基于分裂EM算法的GMM参数估计

期望最大化(Expectation Maximization,EM)算法是一种求参数极大似然估计的迭代算法,常用来估计混合密度分布模型的参数。EM算法的主要问题是参数初始化依赖于先验知识且在迭代过程中容易收敛到局部极大值。提出一种新的基于分裂EM算法的GMM参数估计算法,该方法从一个确定的单高斯分布开始,在EM优化过程中逐渐分裂并估计混合分布的参数,解决了参数迭代收敛到局部极值问题。大量的实验表明,与现有的其他参数估计算法相比,算法具有较好的运算效率和估算准确性。     

未知杂波环境下的多目标跟踪算法

提出了一种未知杂波环境下的多目标跟踪算法. 该算法通过有限混合模型(Finite mixtrue model, FMM)建立多目标似然函数, 其中混合模型参数可通过期望极大化(Expectation maximum, EM)算法及模型合并与删除技术得到. 由估计的混合模型参数可进一步得到杂波模型估计、目标个数估计以及多目标状态估计. 类似基于随机有限集(Random finite set, RFS)的多目标跟踪算法, 该算法也可避免目标与测量的关联过程. 仿真实验表明, 当杂波分布未知并且较复杂时, 本文算法的估计效果要明显优于未进行杂波拟合时的多目标跟踪算法.     

基于极大似然准则和最大期望算法的自适应UKF 算法

针对噪声先验统计特性未知情况下的非线性系统状态估计问题,提出了基于极大似然准则和 最大期望算法的自适应无迹卡尔曼滤波(Unscented Kalman filter, UKF) 算法.利用极大似然准则构造含有噪声统计特性的对数似然函数,通 过最大期望算法将噪声估计问题转化为对数似然函数数学期望极大化问题,最终得到带次优递 推噪声统计估计器的自适应UKF算法.仿真分析表明,与传统UKF算法相比,提出的自适应UKF算法 有效克服了传统UKF算法在系统噪声统计特性未知情况下滤波精度下降的问题,并实现了系统噪 声统计特性的在线估计.     

核密度估计的聚类算法*

相似性度量是聚类分析的重要基础,如何有效衡量类属型符号间的相似性是相似性度量的一个难点.文中根据离散符号的核概率密度衡量符号间的相似性,与传统的简单符号匹配及符号频度估计方法不同,该相似性度量在核函数带宽的作用下,不再依赖同一属性上符号间独立性假设.随后建立类属型数据的贝叶斯聚类模型,定义基于似然的类属型对象-簇间相似性度量,给出基于模型的聚类算法.采用留一估计和最大似然估计,提出3种求解方法在聚类过程中动态确定最优的核带宽.实验表明,相比使用特征加权或简单匹配距离的聚类算法,文中算法可以获得更高的聚类精度,估计的核函数带宽在重要特征识别等应用中具有实际意义.     

结构先验约束下的实时多目标跟踪

多目标跟踪算法通常需要计算多帧、多目标间的数据关联,由于目标样本数量大,优化过程十分耗时,因此往往实际应用受限。提出一种实时的多目标跟踪算法,通过建立在线更新的结构先验模型约束目标间的空间位置关系,从而捕获多帧多目标间的数据相关性;在推理目标的空间置信度时,为克服传统方法使用稀疏采样造成样本不足引起目标状态估计不准确的问题,采用一种新的思路:提取目标及其周围区域作为正例样本,在计算过程中引入循环矩阵理论进行密集采样,并进一步通过对解进行傅里叶变换,实现对搜索窗口内所有样本似然的快速推理,从而为结构先验模型提供目标所有可能位置的置信度。实验结果表明了该算法在提高跟踪精度的同时显著降低了运算时间。     

EM算法研究与应用

引入了可处理缺失数据的EM算法.EM算法是一种迭代算法,每一次迭代都能保证似然函数值增加,并且收敛到一个局部极大值.对EM算法的基本原理和实施步骤进行了分析.算法的命名,是因为算法的每一迭代包括两步:第一步求期望(Expectation Step),称为E步;第二步求极大值(Maximization Step),称为M步.EM算法主要用来计算基于不完全数据的极大似然估计.在此基础上,把EM算法融合到状态空间模型的参数估计问题.给出了基于Kalman平滑和算法的线性状态空问模型参数估计方法.     

