30% precision and 80% recall is achieved for prediction tasks with a time span of 12 hours.

基于遗传算法的K-means初始化EM算法及聚类应用

混合高斯模型能够有效地拟合概率密度函数,常用的混合高斯概率密度模型参数估计方法是EM迭代算法,这种算法的缺点是估计精度过分依赖于初始值,而且不能估计模型阶数。基于遗传算法的K-means初始化EM算法可以同时估计模型阶数和参数。试验结果表明,该算法具有更好的聚类效果。

基于K-Means和高斯混合模型的云肩色彩提取方法对比

为获取传统服饰图像的色彩构成情况,选取极具特色的服饰品云肩,对比K-means和高斯混合模型的色彩提取效果。对云肩原始图像的R,B,G通道进行降噪预处理;将图像BGR色彩空间转换至RGB与HSV空间,采用肘部法确定最佳类簇数目k值;分别借助两种算法对图像进行分割与主色彩聚类,从执行效率、分割效果和提取精准度3方面进行对比,确定适合云肩图像的色彩提取方法。实验结果表明:相比高斯混合模型,K-means算法对云肩图像色彩的聚类提取效果更优。

Splitting of Gaussian Models via Adapted BML Method Pertaining to Cry-Based Diagnostic System

In this paper,we make use of the boosting method to introduce a new learning algorithm for Gaussian Mixture Models (GMMs) called adapted Boosted Mixture Learning (BML). The method possesses the ability to rectify the existing problems in other conventional techniques for estimating the GMM parameters, due in part to a new mixing-up strategy to increase the number of Gaussian components. The discriminative splitting idea is employed for Gaussian mixture densities followed by learning via the introduced method. Then, the GMM classifier was applied to distinguish between healthy infants and those that present a selected set of medical conditions. Each group includes both full-term and premature infants. Cry-pattern for each pathological condition is created by using the adapted BML method and 13-dimensional Mel-Frequency Cepstral Coefficients (MFCCs) feature vector. The test results demonstrate that the introduced method for training GMMs has a better performance than the traditional method based upon random splitting and EM-based re-estimation as a reference system in multi-pathological classification task.

基于改进INFO-CNN-QRGRU模型的农村分布式光伏发电短期概率预测

随着“双碳”目标的推进,清洁能源所占比重大幅度增加,分布式光伏发电在我国农村地区快速发展,但其随机性、间歇性的特点给新能源消纳和电网稳定带来很大的挑战。光伏发电预测可以在一定程度上改善新能源消纳问题,减少光伏发电的不稳定性对电网的冲击。因此,为提高光伏发电功率预测精度,提出一种基于改进向量加权平均算法优化CNN-QRGRU网络的光伏发电概率预测方法。首先采用ReliefF算法对特征变量进行选择,在此基础上利用高斯混合模型(Gaussian mixture model,GMM)聚类方法将天气分为晴天、晴转多云和阴雨天3种类型,将处理好的数据输入到CNN-GRU模型中,并利用向量加权平均(weighted mean of vectors algorithm,INFO)优化算法对模型超参数进行调参,将分位数回归模型(quantile regression,QR)与INFO-CNN-GRU模型相结合得到光伏功率条件分布,结合核密度估计法从条件分布中获得概率密度函数,完成概率预测。以实际光伏电站数据作为基础,将提出的INFO优化算法与其他几种传统的优化算法进行对比,结果表明INFO的优化效果更好,在此基础上进行概率预测,得到的概率预测结果相较于点预测能提供更多有效信息,更具有应用价值。

基于FPGA的两阶段配电网拓扑实时辨识算法

对配电网拓扑进行准确的实时辨识是电力系统安全稳定运行的基础,但随着新能源的接入以及配电网规模不断增大,配电网拓扑结构的动态变化愈加频繁且难以辨识。然而,现有配电网拓扑辨识算法所使用的历史数据需要人工对其进行拓扑标注,且拓扑辨识时间长,难以实现配电网拓扑实时辨识。因此,文中提出了一种基于现场可编程逻辑门阵列(FPAG)的两阶段配电网拓扑结构实时辨识算法。该算法不需要预先给出配电网拓扑类别的数量,即可对已有历史数据进行相应的拓扑标注及分类,并且基于FPGA实现了对配电网拓扑的实时辨别。该算法分为2个阶段:第1阶段采用变分贝叶斯高斯混合模型,对已有历史数据进行相应的拓扑标注及分类;第2阶段采用麻雀搜索算法,使得支持向量机快速收敛得到最优参数,以实现对配电网拓扑结构的精准辨识。基于该算法,利用FPGA并行架构以及高速高密度特性建立了实时拓扑结构辨识平台。最后,通过算例分析验证了所提辨识方法的有效性和优越性。

