CN115909747B - Urban traffic early warning system - Google Patents
Urban traffic early warning system Download PDFInfo
- Publication number
- CN115909747B CN115909747B CN202310016456.6A CN202310016456A CN115909747B CN 115909747 B CN115909747 B CN 115909747B CN 202310016456 A CN202310016456 A CN 202310016456A CN 115909747 B CN115909747 B CN 115909747B
- Authority
- CN
- China
- Prior art keywords
- matrix
- sub
- road
- column
- driver
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000011159 matrix material Substances 0.000 claims abstract description 107
- 238000000034 method Methods 0.000 claims abstract description 41
- 206010039203 Road traffic accident Diseases 0.000 claims description 50
- 230000007704 transition Effects 0.000 claims description 22
- 238000004364 calculation method Methods 0.000 claims description 18
- 238000012546 transfer Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 244000144972 livestock Species 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention belongs to the technical field of traffic control, and particularly relates to an urban traffic early warning system. The system comprises: the regional division unit is configured to input a target city map, uniformly divide the target city region to obtain a plurality of subareas, and the size of each subarea is recorded as N.M, N is not equal to M, M is recorded as a row, and N is recorded as a column; the time matrix generation unit is configured to set a time period T, uniformly divide the time period T into M parts and obtain M sub-times; and allocating the M sub-times and each sub-region with the size of N by M according to the distribution, so that each column in each sub-region corresponds to one sub-time M. According to the invention, after the target city map is divided, a time matrix is formed by setting a time, and then, based on all data in each subarea, which can influence traffic safety, the comprehensive early warning of road traffic is realized, and the method has the advantages of high early warning accuracy and high reliability.
Description
Technical Field
The invention belongs to the technical field of traffic control, and particularly relates to an urban traffic early warning system.
Background
Urban traffic refers to public travel and passenger and cargo transportation between urban (including urban and suburban) road (ground, underground, overhead, waterway, cableway, etc.) systems. Before a human takes a vehicle as a transportation means, the urban public walks to take the main action of walking, or takes the steps of riding livestock, riding a car and the like instead of walking. The goods are transferred by shoulder picking or transported by a simple transport means.
However, urban traffic is developed to the current stage, and safety becomes the most important problem. The lack of urban infrastructure, the shallow level of driver traffic safety awareness, and the irrational traffic control strategies have led to a continual rise in the incidence of traffic accidents. The current traffic safety early warning system mainly takes measures to regulate and control when people or vehicles in traffic environment are in dangerous states. For example, when the conditions of poor physical and psychological states, poor road weather conditions, poor vehicle conditions, poor road surface conditions and the like of a driver occur, the driver is changed into a safe situation through monitoring, or losses are reduced through monitoring and foreknowledge in advance, and traffic accidents are avoided.
Patent document CN201610815465.1A discloses a road traffic classification early warning method based on dynamic traffic information. The method comprises the following steps: obtaining the average speed of a road section; fusing average speeds of road sections; according to the time stamp of the sampling period, the average speeds of the road sections after fusion are numbered, sequenced and stored; predicting the average speed of the road section of the next sampling period based on the time sequence; and obtaining the road section traffic congestion index of the next sampling period, and realizing traffic operation grading early warning. Although the invention realizes the graded early warning of road traffic in the aspect of road congestion, the accuracy of the early warning method is lower because other factors which can influence the road traffic safety are not considered and because of the complexity of road congestion.
Disclosure of Invention
The invention mainly aims to provide an urban traffic early warning system, which is characterized in that after a target urban map is divided, a time matrix is formed by setting a time, and the early warning of road traffic is realized based on data which can influence traffic safety in each subarea by taking into consideration, and has the advantages of high early warning accuracy and high reliability.
