Accuracy Assessment and Guidelines for Manual Traffic Counts from Pre-Recorded Video Data

Traffic count is the fundamental data source for transportation planning, management, design, and effectiveness evaluation. Recording traffic flow and counting from the recorded videos are increasingly used due to convenience, high accuracy, and cost-effectiveness. Manual counting from pre-recorded video footage can be prone to inconsistencies and errors, leading to inaccurate counts. Besides, there are no standard guidelines for collecting video data and conducting manual counts from the recorded videos. This paper aims to comprehensively assess the accuracy of manual counts from pre-recorded videos and introduces guidelines for efficiently collecting video data and conducting manual counts by trained individuals. The accuracy assessment of the manual counts was conducted based on repeated counts, and the guidelines were provided from the experience of conducting a traffic survey on forty strip mall access points in Baton Rouge, Louisiana, USA. The percentage of total error, classification error, and interval error were found to be 1.05 percent, 1.08 percent, and 1.29 percent, respectively. Besides, the percent root mean square errors (RMSE) were found to be 1.13 percent, 1.21 percent, and 1.48 percent, respectively. Guidelines were provided for selecting survey sites, instruments and timeframe, fieldwork, and manual counts for an efficient traffic data collection survey.

WT-FCTGN:A wavelet-enhanced fully connected time-gated neural network for complex noisy traffic flow modeling

Accurate forecasting of traffic flow provides a powerful traffic decision-making basis for an intelligent transportation system. However, the traffic data's complexity and fluctuation, as well as the noise produced during collecting information and summarizing original data of traffic flow, cause large errors in the traffic flow forecasting results. This article suggests a solution to the above mentioned issues and proposes a fully connected time-gated neural network based on wavelet reconstruction(WT-FCTGN). To eliminate the potential noise and strengthen the potential traffic trend in the data, we adopt the methods of wavelet reconstruction and periodic data introduction to preprocess the data. The model introduces fully connected time-series blocks to model all the information including time sequence information and fluctuation information in the flow of traffic, and establishes the time gate block to comprehend the periodic characteristics of the flow of traffic and predict its flow. The performance of the WT-FCTGN model is validated on the public Pe MS data set. The experimental results show that the WT-FCTGN model has higher accuracy, and its mean absolute error(MAE), mean absolute percentage error(MAPE) and root mean square error(RMSE) are obviously lower than those of the other algorithms. The robust experimental results prove that the WT-FCTGN model has good anti-noise ability.

Investigation of the factors affecting the consistency of short-period traffic counts

The main intent of this study is to investigate the accuracy of short-duration traffic counts conducted during winter months. The investigation is based on 11-year sample data collected using permanent traffic counters at various locations in Alberta, Canada. Four types of road sites： commuter, regional commuter, rural long-distance, and recreational sites are studied. The sample data consti- tute six different durations of counts （12-, 24-, 48-, 72-, 96-h, and 1 week） taken during summer and winter months. The coefficient of variation （CV） is used as the relative measure of deviation for counts of different dura- tions to measure the accuracy of short-period traffic counts. The study results indicate that 48-h count seems to be the most cost-effective counting interval during both summer and winter months. It is also found that the lowest values of CV result for counts taken at commuter sites, and the highest values are observed for recreational sites. Frequent changes in temperature and other weather events cause significant variation in traffic volume, which results in an increase in CV values for counts taken during winter months. The application of an adjustment factor to remove the effect of cold and snow from short-period counts is also included in this study. Introduced adjustment factors can reduce the values of CV for all counts taken during winter months. The findings of this study can lead highway agencies to improve the cost-effectiveness of their short- period traffic counting programs.

Conditional autoregressive negative binomial model for analysis of crash count using Bayesian methods

In order to improve crash occurrence models to account for the influence of various contributing factors, a conditional autoregressive negative binomial （CAR-NB） model is employed to allow for overdispersion （tackled by the NB component）, unobserved heterogeneity and spatial autocorrelation （captured by the CAR process）, using Markov chain Monte Carlo methods and the Gibbs sampler. Statistical tests suggest that the CAR-NB model is preferred over the CAR-Poisson, NB, zero-inflated Poisson, zero-inflated NB models, due to its lower prediction errors and more robust parameter inference. The study results show that crash frequency and fatalities are positively associated with the number of lanes, curve length, annual average daily traffic （AADT） per lane, as well as rainfall. Speed limit and the distances to the nearest hospitals have negative associations with segment-based crash counts but positive associations with fatality counts, presumably as a result of worsened collision impacts at higher speed and time loss during transporting crash victims.