基于实时图像处理算法的交通信号主动智能优化方法研究

为了提升城市交通的通勤效率,文中基于图像处理技术对交通信号灯的智能优化方案进行了研究。该方案引入了一种基于混合高斯模型的运动目标检测方法,可有效从道路背景中分离车辆的前景信息。并采用虚拟线圈法进行车辆统计,在识别出交叉路口的车道信息后按照不同车道分别统计车辆数量。同时还设计了一个以平均排队时长、排队长度和停车次数为优化目标的多目标约束规划模型,并通过粒子群算法完成了模型的求解。仿真结果表明,所提技术方案可适应不同交通流量交叉路口的车辆统计,且精度能够达到95.4%。相较于现有的Webster方案,文中信号灯优化方案的平均延误时间、平均停车次数与平均等待长度分别下降了2.76%、8.35%及12.44%。

分布式光伏接入的配电网规划综合评价方法

为充分考虑分布式光伏接入对配电网规划评价的影响,基于传统配电网的规划评价体系,提出一种计及光伏输出功率随机性和相关性的有源配电网规划评价方法。首先,为精准刻画光伏出力的随机性与波动性,提出基于改进最优粒子群算法的高斯混合模型,计算多个光伏出力的联合概率密度函数;然后,将潮流方程线性化,推导节点电压和线路潮流线性表达式,分别获取多节点电压和多线路潮流的联合概率分布,并基于此构建考虑光伏接入后的配电网可靠性指标和电压质量指标等。最后,将新构建的电压越限风险指标、电压偏差指标以及潮流断面越限风险指标等新型电网规划评价指标纳入评估体系中,采用层次分析法计算得到组合权重并组合得到最终综合评价结果。仿真结果验证了该评价方法的有效性。

基于GMM和GA-LSTM的稀土熔盐电解过程原料含量状态识别模型

在高温高风险的稀土熔盐电解工艺中,为了实现稀土熔盐电解过程原料含量状态的智能识别,提出了一种基于混合高斯背景建模(GMM)和遗传算法优化的长短期记忆神经网络(GA-LSTM)的分类模型。模型通过GMM算法、R通道自适应滤波和中值滤波准确提取图像的火焰前景和特征,以量化熔盐电解反应的剧烈程度,进而判断稀土熔盐电解处于原料含量过多或含量正常状态;然后利用GA-LSTM神经网络建立熔盐表面火焰特征和稀土熔盐电解过程原料含量状态的非线性映射关系。结果表明:模型的识别精度高达99.79%,具有较好的泛化性,为实现稀土熔盐电解工艺自动化提供了一定的参考价值。

基于高斯混合模型及EM算法的建筑工程数据预警治理方法

结合初期雨水调蓄大直径顶管工程的实际设计及施工经验,对软弱地层条件下长距离大直径平行双管曲线顶管在设计及施工过程中存在的重点难点问题进行总结,并对顶管过程中的顶力及管周摩阻力做了深入分析研究,有针对性地提出了相应的解决方案,使该顶管工程顺利贯通。建筑工程行业在现代社会中发挥着重要的经济和社会作用,然而,它也伴随着诸多风险和不确定性。为了有效地管理和预测这些风险,本文提出了一种基于高斯混合模型(GMM)和期望最大化(EM)算法的数据预警治理方法。该方法旨在通过对建筑工程数据的建模和分析,提前识别潜在的问题和风险,从而改善工程项目的管理和决策。

基于道路扫描点云数据的城市道路标线提取

提出了一种基于车载激光扫描点云的道路标线提取方法。该方法实现道路标线提取的流程为:首先,为尽可能减少无用点云数据对道路标线提取的影响,使用布料模拟滤波(Cloth Simulation Filter,CSF)算法提取地面点,滤除非地面点,并利用基于法向量的区域生长算法提取得到路面点;其次,将路面点投影为强度特征图,根据标线几何特征提取标线边缘;最后,根据道路标线边缘信息实现标线候选点提取,并利用高斯混合模型(Gaussian Mixture Model,GMM)将噪声点剔除。使用两段道路点云数据对本文方法进行验证,结果表明本文方法提取道路标线点结果的精度指标均优于对比算法提取结果,能够提取较为完整的道路标线。

Semi-Supervised Classification based on Gaussian Mixture Model for remote imagery

Semi-Supervised Classification (SSC),which makes use of both labeled and unlabeled data to determine classification borders in feature space,has great advantages in extracting classification information from mass data.In this paper,a novel SSC method based on Gaussian Mixture Model (GMM) is proposed,in which each class’s feature space is described by one GMM.Experiments show the proposed method can achieve high classification accuracy with small amount of labeled data.However,for the same accuracy,supervised classification methods such as Support Vector Machine,Object Oriented Classification,etc.should be provided with much more labeled data.