CN111192456A - Road traffic operation situation multi-time scale prediction method - Google Patents
Road traffic operation situation multi-time scale prediction method Download PDFInfo
- Publication number
- CN111192456A CN111192456A CN202010035665.1A CN202010035665A CN111192456A CN 111192456 A CN111192456 A CN 111192456A CN 202010035665 A CN202010035665 A CN 202010035665A CN 111192456 A CN111192456 A CN 111192456A
- Authority
- CN
- China
- Prior art keywords
- data
- traffic
- unit
- classified
- traffic data
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0133—Traffic data processing for classifying traffic situation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a road traffic operation situation multi-time scale prediction method, which comprises the following steps: A. firstly, collecting traffic data of a plurality of roads through a traffic data collecting sensor, and preprocessing the traffic data through a data preprocessing unit; B. the preprocessed data are analyzed by the main control unit and then transmitted to the screening unit, and traffic information in an abnormal operation state is screened out; C. transmitting the screened data to a traffic data classification unit for data classification to obtain traffic data classified under a normal state; D. then sending the classified traffic data to an anomaly analysis unit for anomaly analysis, and predicting future traffic data through a deep learning algorithm; E. transmitting the predicted future goodness data to a social network through a data transmission unit for real-time sharing by a user; the prediction method adopted by the invention is simple to operate and high in precision, provides a quick response signal for relevant management departments, and provides a trip decision basis for residents.
Description
Technical Field
The invention relates to the technical field of traffic operation prediction, in particular to a multi-time scale prediction method for road traffic operation situation.
Background
The prediction of the road traffic operation situation is the basis for the intelligent traffic system to implement road traffic management and control. The accurate prediction of the road traffic operation situation can ensure the safe and smooth operation of the road traffic flow, help road traffic users reasonably plan a travel scheme according to the change situation of the road traffic operation situation at the future moment, help road traffic managers to know the road traffic operation situation in advance so as to be convenient for the accurate formulation of traffic control measures, further reduce the road traffic congestion and the road environmental pollution, and improve the road traffic safety and the traffic efficiency.
In early research aiming at predicting the traffic operation situation of the highway, the identification of the traffic operation situation of the highway is mainly realized by predicting the traffic flow of the highway. In the last 70 th century, with the construction of the U.S. highway network, relevant scholars gradually turned the research on traffic flow prediction from urban roads (road network) to highway network traffic flow prediction, and preliminarily formed a theoretical method for predicting road traffic operation situation based on traffic prediction.
The change rule of the road traffic operation situation can be divided into three practical scales of short, medium and long according to the evolution trend of historical data. The expression forms of the traffic flow in three different time scales are related to each other and have certain difference. The method mainly applies shallow traffic flow prediction models such as a neural network, a support vector machine and an exponential smoothing to predict traffic flow parameter data in medium-term and long-term traffic flow operation situation prediction, the prediction models are simple and have high stability, but the shallow prediction models can realize low accuracy of output values of medium-term and long-term traffic flow parameter prediction results, have the problems of high concussion of prediction effects, long operation time and the like, and are applied to traffic parameter prediction models of road intelligent traffic systems to realize low reliability.
The conventional road traffic flow operation situation prediction method mainly utilizes a basic prediction model to predict the short-time change situation of traffic flow operation traffic parameter data, and the accuracy of a prediction result is low, so that improvement is needed.
Disclosure of Invention
The invention aims to provide a road traffic operation situation multi-time scale prediction method to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme: a road traffic operation situation multi-time scale prediction method comprises the following steps:
A. firstly, collecting traffic data of a plurality of roads through a traffic data collecting sensor, and preprocessing the traffic data through a data preprocessing unit;
B. the preprocessed data are analyzed by the main control unit and then transmitted to the screening unit, traffic information under the abnormal operation state is screened out, the possible duration time of the traffic information under the screened abnormal operation state is predicted by utilizing a comprehensive algorithm, an end-to-end self-learning model is established, and visual marking is carried out on a map;
C. transmitting the screened data to a traffic data classification unit for data classification to obtain traffic data classified under a normal state;
D. then sending the classified traffic data to an anomaly analysis unit for anomaly analysis, and predicting future traffic data through a deep learning algorithm;
E. and transmitting the predicted future Jiatong data to the background terminal through the data transmission unit for real-time sharing by the user.
