基于轨迹分析的行人异常行为识别

提出一种基于轨迹分段主题模型的异常行为检测方法。为了解决跟踪偏差引起的轨迹不连续问题,首先使用模糊聚类算法对所有的轨迹进行全局聚类,然后对每一类轨迹采用分段采样的方式对段内轨迹点使用主题模型LDA进行局部聚类;以最大概率的轨迹点作为视觉单词,每类轨迹表示成一系列视觉单词的集合,在此基础上建立局部隐马尔科夫模型HMM;最后通过轨迹匹配的方法进行异常轨迹识别。在CAVIAR数据库上的实验结果表明,该算法能识别多种异常行为,提高了异常行为检测的准确率。     

Recognition of pedestrian trajectories and attributes with computer vision and deep learning techniques

Analyzing the walking behavior of the public is vital for revealing the need for infrastructure design in a local neighborhood, supporting human-centric urban area development. Traditional walking behavior analysis practices relying on manual on-street surveys to collect pedestrian flow data are labor-intensive and tedious. On the contrary, automated video analytics using surveillance cameras based on computer vision and deep learning techniques appears more effective in generating pedestrian flow statistics. Nevertheless, most existing methods of pedestrian tracking and attribute recognition suffer from several challenging conditions, such as inter-person occlusion and appearance variations, which leads to ambiguous identities and hence inaccurate pedestrian flow statistics.Therefore, this paper proposes a more robust methodology of pedestrian tracking and attribute recognition, facilitating the analysis of pedestrian walking behavior. Specific limitations of a current state-of-the-art method are inferred, based on which several improvement strategies are proposed: 1) incorporating high-level pedestrian attributes to enhance pedestrian tracking, 2) a similarity measure integrating multiple cues for identity matching, and 3) a probation mechanism for more robust identity matching. From our evaluation using two public benchmark datasets, the developed strategies notably enhance the robustness of pedestrian tracking against the challenging conditions mentioned above. Subsequently, the outputs of trajectories and attributes are aggregated into fine-grained pedestrian flow statistics among different pedestrian groups. Overall, our developed framework can support a more comprehensive and reliable decision-making for human-centric planning and design in different urban areas. The framework is also applicable to exploiting pedestrian movement patterns in different scenes for analyses such as urban walkability evaluation. Moreover, the developed mechanisms are generalizable to future researches as a baseline, which provides generic insights of how to fundamentally enhance pedestrian tracking.     

行人惯性导航零速检测算法

在行人惯性导航中,零速检测是实现速度误差清零和导航误差估计的前提,有着重要的作用.针对行人运动过程中零速区间时间间隔短难以检测的问题,提出了一种基于人体脚部运动特征的零速检测算法,将步行运动抽象成了一个包含4个隐含状态与15个观测量的隐马尔可夫模型,并阐述了模型构建机理.利用Baum-Welch算法训练和优化模型参数,提高了检测准确率.实验结果表明:所提出的方法零速检测效果较好,且采用该方法的行人惯性导航系统,其定位误差约为行进距离的0.73％,定位精度较高.     

DPHK: real-time distributed predicted data collecting based on activity pattern knowledge mined from trajectories in smart environments

In this paper, we have proposed and designed DPHK (data prediction based on HMM according to activity pattern knowledge mined from trajectories), a real-time distributed predicted data collection system to solve the congestion and data loss caused by too many connections to sink node in indoor smart environment scenarios (like Smart Home, Smart Wireless Healthcare and so on). DPHK predicts and sends predicted data at one time instead of sending the triggered data of these sensor nodes which people is going to pass in several times. Firstly, our system learns the knowledge of transition probability among sensor nodes from the historical binary motion data through data mining. Secondly, it stores the corresponding knowledge in each sensor node based on a special storage mechanism. Thirdly, each sensor node applies HMM (hidden Markov model) algorithm to predict the sensor node locations people will arrive at according to the receivedmessage. At last, these sensor nodes send their triggered data and the predicted data to the sink node. The significances of DPHK are as follows: (a) the procedure of DPHK is distributed; (b) it effectively reduces the connection between sensor nodes and sink node. The time complexities of the proposed algorithms are analyzed and the performance is evaluated by some designed experiments in a smart environment.     

Unified HMM-based layout analysis framework and algorithm

To manipulate the layout analysis problem for complex or irregular document image, a Unified HMM-based Layout Analysis Framework is presented in this paper. Based on the multi-resolution wavelet analysis results of the document image, we use HMM method in both inner-scale image model and trans-scale context model to classify the pixel region properties, such as text, picture or background. In each scale, a HMM direct segmentation method is used to get better inner-scale classification result. Then another HMM method is used to fuse the inner-scale result in each scale and then get better final segmentation result. The optimized algorithm uses a stop rule in the coarse to fine multi-scale segmentation process, so the speed is improved remarkably. Experiments prove the efficiency of proposed algorithm.     

