技术领域technical field
本发明涉及一种适用于车载短距离通信网络的危险路段交通事故预警方法，属于通信与信息领域，尤其是车载通信技术领域。The invention relates to a method for early warning of traffic accidents on dangerous road sections applicable to a vehicle-mounted short-distance communication network, which belongs to the field of communication and information, in particular to the technical field of vehicle-mounted communication.
背景技术Background technique
在交通事故的多发路段，历史数据和经验起到很大的作用，如果车辆能获知历史上交通事故发生的原因，并且结合自己当前的车辆驾驶状态进行判断，可以有效避免类似的交通事故发生。但是，大量经过危险路段的车辆对历史发生的交通事故原因不了解，即使在有些路段有指示牌提醒，但是信息量有限，驾驶员在短时间内，也很难结合当前的车辆状态做出判断。Historical data and experience play a big role in traffic accident-prone road sections. If vehicles can learn the causes of traffic accidents in history and make judgments based on their current driving status, similar traffic accidents can be effectively avoided. However, a large number of vehicles passing through dangerous road sections do not understand the causes of traffic accidents that occurred in history. Even if there are signage reminders on some road sections, the amount of information is limited, and it is difficult for drivers to make judgments based on the current vehicle status in a short period of time. .
车载短距离通信(Vehicle to X：V2X)网络是通过无线通信、GPS/GIS、传感等短距离通信技术实现的车内(CAN-Controller Area Network)、车路(Vehicle-2-RSU)、车间(Vehicle-2-Vehicle)、车外(vehicle-2-Infrastructure)、人车(Vehicle-2-Person)之间的通信。Vehicle short-distance communication (Vehicle to X: V2X) network is realized by short-distance communication technologies such as wireless communication, GPS/GIS, and sensors. Communication between the workshop (Vehicle-2-Vehicle), the outside of the vehicle (vehicle-2-Infrastructure), and the vehicle (Vehicle-2-Person).
V2X网络中，节点包括车载节点(OBU)和路侧节点(RSU)等，每个车载节点拥有车辆识别码(VIN)作为车辆的唯一标识，车载节点配备有北斗或者GPS等提供地理位置信息的设备，车辆的车载节点定期将VIN和位置信息向周围广播(简称心跳信息)。路侧节点(RSU)也具有同样的功能，而且具有运算能力强，天线部署位置高、供电不受限制，覆盖范围大的优势。In the V2X network, nodes include on-board nodes (OBU) and roadside nodes (RSU), etc. Each on-board node has a vehicle identification number (VIN) as the unique identifier of the vehicle, and the on-board nodes are equipped with Beidou or GPS to provide geographic location information. The equipment, the on-board node of the vehicle periodically broadcasts VIN and location information to the surroundings (referred to as heartbeat information). The roadside unit (RSU) also has the same function, and has the advantages of strong computing power, high antenna deployment position, unlimited power supply, and large coverage.
在危险路段部署路侧节点，通过V2X网络的信道，可以将危险路段中容易引起交通事故的因素向经过的车辆广播，是降低交通事故的有效方式。这种方式虽然简单，但是会对正常驾驶的车辆造成干扰，针对性也不强。能及时对容易发生交通事故的车辆进行预测，即可以不干扰正常驾驶，同时还可以有效降低交通事故，但是需要路侧节点具有收集车辆信息并进行智能判断的能力。Deploying roadside nodes on dangerous road sections can broadcast the factors that are likely to cause traffic accidents in dangerous road sections to passing vehicles through the channel of the V2X network, which is an effective way to reduce traffic accidents. Although this method is simple, it will interfere with normal driving vehicles, and the pertinence is not strong. It can predict the vehicles that are prone to traffic accidents in time, that is, it can not interfere with normal driving, and can effectively reduce traffic accidents, but it requires roadside nodes to have the ability to collect vehicle information and make intelligent judgments.
