CN113723529B - Traffic information credible identification method based on speed prediction algorithm - Google Patents
Traffic information credible identification method based on speed prediction algorithm Download PDFInfo
- Publication number
- CN113723529B CN113723529B CN202111023562.4A CN202111023562A CN113723529B CN 113723529 B CN113723529 B CN 113723529B CN 202111023562 A CN202111023562 A CN 202111023562A CN 113723529 B CN113723529 B CN 113723529B
- Authority
- CN
- China
- Prior art keywords
- rear vehicle
- vehicle
- sequence
- speed
- training
- 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
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000012549 training Methods 0.000 claims description 35
- 238000005070 sampling Methods 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 7
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 abstract description 9
- 238000013528 artificial neural network Methods 0.000 abstract description 5
- 230000002159 abnormal effect Effects 0.000 abstract description 4
- 230000002452 interceptive effect Effects 0.000 abstract description 4
- 230000015654 memory Effects 0.000 abstract description 4
- 238000013135 deep learning Methods 0.000 abstract description 3
- 230000006399 behavior Effects 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005562 fading Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000006386 memory function Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a traffic information credible identification method based on a speed prediction algorithm, which is characterized in that a deep learning long-time and short-time memory network is used, a neural network capable of predicting the speed of a rear vehicle is trained through a large amount of data of front and rear vehicles in a following scene, then relevant data of the front and rear vehicles are input, the speed of the rear vehicle is predicted, an actual speed value and a predicted speed value are compared, a credible probability value is given, and whether interactive information is legal or not is judged. The method and the system can effectively detect the abnormal conditions of the vehicle communication data, including the conditions of vehicle sensor data error or hacker attack tampering communication data and the like, and improve the safety and reliability of the intelligent traffic system under the vehicle-road cooperative environment.
Description
Technical Field
The invention relates to the technical fields of vehicle-road cooperation, information interaction, behavior characteristic identification and the like, in particular to a traffic information credible identification method based on a speed prediction algorithm.
Background
The vehicle-road cooperative system and the technology are the development trend of a new generation of intelligent traffic system, and can realize more efficient and safer traffic organization and management benefits based on vehicle-vehicle and vehicle-road real-time interaction. How to ensure the safety and reliability of traffic information interaction has important significance for the application of a vehicle-road cooperative system. However, for the application environment of the current vehicle-road coordination system, the reliability requirement of the traffic information cannot only consider the reliability and the security of the traditional communication layer, and the credibility of the interactive information needs to be discriminated by combining the traffic service characteristics.
At present, credible identification in a following scene in a credible identification technology is usually realized by dividing a motion state angle, namely, the acceleration of a rear vehicle in the following scene is estimated by column writing following. The characteristic parameters considered by the identification method are simple, analysis is only carried out according to relevant data at one moment, accuracy is insufficient, and subjective influences of drivers are large.
Disclosure of Invention
The invention aims to provide a traffic information credible identification method based on a speed prediction algorithm, which can effectively detect abnormal conditions of vehicle communication data, including conditions of vehicle sensor data error or hacker attack tampering communication data and the like, and improve the safety and reliability of an intelligent traffic system under a vehicle-road cooperative environment.
The technical scheme adopted by the invention is as follows:
a traffic information credible identification method based on a speed prediction algorithm comprises the following steps:
s1, establishing a rear vehicle speed prediction model based on an LSTM network, wherein the number of network units in the LSTM network is N; the input-output relation of each network element is as follows:
v(t)＝f(v(t-τ:t-Δt),Δv(t-τ:t-Δt),Δx(t-τ:t-Δt))
wherein v (t) represents the speed value of the rear vehicle at the time t, tau represents the time length of the selection sequence, delta t represents the sampling interval, f (-) represents the mapping relation function between the input variable and the output variable, v (t)1:t2) Represents the time t1To t2Internal rear vehicle speed sequence, i.e. [ v (t)1),v(t1+Δt),…,v(t2)]，Δv(t1:t2) Represents the time t1To t2Inner rear and front vehicle speed difference sequence, i.e. [ Delta v (t) ]1),Δv(t1+Δt),…,Δv(t2)]，Δx(t1:t2) Represents the time t1To t2The sequence of the position difference (head spacing) between the rear vehicle and the front vehicle, i.e. [ Delta x (t) ]1),Δx(t1+Δt),…,Δx(t2)]；
S2, constructing a historical following data training data set to train and optimize a rear vehicle speed prediction model;
s3, selecting N +1 time sampling points, and acquiring rear vehicle OBU dynamic data and front vehicle OBU dynamic data; the OBU dynamic data of the rear vehicle comprise a rear vehicle speed sequence, a rear vehicle position sequence, a rear vehicle and front vehicle speed difference sequence and a rear vehicle and front vehicle spacing sequence, and the OBU dynamic data of the front vehicle comprise a front vehicle speed sequence and a front vehicle position sequence;
s4, inputting the rear vehicle speed, the rear vehicle-front vehicle speed difference and the rear vehicle-front vehicle inter-vehicle distance corresponding to the N +1 time sampling points into a trained and optimized rear vehicle speed prediction model, and outputting a rear vehicle speed prediction value
k∈N；
S5, according to the real-time acquired rear vehicle speed
Predicted value of speed of following vehicle
Calculating a credible probability value P; the calculation formula is as follows:
s6, comparing the obtained credibility value P with a preset threshold value alpha, if P is larger than alpha, credibility is achieved, and otherwise, credibility is not achieved.
