CN109887283B - Road congestion prediction method, system and device based on checkpoint data - Google Patents
Road congestion prediction method, system and device based on checkpoint data Download PDFInfo
- Publication number
- CN109887283B CN109887283B CN201910171067.4A CN201910171067A CN109887283B CN 109887283 B CN109887283 B CN 109887283B CN 201910171067 A CN201910171067 A CN 201910171067A CN 109887283 B CN109887283 B CN 109887283B
- Authority
- CN
- China
- Prior art keywords
- road
- congestion
- sequence
- congestion prediction
- acquiring
- 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
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a road congestion prediction method, a system and a device based on checkpoint data, wherein the method comprises the following steps: acquiring dynamic characteristics of a road in the previous time period through the checkpoint data; and predicting the congestion level of the road in the next time period by combining the dynamic characteristics and a preset road congestion prediction model. According to the method, the dynamic characteristics of the road are obtained through the checkpoint data, and the congestion condition of the road in the next time period is predicted by combining the dynamic characteristics and the road congestion prediction model, so that the traffic congestion condition can be effectively and accurately predicted, and the problem of inaccurate prediction caused by artificial prediction is solved; the method can predict the traffic jam condition in a large-scale area, improves the prediction efficiency, provides the management efficiency of a traffic management department, shortens the travel time of the vehicle owner and reduces the travel cost, and can be widely applied to the technical field of intelligent transportation.
Description
Technical Field
The invention relates to the technical field of intelligent traffic, in particular to a road congestion prediction method, system and device based on checkpoint data.
Background
At present, the quantity of motor vehicles in cities is continuously increased, traffic pressure is sharply increased, traffic jam frequently occurs in partial areas, great challenges are brought to smooth operation guarantee of urban traffic, management problems of traffic related departments are aggravated, and inconvenience is brought to vehicle owners. In the prior art, congestion prediction given to the user is generally carried out by depending on subjective experience of people, the traffic congestion analysis result is inaccurate, congestion prediction analysis in a small area can be realized only, the traffic prediction efficiency is low, the trip time of the vehicle owner is prolonged, and the trip cost is high.
The noun explains:
bayonet: the system comprises a security check and monitoring bayonet arranged in a public security system and a monitoring system of a road traffic security bayonet, and is characterized in that advanced technologies such as photoelectricity, computer, image processing, mode recognition, WEB data access and the like are utilized to continuously record front characteristic images, vehicle panoramic images and road surface real-time video streams of each motor vehicle for monitoring a road surface all-weather in real time, a license plate recognition instrument carries out full-automatic recognition on vehicle numbers according to the picked images and can carry out dynamic vehicle control and violation alarm, and information of each monitoring point can be organically shared through a public security network.
Disclosure of Invention
In order to solve the above technical problems, an object of the present invention is to provide a prediction method, system and device capable of accurately predicting traffic congestion conditions in a large area.
The first technical scheme adopted by the invention is as follows:
a road congestion prediction method based on checkpoint data comprises the following steps:
acquiring dynamic characteristics of a road in the previous time period through the checkpoint data;
and predicting the congestion level of the road in the next time period by combining the dynamic characteristics and a preset road congestion prediction model.
Further, the method also comprises a step of establishing a road congestion prediction model, wherein the step of establishing the road congestion prediction model specifically comprises the following steps:
acquiring gate data of a road, and acquiring vehicle information of a plurality of time periods according to the gate data;
acquiring a dynamic characteristic sequence of a road according to vehicle information, and acquiring a static characteristic sequence of the road according to a preset mode;
acquiring a time congestion sequence of a road by combining the dynamic characteristic sequence, the static characteristic sequence and a preset congestion level marking mode;
and establishing a road congestion prediction model by combining the time congestion sequence and a preset algorithm.
Further, the vehicle information includes large vehicle information and small vehicle information, and the step of obtaining the dynamic characteristic sequence of the road according to the vehicle information specifically includes the following steps:
calculating a first vehicle flow and a first average vehicle speed of each time period according to the vehicle information;
calculating a second vehicle flow rate and a second average vehicle speed of the large-sized vehicle for each time zone based on the large-sized vehicle information, and calculating a third vehicle flow rate and a third average vehicle speed of the small-sized vehicle for each time zone based on the small-sized vehicle information;
and combining the first vehicle flow, the first average vehicle speed, the second vehicle flow, the second average vehicle speed, the third vehicle flow and the third average vehicle speed of each hour to obtain a dynamic characteristic sequence of the road.