V2X网路中具有短距离通信信道，路侧节点通过接收车载节点定期发送到心跳信息，可以获得周围车辆的状态，包括速度和车辆类型等。路侧节点的设备中的软件，配置具有学习历史数据的能力算法，以及根据现有车辆的状态，进行预测的能力的算法，即可以达到学习和预测的目的。There is a short-distance communication channel in the V2X network. The roadside node can obtain the status of the surrounding vehicles, including speed and vehicle type, by receiving the heartbeat information sent periodically by the vehicle node. The software in the equipment of the roadside node is configured with an algorithm capable of learning historical data and predicting according to the state of existing vehicles, that is, the purpose of learning and prediction can be achieved.
本发明实施例利用V2X中的通信信道，通过路侧节点中的贝叶斯网络学习该路段发生交通事故的历史数据和专家经验，然后收集经过危险路段的车辆的信息，对车辆发生交通事故的概率进行预测，对概率超过门限值的车辆进行及时提醒，从而达到降低危险路段交通事故的目的。The embodiment of the present invention utilizes the communication channel in V2X, learns the historical data and expert experience of traffic accidents in the road section through the Bayesian network in the roadside node, and then collects the information of the vehicles passing through the dangerous road section, and analyzes the traffic accidents of the vehicles. The probability is predicted, and the vehicles whose probability exceeds the threshold value are reminded in time, so as to achieve the purpose of reducing traffic accidents on dangerous road sections.
发明内容Contents of the invention
本发明公开了一种适用于车载短距离通信网络的危险路段交通事故预警方法，在危险路段路旁部署路侧节点，通过车载短距通信网络的通信信道，收集经过车辆定期发送的包含车辆速度和类型的信息，利用具有历史数据学习功能的贝叶斯网络，对车辆发生交通事故的概率进行预测。The invention discloses a method for early warning of traffic accidents on dangerous road sections applicable to a vehicle-mounted short-distance communication network. Roadside nodes are deployed on the side of the dangerous road section, and through the communication channel of the vehicle-mounted short-distance communication network, information including vehicle speed regularly sent by vehicles is collected. and types of information, using the Bayesian network with historical data learning function to predict the probability of vehicle accidents.
为实现上述目的，本发明采用以下技术方案：一种适用于车载短距离通信网络的危险路段交通事故预警方法，在危险路段路旁部署路侧节点，通过车载短距通信网络的通信信道，收集经过车辆定期发送的包含车辆速度和类型的信息，利用具有历史数据学习功能的贝叶斯网络，对车辆发生交通事故的概率进行预测。In order to achieve the above object, the present invention adopts the following technical solutions: a method for early warning of traffic accidents on dangerous sections of the vehicle-mounted short-distance communication network, deploying roadside nodes on the side of the dangerous section of the road, through the communication channel of the vehicle-mounted short-distance communication network, collecting After the information including the speed and type of the vehicle sent regularly by the vehicle, the Bayesian network with the function of learning historical data is used to predict the probability of a vehicle accident.
优选的，路侧节点利用车载短距离通信网络的信道收集的经过车辆的速度和车辆类型信息，转换成车辆的速度和车距信息，作为交通事故预测的因素之一。Preferably, the roadside node converts the speed and vehicle type information of passing vehicles collected by the channel of the vehicle-mounted short-distance communication network into vehicle speed and distance information as one of the factors for predicting traffic accidents.
优选的，路侧节点利用其运算能力强，供电不受影响，天线部署位置高，覆盖范围大的特点，可以收集较大范围的车辆数据并进行多个车辆的预测。Preferably, the roadside node can collect a large range of vehicle data and perform multiple vehicle predictions by taking advantage of its strong computing power, unaffected power supply, high antenna deployment position, and large coverage area.
优选的，路侧节点内部的贝叶斯网络通过历史数据和专家经验确定各个节点的条件概率，从而达到学习的目的。Preferably, the Bayesian network inside the roadside node determines the conditional probability of each node through historical data and expert experience, so as to achieve the purpose of learning.