一种基于模糊自适应GA的广义S维分配算法

多传感器多目标跟踪系统进行目标状态估计的数据关联问题可以阐述为广义S维分配问题.本文提出了一种基于模糊自适应GA的广义S维分配算法.该算法利用六个模糊控制器对符号编码遗传算法的遗传操作进行自适应控制,并将S维分配问题中的目标代价函数极小化问题作为组合优化问题进行求解,同时结合极大似然方法进行目标识别和目标状态估计.在考虑虚警和漏检前提下,对算法进行了稀疏目标和密集目标两种仿真环境下的Monte Carlo试验,对试验结果进行了对比分析.     

一种基于SVM重采样的似然粒子滤波算法

针对弱观测噪声条件下非线性、非高斯动态系统的滤波问题,提出一种基于支持向量机的似然粒子滤波算法.首先,采用似然函数作为提议分布,融入最新的观测信息,比采用先验转移密度的一般粒子滤波算法更接近状态的真实后验密度;然后,利用当前粒子及其权值,使用支持向量机估计出状态的后验概率密度模型;最后,根据此模型重采样更新粒子集,有效地克服粒子退化现象并提高状态估计精度.仿真结果表明了所提出算法的可行性和有效性.     

动态模糊极大似然估计算法

在机器学习中,一个广泛的应用是对模型的参数进行估计,即极大似然估计(MLE),EM算法是根据点估计中的MLE改进的一种迭代算法,是求极大似然估计的一种强有力的工具,但它收敛速度较慢,于是引入α-EM算法,克服了EM算法的缺陷.由于学习的过程中可能存在着大量的缺失数据及其动态模糊性,给出基于不完全数据的动态模糊极大似然估计算法并给出实例验证.     

状态空间双线性系统的极大似然辨识

提出了状态空间双线性系统的极大似然辨识方法。得到了以输入-输出序列为条件概率的似然函数解析表达式,推导了极大化似然函数的参数矩阵计算公式,给出适用于双线性系统状态估计的改进卡尔曼滤波方法,以及辨识系统参数的迭代估计算法。最后进行了数值仿真,结果说明了该方法的有效性。     

Multi-object trajectory tracking

The majority of existing tracking algorithms are based on the maximum a posteriori solution of a probabilistic framework using a Hidden Markov Model, where the distribution of the object state at the current time instance is estimated based on current and previous observations. However, this approach is prone to errors caused by distractions such as occlusions, background clutters and multi-object confusions. In this paper, we propose a multiple object tracking algorithm that seeks the optimal state sequence that maximizes the joint multi-object state-observation probability. We call this algorithm trajectory tracking since it estimates the state sequence or “trajectory” instead of the current state. The algorithm is capable of tracking unknown time-varying number of multiple objects. We also introduce a novel observation model which is composed of the original image, the foreground mask given by background subtraction and the object detection map generated by an object detector. The image provides the object appearance information. The foreground mask enables the likelihood computation to consider the multi-object configuration in its entirety. The detection map consists of pixel-wise object detection scores, which drives the tracking algorithm to perform joint inference on both the number of objects and their configurations efficiently. The proposed algorithm has been implemented and tested extensively in a complete CCTV video surveillance system to monitor entries and detect tailgating and piggy-backing violations at access points for over six months. The system achieved 98.3% precision in event classification. The violation detection rate is 90.4% and the detection precision is 85.2%. The results clearly demonstrate the advantages of the proposed detection based trajectory tracking framework.     