Further, the step of obtaining the static feature sequence of each road according to a preset mode specifically includes:
and acquiring attribute information of the road, and acquiring a road static characteristic sequence by combining the attribute information and a preset quantization standard.
Further, the step of acquiring the time congestion sequence of the road by combining the dynamic feature sequence, the static feature sequence and a preset congestion level marking mode specifically comprises the following steps:
combining the dynamic characteristic sequence and the static characteristic sequence and carrying out normalization processing to obtain a characteristic set of each time period;
and marking each feature set according to a preset congestion level marking mode to obtain a time congestion sequence.
Further, the preset algorithm is a recurrent neural network algorithm, and the step of establishing the road congestion prediction model by combining the time congestion sequence and the preset algorithm specifically comprises the following steps:
training a road congestion prediction model by combining a time congestion sequence and a recurrent neural network algorithm to obtain an initial road congestion prediction model;
and optimizing the initial road congestion prediction model by adopting a cross training method to obtain a final road congestion prediction model.
Further, the initial road congestion prediction model specifically includes:
At＝φ(S*WF+At-1*WA+b)
wherein, A istRepresenting the dynamic feature of the next time period, the phi () representing a neuron function, the S representing a static feature, the At-1Representing the dynamic characteristic of the previous time period, wherein WF represents the weight occupied by the road static characteristic in the neuron function, WA represents the weight occupied by the road dynamic characteristic in the neuron function, and b represents the bias term constant.
The second technical scheme adopted by the invention is as follows:
a road congestion prediction system based on checkpoint data, comprising:
the acquisition characteristic module is used for acquiring the dynamic characteristics of the road in the previous time period through the checkpoint data;
and the congestion prediction module is used for predicting the congestion level of the road in the next time period by combining the dynamic characteristics and a preset road congestion prediction model.
The system further comprises a model building module, wherein the model building module comprises an information obtaining unit, a feature obtaining unit, a congestion marking unit and a modeling unit;
the information acquisition unit is used for acquiring the gate data of the road and acquiring the vehicle information of a plurality of time periods according to the gate data;
the characteristic acquisition unit is used for acquiring a dynamic characteristic sequence of a road according to vehicle information and acquiring a static characteristic sequence of the road according to a preset mode;
the congestion marking unit is used for acquiring a time congestion sequence of the road by combining the dynamic characteristic sequence, the static characteristic sequence and a preset congestion level marking mode;
the modeling unit is used for establishing a road congestion prediction model by combining a time congestion sequence and a preset algorithm.
The third technical scheme adopted by the invention is as follows:
a road congestion prediction device based on checkpoint data comprises:
at least one processor;
at least one memory for storing at least one program;
when the at least one program is executed by the at least one processor, the at least one processor may implement a road congestion prediction method based on bayonet data as described above.
The invention has the beneficial effects that: according to the method, the dynamic characteristics of the road are obtained through the checkpoint data, and the congestion condition of the road in the next time period is predicted by combining the dynamic characteristics and the road congestion prediction model, so that the traffic congestion condition can be effectively and accurately predicted, and the problem of inaccurate prediction caused by artificial prediction is solved; the invention can predict the traffic jam condition in a large area, improves the prediction efficiency, provides the management efficiency of a traffic management department, shortens the travel time of the vehicle owner and reduces the travel cost.
Drawings
FIG. 1 is a flowchart illustrating steps of a road congestion prediction method based on checkpoint data according to the present invention;
fig. 2 is a block diagram of a road congestion prediction system based on checkpoint data according to the present invention.
Detailed Description
Example one
As shown in fig. 1, the present embodiment provides a road congestion prediction method based on checkpoint data, including the following steps
And S1, acquiring the dynamic characteristics of the road in the previous time period through the bayonet data.
And S2, predicting the congestion level of the road in the next time period by combining the dynamic characteristics and the preset road congestion prediction model.