优选的，路侧节点通过传感器确定天气状况，进而推导出道路状况，或者通过网络接收后台发布的道路状况，作为预测的因素之一。Preferably, the roadside node determines the weather condition through the sensor, and then derives the road condition, or receives the road condition issued by the background through the network, as one of the predictive factors.
优选的，不同危险路段，可以选择不同的容易导致交通事故的因素，并且根据专家经验，确定各个因素之间的联系，作为贝叶斯网络构架的依据。Preferably, for different dangerous road sections, different factors that are likely to cause traffic accidents can be selected, and according to expert experience, the relationship between various factors can be determined as the basis of the Bayesian network structure.
本发明一种适用于车载短距离通信网络的危险路段交通事故预警方法实施方法包括五个部分，第一部分是确定事故预测的因素及其取值范围，第二部分是根据预测因素和取值范围确定贝叶斯预测模型，第三部分是通过交通事故的历史数据和专家经验，进行贝叶斯网络的学习并确定各个条件概率，第四部分确定贝叶斯网络的推理方法，第五部分是路侧节点收集车辆信息的方法和对车辆交通事故预测的方法。An implementation method of an early warning method for traffic accidents on dangerous road sections applicable to a vehicle-mounted short-distance communication network of the present invention includes five parts. Determine the Bayesian prediction model, the third part is to learn the Bayesian network and determine each conditional probability through the historical data of traffic accidents and expert experience, the fourth part is to determine the reasoning method of the Bayesian network, the fifth part is A method for roadside nodes to collect vehicle information and a method for predicting vehicle traffic accidents.
附图说明Description of drawings
图1是本发明实施例的主要实施步骤。Fig. 1 is the main implementation steps of the embodiment of the present invention.
图2是路侧节点示意图。Figure 2 is a schematic diagram of roadside nodes.
图3是预测模型。Figure 3 is the prediction model.
具体实施方式Detailed ways
本实施例实现了一种适用于车载短距离通信网络的危险路段交通事故预警方法，目的是通过V2X网络中车载节点和路侧节点的短距路通信方式，由路侧节点收集车辆的实时信息，结合该危险路段发生的交通事故的历史数据，进行及时的预警。This embodiment implements a traffic accident early warning method for dangerous road sections suitable for vehicle-mounted short-distance communication networks. The purpose is to collect real-time information of vehicles by roadside nodes through the short-distance communication mode between vehicle-mounted nodes and roadside nodes in the V2X network. , Combined with the historical data of traffic accidents on the dangerous road section, a timely warning is given.
如图1至图3所示，本实施例利用V2X的这个特点，在道路危险路段，部署路侧节点，对诱发交通事故的各个因素，结合经过危险路段的车辆的实际行驶状况，通过贝叶斯网络进行综合评测，当车辆发生交通事故的概率较高时，及时通过V2X网络通知车辆，提醒驾驶员，从而降低危险路段发生的交通事故。As shown in Figures 1 to 3, this embodiment utilizes this feature of V2X to deploy roadside nodes on dangerous sections of the road, and to analyze various factors that induce traffic accidents, combined with the actual driving conditions of vehicles passing through dangerous sections, through Bayeux When the probability of a traffic accident is high, the vehicle will be notified through the V2X network in time to remind the driver, thereby reducing traffic accidents on dangerous roads.
由于引起交通事故的因素较多，并且在各个危险路段，这些危险因素的种类和危险性相差较大，贝叶斯网络能较好表示各变量之间的不确定性和相关性，为实施例以贝叶斯网络为基础，构建路侧节点对车辆进行交通事故发生概率的评测算法。Because there are many factors causing traffic accidents, and in each dangerous road section, the types and dangers of these risk factors are quite different, and the Bayesian network can better represent the uncertainty and correlation between the variables. Based on the Bayesian network, an evaluation algorithm for the probability of traffic accidents on vehicles by roadside nodes is constructed.
