基于多特征融合的视频交通数据采集方法

提出了一种基于多特征融合的视频交通数据采集方法, 核心思想是: 在图像中设置虚拟线圈, 假设车辆从虚拟线圈上驶过时引起像素变化, 通过识别这种像素变化来检测车辆并估计车速. 与现有技术相比, 本文的贡献在于: 1) 综合利用虚拟线圈内的前景面积、纹理变化、像素运动等特征来检测车辆, 提出了有效的多特征融合方法, 显著提高了车辆检测精度; 2) 根据单个虚拟线圈内的像素运动向量来估计车速, 避免了双线圈测速法的错误匹配问题. 算法测试结果表明本文算法能够在复杂多样的交通场景和天气条件下, 准确地检测车辆和估计车速. 在算法研究的基础上, 研制了一款嵌入式交通视频检测器, 在路口长期采集交通数据, 为交通信号控制和交通规律分析提供决策依据.     

车路协同环境下智能交叉口车速控制

传统信号控制交叉口通过相位禁行方式来解决交通冲突,导致交叉口时空资源利用率低,延误增加.为提高车路协同环境下的交叉口通行效率,本文提出了一种基于时空间隙动态分配的智能交叉口车速控制方法,对交叉口车辆通行时间进行归一处理,建立了车辆跟驰控制模型和冲突避碰模型,使车辆能够根据交叉口控制区域内的实时路况信息预先进行速度调整,达到不停车通过交叉口的最优安全速度.运用VISSIM和MATLAB联合搭建仿真运行环境,分别在600 pcu·h^-1, 1200 pcu·h^-1和1800 pcu·h^-1交通流量条件下,对智能控制和传统控制交叉口的控制效益进行评价对比,结果表明:该智能控制方法均能够有效缩短交叉口车辆延误,减少车辆油耗和各类污染物的排放,且交通流量越高,改善效果越明显.     

Hybrid model of clustering and kernel autoassociator for reliable vehicle type classification

Automatic vehicle classification is an important area of research for intelligent transportation, traffic surveillance and security. A working image-based vehicle classification system is proposed in this paper. The first component vehicle detection is implemented by applying histogram of oriented gradient features and SVM classifier. The second component vehicle classification, which is the emphasis of this paper, is accomplished by a hybrid model composed of clustering and kernel autoassociator (KAA). The KAA model is a generalization of auto-associative networks by training to recall the inputs through kernel subspace. As an effective one-class classification strategy, KAA has been proposed to implement classification with rejection, showing balanced error–rejection trade-off. With a large number of training samples, however, the training of KAA becomes problematic due to the difficulties involved with directly creating the kernel matrix. As a solution, a hybrid model consisting of self-organizing map (SOM) and KAM has been proposed to first acquire prototypes and then construct the KAA model, which has been proven efficient in internet intrusion detection. The hybrid model is further studied in this paper, with several clustering algorithms compared, including k-mean clustering, SOM and Neural Gas. Experimental results using more than 2,500 images from four types of vehicles (bus, light truck, car and van) demonstrated the effectiveness of the hybrid model. The proposed scheme offers a performance of accuracy over $95~\%$ with a rejection rate $8~\%$ and reliability over $98~\%$ with a rejection rate of $20~\%$ . This exhibits promising potentials for real-world applications.     

基于机器视觉的交叉口特种车辆快速通行技术研究

交叉口是道路网络中重要的交通节点,容易产生交通堵塞问题,为了在保证通行安全的情况下提高特种车辆的通行效率,研究基于机器视觉的交叉口特种车辆快速通行技术。优化通行基础采用图像采集及预处理、检测识别和通行控制作为技术框架结构,利用机器视觉技术采集交叉口实时交通图像,通过图像滤波、图像增强等步骤,实现初始图像的预处理。利用Car-YOLO网络识别交叉口通行能力,规划快速通行路线,考虑前车行驶状态,求解特种车辆通行速度,针对车辆所占车道,通过绿灯早启、绿灯周期时间延长等方式控制交叉口信号灯,实现交叉口特种车辆快速通行。实验结果表明:在拥堵和正常通行场景下,优化设计技术的特种车辆通过时间的平均值分别为18.2s、10.1s,事故发生概率分别低于2%、1.4%,具有较好的应用效果。     