Preferably, the traffic data classification method in step C includes the steps of:
a. acquiring traffic operation data, and calculating by a preset method to obtain a sparse coefficient vector corresponding to the traffic operation data, wherein the sparse coefficient vector is a coefficient vector obtained when the traffic operation data is mapped to a dictionary obtained by training;
b. carrying out normalization processing according to at least one characteristic data to be classified extracted from the traffic operation data to be classified to form characteristic data of the traffic operation data to be classified; processing the characteristic data of the traffic data to be classified by using a binarization compression code encoder to obtain a binarization compression code of the traffic data to be classified;
c. for each non-zero variable in the sparse coefficient vector, determining the posterior probability of the non-zero variable aiming at each class label according to a training matrix obtained by training;
d. calculating to obtain the sum of the posterior probabilities corresponding to each class label according to the posterior probability corresponding to each class label, and indicating the class with the maximum sum of the posterior probabilities by the class label; and classifying the binary compression codes of the traffic operation data to be classified by using a classifier based on the binary compression codes, and determining the traffic operation data to be the category of the traffic operation data.
Preferably, the traffic data acquisition sensor in the step a comprises a traffic flow sensor, a vehicle speed sensor and a vehicle image sensor; the traffic flow sensor is used for collecting traffic flow on a plurality of roads; the vehicle speed sensor is used for acquiring the speed of the vehicle; the vehicle image sensor is used for collecting vehicle images for identifying whether traffic jam occurs.
Preferably, the traffic data acquisition sensor is connected with the main control unit through the data preprocessing unit, the main control unit is respectively connected with the screening unit, the data classification unit, the abnormal data analysis unit and the data classification unit, and the main control unit is connected with the background terminal through the data transmission unit.
Compared with the prior art, the invention has the beneficial effects that:
(1) the prediction method adopted by the invention is simple to operate and high in precision, can remarkably improve the coordination degree of road traffic command and management, provides a quick response signal for relevant management departments, and provides a trip decision basis for residents.
(2) The traffic data classification method adopted by the invention has the problem that the classification speed is slow because a general classification method needs to train a complex classifier and a large number of model files exist; the effect of improving classification efficiency is achieved.
Drawings
FIG. 1 is a flow chart of the present invention;
fig. 2 is a control schematic diagram of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-2, the present invention provides a technical solution: a road traffic operation situation multi-time scale prediction method comprises the following steps:
A. firstly, collecting traffic data of a plurality of roads through a traffic data collecting sensor, and preprocessing the traffic data through a data preprocessing unit; the traffic data acquisition sensor comprises a traffic flow sensor 1, a vehicle speed sensor 2 and a vehicle image sensor 3; the traffic flow sensor is used for collecting traffic flow on a plurality of roads; the vehicle speed sensor is used for acquiring the speed of the vehicle; the vehicle image sensor is used for acquiring a vehicle image for identifying whether traffic jam occurs or not;
B. the preprocessed data are analyzed by the main control unit and then transmitted to the screening unit, traffic information under the abnormal operation state is screened out, the possible duration time of the traffic information under the screened abnormal operation state is predicted by utilizing a comprehensive algorithm, an end-to-end self-learning model is established, and visual marking is carried out on a map;
C. transmitting the screened data to a traffic data classification unit for data classification to obtain traffic data classified under a normal state;
D. then sending the classified traffic data to an anomaly analysis unit for anomaly analysis, and predicting future traffic data through a deep learning algorithm;
E. and transmitting the predicted future Jiatong data to the background terminal through the data transmission unit for real-time sharing by the user.
The traffic data acquisition sensor is connected with a main control unit 5 through a data preprocessing unit 4, the main control unit 5 is respectively connected with a screening unit 6, a data classification unit 7, an abnormal data analysis unit 8 and a data classification unit 9, and the main control unit 5 is connected with a background terminal 11 through a data transmission unit 10.
In the invention, the traffic data classification method in the step C comprises the following steps:
a. acquiring traffic operation data, and calculating by a preset method to obtain a sparse coefficient vector corresponding to the traffic operation data, wherein the sparse coefficient vector is a coefficient vector obtained when the traffic operation data is mapped to a dictionary obtained by training;
b. carrying out normalization processing according to at least one characteristic data to be classified extracted from the traffic operation data to be classified to form characteristic data of the traffic operation data to be classified; processing the characteristic data of the traffic data to be classified by using a binarization compression code encoder to obtain a binarization compression code of the traffic data to be classified;
c. for each non-zero variable in the sparse coefficient vector, determining the posterior probability of the non-zero variable aiming at each class label according to a training matrix obtained by training;
d. calculating to obtain the sum of the posterior probabilities corresponding to each class label according to the posterior probability corresponding to each class label, and indicating the class with the maximum sum of the posterior probabilities by the class label; and classifying the binary compression codes of the traffic operation data to be classified by using a classifier based on the binary compression codes, and determining the traffic operation data to be the category of the traffic operation data.