自助重要性采样用于实时多目标视觉跟踪

多目标视觉跟踪的主要困难来自于多个目标交互(部分或完全遮挡)导致的歧义性. 马尔可夫随机场(Markov random field, MRF)可以消除这种歧义性且无需显式的数据关联. 但是, 通用概率推理算法的计算代价很高. 针对上述问题, 本文做出了3点贡献: 1)设计了新的具有"分散-集中-分散"结构的递归贝叶斯跟踪框架—自助重要性采样粒子滤波器, 它 使用融入当前时刻观测的重要性密度函数解决维数灾难问题, 将计算复杂度从指数增长变为线性增长; 2)提出了新的蒙特卡洛策略— 自助重要性采样, 利用MRF的因子分解性质进行重要性采样, 并使用自助法产生低成本高质量的样本、降低似然度计算次数和维持多模式分布; 3)采用了新的边缘化技术—使用辅助变量采样进行边缘化, 使用自助直方图对边缘后验分布进行密度估计. 实验结果表明, 本文提出的算法能够对大量目标进行实时跟踪, 能够处理目标间复杂的交互, 能够在目标消失后维持多模式分布.     

基于卡尔曼滤波的多目标跟踪方法

针对视频多目标跟踪中由于目标间的遮挡、交错或目标漂移而导致跟踪失败的情况,提出一种基于卡尔曼滤波以及空间颜色直方图的遮挡预测跟踪算法。利用空间颜色直方图对目标进行建模,可以对不同目标进行区分进而在目标之间出现交错或目标漂移时仍能跟踪到目标。通过卡尔曼滤波算法可以 预测 目标的状态,对预测位置之间存在交错的目标进行遮挡标记,以便在下一帧中仍然可以跟踪到被遮挡的目标。采用2D MOT 2015数据集进行实验,跟踪的平均精度达到了34.1%。实验结果表明,所提方法对多目标跟踪的效果有所提高。     

Categorization of Multiple Objects in a Scene Using a Biased Sampling Strategy

Recently, various bag-of-features (BoF) methods show their good resistance to within-class variations and occlusions in object categorization. In this paper, we present a novel approach for multi-object categorization within the BoF framework. The approach addresses two issues in BoF related methods simultaneously: how to avoid scene modeling and how to predict labels of an image when multiple categories of objects are co-existing. We employ a biased sampling strategy which combines the bottom-up, biologically inspired saliency information and loose, top-down class prior information for object class modeling. Then this biased sampling component is further integrated with a multi-instance multi-label leaning and classification algorithm. With the proposed biased sampling strategy, we can perform multi-object categorization within an image without semantic segmentation. The experimental results on PASCAL VOC2007 and SUN09 show that the proposed method significantly improves the discriminative ability of BoF methods and achieves good performance in multi-object categorization tasks.     

Simulated annealing using a reversible jump Markov chain Monte Carlo algorithm for fuzzy clustering

In this paper, an approach for automatically clustering a data set into a number of fuzzy partitions with a simulated annealing using a reversible jump Markov chain Monte Carlo algorithm is proposed. This is in contrast to the widely used fuzzy clustering scheme, the fuzzy c-means (FCM) algorithm, which requires the a priori knowledge of the number of clusters. The said approach performs the clustering by optimizing a cluster validity index, the Xie-Beni index. It makes use of the homogeneous reversible jump Markov chain Monte Carlo (RJMCMC) kernel as the proposal so that the algorithm is able to jump between different dimensions, i.e., number of clusters, until the correct value is obtained. Different moves, like birth, death, split, merge, and update, are used for sampling a candidate state given the current state. The effectiveness of the proposed technique in optimizing the Xie-Beni index and thereby determining the appropriate clustering is demonstrated for both artificial and real-life data sets. In a part of the investigation, the utility of the fuzzy clustering scheme for classifying pixels in an IRS satellite image of Kolkata is studied. A technique for reducing the computation efforts in the case of satellite image data is incorporated.     