The impact of verbal interaction on driver lateral control: an experimental assessment

Driver distraction is acknowledged as one of the key contributors to driver accidents (Treat, J.R., et al., 1977 Treat, J. R. 1977. Tri-level study of the causes of traffic accidents (No. DOT-HS-034-535-77-TAC(1)), Bloomington, IN: Institute for Research in Public Safety – Indiana University.  [Google Scholar]. Tri-level study of the causes of traffic accidents (No. DOT-HS-034‐535‐77-TAC(1)). Bloomington, IN: Institute for Research in Public Safety – Indiana University; Knipling, R.R., et al., 1993 Knipling, R. R. 1993. Assessment of IVHS countermeasures for collision avoidance: Rear-end crashes (No. DOT HS 807 995), Washington, DC: National Highway Traffic Safety Administration.  [Google Scholar]. Assessment of IVHS countermeasures for collision avoidance: Rear-end crashes (No. DOT HS 807 995). Washington, DC: National Highway Traffic Safety Administration). As driving is mainly considered a visual task (Wierwille, W.W., 1993 Wierwille, W. W. 1993. “Visual and manual demands of in-car controls and displays”. In Automotive ergonomics, Edited by: Peakock, B. and Karwowski, W. 229–320. London: Taylor and Francis.  [Google Scholar]. Visual and manual demands of in-car controls and displays. In: B. Peakock and W. Karwowski, eds. Automotive ergonomics. London: Taylor and Francis, 229–320) the use of auditory channels for interacting with intelligent vehicle systems has been suggested as a solution to possible visual overload. This article presents two studies which assess the potential impact of distraction caused by verbal interaction on the driving task. The first study used a low-cost, game-based, simulation and the second study used the same experimental design with a generic driving simulation, the Lane Change Task (Mattes, S., 2003. The lane change task as a tool for driver distraction evaluation. In: H. Strasser, H. Rascher, and H. Bubb, eds. Quality of work and products in enterprises of the future. Stuttgart: Ergonomia Verlag, 57–60). Twenty-four young adults, 12 males and 12 females, participated in the first study and 12 young adults, 6 males and 6 females, in the second study. Road departures, time/speed and subjective workload were the measures in the first study, while the second study used mean course-departure and subjective workload as dependent variables. The results indicated that game-based simulation can be a solution when realism is needed but resources are limited, and suggested that concurrent verbal interaction may impair lateral vehicle control.     

Blind and sighted pedestrians' judgments of gaps in traffic at roundabouts

This paper reports two experiments about street crossing under conditions of free flowing traffic, with a focus on modem roundabout intersections. Experiment 1 was conducted at three roundabouts varying in size and traffic volume. Six totally blind and six sighted adults judged whether gaps in traffic were long enough to permit crossing to the median (splitter) island before the next vehicle arrived. Gap distributions and measures of judgment quality are reported. Overall, blind participants were about 2.5 times less likely to make correct judgments than sighted participants, took longer to detect crossable gaps, and were more likely to miss crossable gaps altogether. However, the differences were significant only at the two higher volume roundabouts. In Experiment 2, we evaluated the response of drivers to pedestrians with and without mobility devices (i.e., long canes, dog guides). The experiment was conducted at a single-lane roundabout, a midblock crossing, and a two-way-stop-controlled intersection. Site-specific characteristics appeared to have a greater impact on drivers' yielding than did a mobility device. Actual or potential applications of this research include the development of methods for assessing pedestrian safety and driver behavior as well as identifying intersections that may require modification in order to be accessible to blind pedestrians.     

An application of a fuzzy classifier extracted from data for collision avoidance support in road vehicles

Road traffic collisions are an outstanding problem in current developed societies. This paper presents a solution to support collision avoidance based on the timely detection of the vehicle maneuvers. Since the longitudinal interaction among vehicles, with the commonly known car-following behavior, is one of the most important causes of crashes, it was decided to focus on longitudinal maneuvers, identifying the maneuvering states of cruise, accelerating or decelerating and stop. The classification is carried out by means of fuzzy rules extracted from navigational data. Therefore, in our proposal no extra sensors are needed apart from two commonly installed for navigation purposes: the odometry of the vehicle and an accelerometer. The system was tested with low-cost sensors showing good results when compared to the literature of the field.     