The license plate number, the license plate type and the vehicle speed of passing vehicles can be obtained through the gate, the dynamic characteristics of the road comprise the characteristics of the traffic flow, the vehicle speed and the like, after the dynamic characteristics of the previous time period are obtained, the dynamic characteristics are input into a road congestion prediction model to predict the characteristics of the traffic flow, the vehicle speed and the like of the next time period, and the congestion condition is predicted. The last time period and the next time period are two continuous time periods, and the time period is selected according to the actual situation; for example: the previous time period may be a previous hour, and the next time period may be a next hour, for example, if the previous time period is 7 am, the next time period is 8 am; or the last time period is 7 o 'clock, and the next time period is 7 o' clock. The traffic jam condition is predicted by combining the dynamic characteristics and the preset model, and the jam condition of the next time slot can be predicted more accurately due to the combination of more effective road parameter information. In addition, because more bayonets are arranged in the city, the traffic condition can be predicted in a large-scale area according to the information of the bayonets, the prediction efficiency is improved, and the traffic management department can be more effectively helped to manage roads and improve the travel efficiency of car owners.
A road congestion prediction model is established through steps A1-A4:
a1, obtaining gate data of a road, and obtaining vehicle information of a plurality of time periods according to the gate data; the vehicle information includes large vehicle information and small vehicle information
A2, acquiring a dynamic characteristic sequence of a road according to vehicle information, and acquiring a static characteristic sequence of the road according to a preset mode;
a3, acquiring a time congestion sequence of a road by combining the dynamic characteristic sequence, the static characteristic sequence and a preset congestion level marking mode;
and A4, establishing a road congestion prediction model by combining the time congestion sequence and a preset algorithm.
When the model is established, the acquired data is used as a training set to train the model, the bayonet data of a period of time is acquired, the bayonet data is divided and extracted, and vehicle information of a plurality of time periods is acquired, for example, the bayonet data of one day is acquired, the day is divided into 24 hours, and the vehicle information of each day is extracted respectively. Acquiring a dynamic characteristic sequence and dynamic characteristics of different time periods according to the vehicle information; the method comprises the steps of obtaining a static characteristic sequence of a road according to a preset mode, such as a width parameter of the road or a grade parameter of the road, and obtaining whether public place buildings, such as schools, markets, hospitals and the like, exist in road accessories. And combining the dynamic characteristic sequence and the static characteristic sequence in the time period, marking the congestion level on the combined characteristic sequence, obtaining a time congestion sequence on the time sequence, and training by combining the time congestion sequence and a preset algorithm to obtain a road congestion prediction model. After the road congestion prediction model is established, the road congestion condition in the next time period can be predicted only by inputting the dynamic characteristics of the previous time period into the road congestion prediction model.
Specifically, the step of acquiring the dynamic characteristic sequence of the road according to the vehicle information in the step a2 includes steps B1 to B3:
b1, calculating a first vehicle flow and a first average vehicle speed of each time period according to the vehicle information;
b2, calculating a second flow rate and a second average vehicle speed of the large-sized vehicle in each time period according to the large-sized vehicle information, and calculating a third flow rate and a third average vehicle speed of the small-sized vehicle in each time period according to the small-sized vehicle information;
and B3, combining the first vehicle flow, the first average vehicle speed, the second vehicle flow, the second average vehicle speed, the third vehicle flow and the third average vehicle speed of each hour to obtain a dynamic characteristic sequence of the road.
The gate can extract the number of the passing vehicle license plate, the type of the license plate and the record of the speed of the passing vehicle. The vehicle can be judged to be a large vehicle or a small vehicle according to the type of the license plate. The number of vehicles passing through the road recorded by the bayonet in the past hour is the traffic flow of the road. And dividing the sum of the speeds of all vehicles passing the gate by the corresponding number of the vehicles passing the gate to obtain the average vehicle speed of the corresponding group. Specifically in the present embodiment, the day is divided into 24 hours, and the average vehicle speed V of all vehicles on the road of the road in each hour is extractedtWhere t represents a time period, and then the average vehicle speed Vb of the large-sized vehicle is extracted separatelytAnd average vehicle speed Vs of small-sized vehiclet(ii) a Dividing a day into 24 hours, and extracting the traffic flow Q of the road in each hourtWhere t represents a time period, and then the traffic flow rate Qb of the large-sized vehicle is extracted separatelytAnd the traffic flow rate Qs of small-sized vehiclest(ii) a Finally, the dynamic characteristic A of the vehicle at the moment t is obtainedt＝{Vt,Vbt,Vst,Qt,Qbt,Qst}。
The step of obtaining the static feature sequence of each road according to the preset mode in step a2 specifically includes: and acquiring attribute information of the road, and acquiring a road static characteristic sequence by combining the attribute information and a preset quantization standard.