In order to achieve the above purpose, the technical scheme of the invention is realized as follows:
an urban traffic early warning system, the system comprising: the regional division unit is configured to input a target city map, uniformly divide the target city region to obtain a plurality of subareas, and the size of each subarea is recorded as N.M, N is not equal to M, M is recorded as a row, and N is recorded as a column; the time matrix generation unit is configured to set a time period T, uniformly divide the time period T into M parts and obtain M sub-times; distributing M sub-times and each sub-region with the size of N x M according to the distribution, so that each column in each sub-region corresponds to one sub-time M, and simultaneously, obtaining a time matrix R of each sub-region; the sub-area road quality calculation unit is configured to obtain corresponding vehicle flow, congestion road section length, lane number and road length in each column of each sub-area based on a time matrix R of the sub-area, calculate and obtain a road quality index matrix L of each sub-area, wherein each road quality index matrix comprises N road quality indexes; the driving vehicle safety coefficient calculation unit is configured to obtain a driving data information set Y of a driver in each vehicle in each sub-area, each vehicle in each sub-area corresponds to one driving data information set Y, the driving data information set Y is substituted into a preset driving vehicle safety calculation model to obtain a driving safety coefficient D, and all driving safety coefficients are combined into a driving safety coefficient matrix D; the accident prediction unit is configured to acquire basic data and traffic accident data of each column in each sub-area, generate a model based on a preset traffic accident matrix, and generate a traffic accident matrix A of each sub-area; the early warning unit is configured to output probability according to the traffic accident matrix A, the driving safety coefficient matrix D, the road quality index matrix L and the time matrix R of the subareas respectively based on the Markov transfer chain so as to represent the danger coefficient of each subarea and perform traffic early warning based on the danger coefficient.
Further, the sub-area road quality calculation unit obtains the vehicle flow, the congestion road section length, the number of lanes and the road length of each sub-area based on the time matrix R of the sub-area, and calculates the road quality index of each sub-areaThe method of matrix L comprises: the road quality index for a column within each sub-region is calculated using the following formula:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>
For the road index, this value is determined by the length of the congested road segment in the road, +.>
For the traffic flow +.>
For the number of lanes>
For the length of the road->
Is the total road length of the sub-area; then, the road quality index of each column is in the order of each column in the time matrix R to generate a road quality index matrix L.
Further, the calculation formula of the road index is as follows:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>
For the length of the congested road segment in each column.
Further, the driving data information set at least includes the following data: driver driving age, driver violation coefficient, driver gender, and driver marital status.
Further, the driving vehicle safety factor calculating unit obtains a driving data information set Y of the driver in each vehicle of each column in each sub-area, and sets the driving data information setThe method for substituting Y into a preset driving vehicle safety calculation model to obtain the driving safety coefficient D comprises the following steps:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>
For the age of the driver,
for driving age of driver->
The violation coefficients are for the driver;
The value is 1.2 when the driver is married and 0.8 when the driver is not married;
For the sex of the driver, the value is 0.9 when the driver is female, and 1.1 when the driver is male.
Further, the base data includes: bayonet traffic, weather data, GPS speed data, rainfall and visibility; the traffic accident data includes: the occurrence rate and the number of traffic accidents.
Further, the accident prediction unit obtains basic data and traffic accident data of each column in each sub-area, and the method for generating the traffic accident matrix a of each sub-area based on the preset traffic accident matrix generation model comprises the following steps: the basic data coefficient of each column in the subarea is calculated based on the basic data of each column, the traffic accident coefficient of each column in the subarea is calculated based on the traffic accident number, the basic data coefficient of each column and the traffic accident coefficient are combined into a coefficient set, and then the coefficient set is formed into a matrix according to the position of each column in the subarea to serve as a traffic accident matrix A.
Further, the base data coefficients are calculated using the following formula:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>
For bayonet flow->
Is weather data->
For GPS speed data,/->
For rainfall, add->
Is visibility; the traffic accident coefficient is calculated using the following formula:
The method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>
Is traffic accident coefficient>
Is the incidence of traffic accident->
Is the number of times of traffic accidents.
Further, the early warning unit outputs the probability based on the markov transfer chain according to the traffic accident matrix a, the driving safety coefficient matrix D, the road quality index matrix L and the time matrix R of the subarea, respectively, and the method comprises: the traffic accident matrix A is regarded as a first state in a Markov chain, the driving safety coefficient matrix D is regarded as a second state in the Markov chain, the road quality index matrix L is regarded as a third state in the Markov chain, the time matrix R of the subarea is regarded as a fourth state in the Markov chain, a transition matrix is constructed, and the probability is output after the first state, the second state, the third state and the fourth state are substituted into the transition matrix of the Markov chain.
Further, the torque matrix of the markov chain is as follows:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein,,
for the transition probability value>
For transferring the matrix, the following constraints have to be satisfied:
。
The urban traffic early warning system has the following beneficial effects:
1. the reliability is high: the traffic early warning system has the advantages that the early warning result is obtained by integrating various factors which can influence the road traffic safety, and compared with the judgment of a single factor in the prior art, the result reliability is higher. In the process of integrating various factors, a process of probability generation based on a Markov chain is used, a corresponding matrix of each result is generated before each factor is imported into the Markov chain, and in the process of generating the matrix, specific algorithm processing is performed, so that each result can take comprehensive consideration, and the reliability of the final result is higher.