无信号交叉口网联车调度与分布式控制策略

针对多车道无信号交叉口,在高交通流量时易发生拥堵的问题,提出了一种适用于交叉口智能网联车(connected automated vehicle, CAV)通行的解决方案,将问题解耦成顺序决策和分布式控制两个问题。而车辆调度是方案中的关键点,对通行效率有很大的影响,且问题的复杂度是指数级。为解决该问题,提出一种基于队列评价模型的决策方法(queue evaluation spanning tree, QEST),将网联车存到的多个队列模型中,并以通行效率和车辆延迟建立代价函数,以此对队列进行评价,通过不断循环选择最佳的队列,优化车辆在交叉口的通行顺序,有效提升了通行效率。对第二个问题,提出一种分布式控制框架,使得车辆按预定顺序通过交叉口。结果表明,该方案在中高交通流量时能有效提升交叉口的通行效率并降低车辆延迟和能量消耗。     

基于无线通信的车辆主动防撞预警系统设计

提出了一种基于无线通信的车辆主动防撞预警系统,利用梯度方向直方图特征与支持向量机配合单目测距模型实现前方车辆的实时检测与测距,并利用传感器无线通信网络获取相对车速信息,最后根据相对车距与相对车速配合TTC预警模型实现碰撞预警。试验结果表明,系统平均处理时间100ms,车辆检测准确率95%,单目测距误差小于±4m,实现了实时、准确的车辆预警。     

Classify vehicles in traffic scene images with deformable part-based models

Vehicle classification is an important and challenging task in intelligent transportation systems, which has a wide range of applications. In this paper, we propose to integrate vehicle detection and vehicle classification into one single framework by using deformable part-based models. First of all, we use annotated vehicle images to train a deformable part-based model for each class of vehicles to be classified. Then, given a traffic scene image, we employ the obtained vehicle models to perform vehicle detection in it for vehicle extraction. After that, model alignment is performed on the extracted image crop, based on which features are extracted for creating a representation for the vehicle in the given image. We train a linear multi-class Support Vector Machine classifier based on representations of images in a validation set. Finally, we adopt the SVM classifier for vehicle classification. The proposed method is evaluated on the BIT-Vehicle Dataset, and can achieve an accuracy of \(91.08\%\), which is superior to methods used for comparison. Obtained results demonstrated the effectiveness of the proposed method.     

Real-time vehicle tracking mechanism with license plate recognition from road images

Abstract Information about vehicles on the road is very important for the maintenance of traffic control in current complex traffic condition. Images of vehicles are captured by vehicle-directed cameras. This paper proposes a new vehicle tracking mechanism using license plate recognition technology, which is essential to having information about vehicles on the roads. The proposed method is a real-time processing system using multistep image processing, as well as recognition and tracking processes from 2D and 3D images. The experimental results of real environmental images in recognition and tracking using the proposed method are shown.     

A Multimedia Data Mining Framework: Mining Information from Traffic Video Sequences

The analysis and mining of traffic video sequences to discover important but previously unknown knowledge such as vehicle identification, traffic flow, queue detection, incident detection, and the spatio-temporal relations of the vehicles at intersections, provide an economic approach for daily traffic monitoring operations. To meet such demands, a multimedia data mining framework is proposed in this paper. The proposed multimedia data mining framework analyzes the traffic video sequences using background subtraction, image/video segmentation, vehicle tracking, and modeling with the multimedia augmented transition network (MATN) model and multimedia input strings, in the domain of traffic monitoring over traffic intersections. The spatio-temporal relationships of the vehicle objects in each frame are discovered and accurately captured and modeled. Such an additional level of sophistication enabled by the proposed multimedia data mining framework in terms of spatio-temporal tracking generates a capability for automation. This capability alone can significantly influence and enhance current data processing and implementation strategies for several problems vis-à-vis traffic operations. Three real-life traffic video sequences obtained from different sources and with different weather conditions are used to illustrate the effectiveness and robustness of the proposed multimedia data mining framework by demonstrating how the proposed framework can be applied to traffic applications to answer the spatio-temporal queries.     

