Road scene analysis for determination of road traffic density

Road traffic density has always been a concern in large cities around the world, and many approaches were developed to assist in solving congestions related to slow traffic flow. This work proposes a congestion rate estimation approach that relies on real-time video scenes of road traffic, and was implemented and evaluated on eight different hotspots covering 33 different urban roads. The approach relies on road scene morphology for estimation of vehicles average speed along with measuring the overall video scenes randomness acting as a frame texture analysis indicator. Experimental results shows the feasibility of the proposed approach in reliably estimating traffic density and in providing an early warning to drivers on road conditions, thereby mitigating the negative effect of slow traffic flow on their daily lives.     

ECG beat classification using particle swarm optimization and support vector machine

In this paper, we propose a novel ECG arrhythmia classification method using power spectral-based features and support vector machine (SVM) classifier. The method extracts electrocardiogram’s spectral and three timing interval features. Non-parametric power spectral density (PSD) estimation methods are used to extract spectral features. The proposed approach optimizes the relevant parameters of SVM classifier through an intelligent algorithm using particle swarm optimization (PSO). These parameters are: Gaussian radial basis function (GRBF) kernel parameter σ and C penalty parameter of SVM classifier. ECG records from the MIT-BIH arrhythmia database are selected as test data. It is observed that the proposed power spectral-based hybrid particle swarm optimization-support vector machine (SVMPSO) classification method offers significantly improved performance over the SVM which has constant and manually extracted parameter.     

Vehicle collision risk estimation based on RGB-D camera for urban road

Traffic violation is the main cause of traffic accidents. To reduce the incidence of traffic accidents, the common practice at present is to strength the penalties for traffic violation. However, little attention has been paid to issue warning for dangerous driving behaviors, especially for the case where two vehicles have a good chance of collision. In this paper, a framework for collision risk estimation using RGB-D camera is proposed for vehicles running on the urban road, where the depth information is fused with the video information for accurate calculation of the position and speed of the vehicles, two essential parameters for motion trajectory estimation. Considering that the motion trajectory or its differences can be considered as a steady signal, a method based on autoregressive integrated moving average (ARIMA) models is presented to predict vehicle trajectory. Then, the collision risk is estimated based on the predicted trajectory. The experiments are carried out on the data from the real vehicles. The result shows that the accuracy of position and speed estimation can be guaranteed within urban road and the error of trajectory prediction is very minor which is unlikely to have a significant impact on calculating the probability of collision in most situations, so the proposed framework is effective in collision risk estimation.     

一种交通拥堵自动检测方法

目前,高速公路交通拥堵日趋频繁,然而大部分高速公路的管理方式仍然是通过人工查看轮巡监控视频来发现交通拥堵,效率低下。本文提出一种对高速公路轮巡监控视频自动检测交通拥堵的方法。该方法实时检测监控视频场景是否轮巡、切换、变动,自适应提取变动场景的道路边界结构并分类,然后在提取的道路边界结构范围内,计算宏观边缘占有率与加权平均光流速度两个宏观交通状态参数,并构造特征集,根据不同的道路边界类型选择对应支持向量机来实现对交通拥堵的自动检测和判别。实验结果表明,该方法能有效地对轮巡模式工作的高速公路监控视频检测交通拥堵,检测时间不大于30s,检测正确率达91.8%。     

基于Radon变换的视频测速算法

为了从视频监测图像中自动提取车辆行驶速度,提出了一种基于Radon变换的视频测速算法。根据车辆行驶轨迹的时空特点,利用道路交通标线为图像与道路建立距离映射关系,简化了现场标定的条件和过程;利用时间堆栈成像方法,建立了车辆行驶轨迹的时空关系;基于Radon变换的图像处理,实现了行驶车辆的视频测速技术。算法具有较好的鲁棒性,与传统方法相比,计算复杂性也要低很多。     

基于角点特征分析的车辆排队长度检测方法

针对交通堵塞造成的各种状况,通过视频分析实现实时高效的车辆排队长度检测,从而获取更多的交通信息改善交通状况.本文通过传统的FAST角点检测方法与运动检测的过程相结合得到改进后的FAST算法,使用改进后的FAST角点特征分析技术,不仅可以提取出当前交通道路上表征车辆存在的角点特征图,还可以获取角点位置的运动状态.通过对交通监控下的视频进行预处理后,单一车道内处于静态的角点特征形成车辆排队,并进行PCA处理得到一维向量,最后对一维向量进行形态学处理来检测单一车道内的车辆排队长度.实验表明,本方法检测精度平均98%,满足应用于实际场景.     