交通场景中基于注意力机制神经网络的人群计数

人群计数是计算机视觉领域的重要任务。交通场景中的人群计数任务对于维护公众出行安全、实现交通智能化具有重要作用。公共交通场景中通常存在行人相互遮挡、背景复杂等现象,给人群计数带来了困难。为了实现高精度的人群计数,研究了基于注意力机制的人群密度估计网络。网络包含3个部分:特征提取模块通过生成多尺度的特征图,增强网络的特征表达能力,提高网络对行人大小变化的鲁棒性;注意力模块通过抑制背景噪声响应,强化人群特征响应,生成特征图中人群区域的概率分布,增强网络区分人群区域与背景区域的能力;密度估计模块在注意力机制的约束下指导网络回归高分辨率的人群密度图,提高网络对人群区域的敏感性。设计了基于背景感知的结构损失函数,能够降低模型的错误识别率,提高模型的计数准确率;采用多级监督机制指导网络进行学习,能够帮助梯度反向传播和减少过度拟合,进一步提高网络的人群计数精度。在公共数据集ShanghaiTech上进行了实验,实验结果表明:与目前最先进的算法相比,在ShanghaiTechA和ShanghaiTechB数据集上,平均绝对误差(mean absolute error,MAE)分别提高了2.4%和1.5%,均方误差(mean square error,MSE)分别提高了3.3%和0.9%,证明了提出的算法在人群拥挤和稀疏的场景中均有更好的准确性和鲁棒性。同时,在真实场景数据集上进行了实验,MAE=7.7,MSE=12.6,证明了提出的算法具有良好的实用性。

基于智能手机的城市道路车辆即时识别

为及时了解路段交通状况,使用计算机视觉方法对城市道路上行驶中的车辆进行即时检测并分类计数,以便更便捷地对某路段交通状况进行定性定量的评估。使用普通的智能手机对城市道路拍摄视频,采用一种以YOLOv3为基础的目标检测和跟踪方法,实现了对车辆的分类识别、跟踪与计数。在配置好的Python环境下,YOLOv3算法可以快速准确地进行车辆分类检测,随后利用Deep Sort跟踪算法对各类车辆进行分类计数,得到了每帧画面中的各类车辆的数量。统计通过该路段的1000多辆车的型号,结合已有的汽车质量数据,对不同种类汽车重量的统计结果分别进行分布拟合,得到了每种车辆的车身质量的代表值。将质量代表值代入到识别出的计数结果中,对这一交通要道任一时段的汽车荷载进行了分析。结果表明:得出的汽车质量代表值和汽车数量分布,可以估算出每帧路面的车辆均布荷载,得到各个高峰期车辆均布荷载的分布区间;将其与规范规定的均布荷载标准值进行对比,发现至少在95%的情况下车辆均布荷载不会超过规定的均布荷载标准值,大部分时间符合规范要求;但在交通拥堵的情况下,车辆均布荷载也会超过规定的均布荷载标准值。因此,使用智能手机随时随地采集视频可快速准确地对车辆进行分类识别,并统计该路段的负载情况,对交通流量限制措施具有指导作用。

Solving traffic data occlusion problems in computer vision algorithms using DeepSORT and quantum computing

Inaccuracies of traffic sensors during traffic counting and vehicle classification have persisted as transportation agencies have been prompted to calibrate sensors periodically.Detection of multiple objects,heavy occlusions,and similar appearances in congested places are some causes of computer vision model inaccuracies.This paper used the YOLOv5 model for detection and the DeepSORT model for tracking objects.Due to the nature of the reported problem caused by many misses and mismatches,the power of quantum computing with the alternating direction method of multipliers(ADMM)optimizer was leveraged.A basic Kalman filter and the Hungarian algorithm features were used in combination with a quantum optimizer to present robust multiple object tracking(MOT)algorithms.This hybrid combination of the classical and quantum model has fastened learning the occludes during frame matching of tracks and detections by generating minimum quantum cost function value.Comparisons with the existing models indicated a significant increase in the primary MOT metric multiple object tracking accuracy(MOTA)by 16%more than the regular YOLOv5-DeepSORT model when using a quantum optimizer.Also,a 6%multiple object tracking precision(MOTP)increases and a 6%identification metrics(F_(1))score increase were observed using the quantum optimizer with identity switching reduced from 6 to 4.This model is expected to assist transportation officials in improving the accuracy of traffic counts and vehicle classification and reduce the need for regular computer vision software calibration.