2. The accuracy is high: compared with the prior art, the traffic early warning system has higher accuracy, integrates various influencing factors, and uses a specific algorithm when processing the factors, so that the error of each result is smaller, and the accuracy is improved.
Drawings
FIG. 1 is a schematic diagram of a system architecture of an urban traffic early warning system according to an embodiment of the present invention;
fig. 2 is a schematic diagram of probability generation based on a markov chain of an urban traffic early warning system according to an embodiment of the present invention.
Detailed Description
The method of the present invention will be described in further detail with reference to the accompanying drawings.
Example 1
As shown in fig. 1, an urban traffic early warning system, the system comprising: the regional division unit is configured to input a target city map, uniformly divide the target city region to obtain a plurality of subareas, and the size of each subarea is recorded as N.M, N is not equal to M, M is recorded as a row, and N is recorded as a column; the time matrix generation unit is configured to set a time period T, uniformly divide the time period T into M parts and obtain M sub-times; distributing M sub-times and each sub-region with the size of N x M according to the distribution, so that each column in each sub-region corresponds to one sub-time M, and simultaneously, obtaining a time matrix R of each sub-region; the sub-area road quality calculation unit is configured to obtain corresponding vehicle flow, congestion road section length, lane number and road length in each column of each sub-area based on a time matrix R of the sub-area, calculate and obtain a road quality index matrix L of each sub-area, wherein each road quality index matrix comprises N road quality indexes; the driving vehicle safety coefficient calculation unit is configured to obtain a driving data information set Y of a driver in each vehicle in each sub-area, each vehicle in each sub-area corresponds to one driving data information set Y, the driving data information set Y is substituted into a preset driving vehicle safety calculation model to obtain a driving safety coefficient D, and all driving safety coefficients are combined into a driving safety coefficient matrix D; the accident prediction unit is configured to acquire basic data and traffic accident data of each column in each sub-area, generate a model based on a preset traffic accident matrix, and generate a traffic accident matrix A of each sub-area; the early warning unit is configured to output probability according to the traffic accident matrix A, the driving safety coefficient matrix D, the road quality index matrix L and the time matrix R of the subareas respectively based on the Markov transfer chain so as to represent the danger coefficient of each subarea and perform traffic early warning based on the danger coefficient.
Specifically, the time matrix R is obtained by uniformly dividing a time period T to obtain M sub-times, and then distributing the M sub-times in the sub-regions. In this case, the time period T has a start-stop time. Thus, in the sub-area, each sub-time is also a start-stop time. The sub-times are in existing order. This allows the arrangement in each sub-region to be in existing order.
In practice, the factors affecting road traffic safety, besides the factors of drivers and the road itself, also include the factors of weather and the factors of accidents of the road in the actual process.
Taking these factors into consideration, not only is proper processing means needed, but also the data needs to be processed to a certain extent, so that a relatively simple value is used for representing these factors to improve efficiency.
The city is divided into a plurality of sub-areas because if the city is uniformly processed, it is easy to process it because of the complexity of data.
Example 2
On the basis of the above embodiment, the method for obtaining the road quality index matrix L of each sub-area by the sub-area road quality calculation unit based on the time matrix R of the sub-area includes: the road quality index for a column within each sub-region is calculated using the following formula:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>
Is a road index, which is defined byLength determination of congested road segment in road, +.>
For the traffic flow +.>
For the number of lanes>
For the length of the road->
Is the total road length of the sub-area; then, the road quality index of each column is in the order of each column in the time matrix R to generate a road quality index matrix L.
Specifically, the multiplication of the traffic flow, the number of lanes and the length of the road is the total mileage of all vehicles in the road.
The amount of total mileage affects the road quality index. If the number of vehicles is large in a section of road, the total mileage of the road is large if the number of group roads is large. Under the condition of more total mileage of the road, the road is proved to contain more vehicles, the congestion probability is lower, and the road quality index is higher.
Example 3
On the basis of the above embodiment, the calculation formula of the road index is as follows:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>
For the length of the congested road segment in each column.
Specifically, the road index refers to the degree of congestion of a road. In practice, the more the road is congested, the lower the safety of the road will be.