In the present embodiment, the static feature of the road is S { S1, S2., sn }, where n represents the number of static feature dimensions of the road, for example, if the road is a dual lane, then the dual lane feature S1 ═ 2, and the other lanes record corresponding values; if a hospital is near the road, the road facility characteristic s2 is 1, or if a school is near the road, the road facility characteristic s2 is 2, and the working time period of the school can be correspondingly recorded; and by analogy, all static characteristics of the road are obtained. And confirming the dimension quantity and the quantization standard of the road static features to be used, and extracting the road static features S according to the standard.
Wherein, the step A3 specifically comprises the steps A31-A32:
and A31, combining the dynamic characteristic sequence and the static characteristic sequence and carrying out normalization processing to obtain a characteristic set of each time segment.
A32, marking each feature set according to a preset congestion level marking mode, and then obtaining a time congestion sequence.
Combining the dynamic characteristic sequence and the static characteristic sequence, and obtaining a characteristic set of each time period after normalization processing, specifically, in this example, the characteristic F of the road at the time ttFrom a dynamic signature sequence At＝{Vt，Vbt，Vst，Qt，Qbt，QstF, and the road static signature sequence S ═ S1, S2t＝{Vt，Vbt，Vst，Qt，Qbt，QstS1, s 2.., sn }, for feature set Ft＝{Vt，Vbt，Vst，Qt，Qbt，QstS1, s 2.., sn }, performing normalization processing, removing the features with the feature value of 0, and marking the feature sequence to obtain a normalized feature set; for the road characteristics Ft of each moment, matching a corresponding congestion condition evaluation grade ytAnd finally obtaining the time congestion sequence.
The algorithm preset in the step A4 is a recurrent neural network algorithm, and the step A4 comprises the steps A41-A42:
a41, training the road congestion prediction model by combining the time congestion sequence and the recurrent neural network algorithm, and then obtaining the initial road congestion prediction model.
And A42, optimizing the initial road congestion prediction model by adopting a cross training method to obtain a final road congestion prediction model.
Will the road characteristic Ft＝{Vt，Vbt，Vst，Qt，Qbt，QstS1, s 2.., sn } and the corresponding congestion level ytInputting the synthesized time congestion sequence into a recurrent neural network model M for training, wherein the training mode is yt＝M(Ft-1) And finally, optimal model parameters are obtained through cross training, so that the model M (F) has the highest precision aiming at sample classification, and higher prediction precision is obtained.
Specifically, at time t, the road characteristic is Ft＝{Vt，Vbt，Vst，Qt，Qbt，QstS1, s 2.., sn }, wherein the dynamic characteristic is at＝{Vt，Vbt，Vst，Qt，Qbt，QstThe static signature is S ═ S1, S2.., sn }, and the output of a recurrent neuron in a Recurrent Neural Network (RNN) for an instance is:
At＝φ(S*WF+At-1*WA+b)
wherein, A istRepresenting the dynamic feature of the next time period, the phi () representing a neuron function, the S representing a static feature, the At-1Representing the dynamic characteristic of the previous time period, wherein WF represents the weight occupied by the road static characteristic in the neuron function, WA represents the weight occupied by the road dynamic characteristic in the neuron function, and b represents the bias term constant. By calculating the correlation between the road traffic flow and the average speed at the previous moment and the road characteristics to the road traffic flow and the average speed at the next moment, the trained neural network can calculate the road traffic flow and the average speed at the next moment so as to predict the congestion level of the road.
In summary, the road congestion prediction method based on the checkpoint data has the following beneficial effects:
(1) the dynamic characteristics and the static characteristics of the road are obtained through the checkpoint data, and the congestion situation of the road in the next time period is predicted by combining the road congestion prediction model, so that the traffic congestion situation can be effectively and accurately predicted, and the problem of inaccurate prediction caused by artificial prediction is solved; the invention can predict the traffic jam condition in a large area, improves the prediction efficiency, provides the management efficiency of a traffic management department, shortens the travel time of the vehicle owner and reduces the travel cost.
(2) The method comprises the steps of extracting road characteristics in a multi-dimensional mode, refining and extracting static characteristics (including dimensions such as lanes of roads, facilities near the roads, levels of the roads and whether the roads belong to bridges) and dynamic characteristics (traffic flow and average speed of different roads in different periods of the same day), carrying out sample cross training on training sample data, eliminating the problem of fitting, improving the accuracy of a classifier, and greatly improving the accuracy of prediction.