The traffic data classification method adopted by the invention has the problem that the classification speed is slow because a general classification method needs to train a complex classifier and a large number of model files exist; the effect of improving classification efficiency is achieved.
In conclusion, the prediction method adopted by the invention is simple to operate and high in precision, can remarkably improve the coordination degree of road traffic command and management, provides a quick response signal for relevant management departments, and provides a trip decision basis for residents.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (4)
1. A road traffic operation situation multi-time scale prediction method is characterized by comprising the following steps: the method comprises the following steps:
A. firstly, collecting traffic data of a plurality of roads through a traffic data collecting sensor, and preprocessing the traffic data through a data preprocessing unit;
B. the preprocessed data are analyzed by the main control unit and then transmitted to the screening unit, traffic information under the abnormal operation state is screened out, the possible duration time of the traffic information under the screened abnormal operation state is predicted by utilizing a comprehensive algorithm, an end-to-end self-learning model is established, and visual marking is carried out on a map;
C. transmitting the screened data to a traffic data classification unit for data classification to obtain traffic data classified under a normal state;
D. then sending the classified traffic data to an anomaly analysis unit for anomaly analysis, and predicting future traffic data through a deep learning algorithm;
E. and transmitting the predicted future Jiatong data to the background terminal through the data transmission unit for real-time sharing by the user.
2. The road traffic operation situation multi-time scale prediction method according to claim 1, characterized in that: the traffic data classification method in the step C includes the steps of:
a. acquiring traffic operation data, and calculating by a preset method to obtain a sparse coefficient vector corresponding to the traffic operation data, wherein the sparse coefficient vector is a coefficient vector obtained when the traffic operation data is mapped to a dictionary obtained by training;
b. carrying out normalization processing according to at least one characteristic data to be classified extracted from the traffic operation data to be classified to form characteristic data of the traffic operation data to be classified; processing the characteristic data of the traffic data to be classified by using a binarization compression code encoder to obtain a binarization compression code of the traffic data to be classified;
c. for each non-zero variable in the sparse coefficient vector, determining the posterior probability of the non-zero variable aiming at each class label according to a training matrix obtained by training;
d. calculating to obtain the sum of the posterior probabilities corresponding to each class label according to the posterior probability corresponding to each class label, and indicating the class with the maximum sum of the posterior probabilities by the class label; and classifying the binary compression codes of the traffic operation data to be classified by using a classifier based on the binary compression codes, and determining the traffic operation data to be the category of the traffic operation data.
3. The road traffic operation situation multi-time scale prediction method according to claim 1, characterized in that: the traffic data acquisition sensor in the step A comprises a traffic flow sensor (1), a vehicle speed sensor (2) and a vehicle image sensor (3); the traffic flow sensor is used for collecting traffic flow on a plurality of roads; the vehicle speed sensor is used for acquiring the speed of the vehicle; the vehicle image sensor is used for collecting vehicle images for identifying whether traffic jam occurs.
4. The road traffic operation situation multi-time scale prediction method according to claim 1, characterized in that: the traffic data acquisition sensor is connected with a main control unit (5) through a data preprocessing unit (4), the main control unit (5) is respectively connected with a screening unit (6), a data classification unit (7), an abnormal data analysis unit (8) and a data classification unit (9), and the main control unit (5) is connected with a background terminal (11) through a data transmission unit (10).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010035665.1A CN111192456A (en) | 2020-01-14 | 2020-01-14 | Road traffic operation situation multi-time scale prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010035665.1A CN111192456A (en) | 2020-01-14 | 2020-01-14 | Road traffic operation situation multi-time scale prediction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111192456A true CN111192456A (en) | 2020-05-22 |
Family
ID=70708042
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010035665.1A Withdrawn CN111192456A (en) | 2020-01-14 | 2020-01-14 | Road traffic operation situation multi-time scale prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111192456A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070208497A1 (en) * | 2006-03-03 | 2007-09-06 | Inrix, Inc. | Detecting anomalous road traffic conditions |