基于深度学习的交通流预测

为进一步完善建设智能交通、促进路网充分利用、缓解交通拥堵并减少CO_(2)排放进而加速实现“碳达峰”,设计并建立一套考虑数据预处理的路网交通流预测模型。模型使用3σ原则对交通流数据进行异常点检测,采用K-means方法对检测到的异常点进行填补,并建立长短时记忆网络对交通流进行预测。以真实案例为样本,采用长短时记忆网络对贵州省某区域路网的交通情况交通流进行预测仿真,实验表明该模型对于具有周期性的交通流预测精度能够达到87.78%。

基于HighD数据集的高速公路交通冲突预测方法

为改进高速公路交通冲突模型,基于High D数据集提取某路段交通冲突数据和交通流数据,依据TTC(time to collision,碰撞时间)的大小确定轻微冲突、一般冲突以及严重冲突的阈值。研究不同影响因素与冲突次数之间的关系,并对4种模型的效果进行比较,为冲突预测方法的研究提供思路。首先,针对不同严重程度的交通冲突数分别采用Poisson(泊松)模型、NB(Negative Binomial,负二项)模型、ZINB(Zero-inflated Negative Binomial,零膨胀负二项)模型及ZIP(Zero-inflated Poisson,零膨胀泊松)模型进行回归分析。其次,利用赤池信息量准则、贝叶斯信息准则对4种模型的拟合效果进行比较。结果表明:不同冲突次数预测模型中表现最佳的模型分别为NB模型、ZIP模型以及Poisson模型,3种模型中加速度标准差和平均速度都与冲突次数显著相关。

基于超声计数的智能交通灯控制系统

基于超声测距原理,以MSP430单片机为控制核心,设计了根据道路实时车流量来动态调节各路口通行时间的智能交通灯控制系统。通过相关算法将超声测距模块的输出回响信号转换成车辆信号,计算出某时刻车道在一段固定距离内的车辆数,并动态分配车道车辆的通行时间,从而提高了交通路口通行效率,有效缓解交通拥堵。系统引入手动遥控模块,可以应对严重交通堵塞。

基于交通安全的交叉口倒计时信号灯设置研究

交通信号倒计时装置被国内一些城市广泛采用。在体现交通“以人为本”原则的同时,倒计时装置的应用也应注意其带来了一些交通安全和通行效率上的问题。倒计时会诱发一部分驾驶员在绿灯末尾时加速通过路口,和红灯变绿灯下一相时头车提前高速到达冲突点,可能引发重特大交通事故,因而需要更长的绿灯间隔时间保证信号换相时的交通安全。由于绿灯间隔时间增长,交通信号倒计时装置降低了交叉口的通行能力,且不当的绿间隔设置还会造成严重的交通冲突。因而应谨慎采用机动车交通信号灯倒计时装置,并应辅以绿灯间隔时间调整、交通安全宣传教育和明确交通规则等措施。

基于路面标记的车辆检测和计数

交通监视系统通过采集实时交通流量数据 ,为智能化交通运输服务和控制管理提供依据 ,在智能交通系统中有着极其重要的作用。在基于视频图像的交通监视系统中 ,由路边建筑、树木等物体引起的静态阴影和由运动物体如车辆引起的运动阴影 ,是导致车辆检测错误的一大主要因素。提出了一种基于路面标记的自动车辆检测算法 ,用于检测车辆并排除阴影干扰 ,进而实现对过往车辆进行正确计数 ,能更可靠地收集各车道的实时车流信息。

交通检测点分布规则及其数学模型

针对估计ＯＤ出行分布矩阵需检测路段流量的问题，分析了检测点合理分布的４种规则，并在已知ＯＤ对间的有效出行路径的条件下，建立了相应的数学规划模型，同时也提出了有效的启发式算法．

基于MGCBF算法的长流信息统计

为提高流测量系统的运行效率,减小其所需存储资源,在分析网络中流长分布特性的基础上,提出一种新的用于测量长流数量并维护其流信息的算法———多粒度计数bloom filter(MGCBF).利用较少的固定存储空间,MGCBF可以在保持较小误差比例的情况下,对所有到达的流基于报文计数.在MGCBF算法的基础上以指定报文数为阈值建立了一个长流信息统计模型,并对该模型所需的存储空间、计算复杂度和计算误差进行了分析和讨论.通过将其分别应用于来自不同网络的TRACE:CERNET和CESCAI,验证了该算法在保证测量精度的同时可以大幅度减小维护流信息所需的系统资源.