(3) The road traffic jam prediction model has strong expansibility, more dimensional characteristic data are added along with more comprehensive acquired roads, and the road coverage rate of the bayonet is expanded, so that the accuracy rate of the jam prediction model can be further improved.
Example two
As shown in fig. 2, the present embodiment provides a road congestion prediction system based on bayonet data, including:
the acquisition characteristic module is used for acquiring the dynamic characteristics of the road in the previous time period through the checkpoint data;
and the congestion prediction module is used for predicting the congestion level of the road in the next time period by combining the dynamic characteristics and a preset road congestion prediction model.
Further as a preferred embodiment, the system further comprises a model establishing module, wherein the model establishing module comprises an information acquiring unit, a feature acquiring unit, a congestion marking unit and a modeling unit;
the information acquisition unit is used for acquiring the gate data of the road and acquiring the vehicle information of a plurality of time periods according to the gate data;
the characteristic acquisition unit is used for acquiring a dynamic characteristic sequence of a road according to vehicle information and acquiring a static characteristic sequence of the road according to a preset mode;
the congestion marking unit is used for acquiring a time congestion sequence of the road by combining the dynamic characteristic sequence, the static characteristic sequence and a preset congestion level marking mode;
the modeling unit is used for establishing a road congestion prediction model by combining a time congestion sequence and a preset algorithm.
According to the system, the dynamic characteristics and the static characteristics of the road are obtained through the checkpoint data, and the congestion condition of the road in the next time period is predicted by combining the road congestion prediction model, so that the traffic congestion condition can be effectively and accurately predicted, and the problem of inaccurate prediction caused by artificial prediction is solved; the invention can predict the traffic jam condition in a large area, improves the prediction efficiency, provides the management efficiency of a traffic management department, shortens the travel time of the vehicle owner and reduces the travel cost.
EXAMPLE III
The present embodiment provides a road congestion prediction apparatus based on checkpoint data, including:
at least one processor;
at least one memory for storing at least one program;
when the at least one program is executed by the at least one processor, the at least one processor may implement a road congestion prediction method based on checkpoint data according to an embodiment.
The road congestion prediction device based on the checkpoint data can execute the road congestion prediction method based on the checkpoint data provided by the embodiment of the method, can execute any combination of the implementation steps of the embodiment of the method, and has corresponding functions and beneficial effects of the method.
While the preferred embodiments of the present invention have been illustrated and described, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (6)
1. A road congestion prediction method based on checkpoint data is characterized by comprising the following steps:
acquiring dynamic characteristics of a road in the previous time period through the checkpoint data;
predicting the congestion level of the road in the next time period by combining the dynamic characteristics and a preset road congestion prediction model;
the method further comprises the step of establishing a road congestion prediction model, wherein the step of establishing the road congestion prediction model specifically comprises the following steps:
acquiring gate data of a road, and acquiring vehicle information of a plurality of time periods according to the gate data;
acquiring a dynamic characteristic sequence of a road according to vehicle information, and acquiring a static characteristic sequence of the road according to a preset mode;
acquiring a time congestion sequence of a road by combining the dynamic characteristic sequence, the static characteristic sequence and a preset congestion level marking mode;
establishing a road congestion prediction model by combining a time congestion sequence and a preset algorithm;
the dynamic characteristics comprise traffic flow and vehicle speed;
the preset algorithm is a recurrent neural network algorithm, and the step of establishing the road congestion prediction model by combining the time congestion sequence and the preset algorithm specifically comprises the following steps:
training a road congestion prediction model by combining a time congestion sequence and a recurrent neural network algorithm to obtain an initial road congestion prediction model;
optimizing the initial road congestion prediction model by adopting a cross training method to obtain a final road congestion prediction model;
the initial road congestion prediction model specifically comprises the following steps:
At＝φ(S*WF+At-1*WA+b)
wherein, A istRepresenting the dynamic feature of the next time period, the phi () representing a neuron function, the S representing a static feature, the At-1Representing the dynamic characteristic of the previous time period, wherein WF represents the weight occupied by the road static characteristic in the neuron function, WA represents the weight occupied by the road dynamic characteristic in the neuron function, and b represents the bias term constant.