| CN101751782A (en) * | 2009-12-30 | 2010-06-23 | 北京大学深圳研究生院 | Crossroad traffic event automatic detection system based on multi-source information fusion |
| CN104298729A (en) * | 2014-09-28 | 2015-01-21 | 小米科技有限责任公司 | Data classifying method and device |
| CN104778837A (en) * | 2015-04-14 | 2015-07-15 | 吉林大学 | Multi-time scale forecasting method for road traffic running situation |
| CN104951791A (en) * | 2014-03-26 | 2015-09-30 | 华为技术有限公司 | Data classification method and apparatus |
| CN107392115A (en) * | 2017-06-30 | 2017-11-24 | 中原智慧城市设计研究院有限公司 | A kind of traffic sign recognition method based on layered characteristic extraction |
| CN107742420A (en) * | 2017-09-22 | 2018-02-27 | 北京交通大学 | It is a kind of to be used for the method that road traffic flow is predicted under emergent traffic incident |
| WO2018122801A1 (en) * | 2016-12-30 | 2018-07-05 | 同济大学 | Method for detecting traffic anomaly of urban road |
| EP3358541A1 (en) * | 2017-02-01 | 2018-08-08 | Kapsch TrafficCom AG | A method of predicting a traffic behaviour in a road system |
| CN110390816A (en) * | 2019-07-18 | 2019-10-29 | 电子科技大学 | A kind of condition discrimination method based on multi-model fusion |
-
2020
- 2020-01-14 CN CN202010035665.1A patent/CN111192456A/en not_active Withdrawn
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070208497A1 (en) * | 2006-03-03 | 2007-09-06 | Inrix, Inc. | Detecting anomalous road traffic conditions |
| CN101751782A (en) * | 2009-12-30 | 2010-06-23 | 北京大学深圳研究生院 | Crossroad traffic event automatic detection system based on multi-source information fusion |
| CN104951791A (en) * | 2014-03-26 | 2015-09-30 | 华为技术有限公司 | Data classification method and apparatus |
| CN104298729A (en) * | 2014-09-28 | 2015-01-21 | 小米科技有限责任公司 | Data classifying method and device |
| CN104778837A (en) * | 2015-04-14 | 2015-07-15 | 吉林大学 | Multi-time scale forecasting method for road traffic running situation |
| WO2018122801A1 (en) * | 2016-12-30 | 2018-07-05 | 同济大学 | Method for detecting traffic anomaly of urban road |
| EP3358541A1 (en) * | 2017-02-01 | 2018-08-08 | Kapsch TrafficCom AG | A method of predicting a traffic behaviour in a road system |
| CN107392115A (en) * | 2017-06-30 | 2017-11-24 | 中原智慧城市设计研究院有限公司 | A kind of traffic sign recognition method based on layered characteristic extraction |
| CN107742420A (en) * | 2017-09-22 | 2018-02-27 | 北京交通大学 | It is a kind of to be used for the method that road traffic flow is predicted under emergent traffic incident |
| CN110390816A (en) * | 2019-07-18 | 2019-10-29 | 电子科技大学 | A kind of condition discrimination method based on multi-model fusion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yang et al. | Image-based visibility estimation algorithm for intelligent transportation systems | |
| CN116504076A (en) | Expressway traffic flow prediction method based on ETC portal data | |
| CN109146144A (en) | Based on the landslide disaster prediction technique for improving Bayesian network | |
| CN110675626B (en) | Traffic accident black point prediction method, device and medium based on multidimensional data | |
| CN113570862B (en) | XGboost algorithm-based large traffic jam early warning method | |
| CN112507624B (en) | Inter-city road trip mode identification model construction and identification method and device | |
| CN110555551A (en) | air quality big data management method and system for smart city | |
| CN103679214A (en) | Vehicle detection method based on online area estimation and multi-feature decision fusion | |
| Wang et al. | Vehicle reidentification with self-adaptive time windows for real-time travel time estimation | |
| KR20220039531A (en) | Driving pattern classifying method of autonomous vehicles | |
| CN112149922A (en) | Method for predicting severity of accident in exit and entrance area of down-link of highway tunnel | |
| CN116168356A (en) | Vehicle damage judging method based on computer vision | |
| CN117133099A (en) | Automatic monitoring system for disaster of expressway high slope | |
| CN111192456A (en) | Road traffic operation situation multi-time scale prediction method | |
| CN111127884A (en) | Long downhill road section vehicle stall judging method and system based on vehicle behaviors | |
| CN110765900A (en) | DSSD-based automatic illegal building detection method and system | |
| CN115941807A (en) | Efficient data compression method for park security system | |
| Žunić et al. | Cluster-based analysis and time-series prediction model for reducing the number of traffic accidents | |
| CN114116756A (en) | Engineering cost data correction system and method thereof | |
| CN116401944B (en) | Intelligent traffic management system based on big data | |
| CN116699730B (en) | Road group fog prediction method based on edge calculation | |
| CN116631186B (en) | Expressway traffic accident risk assessment method and system based on dangerous driving event data | |
| CN117270913B (en) | Map updating method, device, electronic equipment and storage medium | |
| CN116884225B (en) | Method and device for evaluating influence of proportion of automatic driving vehicles on traffic efficiency | |
| CN117058888B (en) | Traffic big data processing method and system thereof |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200522 |
|
| WW01 | Invention patent application withdrawn after publication |