贝叶斯网络包括两部分：(1)有向无环的贝叶斯网络结构图，节点代表变量，有向弧代表相互关联；(2)节点与节点之间的条件概率表，表示节点之间关系的关系。贝叶斯网络用N＝{<V,E>,P}，X＝(X1,X2,...,Xn)是节点集合。The Bayesian network consists of two parts: (1) directed acyclic Bayesian network structure diagram, nodes represent variables, and directed arcs represent interrelationships; (2) the conditional probability table between nodes, which represents the relationship between nodes relationship between. Bayesian network uses N={<V,E>,P}, X=(X1 ,X2 ,...,Xn ) is a node set.
在各个危险路段中，引起交通事故的因素不同，各个因素占的比例也差别较大，因此，贝叶斯网络构建，应该根据不同路段的情况，分别选择不同的因素进行构建。在本实施例中，选择了一种危险路段进行说明，如图1所示，车辆从A端经B点向C端行驶，在B点有一个拐弯，在C点部署一个路侧节点R，接收从A向C方向行驶的各个车辆定期发送的心跳信息，进而确定各个车辆的速度和位置，以及相互之间的距离，并对各个车辆的事故概率进行预测。In each dangerous road section, the factors that cause traffic accidents are different, and the proportion of each factor is also quite different. Therefore, the construction of Bayesian network should be based on the conditions of different road sections, and different factors should be selected for construction. In this embodiment, a dangerous road section is selected for illustration. As shown in Figure 1, the vehicle travels from end A to end C via point B. There is a turn at point B, and a roadside node R is deployed at point C. Receive the heartbeat information regularly sent by each vehicle traveling from A to C, and then determine the speed and position of each vehicle, as well as the distance between each other, and predict the accident probability of each vehicle.
本实施例的实施步骤包括五个部分。The implementation steps of this embodiment include five parts.
第一部分、确定事故预测的因素及其取值。The first part is to determine the factors and values of accident prediction.
1.1、确定事故预测因素。本实施例的场景中，根据已经发生交通事故的历史数据，B点的拐弯处是事故高发地点，主要原因同以下因素有关：车速V、车距D、车辆类型T、天气状况W、车流量S。1.1. Determine the accident prediction factors. In the scene of this embodiment, according to the historical data of traffic accidents that have occurred, the corner at point B is a place where accidents occur frequently, and the main reasons are related to the following factors: vehicle speed V, vehicle distance D, vehicle type T, weather conditions W, traffic flow S.
1.2、确定各个因素的取值。本实施例中，综合考虑算法复杂度和各个因素的判断精度，各个因素的取值如下：车速V＝{40以下，40-80，80-100，100-120，120以上}，单位公里(km)/小时(h)；车距D＝{近(小于5米)，中(5-20米),远(20米以上)}；车辆类型T＝{载重卡车、大客车、小客车}；天气状况W＝{晴天、雪地、雨地}。1.2. Determine the value of each factor. In this embodiment, considering the complexity of the algorithm and the judgment accuracy of each factor comprehensively, the values of each factor are as follows: vehicle speed V={below 40, 40-80, 80-100, 100-120, above 120}, unit kilometer ( km)/hour (h); vehicle distance D={near (less than 5 meters), medium (5-20 meters), far (more than 20 meters)}; vehicle type T={truck, bus, passenger car} ;Weather condition W={sunny, snowy, rainy}.
第二部分、贝叶斯预测模型构建。The second part, Bayesian prediction model construction.
2.1、根据专家经验确定贝叶斯预测模型。本实施例中，选择车速V、车距D、车辆类型T、天气状况W、车流量S作为父节点，交通事故R作为子节点，构成贝叶斯预测模型，如图2所示。2.1. Determine the Bayesian prediction model based on expert experience. In this embodiment, vehicle speed V, vehicle distance D, vehicle type T, weather condition W, and traffic volume S are selected as parent nodes, and traffic accident R is selected as child nodes to form a Bayesian prediction model, as shown in FIG. 2 .