2. The road congestion prediction method based on checkpoint data as claimed in claim 1, wherein the vehicle information includes large vehicle information and small vehicle information, and the step of obtaining the dynamic feature sequence of the road according to the vehicle information specifically includes the following steps:
calculating a first vehicle flow and a first average vehicle speed of each time period according to the vehicle information;
calculating a second vehicle flow rate and a second average vehicle speed of the large-sized vehicle for each time zone based on the large-sized vehicle information, and calculating a third vehicle flow rate and a third average vehicle speed of the small-sized vehicle for each time zone based on the small-sized vehicle information;
and combining the first vehicle flow, the first average vehicle speed, the second vehicle flow, the second average vehicle speed, the third vehicle flow and the third average vehicle speed of each hour to obtain a dynamic characteristic sequence of the road.
3. The road congestion prediction method based on checkpoint data as claimed in claim 2, wherein the step of obtaining the static feature sequence of each road according to a preset mode specifically comprises:
and acquiring attribute information of the road, and acquiring a road static characteristic sequence by combining the attribute information and a preset quantization standard.
4. The road congestion prediction method based on checkpoint data as claimed in claim 3, wherein the step of obtaining the time congestion sequence of the road by combining the dynamic feature sequence, the static feature sequence and a preset congestion level marking mode specifically comprises the following steps:
combining the dynamic characteristic sequence and the static characteristic sequence and carrying out normalization processing to obtain a characteristic set of each time period;
and marking each feature set according to a preset congestion level marking mode to obtain a time congestion sequence.
5. A road congestion prediction system based on checkpoint data, comprising:
the acquisition characteristic module is used for acquiring the dynamic characteristics of the road in the previous time period through the checkpoint data;
the congestion prediction module is used for predicting the congestion level of the road in the next time period by combining the dynamic characteristics and a preset road congestion prediction model;
the system also comprises a model establishing module, wherein the model establishing module comprises an information acquiring unit, a characteristic acquiring unit, a congestion marking unit and a modeling unit;
the information acquisition unit is used for acquiring the gate data of the road and acquiring the vehicle information of a plurality of time periods according to the gate data;
the characteristic acquisition unit is used for acquiring a dynamic characteristic sequence of a road according to vehicle information and acquiring a static characteristic sequence of the road according to a preset mode;
the congestion marking unit is used for acquiring a time congestion sequence of the road by combining the dynamic characteristic sequence, the static characteristic sequence and a preset congestion level marking mode;
the modeling unit is used for establishing a road congestion prediction model by combining a time congestion sequence and a preset algorithm;
the dynamic characteristics comprise traffic flow and vehicle speed;
the preset algorithm is a recurrent neural network algorithm, and the step of establishing the road congestion prediction model by combining the time congestion sequence and the preset algorithm specifically comprises the following steps:
training a road congestion prediction model by combining a time congestion sequence and a recurrent neural network algorithm to obtain an initial road congestion prediction model;
optimizing the initial road congestion prediction model by adopting a cross training method to obtain a final road congestion prediction model;
the initial road congestion prediction model specifically comprises the following steps:
At＝φ(S*WF+At-1*WA+b)
wherein, A istRepresenting the dynamic feature of the next time period, the phi () representing a neuron function, the S representing a static feature, the At-1Representing the dynamic characteristics of the last time period, wherein the WF represents the occupation of the road static characteristics in the neuron functionsRepresents the weight of the road dynamic characteristic in the neuron function, and b represents the bias term constant.