Example 4
On the basis of the above embodiment, the driving vehicle safety factor calculation unit obtainsThe method for obtaining the driving safety coefficient D by substituting the driving data information set Y into a preset driving vehicle safety calculation model by taking the driving data information set Y of the driver in each row of each vehicle in each subarea comprises the following steps:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>
For the age of the driver,
for driving age of driver->
The violation coefficients are for the driver;
The value is 1.2 when the driver is married and 0.8 when the driver is not married;
For the sex of the driver, the value is 0.9 when the driver is female, and 1.1 when the driver is male.
In experiments, the marital status and sex of the driver will affect the driving safety. The marital status and sex of the driver are obtained by acquiring information that the driver fills in when obtaining the driver's license. The marital status and sex of the driver are both voluntarily provided by the driver.
Example 5
On the basis of the above embodiment, the basic data coefficient is calculated using the following formula:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>
For bayonet flow->
Is weather data->
For GPS speed data,/->
For rainfall, add->
Is visibility; the traffic accident coefficient is calculated using the following formula:
The method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>
Is traffic accident coefficient>
Is the incidence of traffic accident->
Is the number of times of traffic accidents.
Example 6
Referring to fig. 2, based on the above embodiment, the early warning unit outputs probabilities based on the markov transition chain according to the traffic accident matrix a, the driving safety coefficient matrix D, the road quality index matrix L and the time matrix R of the sub-region, respectively, and the method includes: the traffic accident matrix A is regarded as a first state in a Markov chain, the driving safety coefficient matrix D is regarded as a second state in the Markov chain, the road quality index matrix L is regarded as a third state in the Markov chain, the time matrix R of the subarea is regarded as a fourth state in the Markov chain, a transition matrix is constructed, and the probability is output after the first state, the second state, the third state and the fourth state are substituted into the transition matrix of the Markov chain.
Specifically, in the present invention, each element of the transition matrix is non-negative, and the sum of each row of elements is equal to 1, and each element is represented by probability, and is mutually transitioned under certain conditions, so that the transition matrix is called a transition probability matrix. As used in market decisions, the elements in the matrix are probabilities of market or customer retention, acquisition or loss. P (k) represents a k-step transition probability matrix.
When the total number of possible transition times of the state m in the sample is i and the state m is converted to the state ai from any time in the future, the transition probability of the state aj at any time in the future at the time of m+n is as follows:
。
these transition probabilities may be arranged into a transition probability matrix:
。
when m=1, a first-order transition probability matrix is used, when m >2, a high-order probability transition matrix is used, and the probability transition matrix is used, so that one-step and multi-step transition rules between states are obtained, wherein the rules are tables of evolution rules between loan states, and when an initial state is known, predictions in different periods can be made by looking up the tables.
Example 7
On the basis of the above embodiment, the torque matrix of the markov chain is:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>
For the transition probability value>
For transferring the matrix, the following constraints have to be satisfied:
。
While specific embodiments of the present invention have been described above, it will be understood by those skilled in the art that these specific embodiments are by way of example only, and that various omissions, substitutions, and changes in the form and details of the methods and systems described above may be made by those skilled in the art without departing from the spirit and scope of the invention. For example, it is within the scope of the present invention to combine the above-described method steps to perform substantially the same function in substantially the same way to achieve substantially the same result. Accordingly, the scope of the invention is limited only by the following claims.
Claims (8)