2.2、确定各个因素之间的关联性。本实施例中，车距D同车速V相关，车距D、车速V同天气状况W和车辆类型T相关。2.2. Determine the correlation between various factors. In this embodiment, the vehicle distance D is related to the vehicle speed V, and the vehicle distance D and the vehicle speed V are related to the weather condition W and the vehicle type T.
第三部分、贝叶斯网络学习和条件概率确定Part III, Bayesian Network Learning and Conditional Probability Determination
贝叶斯网络中，设节点集合X＝(X1,X2,...,Xn)，联合概率分布其中，Parent(xi)表示xi节点的父节点。从现有信息的统计结果获得各相关节点的先验概率和节点间的条件概率，称为贝叶斯网络的学习过程。贝叶斯网络条件概率确定后，利用p(X)就可以推理其他节点的概率，这个过程称为贝叶斯网络的推理过程。贝叶斯网络(BN)推理方法是，在给定对变量集合E的实际值时,计算出变量集合Q的后验条件概率分布P(Q|E)。In the Bayesian network, set the node set X=(X1 ,X2 ,...,Xn ), the joint probability distribution Wherein, Parent(xi) represents the parent node of node x i. The prior probability of each relevant node and the conditional probability between nodes are obtained from the statistical results of existing information, which is called the learning process of Bayesian network. After the conditional probability of the Bayesian network is determined, the probability of other nodes can be inferred by using p(X). This process is called the inference process of the Bayesian network. The Bayesian Network (BN) inference method is to calculate the posterior conditional probability distribution P(Q|E) of the variable set Q when the actual value of the variable set E is given.
3.1、通过历史数据或者专家经验，确定各个节点的条件概率。贝叶斯学习的主要依据是贝叶斯公式：3.1. Determine the conditional probability of each node through historical data or expert experience. The main basis for Bayesian learning is the Bayesian formula:
其中，P(h)是事件h的先验概率,表示没有训练数据前的初始概率。P(D)表示要观察的训练数据D的先验概率，P(D|h)表示h成立时的D发生的概率。P(h|D)则表示给定训练数据D时h成立的概率,也称为h的后验概率，反映了训练数据D对h的影响。Among them, P(h) is the prior probability of event h, which represents the initial probability before there is no training data. P(D) represents the prior probability of the training data D to be observed, and P(D|h) represents the probability of D occurring when h holds true. P(h|D) represents the probability of h being established when training data D is given, also known as the posterior probability of h, which reflects the influence of training data D on h.
则根据贝叶斯网络的架构，根据历史数据或者现场测试数据，可以获得P(v|w,D,T)条件概率，例如：表1是发生交通事故的历史数据中，{w,D,T}不同组合对应不同速度的比例，其中对应{雨地，中，小客车}这组组合中，各个速度段所占的比例分别是{0.02,0.08,0.12,0.28,0.50}，所有的组合比例和为1。通过历史数据的学习或者专家经验确认，贝叶斯网络完成学习，获得相应的条件概率。.According to the framework of the Bayesian network, according to historical data or field test data, the conditional probability of P(v|w,D,T) can be obtained, for example: Table 1 is the historical data of traffic accidents, {w,D, T} Different combinations correspond to the proportions of different speeds. In the combination of {rain, medium, small passenger cars}, the proportions of each speed segment are {0.02, 0.08, 0.12, 0.28, 0.50}, and all combinations The ratio sums to 1. Through the learning of historical data or the confirmation of expert experience, the Bayesian network completes the learning and obtains the corresponding conditional probability. .