Motion planning of autonomous vehicles in a non-autonomous vehicle environment without speed lanes

Planning is one of the key problems for autonomous vehicles operating in road scenarios. Present planning algorithms operate with the assumption that traffic is organised in predefined speed lanes, which makes it impossible to allow autonomous vehicles in countries with unorganised traffic. Unorganised traffic is though capable of higher traffic bandwidths when constituting vehicles vary in their speed capabilities and sizes. Diverse vehicles in an unorganised exhibit unique driving behaviours which are analysed in this paper by a simulation study. The aim of the work reported here is to create a planning algorithm for mixed traffic consisting of both autonomous and non-autonomous vehicles without any inter-vehicle communication. The awareness (e.g. vision) of every vehicle is restricted to nearby vehicles only and a straight infinite road is assumed for decision making regarding navigation in the presence of multiple vehicles. Exhibited behaviours include obstacle avoidance, overtaking, giving way for vehicles to overtake from behind, vehicle following, adjusting the lateral lane position and so on. A conflict of plans is a major issue which will almost certainly arise in the absence of inter-vehicle communication. Hence each vehicle needs to continuously track other vehicles and rectify plans whenever a collision seems likely. Further it is observed here that driver aggression plays a vital role in overall traffic dynamics, hence this has also been factored in accordingly. This work is hence a step forward towards achieving autonomous vehicles in unorganised traffic, while similar effort would be required for planning problems such as intersections, mergers, diversions and other modules like localisation.     

交通强度优先的交叉口模糊控制研究

为了降低交叉口车辆延误,提高通行能力,研究了一个四相位交叉口交通信号的模糊控制方法。用交通强度刻画各相位交通流通行需求的紧急程度,根据各相位的交通强度由模糊推理得到当前相位的绿灯延长时间,并选取后续绿灯相位。以交叉口车辆平均延误作为交叉口信号控制的性能评价指标,在相同交通条件下对几种控制方式进行了仿真试验。结果表明,该文的控制方法相对于感应控制方法和直接采用车辆排队长度作为输入的模糊控制方法,更能有效减小交叉口的车辆平均延误。     

Taking context into account in conceptual models using a Model Driven Engineering approach

Context

In public transport, travelers (considered as information systems users) do not have the same objectives and/or concerns at the same time. For this reason it is not always easy to provide them with the right information at the right time. If personalizing the information to the user allows to do this to some extend it is not enough since the information could also depend on the use of the context and the environment (e.g., place, time, etc.).

Objective

This paper proposes a solution allowing the context to be managed inside an application’s conceptual models in order to provide more flexible web applications from the user’s point of view.

Method

Our work is based on a modeling method using the Model Driven Engineering (MDE) approach and on practical field experiences permitting us to validate our solution. Our domain of application is personalized transport information.

Results

Introducing the notion of context into rules and decision trees that are used inside conceptual models allowed us to incorporate context as important information for personalizing web applications.

Conclusion

The context should be integrated into an application during the modeling phase to allow a smooth integration inside the application and to facilitate the evolution over time. Our solution offers a better user’s experience through an extended personalization of web applications.     

Safe design of mobile equipment traffic management systems

Designing and implementing safe, efficient and operator-centred traffic management systems for mobile equipment, other vehicles and pedestrians is of key importance in almost every industrial domain. Such systems rarely develop successfully on their own; whilst standards and guidelines do exist, they are often not stringently and comprehensively employed in all industrial settings, and additional guidance to managers responsible for traffic management would be beneficial.Building on models of the elements required for effective traffic management, the work described in this paper used a review of the literature, case studies from a variety of different industrial domains and operator-centred safe design processes to develop a set of 50 human element questions to help ensure mobile equipment safety. The process was iterative, and involved subject matter expert feedback, trialling the draft question set in an audit of several sites following a major incident and incorporating emerging findings about the possible use of new assistive technologies (such as collision detection systems).

Relevance to industry

In terms of industrial applications, the resultant question list can be used to identify potential problem areas, primarily safety but also partly inefficiency, regarding mobile equipment interactions with pedestrians, infrastructure or other equipment. Potential problem areas revealed could then undergo more detailed investigation and possible correction using risk assessment techniques or similar.     