基于视觉注意模型和HMM的足球视频语义分析

HMM模型具有良好的适应性,可以自动学习,对预测随机时序数据性能良好。场景是足球视频的基本特征,场景的转换体现了足球视频的摄制、编辑模式,表现了足球视频的语义。提出了一种基于场景分析和HMM的视频语义分析框架,用于识别足球视频中的一些语义事件。为了克服以往基于主颜色和其他底层特征的视频场景分析中存在的较大误差,又提出基于视觉注意模型对足球视频中的场景进行分析。实验结果表明,基于场景分析和HMM的事件识别方法对足球视频中的任意球事件有良好的识别效果     

基于隐马尔可夫模型的运动目标轨迹识别 *

引入改进的隐马尔可夫模型算法,针对真实场景中运动目标轨迹的复杂程度对各个轨迹模式类建立相应的隐马尔可夫模型,利用训练样本训练模型得到可靠的模型参数;计算测试样本对于各个模型的最大似然概率,选取最大概率值对应的轨迹模式类作为轨迹识别的结果,对两种场景中聚类后的轨迹进行训练与识别。实验结果表明,平均识别率分别达到87.76 %和94. 19%。     

Continuous-time hidden Markov models for network performance evaluation

In this paper, we study the use of continuous-time hidden Markov models (CT-HMMs) for network protocol and application performance evaluation. We develop an algorithm to infer the CT-HMM from a series of end-to-end delay and loss observations of probe packets. This model can then be used to simulate network environments for network performance evaluation. We validate the simulation method through a series of experiments both in ns and over the Internet. Our experimental results show that this simulation method can represent a wide range of real network scenarios. It is easy to use, accurate and time efficient.     

A novel sequence representation for unsupervised analysis of human activities

Formalizing computational models for everyday human activities remains an open challenge. Many previous approaches towards this end assume prior knowledge about the structure of activities, using which explicitly defined models are learned in a completely supervised manner. For a majority of everyday environments however, the structure of the in situ activities is generally not known a priori. In this paper we investigate knowledge representations and manipulation techniques that facilitate learning of human activities in a minimally supervised manner. The key contribution of this work is the idea that global structural information of human activities can be encoded using a subset of their local event subsequences, and that this encoding is sufficient for activity-class discovery and classification.In particular, we investigate modeling activity sequences in terms of their constituent subsequences that we call event n-grams. Exploiting this representation, we propose a computational framework to automatically discover the various activity-classes taking place in an environment. We model these activity-classes as maximally similar activity-cliques in a completely connected graph of activities, and describe how to discover them efficiently. Moreover, we propose methods for finding characterizations of these discovered classes from a holistic as well as a by-parts perspective. Using such characterizations, we present a method to classify a new activity to one of the discovered activity-classes, and to automatically detect whether it is anomalous with respect to the general characteristics of its membership class. Our results show the efficacy of our approach in a variety of everyday environments.     

大数据环境下移动对象自适应轨迹预测模型

已有的轨迹预测算法针对移动对象运动模式,使用数学模型进行交通流模拟,难以对路网中的移动对象进行准确的描述.为了解决这一问题,提出基于隐马尔可夫模型(hidden Markov model,简称HMM)的自适应轨迹预测模型SATP(self-adaptive trajectory prediction model based on HMM),对大数据环境下移动对象海量轨迹利用基于密度的聚类方法进行位置密度分区和高效分段处理,减少HMM的状态数量.根据输入轨迹自动选取参数组合,避免HMM模型中隐状态不连续、状态停留等问题.实验结果表明,SATP模型在实验中表现出较高的预测准确性,并维持较低的时间开销.针对速度随机改变的移动对象,其平均预测准确率为84.1%;相同情况下,平均高出朴素预测算法46.7%.     

Simulation-based sequential analysis of Markov switching stochastic volatility models

We propose a simulation-based algorithm for inference in stochastic volatility models with possible regime switching in which the regime state is governed by a first-order Markov process. Using auxiliary particle filters we developed a strategy to sequentially learn about states and parameters of the model. The methodology is tested against a synthetic time series and validated with a real financial time series: the IBOVESPA stock index (São Paulo Stock Exchange).     

面向新闻视频内容分析的音频分层分类算法*

提出了一种规则和隐马尔可夫模型相结合的音频分层分类算法,首先利用规则将新闻节目中的音频分为静音、语音和音乐三类,然后采用隐马尔可夫模型进一步将语音和音乐细分为男主持人语音、女主持人语音、交替报道、独白语音、现场语音和音乐六类。实验结果表明,男主持人语音、女主持人语音以及音乐的分类效果最好,查准率和查全率均可达90％以上;交替报道的分类性能最差,查准率为57.5％,查全率为79.3％;其他类别的分类性能居中,在70%～90％左右。与同类算法相比,该算法分类性能较高。     

HMM改进Ad hoc网络延时的模型及抗毁性研究

为了更高效地处理无线移动自组织(Ad hoc)网络中的延时问题,采用了隐马尔科夫模型(HMM)进行移动方位的评估.HMM求解实现了Ad网络3个基本问题的求解,设计了移动节点观察的模型,MATLAB仿真表明参数值完全正确,符合观察要求.对模型进行抗毁性试验,网络的连通度较好,表明了抗毁性较强;节点最多发生在公共区域,表明网络连通性比较强.这一研究对于Ad hoc网络实际应用的拓展具有一定的价值.     