1. An urban traffic early warning system, the system comprising: the regional division unit is configured to input a target city map, uniformly divide the target city region to obtain a plurality of subareas, and the size of each subarea is recorded as N.M, N is not equal to M, M is recorded as a row, and N is recorded as a column; the time matrix generation unit is configured to set a time period T, uniformly divide the time period T into M parts and obtain M sub-times; distributing M sub-times and each sub-region with the size of N x M according to the distribution, so that each column in each sub-region corresponds to one sub-time M, and simultaneously, obtaining a time matrix R of each sub-region; the sub-area road quality calculation unit is configured to obtain corresponding vehicle flow, congestion road section length, lane number and road length in each column of each sub-area based on a time matrix R of the sub-area, calculate and obtain a road quality index matrix L of each sub-area, wherein each road quality index matrix comprises N road quality indexes; the driving vehicle safety coefficient calculation unit is configured to obtain a driving data information set Y of a driver in each vehicle in each sub-area, each vehicle in each sub-area corresponds to one driving data information set Y, the driving data information set Y is substituted into a preset driving vehicle safety calculation model to obtain a driving safety coefficient D, and all driving safety coefficients are combined into a driving safety coefficient matrix D; the accident prediction unit is configured to acquire basic data and traffic accident data of each column in each sub-area, generate a model based on a preset traffic accident matrix, and generate a traffic accident matrix A of each sub-area; the early warning unit is configured to output probability according to the traffic accident matrix A, the driving safety coefficient matrix D, the road quality index matrix L and the time matrix R of the subareas respectively based on the Markov transfer chain so as to represent the danger coefficient of each subarea and perform traffic early warning based on the danger coefficient;
the early warning unit is respectively based on a Markov transfer chain according to a traffic accident matrix A, a driving safety coefficient matrix D, a road quality index matrix L and a time matrix R of a subarea, and the method for outputting the probability comprises the following steps: the traffic accident matrix A is regarded as a first state in a Markov chain, the driving safety coefficient matrix D is regarded as a second state in the Markov chain, the road quality index matrix L is regarded as a third state in the Markov chain, the time matrix R of the subarea is regarded as a fourth state in the Markov chain, a transition matrix is constructed, and the first state, the second state, the third state and the fourth state are substituted into the transition matrix of the Markov chain, and then the probability is output;
the torque matrix of the Markov chain is as follows:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>
For the transition probability value>
For transferring the matrix, the following constraints have to be satisfied:
。
2. The system according to claim 1, wherein the sub-area road quality calculation unit obtains the vehicle flow, the congestion section length, the number of lanes of each sub-area based on the time matrix R of the sub-areaThe method for calculating the road quality index matrix L of each sub-area comprises the following steps: the road quality index for a column within each sub-region is calculated using the following formula:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>
For the road index, this value is determined by the length of the congested road segment in the road, +.>
For the traffic flow +.>
For the number of lanes>
For the length of the road->
Is the total road length of the sub-area; then, the road quality index of each column is in the order of each column in the time matrix R to generate a road quality index matrix L.
3. The system of claim 2, wherein the road index is calculated as follows:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>
For the length of the congested road segment in each column.
4. The system of claim 1, wherein the set of driving data information includes at least the following data: driver driving age, driver violation coefficient, driver gender, and driver marital status.
5. The system according to claim 4, wherein the driving vehicle safety factor calculating unit obtains a driving data information set Y of a driver in each vehicle of each column in each sub-area, and substitutes the driving data information set Y into a preset driving vehicle safety calculation model, and the method for obtaining the driving safety factor D includes:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>
For the age of the driver,
for driving age of driver->
The violation coefficients are for the driver;
The value is 1.2 when the driver is married and 0.8 when the driver is not married;
For the sex of the driver, the value is 0.9 when the driver is female, and 1.1 when the driver is male.
6. The system of claim 1, wherein the base data comprises: bayonet traffic, weather data, GPS speed data, rainfall and visibility; the traffic accident data includes: the occurrence rate and the number of traffic accidents.
7. The system of claim 6, wherein the accident prediction unit obtains basic data and traffic accident data of each column in each sub-area, and the method for generating the traffic accident matrix a of each sub-area based on the preset traffic accident matrix generation model comprises: the basic data coefficient of each column in the subarea is calculated based on the basic data of each column, the traffic accident coefficient of each column in the subarea is calculated based on the traffic accident number, the basic data coefficient of each column and the traffic accident coefficient are combined into a coefficient set, and then the coefficient set is formed into a matrix according to the position of each column in the subarea to serve as a traffic accident matrix A.