一种基于支持矢量机的交叉路口车型分类方法及流量参数的提取

对交叉路口行驶车辆进行有效分类,是进行流量统计、交通状况分析,以及交通事故分析的基础。在运动目标检测和图像标定技术的基础上,通过引入多类支持矢量机方法,提出了一种利用车辆的多个特征对交叉路口车辆进行分类的方法,解决了传统分类方法存在的"误分"问题,实验结果表明,该方法分类精确度高,满足交叉路口车型分类的要求。另外,又给出了一种"车流速度"的提取方法,为交通管理部门分析交通状况提供了依据。     

Personal factors influencing the visual reaction time of pedestrians to detect turn indicators in the presence of Daytime Running Lamps

Daytime running lamps (DRL) on vehicles have proven to be an effective measure to prevent accidents during the daytime, particularly when pedestrians and cyclists are involved. However, there are negative interactions of DRL with other functions in automotive lighting, such as delays in pedestrians’ visual reaction time (VRT) when turn indicators are activated in the presence of DRL. These negative interactions need to be reduced. This work analyses the influence of variables inherent to pedestrians, such as height, gender and visual defects, on the VRT using a classification and regression tree as an exploratory analysis and a generalized linear model to validate the results. Some pedestrian characteristics, such as gender, alone or combined with the DRL colour, and visual defects, were found to have a statistically significant influence on VRT and, hence, on traffic safety. These results and conclusions concerning the interaction between pedestrians and vehicles are presented and discussed.

Practitioner Summary: Visual interactions of vehicle daytime running lamps (DRL) with other functions in automotive lighting, such as turn indicators, have an important impact on a vehicle’s conspicuity for pedestrians. Depending on several factors inherent to pedestrians, the visual reaction time (VRT) can be remarkably delayed, which has implications in traffic safety.     

Dynamic distributed lanes: motion planning for multiple autonomous vehicles

Unorganized traffic is a generalized form of travel wherein vehicles do not adhere to any predefined lanes and can travel in-between lanes. Such travel is visible in a number of countries e.g. India, wherein it enables a higher traffic bandwidth, more overtaking and more efficient travel. These advantages are visible when the vehicles vary considerably in size and speed, in the absence of which the predefined lanes are near-optimal. Motion planning for multiple autonomous vehicles in unorganized traffic deals with deciding on the manner in which every vehicle travels, ensuring no collision either with each other or with static obstacles. In this paper the notion of predefined lanes is generalized to model unorganized travel for the purpose of planning vehicles travel. A uniform cost search is used for finding the optimal motion strategy of a vehicle, amidst the known travel plans of the other vehicles. The aim is to maximize the separation between the vehicles and static obstacles. The search is responsible for defining an optimal lane distribution among vehicles in the planning scenario. Clothoid curves are used for maintaining a lane or changing lanes. Experiments are performed by simulation over a set of challenging scenarios with a complex grid of obstacles. Additionally behaviours of overtaking, waiting for a vehicle to cross and following another vehicle are exhibited.     

结合状态机和动态目标路径的无人驾驶决策仿真

目的 决策系统是无人驾驶技术的核心研究之一。已有决策系统存在逻辑不合理、计算效率低、应用场景局限等问题,因此提出一种动态环境下无人驾驶路径决策仿真。方法 首先,基于规则模型构建适于无人驾驶决策系统的交通有限状态机;其次,针对交通动态特征,提出基于统计模型的动态目标路径算法计算状态迁移风险;最后,将交通状态机和动态目标路径算法有机结合,设计出一种基于有限状态机的无人驾驶动态目标路径模型,适用于交叉口冲突避免和三车道换道行为。将全速度差连续跟驰模型运用到换道规则中,并基于冲突时间提出动态临界跟车距离。结果 为验证模型的有效性和高效性,对交通环境进行虚拟现实建模,模拟交叉口通行和三车道换道行为,分析文中模型对车流量和换道率的影响。实验结果显示,在交叉口通行时,自主车辆不仅可以检测冲突还可以根据风险评估结果执行安全合理的决策。三车道换道时,自主车辆既可以实现紧急让道,也可以通过执行换道达成自身驾驶期望。通过将实测数据和其他两种方法对比,当车流密度在0.20.5时,本文模型的平均速度最高分别提高32 km/h和22 km/h。当车流密度不超过0.65时,本文模型的换道成功率最高分别提升37%和25%。结论 实验结果说明本文方法不仅可以在动态城区环境下提高决策安全性和正确性,还可以提高车流量饱和度,缓解交通堵塞。