Stochastic sampling algorithms for state estimation of jump Markovlinear systems

Jump Markov linear systems are linear systems whose parameters evolve with time according to a finite-state Markov chain. Given a set of observations, our aim is to estimate the states of the finite-state Markov chain and the continuous (in space) states of the linear system. The computational cost in computing conditional mean or maximum a posteriori (MAP) state estimates of the Markov chain or the state of the jump Markov linear system grows exponentially in the number of observations. We present three globally convergent algorithms based on stochastic sampling methods for state estimation of jump Markov linear systems. The cost per iteration is linear in the data length. The first proposed algorithm is a data augmentation (DA) scheme that yields conditional mean state estimates. The second proposed scheme is a stochastic annealing (SA) version of DA that computes the joint MAP sequence estimate of the finite and continuous states. Finally, a Metropolis-Hastings DA scheme based on SA is designed to yield the MAP estimate of the finite-state Markov chain. Convergence results of the three above-mentioned stochastic algorithms are obtained. Computer simulations are carried out to evaluate the performances of the proposed algorithms. The problem of estimating a sparse signal developing from a neutron sensor based on a set of noisy data from a neutron sensor and the problem of narrow-band interference suppression in spread spectrum code-division multiple-access (CDMA) systems are considered     

融合人群密度的自适应深度多目标跟踪算法

多目标跟踪技术不能较好地解决目标严重遮挡场景下的多目标跟踪问题,因此文中提出融合人群密度的自适应深度多目标跟踪算法.首先,融合人群密度图和目标检测结果,利用人群密度图的位置和计数信息修正检测器结果,消除漏检、误检.然后,使用自适应三元组损失改进行人重识别模型的损失函数,提高对重识别特征的辨别能力.最后,使用外观和运动信...     

Robust particle tracker via Markov Chain Monte Carlo posterior sampling

Particle Filter has grown to be a standard framework for visual tracking. This paper proposes a robust particle tracker based on Markov Chain Monte Carlo method, aiming at solving the thorny problems in visual tracking induced by object appearance changes, occlusions, background clutter, and abrupt motions. In this algorithm, we derive the posterior probability density function based on second order Markov assumption. The posterior probability density is the joint density of the previous two states. Additionally, a Markov Chain with certain length is used to approximate the posterior density to avoid the drawbacks of traditional importance sampling based algorithm, which consequently improves the searching ability of the proposed tracker. We compare our approach with several alternative tracking algorithms, and the experimental results demonstrate that our tracker is superior to others in dealing with various types of challenging scenarios.     

Tracking video objects with feature points based particle filtering

For intelligent video surveillance, the adaptive tracking of multiple moving objects is still an open issue. In this paper, a new multi-object tracking method based on video frames is proposed. A type of particle filtering combined with the SIFT (Scale Invariant Feature Transform) is proposed for motion tracking, where SIFT key points are treated as parts of particles to improve the sample distribution. Then, a queue chain method is adopted to record data associations among different objects, which could improve the detection accuracy and reduce the computational complexity. By actual road tests and comparisons, the system tracks multi-objects with better performance, e.g., real time implementation and robust against mutual occlusions, indicating that it is effective for intelligent video surveillance systems.     

基于帧内关系建模和自注意力融合的多目标跟踪方法

多目标跟踪在视频监控领域有重要的应用价值.随着卷积神经网络(convolutional neural networks,CNN),尤其是图神经网络(graph neural networks,GNN)的发展,多目标跟踪的研究现阶段取得了很大突破.其中,图神经网络由于引入目标-轨迹间的关系建模,显示出更稳定的跟踪性能.然而,已有的基于GNN的多目标跟踪方法都仅在连续两帧之间建立全局关系模型,忽视了帧内目标与周围其他目标的交互,没有考虑在帧内建立合适的局部关系模型.为了解决该问题,提出基于帧内关系建模和自注意力融合模型(INAF-GNN)的多目标跟踪方法.在帧内,INAF-GNN建立目标与邻居目标的关系图模型以获取局部跟踪特征;在帧间,INAF-GNN建立目标与轨迹关系图模型以获得全局跟踪特征,并利用注意力机制设计一个特征融合模块整合局部和全局跟踪特征.在MotChallenge行人标准数据集上进行大量的实验,与多个基于图神经网络的多目标跟踪方法相比较,结果显示,MOTA指标提高1.9%,IDF1指标提高3.6%.同时,在UA-DETRAC车辆数据集上的验证测试表明了所提出方法的有效性和泛化能力.