表1Table 1
第四部分、贝叶斯网络推理Part IV, Bayesian Network Inference
已知一组现有车辆的速度，以及车辆类型、车距和天气状况，预测发生交通事故的概率，应用极大似然，可通过下式求得：Knowing the speed of a group of existing vehicles, as well as vehicle types, distances and weather conditions, predicting the probability of traffic accidents, applying maximum likelihood, can be obtained by the following formula:
P(R|v,D,w,T)＝P(v|w,T)P(D|v,w,T)P(R|v,D,w,T)＝P(v|w,T)P(D|v,w,T)
第五部分、路侧节点危险路段车辆交通事故预测Part V. Prediction of Vehicle Traffic Accidents on Dangerous Sections of Roadside Nodes
5.1、路侧节点部署。在危险路段部署在路侧节点，利用其运算能力强，供电不受影响，天线部署位置高，覆盖范围大的特点，可以收集较大范围的车辆数据并进行多个车辆的预测。路侧节点设备内安装有实现贝叶斯网络交通事故算法的软件，并且系统提供历史数据和专家经验数据进行学习，使贝叶斯网络算法能正常工作。5.1. Roadside node deployment. Deployed on roadside nodes in dangerous road sections, it can collect a large range of vehicle data and predict multiple vehicles by taking advantage of its strong computing power, unaffected power supply, high antenna deployment position, and large coverage area. The roadside node equipment is installed with software that implements the Bayesian network traffic accident algorithm, and the system provides historical data and expert experience data for learning, so that the Bayesian network algorithm can work normally.
5.2、路侧节点信息接收。路侧节点根据传感器确定天气状况，进而推导出道路状况，或者通过网络接收后台发布的道路状况。通过接收经过危险路段的车载节点定期发动的心跳信息，获得各个车辆的位置和车辆类型，进一步确定各个车辆的速度、车距。5.2. Roadside node information reception. Roadside nodes determine weather conditions based on sensors, and then derive road conditions, or receive road conditions released by the background through the network. By receiving the heartbeat information periodically launched by the on-board nodes passing through the dangerous road section, the position and type of each vehicle are obtained, and the speed and distance between each vehicle are further determined.
5.3、路侧节点预测和预警。路侧节点根据获得的各个车辆的位置、速度、车距，结合天气状况，通过贝叶斯网络获得发生交通事故的概率P(R|v,D,w,T)，如果某车辆的交通事故发生的概率大于系统设定的门限值，就通过车载短距通信网络，通知该车辆有发生交通事故的危险，提醒车辆注意速度和车距。5.3. Roadside node prediction and early warning. The roadside node obtains the probability of a traffic accident P(R|v,D,w,T) through the Bayesian network based on the position, speed, and distance of each vehicle obtained, combined with the weather conditions. If a vehicle's traffic accident If the probability of occurrence is greater than the threshold value set by the system, the vehicle will be notified of the danger of a traffic accident through the vehicle-mounted short-distance communication network, and the vehicle will be reminded to pay attention to the speed and distance between vehicles.
通过本实施例，可以针对某些危险路段，针对可能引起交通事故的因素，通过路侧节点对经过的车辆的进行交通事故发生概率的预测，从而有效降低危险路段交通事故发生的概率。本实施例中，主要关注了车速和车距因素，同样的方法，针对不同特点的危险路段，可以选择其他容易引起交通事故的因素。Through this embodiment, for certain dangerous road sections and factors that may cause traffic accidents, the probability of traffic accidents of passing vehicles can be predicted through roadside nodes, thereby effectively reducing the probability of traffic accidents on dangerous road sections. In this embodiment, the vehicle speed and the distance between vehicles are mainly concerned. In the same way, other factors that are likely to cause traffic accidents can be selected for dangerous road sections with different characteristics.