基于交叉路口的动态OD反推模型与算法研究

交叉路口各进出口道之间的实时交通量是信号控制系统重要的输入数据 ,也是难以获得的数据。本文回顾了动态OD反推理论的发展历程 ,以交叉路口各进出口道检测到的路段流量时间序列为基础 ,分析了交叉路口实时交通量的特点 ,提出了基于交叉路口的改进参数优化模型 ,设计了遗传算法对问题进行求解 ,并讨论了算法中的六个关键问题。实例研究表明 ,模型和算法具有较高的效率和准确性 ,能够应用于在线系统。

基于长期监测数据的桥面板焊接细节疲劳寿命评估

基于润扬大桥结构健康监测系统,对钢桥面顶板-纵肋焊接细节附近的疲劳应变进行了长达两年的监测。采用Butterworth滤波以去除应变过程中的电磁干扰,然后通过简化雨流计数提取应变循环,并根据Palmgren-Miner准则和双线性概率S-N曲线对焊接细节进行了疲劳寿命评估。通过实测的环境温度、交通流量以及车辆荷载的疲劳等效,分析了车辆荷载和环境温度的变化对于桥面焊接细节疲劳损伤的影响。研究发现,环境温度对桥面焊接细节疲劳损伤存在着近似线性的影响。比较了润扬悬索桥与斜拉桥对应位置焊接细节的疲劳损伤分析结果,发现环境温度对于疲劳损伤的影响可能普遍存在于大跨缆索支承钢桥中。根据预测的车辆荷载增长模型以及拟合得到的温度、车辆荷载与疲劳损伤的关系,对焊接细节的疲劳寿命评估结果进行了修正。

基于进出口匝道流量的高速公路OD矩阵

分析了高速公路进出口匝道的交通流量特征及其与OD矩阵的关系,建立了高速公路进出口匝道交通量关系模型,生成了高速公路匝道系统的状态空间模型,分析了OD矩阵自身的特点,得到OD矩阵的约束关系,对常规的卡尔曼滤波方法进行了约束条件修正,从而形成了约束卡尔曼滤波递推方法。通过模拟数据的计算分析,约束卡尔曼滤波递推方法的性能与卡尔曼滤波递推方法相比有了很大的提高,能够较好地对高速公路上的时变OD矩阵进行跟踪,求解结果满足现代高速公路控制的需要。

基于机器视觉的地铁站客流自动检测方法

基于机器视觉的地铁站客流自动检测技术目前在检测精度和稳定性上距实际应用要求仍存在一定差距。针对这一问题,提出了一种适应于地铁站的客流自动检测新方法。该方法针对目前地铁站监控设备的普遍布设位置,研究了基于近景、非垂直视野的客流自动检测算法。该方法首先通过采集行人头部的Haar特征,利用由AdaBoost算法训练形成的强分类器进行人头检测,然后使用双线性插值算法,针对图像中的不同位置,以宁缺毋滥的原则,去除尺寸过大或过小的误检框。最后根据人头检测目标,设计行人的追踪统计算法。该算法由目标聚类、断帧合并和行人驶离3部分组成。试验结果显示,采用该方法进行地铁站内的客流自动检测可进行有效的方向区分,统计精度稳定在90%左右,基本满足实际的应用需求。

适于估计OD矩阵的交通检测点的最优分布

讨论了适于估计起迄点出行分布矩阵 ( OD矩阵 )的交通检测点的合理分布问题 .根据检测点应当满足的规则 ,建立了关于检测点分布的非线性规划模型 .在已知极点间转移概率的前提下 ,将检测点的分布问题描述成一个平均报酬 Markov决策过程 ,并通过转化为一个等价的整数线性规划问题来求解 .最后实例结果表明该模型是有效的。

基于车流量的交通信号灯实时控制的研究

道路交通信号灯控制与道路交通标志线的设置共同组成了对道路交通控制和管理的一个完整部分。交通信号灯控制在整个道路交通工程中起到了重要的作用,它主要应用于交通量较大、交通流冲突较多和复杂的交叉路口,以及某些道路路段上需要对交通流方向控制的地方。针对现有的交通信号灯控制中的一些缺陷,本文提出一种利用交通路口中车辆数量为引导因素,利用VC++编写信号灯实时控制程序,以达到对交通信号灯的实时控制。