Further, the specific process of training and optimizing the rear vehicle speed prediction model is as follows:
21: acquiring dynamic data of a rear vehicle OBU and dynamic data of a front vehicle OBU in historical following states, and acquiring a training sample data set, wherein the training sample data set comprises a vehicle distance sample sequence [ s ]10k+1,…,s10k+N+1]Rear vehicle speed sample sequence
And front and rear vehicle speed difference sample sequence [ delta v [ ]10k+1,…,Δv10k+N+1]K represents the number of data sets and
22: dividing a training sample data set into a training set and a test set according to the proportion of 7;
23: setting characteristic parameters of the training process, including loss function, optimizer, learning rate and training round
24: and training and optimizing the rear vehicle speed prediction model until the rear vehicle speed prediction model is converged in the loss function of the test set, stopping training, and storing the model data for later prediction.
Further, the traffic information credible identification method based on speed prediction algorithm according to claim 1 or 2 is characterized in that: and N is 50.
Further, the loss function employs mselos.
Further, the optimizer employs Adam.
The invention has the following beneficial effects:
the method comprises the steps that a neural network capable of predicting the speed of a rear vehicle is trained based on the data of the front vehicle and the rear vehicle in a following scene by using a long-time memory network for deep learning, then the speed of the rear vehicle is predicted by inputting the related data of the front vehicle and the rear vehicle, the actual speed value and the predicted speed value are compared, and a credible probability value is given to judge whether interactive information is legal or not, so that abnormal conditions of vehicle communication data can be effectively detected, including the conditions that data of a vehicle sensor is wrong or hackers attack and falsify the communication data, and the safety and the reliability of an intelligent traffic system in a vehicle-road cooperative environment are improved; meanwhile, the identification method for predicting the speed of the vehicle at the next moment by processing the time sequence of longer historical data by using the LSTM network and integrating the action relationship between the front vehicle and the rear vehicle in the following process is more excellent than the single-point judgment effect.
Drawings
FIG. 1 is a flow chart of the present invention;
fig. 2 is a diagram of an LSTM network architecture in an embodiment.
Detailed Description
As shown in fig. 1, a traffic information credible identification method based on a speed prediction algorithm comprises the following steps:
s1, establishing a rear vehicle speed prediction model based on an LSTM network;
s2, constructing a historical following data training data set to train and optimize a rear vehicle speed prediction model;
s3, selecting N time sampling points, and acquiring rear vehicle OBU dynamic data and front vehicle OBU dynamic data; the OBU dynamic data of the rear vehicle comprise a rear vehicle speed sequence, a rear vehicle position sequence, a rear vehicle and front vehicle speed difference sequence and a rear vehicle and front vehicle distance sequence, and the OBU dynamic data of the front vehicle comprise a front vehicle speed sequence and a front vehicle position sequence;
s4, inputting the rear vehicle speed, the rear vehicle-front vehicle speed difference and the rear vehicle-front vehicle inter-vehicle distance corresponding to the N time sampling points into a rear vehicle speed prediction model optimized through training, and outputting a rear vehicle speed prediction value
k∈N；
S5, according to the real-time acquired rear vehicle speed
And the predicted value of the speed of the following vehicle
Calculating a credible probability value P;
s6, comparing the obtained credibility probability value P with a preset threshold value alpha, if P is larger than alpha, the credibility is achieved, otherwise, the credibility is not achieved.
For a better understanding of the present invention, the following embodiments are provided to further explain the technical solutions of the present invention.