6. A road congestion prediction device based on checkpoint data, comprising:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, the at least one program causes the at least one processor to implement a method for road congestion prediction based on bayonet data according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910171067.4A CN109887283B (en) | 2019-03-07 | 2019-03-07 | Road congestion prediction method, system and device based on checkpoint data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910171067.4A CN109887283B (en) | 2019-03-07 | 2019-03-07 | Road congestion prediction method, system and device based on checkpoint data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109887283A CN109887283A (en) | 2019-06-14 |
| CN109887283B true CN109887283B (en) | 2021-01-26 |
Family
ID=66931226
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910171067.4A Active CN109887283B (en) | 2019-03-07 | 2019-03-07 | Road congestion prediction method, system and device based on checkpoint data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109887283B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110428612B (en) * | 2019-07-05 | 2021-04-13 | 平安国际智慧城市科技股份有限公司 | Vehicle management and control method and device, computer equipment and storage medium |
| CN110335466B (en) * | 2019-07-11 | 2021-01-26 | 青岛海信网络科技股份有限公司 | Traffic flow prediction method and apparatus |
| CN111341098B (en) * | 2020-02-18 | 2021-07-27 | 北京中旖新能源有限公司 | Congestion state prediction method and device |
| CN111341099B (en) * | 2020-02-27 | 2022-05-10 | 阿里巴巴集团控股有限公司 | Data processing method and device and electronic equipment |
| CN111402579A (en) * | 2020-02-29 | 2020-07-10 | 深圳壹账通智能科技有限公司 | Road congestion degree prediction method, electronic device and readable storage medium |
| CN111798579B (en) * | 2020-07-29 | 2021-07-23 | 贵州汇联通电子商务服务有限公司 | ETC portal frame-based highway congestion prediction method and system |
| CN112633602B (en) * | 2020-12-31 | 2023-03-03 | 深圳云天励飞技术股份有限公司 | Traffic congestion index prediction method and device based on GIS map information |
| CN113535819B (en) * | 2021-07-15 | 2023-02-28 | 广州交信投科技股份有限公司 | Traffic situation perception analysis method and device, computer storage medium and terminal |
| CN113610304A (en) * | 2021-08-11 | 2021-11-05 | 北京京东乾石科技有限公司 | Congestion prediction method, device, equipment and storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107038478B (en) * | 2017-04-20 | 2023-10-27 | 百度在线网络技术（北京）有限公司 | Road condition prediction method and device, computer equipment and readable medium |
| CN107085941B (en) * | 2017-06-26 | 2021-01-26 | 广东工业大学 | Traffic flow prediction method, device and system |
| CN107240254B (en) * | 2017-08-02 | 2019-08-13 | 河北冀通慧达科技有限公司 | Traffic prediction technique and terminal device |
| CN108269401B (en) * | 2018-01-30 | 2021-02-23 | 银江股份有限公司 | Data-driven viaduct traffic jam prediction method |
| CN108335485B (en) * | 2018-01-31 | 2020-04-24 | 杭州远眺科技有限公司 | License plate recognition data-based method for predicting dynamic simulation congestion of traffic at major incident |
-
2019
- 2019-03-07 CN CN201910171067.4A patent/CN109887283B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109887283A (en) | 2019-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109887283B (en) | Road congestion prediction method, system and device based on checkpoint data | |
| CN111368687B (en) | Sidewalk vehicle illegal parking detection method based on target detection and semantic segmentation | |
| Cai et al. | Deep learning-based video system for accurate and real-time parking measurement | |
| CN110364008B (en) | Road condition determining method and device, computer equipment and storage medium | |
| CN109325502B (en) | Shared bicycle parking detection method and system based on video progressive region extraction | |
| CN110188807A (en) | Tunnel pedestrian target detection method based on cascade super-resolution network and improvement Faster R-CNN | |
| Atkočiūnas et al. | Image processing in road traffic analysis | |
| CN105513354A (en) | Video-based urban road traffic jam detecting system | |
| CN114170580A (en) | Highway-oriented abnormal event detection method | |
| CN113160575A (en) | Traffic violation detection method and system for non-motor vehicles and drivers | |
| Rabbouch et al. | A vision-based statistical methodology for automatically modeling continuous urban traffic flows | |
| Ketcham et al. | Recognizing the Illegal Parking Patterns of Cars on the Road in Front of the Bus Stop Using the Support Vector Machine | |
| Singh et al. | Intelligent traffic management system | |
| CN112562315B (en) | Method, terminal and storage medium for acquiring traffic flow information | |
| CN115440071B (en) | Automatic driving illegal parking detection method | |
| CN110765900A (en) | DSSD-based automatic illegal building detection method and system | |
| Zhang et al. | Machine learning and computer vision-enabled traffic sensing data analysis and quality enhancement | |
| Parsola et al. | Automated system for road extraction and traffic volume estimation for traffic jam detection | |
| Crawford et al. | Analysing spatial intrapersonal variability of road users using point-to-point sensor data | |
| CN115187886A (en) | Vehicle violation detection method and device and electronic equipment | |
| Khalid et al. | An Android Application for Unwanted Vehicle Detection and Counting | |
| CN111309954B (en) | Scenic spot shopping guide behavior identification system | |
| Muâ et al. | Classifying Vehicle Types from Video Streams for Traffic Flow Analysis Systems | |
| Kansal et al. | Real time system for vehicle counting with speed estimation and license plate detection | |
| Talib et al. | A robust approach for road users classification using the motion cues |
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 |