以上所述是本发明的较佳实施例及其所运用的技术原理，对于本领域的技术人员来说，在不背离本发明的精神和范围的情况下，任何基于本发明技术方案基础上的等效变换、简单替换等显而易见的改变，均属于本发明保护范围之内。The above are the preferred embodiments of the present invention and the technical principles used therefor. For those skilled in the art, without departing from the spirit and scope of the present invention, any technical solution based on the present invention Obvious changes such as equivalent transformation and simple replacement all fall within the protection scope of the present invention.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710007428.2ACN108281039B (en) | 2017-01-05 | 2017-01-05 | Dangerous road traffic accident early warning method suitable for vehicle-mounted short-distance communication network |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710007428.2ACN108281039B (en) | 2017-01-05 | 2017-01-05 | Dangerous road traffic accident early warning method suitable for vehicle-mounted short-distance communication network |
| Publication Number | Publication Date |
|---|---|
| CN108281039Atrue CN108281039A (en) | 2018-07-13 |
| CN108281039B CN108281039B (en) | 2020-04-10 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710007428.2AActiveCN108281039B (en) | 2017-01-05 | 2017-01-05 | Dangerous road traffic accident early warning method suitable for vehicle-mounted short-distance communication network |
| Country | Link |
|---|---|
| CN (1) | CN108281039B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110827575A (en)* | 2018-08-08 | 2020-02-21 | 财团法人工业技术研究院 | Collaborative vehicle safety system and method |
| CN111797768A (en)* | 2020-07-06 | 2020-10-20 | 华侨大学 | A method and system for automatic real-time identification of multiple causes of urban road traffic congestion |
| CN111967091A (en)* | 2020-08-06 | 2020-11-20 | 广州小鹏汽车科技有限公司 | Failure prediction method and failure prediction device for vehicle power module and electronic equipment |
| CN113538909A (en)* | 2021-07-13 | 2021-10-22 | 公安部道路交通安全研究中心 | Traffic incident prediction method and device for automatic driving vehicle |
| CN115223370A (en)* | 2022-08-31 | 2022-10-21 | 四川九通智路科技有限公司 | Traffic accident detection method and system |
| CN116704747A (en)* | 2022-12-29 | 2023-09-05 | 摩斯智联科技有限公司 | System for judging vehicle accident and controlling wind based on edge calculation |
| CN118781819A (en)* | 2024-09-11 | 2024-10-15 | 山东大学 | Traffic conflict assessment method and system based on multivariate and Bayesian network |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104835318A (en)* | 2015-03-23 | 2015-08-12 | 中南大学 | Method for quantifying path safety level based on Bayes combined model |
| CN105139657A (en)* | 2015-10-21 | 2015-12-09 | 重庆云途交通科技有限公司 | V2I (Vehicle to Infrastructure)-based road boundary and accident black spot extraction method and system |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104835318A (en)* | 2015-03-23 | 2015-08-12 | 中南大学 | Method for quantifying path safety level based on Bayes combined model |
| CN105139657A (en)* | 2015-10-21 | 2015-12-09 | 重庆云途交通科技有限公司 | V2I (Vehicle to Infrastructure)-based road boundary and accident black spot extraction method and system |
| Title |
|---|
| 林震等: "基于车速的交通事故贝叶斯预测", 《中国安全科学学报》* |
| 秦小虎等: "一种基于贝叶斯网络模型的交通事故预测方法", 《计算机仿真》* |
| 赵金宝等: "基于贝叶斯网络模型的城市道路交通事故分析", 《东南大学学报》* |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110827575A (en)* | 2018-08-08 | 2020-02-21 | 财团法人工业技术研究院 | Collaborative vehicle safety system and method |
| CN111797768A (en)* | 2020-07-06 | 2020-10-20 | 华侨大学 | A method and system for automatic real-time identification of multiple causes of urban road traffic congestion |
| CN111797768B (en)* | 2020-07-06 | 2023-05-12 | 华侨大学 | A method and system for automatic real-time identification of multiple causes of urban road traffic congestion |
| CN111967091A (en)* | 2020-08-06 | 2020-11-20 | 广州小鹏汽车科技有限公司 | Failure prediction method and failure prediction device for vehicle power module and electronic equipment |
| CN113538909A (en)* | 2021-07-13 | 2021-10-22 | 公安部道路交通安全研究中心 | Traffic incident prediction method and device for automatic driving vehicle |
| CN115223370A (en)* | 2022-08-31 | 2022-10-21 | 四川九通智路科技有限公司 | Traffic accident detection method and system |
| CN116704747A (en)* | 2022-12-29 | 2023-09-05 | 摩斯智联科技有限公司 | System for judging vehicle accident and controlling wind based on edge calculation |