The traditional multi-vehicle scene analysis usually uses a mathematical model, an empirical analysis and column writing formula is carried out on the scene, the most reasonable behavior or the range of the behavior of the vehicle in the next step is obtained, and whether the information is credible or not is judged by judging whether the vehicle exceeds the range or not. With the development of machine learning in recent years, a great deal of experimental data proves that the data-driven model can achieve better effect.
An LSTM Network (Long Short-Term Memory, long-Short duration Memory Neural Network) is a special RNN Network (Recurrent Neural Network). The LSTM is complex in structure, the core of which is cell state C, which is controlled by three gates, namely, forgetting gate, input gate and output gate. The LSTM can process a time sequence of longer historical data, and meanwhile, an LSTM model with a forgetting gate has a fading memory function, and can weaken the effect of outdated data as required in the process of acquiring information from the historical data, which is very consistent with the process of artificial driving. Therefore, the invention realizes the driving speed prediction based on the LSTM network, and further realizes the credible identification of the traffic information. As described in detail below.
First, a rear vehicle speed prediction model based on the LSTM network is established, as shown in fig. 2.
Setting the number of LSTM network elements to be 50, the input-output relation of each network element is as follows:
v(t)＝f(v(t-τ:t-Δt),Δv(t-τ:t-Δt),Δx(t-τ:t-Δt))
wherein v (t) represents the speed value of the rear vehicle at the time t, tau represents the time length of the selection sequence, delta t represents the sampling interval, f (-) represents the mapping relation function between the input variable and the output variable, v (t)1:t2) Represents the time t1To t2Internal rear vehicle speed sequence, i.e. [ v (t)1),v(t1+Δt),…,v(t2)]，Δv(t1:t2) Represents the time t1To t2Inner rear and front vehicle speed difference sequence, i.e. [ Delta v (t) ]1),Δv(t1+Δt),…,Δv(t2)]，Δx(t1:t2) Represents the time t1To t2The sequence of the position difference (head spacing) between the rear vehicle and the front vehicle in the interior, namely [ Delta x (t)1),Δx(t1+Δt),…,Δx(t2)]. And then, carrying out optimization training on the rear vehicle speed prediction model.
A large amount of historical follow-up data training sample data sets are collected, and a group of data is extracted at intervals of 10 sampling points, wherein each group of data comprises 51 sampling points, so that a large amount of data samples for training are obtained. Each set of data includes:
vehicle spacing sequence [ s ]10k+1,…,s10k+51]Rear vehicle speed sequence
Sequence of speed difference between front and rear vehicles [ delta v ]10k+1,…,Δv10k+51]K represents the number of data sets and
s10k+1the trailing and leading car-head spacing representing the first time sample of the kth set of data samples,
rear vehicle speed, Δ v, representing the first time sample of the kth group of data samples10k+1The speed difference between the rear vehicle and the front vehicle of the first time sampling point of the kth group of data samples is shown.
The constructed training sample data set is divided into a training set and a test set according to the proportion of 7.
Before training the model, the characteristic parameters of the training process are set, including a loss function, an optimizer, a learning rate, a training round and the like, in the embodiment, the loss function is set as mselos, and the optimizer is set as Adam.
When training, one round of training is finished, whether the loss function of the model in the test set is converged is judged, and when the loss function of the model in the test set is converged, the training can be stopped, and the model data can be stored and used for prediction later.
Then, the rear vehicle speed prediction model can be used in practical application. The practical application process is as follows:
and selecting 51 time sampling points, inputting the first 50 sampling points into an LSTM model, using the 51 th sampling point for comparison, and predicting the speed of the 51 th sampling point by using the data of the 50 sampling points. The method comprises the steps of obtaining rear vehicle OBU dynamic data and front vehicle OBU dynamic data, wherein the rear vehicle OBU dynamic data comprise a rear vehicle speed sequence, a rear vehicle position sequence, a rear vehicle and front vehicle speed difference sequence and a rear vehicle and front vehicle spacing sequence, and the front vehicle OBU dynamic data comprise a front vehicle speed sequence and a front vehicle position sequence. The rear vehicle speed sequence and the rear vehicle position sequence can be obtained by judging a rear vehicle by a front vehicle, judging the self vehicle by the rear vehicle, judging the rear vehicle by roadside equipment and the like, the front vehicle speed sequence and the front vehicle position sequence can be obtained by judging the self vehicle by the front vehicle, judging the front vehicle by the rear vehicle and judging the front vehicle by the roadside equipment and the like, and the distance sequence between the rear vehicle and the front vehicle can be obtained by calculating the position of the front vehicle and the rear vehicle and can also be obtained by measuring by sensor equipment such as radar and the like.