An automatic video content classification scheme based on combined visual features model with modified DAGSVM

Automatic video content classification attracts much attention from researchers in multimedia analysis because the management of video content is a challenging task. In this paper, a visual feature representation composed of editing, color, texture and motion features is proposed which is shown to be effective in differentiating among various video contents. A modified Directed Acyclic Graph Support Vector Machine (DAGSVM) model as the classifier is also presented. Experiments show that the features extracted have improved the discriminative ability between different video contents and the computational complexity has also been reduced. By introducing the DAG policy, the performance of the classifier has been enhanced and the classification results demonstrate the precision and effectiveness of this approach, compared with the other two classification methods. In addition, the proposed algorithm can be applied to video searching and harmful-video content filtering, etc.     

采用特征描述的H.264压缩视频运动分割

H.264视频压缩标准以其优良的压缩效率和编码灵活性得到了广泛的应用。提出了一种基于H.264压缩域的运动对象分割方法,首先从压缩视频中提取运动场,采用加权中值滤波方法滤除运动场的噪声矢量,再运用后向估计的方法重建预测运动场并进行运动场的累积,然后基于幅度、散度和旋度3个运动特征,采用改进的统计区域合并方法将运动对象分割出来。实验结果表明,该方法可有效地从H.264压缩视频中提取运动对象且分割质量较好。     

基于运动估计的视频隐写检测算法

提出一种基于运动估计的的视频隐写检测算法。通过块均方误差的变化研究信息嵌入对运动估计的影响,发现运动矢量对隐写具有敏感性,且分块越小,对隐写越敏感。反映视频时变特性的运动矢量场被作为隐写检测中视频数据的表征,特征提取过程中,先取定分块大小,使用最小均方误差块匹配运动估计算法,得到运动矢量场。再提取运动矢量场3个方向相邻元素的共生矩阵,使用共生矩阵的主对角线及其相邻元素作为特征。使用支持向量机分类器实施检测,实验结果表明文中算法与Budhia的算法相比,具有更好的检测性能。     

Creating robust high-throughput traffic sign detectors using centre-surround HOG statistics

In this paper, we detail a system for creating object detectors which meet the extreme demands of real-world traffic sign detection applications such as GPS map making and real-time in-car traffic sign detection. The resulting detectors are designed to detect and locate multiple traffic sign types in high-definition video (high throughput) from several cameras captured along thousands of kilometers of road with minimal false-positives and detection rates in excess of 99%. This allows for the accurate detection and location of traffic signs in geo-tagged video datasets of entire national road networks in reasonable time using only moderate computing infrastructure. A key to the success of the methods described in this paper is the use of extremely efficient classifier features. In this paper, we identify two obstacles to achieving the desired performance for all target traffic sign types, feature memory bandwidth requirements and feature discriminance. We introduce our use of centre-surround histogram of oriented gradient (HOG) statistics which greatly reduce the per-feature memory bandwidth requirements. Subsequently we extend our use of centre-surround HOG statistics to the color domain, raising the discriminant power of the final classifiers for more challenging sign types.     

基于三参数模型的快速全局运动估计

提出了一种新的全局运动估计方法——基于三参数模型的快速全局运动估计.新的参数模型在保证准确性的同时,使用更少的参数来描述和估计全局运动,从而简化了计算复杂度.此外,对光流场计算做出了两方面改进：（1）提出了宏块预判的方法,计算光流场前对宏块的梯度信息进行预分析,通过减少参与计算的宏块数目提高光流场的计算速度;（2）提出了快速估计宏块运动向量的方法,在块匹配的过程中同时考虑图像的梯度和灰度信息,通过引入更多的约束提高运动向量的计算速度.实验证明了该方法的有效性.     