8. The system of claim 7, wherein the base data coefficients are calculated using the formula:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>
For bayonet flow->
Is weather data,
For GPS speed data,/->
For rainfall, add->
Is visibility; the traffic accident coefficient is calculated using the following formula:
The method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>
Is traffic accident coefficient>
Is the incidence of traffic accident->
Is the number of times of traffic accidents. />
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310016456.6A CN115909747B (en) | 2023-01-06 | 2023-01-06 | Urban traffic early warning system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310016456.6A CN115909747B (en) | 2023-01-06 | 2023-01-06 | Urban traffic early warning system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115909747A CN115909747A (en) | 2023-04-04 |
| CN115909747B true CN115909747B (en) | 2023-05-23 |
Family
ID=85769198
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310016456.6A Active CN115909747B (en) | 2023-01-06 | 2023-01-06 | Urban traffic early warning system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115909747B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109993983A (en) * | 2019-04-09 | 2019-07-09 | 西安交通大学 | One kind being based on the adaptive abductive approach of markovian intelligent traffic vehicle |
| DE102019209255A1 (en) * | 2019-06-26 | 2020-12-31 | Zf Friedrichshafen Ag | Determining a road condition |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102006060849A1 (en) * | 2006-12-22 | 2008-07-03 | Daimler Ag | Vehicle driver condition e.g. fatigue, determining method, involves developing probabilistic model representing cumulated probabilities, and determining condition as driver condition based on cumulated probabilities using model |
| US8965597B2 (en) * | 2013-02-26 | 2015-02-24 | Ford Global Technologies, Llc | Road grade auto-mapping |
| CN107862413A (en) * | 2017-11-16 | 2018-03-30 | 四维口袋科技（北京）有限公司 | Based on markovian Forecasting Methodology and device |
| US10169993B1 (en) * | 2018-01-11 | 2019-01-01 | Conduent Business Services, Llc | Forecasting with matrix powers |
| CN111242484B (en) * | 2020-01-14 | 2023-09-19 | 沈阳平通高新技术有限公司 | Vehicle risk comprehensive evaluation method based on transition probability |
| CN112949999A (en) * | 2021-02-04 | 2021-06-11 | 浙江工业大学 | High-speed traffic accident risk early warning method based on Bayesian deep learning |
| CN113763713B (en) * | 2021-11-10 | 2022-04-19 | 深圳市城市交通规划设计研究中心股份有限公司 | Road network bottleneck road section excavation and management method and device |
| CN115238958A (en) * | 2022-06-20 | 2022-10-25 | 清华大学 | Dangerous event chain extraction method and system based on complex traffic scene |
| CN115565368A (en) * | 2022-09-19 | 2023-01-03 | 浙江大学 | Urban traffic simulation-oriented traffic demand rapid estimation method |
-
2023
- 2023-01-06 CN CN202310016456.6A patent/CN115909747B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109993983A (en) * | 2019-04-09 | 2019-07-09 | 西安交通大学 | One kind being based on the adaptive abductive approach of markovian intelligent traffic vehicle |
| DE102019209255A1 (en) * | 2019-06-26 | 2020-12-31 | Zf Friedrichshafen Ag | Determining a road condition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115909747A (en) | 2023-04-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109670277B (en) | Travel time prediction method based on multi-mode data fusion and multi-model integration | |
| CN102737504B (en) | Method for estimating bus arrival time in real time based on drive characteristics | |
| CN102081859B (en) | Control method of bus arrival time prediction model | |
| CN107490384B (en) | Optimal static path selection method based on urban road network | |
| CN112927503B (en) | Method for coordinating and controlling main line speed limitation and ramp fusion of expressway in rainy days | |
| WO2016135561A1 (en) | Method and apparatus for determining a safest route within a transportation network | |
| CN111027430B (en) | Traffic scene complexity calculation method for intelligent evaluation of unmanned vehicles | |
| EP3895145B1 (en) | Method and system for vehicle routing on a road segment | |
| CN105427620B (en) | A kind of illegal operation vehicle identification method based on taxi service data | |
| CN113808401A (en) | Traffic congestion prediction method, device, equipment and storage medium | |
| CN116631211B (en) | Emergency vehicle road congestion evacuation system based on Internet of vehicles | |
| Choi et al. | Framework for connected and automated bus rapid transit with sectionalized speed guidance based on deep reinforcement learning: Field test in Sejong city | |
| CN115063978A (en) | Bus arrival time prediction method based on digital twins | |
| CN112249009A (en) | Vehicle speed control method, device and system and electronic equipment | |
| Manan et al. | Factors associated with red-light running among motorcyclists at signalised junctions in Malaysia | |
| Jamaludin et al. | Potential application of artificial neural network (ANN) analysis method on Malaysian road crash data | |
| Nigam et al. | An empirical study on parameters affecting traffic stream variables under rainy conditions | |
| Islam et al. | A hierarchical multinomial logit model to examine the effects of signal strategies on right-turn crash injury severity at signalised intersections | |
| CN115909747B (en) | Urban traffic early warning system | |
| CN105303246A (en) | Multiline arrival time prediction for public transportation | |
| Mahmassani et al. | Concept development and needs identification for Intelligent Network Flow Optimization (INFLO): assessment of relevant prior and ongoing research. | |
| CN106530689B (en) | A kind of real-time predictor method of bus arrival time based on genetic algorithm and running data | |
| Brunner et al. | Safety impacts of rising urban micromobility: statistical analysis of e-scooter use and risky rider behavior in Ingolstadt, Germany | |
| CN114822016B (en) | Road section uniform speed estimation system based on GPS data flow | |
| Lee et al. | Analysis of Relative Risk by Accident Types at Intersections, Crosswalk and Tunnel Sections |
Legal Events
| 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 |