| CN118781819A (en)* | 2024-09-11 | 2024-10-15 | 山东大学 | Traffic conflict assessment method and system based on multivariate and Bayesian network |
| Publication number | Publication date |
|---|---|
| CN108281039B (en) | 2020-04-10 |
| Publication | Publication Date | Title |
|---|---|---|
| CN108281039B (en) | Dangerous road traffic accident early warning method suitable for vehicle-mounted short-distance communication network | |
| US11847908B2 (en) | Data processing for connected and autonomous vehicles | |
| US10788845B2 (en) | Optimization of mission efficiency through platoon opportunity assessment | |
| KR102497716B1 (en) | Control server that porvides an advisory speed limit for autonomous vehicle | |
| CN104376729B (en) | A kind of highway based on truck traffic is to reminding method congested to track | |
| CN104269073B (en) | A kind of reverse track based on truck traffic method for early warning of overtaking other vehicles | |
| CN103544850B (en) | Based on the collision predicting method of vehicle headway probability distribution in car networking | |
| CN103794070B (en) | A kind of based on bus or train route collaborative dynamic induction information broadcasting method and system | |
| CN106297340A (en) | A kind of driving vehicle pre-warning system for monitoring and method | |
| CN106781570B (en) | A kind of identification of highway danger road conditions and alarm method suitable for vehicle-mounted short distance communication network | |
| CN111354193A (en) | An early warning system for abnormal behavior of expressway vehicles based on 5G communication | |
| Sou | Modeling emergency messaging for car accident over dichotomized headway model in vehicular ad-hoc networks | |
| US11495064B2 (en) | Value-anticipating cooperative perception with an intelligent transportation system station | |
| CN108280991B (en) | Vehicle traffic accident prediction method based on in-vehicle short-range communication network | |
| CN105810013A (en) | Vehicle group risk-based vehicle collision-prevention control method and device | |
| CN106251666A (en) | Under the foggy environment of intelligent network connection automobile, expressway safety speed guides system and method | |
| CN105719510B (en) | Road traffic accident chain blocks the efficiency rating method of system under car networking environment | |
| CN108269395A (en) | Suitable for vehicle-mounted short distance communication network traffic congestion prediction and processing method | |
| CN105046983A (en) | Traffic flow prediction system and method based on vehicle-road cooperation | |
| Kaul et al. | Vanet‐TSMA: A traffic safety management approach for smart road transportation in vehicular ad hoc networks | |
| CN109067857A (en) | A kind of car networking big data analysis intelligent optimization algorithm | |
| CN103824456B (en) | A kind of vehicle mounted sensor network real-time road event recommendation method | |
| CN111081030A (en) | Method and system for judging traffic jam on expressway | |
| CN108305505A (en) | A kind of pedestrian traffic accident method for early warning suitable for vehicle-mounted short distance communication network | |
| CN108275158A (en) | The driving behavior evaluating method of vehicle-mounted short haul connection net |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | Address after:322000 1st floor, 128 Gaotang Road, Suxi Town, Yiwu City, Jinhua City, Zhejiang Province Patentee after:Datang Gaohong information communication (Yiwu) Co.,Ltd. Address before:322002 no.968, Xuefeng West Road, Beiyuan street, Yiwu City, Jinhua City, Zhejiang Province Patentee before:DATANG GOHIGH INFORMATION AND COMMUNICATION RESEARCH INSTITUTE (YIWU) CO.,LTD. | |
| CP03 | Change of name, title or address | ||
| TR01 | Transfer of patent right | Effective date of registration:20211230 Address after:401331 10-04 10-5-01 10-5-02 10-06, No. 35, Jinghe Road, Huxi street, high tech Zone, Shapingba District, Chongqing Patentee after:Datang Gaohong Zhilian Technology (Chongqing) Co.,Ltd. Address before:322000 1st floor, 128 Gaotang Road, Suxi Town, Yiwu City, Jinhua City, Zhejiang Province Patentee before:Datang Gaohong information communication (Yiwu) Co.,Ltd. | |
| TR01 | Transfer of patent right |