基于DSP的实时图像处理系统

以DSP TMS320C6416为核0处理器，设计了一种通用的MPEG-4实时图象处理系统。文中对系统的硬件系统及软件设计进行了详细的介绍。其中视频采集、运动估计算法和软件的优化是保证本系统高效工作的关键部分．因此，本文对其进行了重点讨论．提出了相应的解决方法。实验表明，该系统可以满足当前的远程监控、电视电话、会议电视、道路交通管理等诸多视频／图象处理与传输领域应用的需求。     

基于视频信息的城市路段交通安全状态评估方法研究

城市道路交通安全状态实时评估是智能交系统的重要研究内容。针对现有交通安全状态实时评估方法的评估效果不理想的问题,建立了基于视频信息的城市路段交通安全状态评估方法。首先,分析了基于视频信息的交通流参数快速检测方法;然后,从车速离散度的角度提出了影响城市路段交通安全状态的路段车速离散度的概念;最后,建立了基于路段车速离散度的城市路段交通安全状态评估方法。实验表明,所提方法能够实时合理地对城市道路的安全状态水平进行评估,评估结果可以为交通管理部门制定有效的城市路段交通安全改进方案提供相应的依据。     

Fast SqueezeNet算法及在地铁人群密度估计上的应用

针对地铁视频监控一直缺乏一种有效的人群密度分类器的问题,提出了基于人群密度估计算法—Fast SqueezeNet的人群密度分类器,用于在地铁嵌入式计算平台有限的硬件资源限制下,实现对地铁车厢内人群的密度估计.该算法基于轻型卷积神经网络SqueezeNet,结合权值稀疏化和结构稀疏化方法,具有如下3点优势:1)以原始图像作为输入,并在处理的过程中自动提取纹理特征用于拥挤人群密度的估计;2)SqueezeNet经过权值稀疏化后,具有更少的模型参数,可以灵活的布置在安谋(ARM)等具有有限硬件资源的嵌入式平台上;3)结构稀疏化方法使得SqueezeNet具有更快的前向预测速度,提高其在地铁嵌入式平台上的图像处理效率.在3个人群密度数据集PETS_2009,Mall和ShangHai metro上,采用Fast SqueezeNet算法的三分类人群密度分类器,与基于卷积神经网络和单纯的权值稀疏化SqueezeNet网络的分类器进行对比实验研究,结果表明:在预测准确率、参数规模和运行时间3个维度上,基于Fast SqueezeNet的分类器均表现出了较好的性能,有效地克服了地铁车厢拥挤人群中存在的高密度、高耦合、透视变形等图像识别难题对估计结果的影响.最后,在ARM嵌入式平台上的实验表明基于Fast SqueezeNet的分类器可以在有限的硬件资源下,快速准确的得到预测结果,满足高速运行的地铁列车日常使用需求.     

基于AdaBoost分类器的实时交通事故预测

传统的道路交通事故预测是对交通事故次数及其造成的损失的历史趋势进行预测,针对其不能反映交通事故与实时交通特性关系、不能有效地预防事故发生的问题,提出一种基于AdaBoost分类器的交通事故实时预测的方法。首先,将交通道路划分为正常、危险两种交通状态,利用实时采集的交通流数据作为特征变量对不同的状态进行表征,将事故的实时预测问题转化为分类问题;然后,采用Parzen窗非参数估计的方法对两种状态在不同时间尺度下候选交通流特征的概率密度函数（PDF）进行估计,利用基于概率分布的可分性判据分析估计的密度函数,选择合适的特征变量及时间尺度,确定样本数据;最后,根据样本数据训练AdaBoost分类器对不同的交通状态进行分类识别。实验结果表明,采用交通流特性的标准差特征对测试样本分类的正确率比平均值特征高7.9%,更能反映不同交通状态的差别,获得更好的分类结果。     

视像中的摄像机运动检测

摄像机的运动信息是视像内容检索中的一种重要特征。文中介绍了两种基于全局运动的摄像机运动检测方案。首先提取视像中的运动特征作为原始数据,然后分别使用了迭代最小二乘法和支持向量机分类的方法进行摄像机运动的检测,通过对试验结果的对比,前一种方案可更有效地完成摄像机运动类型的判断。     

基于统计学理论的参数模型运动估计方法

运动估计对视频编码十分重要,基于参数模型的运动估计方法也越来越受到人们的关注,参数模型的选择是该方法的关键。基于此,提出了基于统计学原理的模型选择方法,它以少量的图像数据流为基础,通过参数估计,并分析各近似模型的预测风险和误差,选出最优模型,它最符合预测对象的实际发展变化规律,进而利用该模型对未知对象进行运动估计。试验结果表明,在对实际图像序列进行运动估计时,这种方法是可靠并且实用的。     

视频序列中运动参数估计方法研究*

运动参数估计是数字视频处理的一个核心问题。其任务是从视频序列中检测出运动信息,识别与跟踪运动目标和估计三维运动及结构参数。首先对传统的运动估计方法进行了全面介绍,然后重点研究基于小波变换的参数估计方法,并就各种方法的特点及应用范围进行了对比、分析与评价。