电动自行车轨迹简化与自适应地图匹配算法

近年来, 随着全球定位系统(global positioning system, GPS)的大范围应用, 越来越多的电动自行车装配了GPS传感器, 由此产生的海量轨迹数据是深入了解用户出行规律、为城市规划者提供科学决策支持等诸多应用的重要基础. 但是, 电动自行车上普遍使用的价格低廉的GPS传感器无法提供高精度的定位, 同时, 电动自行车轨迹地图匹配过程因以下原因更具有挑战性: (1)存在大量停留点; (2)高采样频率导致相邻轨迹点的距离较短; (3)电动自行车可行驶的路段更多, 存在大量无效轨迹. 针对上述问题, 提出一种可自适应路网精度的电动自行车轨迹地图匹配方法KFTS-AMM. 该方法融合基于分段卡尔曼滤波算法的轨迹简化算法(KFTS), 和分段隐马尔可夫模型的地图匹配算法(AMM). 首先, 利用卡尔曼滤波算法可用于最优状态估计的特性, KFTS能够在轨迹简化过程中对轨迹点进行自动修正, 使轨迹曲线变得平滑并减少了异常点对于地图匹配准确率的影响. 同时, 使用基于分段隐马尔可夫模型的地图匹配算法AMM, 避免部分无效轨迹对整条轨迹匹配的影响. 此外, 在轨迹数据的处理过程加入了停留点的识别与合并, 进一步提升匹配准确率. 在郑州市真实电动自行车轨迹数据的实验结果表明, KFTS-AMM在准确率上相对于已有的对比算法有较大的提升, 并可通过使用简化后的轨迹数据显著提升匹配速度.     

Semantic segmentation and colorization of grayscale aerial imagery with W-Net models

The semantic segmentation of remotely sensed aerial imagery is nowadays an extensively explored task, concerned with determining, for each pixel in an input image, the most likely class label from a finite set of possible labels. Most previous work in the area has addressed the analysis of high-resolution modern images, although the semantic segmentation of historical grayscale aerial photos can also have important applications. Examples include supporting the development of historical road maps, or the development of dasymetric disaggregation approaches leveraging historical building footprints. Following recent work in the area related to the use of fully-convolutional neural networks for semantic segmentation, and specifically envisioning the segmentation of grayscale aerial imagery, we evaluated the performance of an adapted version of the W-Net architecture, which has achieved very good results on other types of image segmentation tasks. Our W-Net model is trained to simultaneously segment images and reconstruct, or predict, the colour of the input images from intermediate representations. Through experiments with distinct data sets frequently used in previous studies, we show that the proposed W-Net architecture is quite effective in colouring and segmenting the input images. The proposed approach outperforms a baseline corresponding to the U-Net model for the segmentation of both coloured and grayscale imagery, and it also outperforms some of the other recently proposed approaches when considering coloured imagery.     

带记忆组合生成器的条件相关性

利用隐马尔可夫模型对带记忆组合生成器概率模型的相关性问题进行了研究,得到快速计算记忆状态条件概率的公式。讨论了上述计算公式在限定条件下的应用。在此基础上对改进的加法生成器进行了条件相关攻击,与其它攻击方法相比,条件相关攻击的计算复杂度和所需密钥流长度达到了折中。     

Hierarchical image segmentation using a correspondence with a tree model

A new general image segmentation system is presented, based on the calculation of a tree representation of the original image in which image regions are assigned to tree nodes, followed by a correspondence process with a model tree, which embeds the a priori knowledge about the images. For this correspondence, an original algorithm is proposed, which performs the minimization of an error function that quantifies the difference between the input image tree and the model tree. We also present a new algorithm for automatically calculating the model tree from a set of manually segmented images. Results on synthetic and MR brain images are presented.     

基于隐马尔可夫模型的股票价格预测组合模型

提出了一种用于股票价格预测的人工神经网络(ANN),隐马尔可夫模型(HMM)和粒子群优化算法(PSO)的组合模型-APHMM模型.在APHMM模型中,ANN算法将股票的每日开盘价、最高价、最低价与收盘价转换为相互独立的量并作为HMM的输入.然后,利用PSO算法对HMM的参数初始值进行优化,并用Baum-Welch算法进行参数训练.经过训练后的HMM在历史数据中找出一组与今天股票的上述4个指标模式最相似数据,加权平均计算每个数据与它后一天的收盘价格差,则今天的股票收盘价加上这个加权平均价格差便为预测的股票收盘价.实验结果表明,APHMM模型具有良好的预测性能.