Inputting the rear vehicle speed, the speed difference between the rear vehicle and the front vehicle and the distance between the rear vehicle and the front vehicle corresponding to 51 time sampling points into a rear vehicle speed prediction model optimized through training, and outputting a rear vehicle speed prediction value
k∈1，…，50。
According to the real-time acquired rear speed
And the predicted value of the speed of the following vehicle
The confidence probability value P can be calculated and obtained.
The calculation formula is as follows:
according to the requirement of the credible identification system on the safety degree during application, a threshold value alpha is set, the obtained credible probability value P is compared with the threshold value alpha, alpha =0.5 is taken in the embodiment, if P > alpha, credibility is achieved, and otherwise, credibility is not achieved.
Aiming at the problem of credible identification of vehicle interaction information in a vehicle-road collaborative environment, the invention introduces the driving behavior characteristics of a driver for credible identification, establishes a credible identification model based on a speed prediction method, uses a long-time memory network for deep learning, and trains a neural network capable of predicting the speed of a rear vehicle through a large amount of front and rear vehicle data in a following scene. When the method is applied, relevant data of the front vehicle and the rear vehicle are input, the speed of the rear vehicle is predicted, the actual speed value and the predicted speed value are compared, and a credible probability numerical value is given to judge whether the interactive information is legal or not. The method and the system can effectively detect the abnormal conditions of the vehicle communication data, including the conditions of vehicle sensor data error or hacker attack tampering communication data and the like, and improve the safety and reliability of the intelligent traffic system under the vehicle-road cooperative environment.
Claims (5)
1. A traffic information credible identification method based on a speed prediction algorithm is characterized by comprising the following steps: the method comprises the following steps:
s1, establishing a rear vehicle speed prediction model based on an LSTM network, wherein the number of network units in the LSTM network is N; the input-output relation of each network element is as follows:
v(t)＝f(v(t-τ：t-Δt)，Δv(t-τ：t-Δt)，Δx(t-τ：t-Δt))
wherein v (t) represents the speed value of the rear vehicle at the time t, tau represents the time length of the selection sequence, delta t represents the sampling interval, f (-) represents the mapping relation function between the input variable and the output variable, v (t)1：t2) Represents the time t1To t2Internal rear vehicle speed sequence, i.e. [ v (t)1)，v(t1+Δt)，...，v(t2)]，Δv(t1：t2) Represents the time t1To t2Inner rear and front vehicle speed difference sequence, i.e. [ Delta v (t) ]1)，Δv(t1+Δt)，...，Δv(t2)]，Δx(t1：t2) Represents the time t1To t2The sequence of the position difference (head spacing) between the rear vehicle and the front vehicle in the interior, namely [ Delta x (t)1)，Δx(t1+Δt)，...，Δx(t2)]；
S2, constructing a historical following data training data set to train and optimize the rear vehicle speed prediction model;
s3, selecting N +1 time sampling points, and acquiring rear vehicle OBU dynamic data and front vehicle OBU dynamic data; the OBU dynamic data of the rear vehicle comprise a rear vehicle speed sequence, a rear vehicle position sequence, a rear vehicle and front vehicle speed difference sequence and a rear vehicle and front vehicle spacing sequence, and the OBU dynamic data of the front vehicle comprise a front vehicle speed sequence and a front vehicle position sequence;
s4, corresponding rear vehicle speeds to the N +1 time sampling pointsInputting the speed difference and the distance between the rear vehicle and the front vehicle into a rear vehicle speed prediction model optimized through training, and outputting a rear vehicle speed prediction value
S5, according to the real-time acquired rear vehicle speed
And the predicted value of the speed of the following vehicle
Calculating a credibility probability value P; the calculation formula is as follows:
s6, comparing the obtained credibility value P with a preset threshold value alpha, if P is larger than alpha, credibility is achieved, and otherwise, credibility is not achieved.
2. The method for credibly identifying traffic information based on speed prediction algorithm according to claim 1, characterized in that: the specific process for training and optimizing the rear vehicle speed prediction model is as follows:
21: acquiring dynamic data of a rear vehicle OBU and dynamic data of a front vehicle OBU in historical following states, and acquiring a training sample data set, wherein the training sample data set comprises a vehicle distance sample sequence [ s ]10k+1，...，s10k+N+1]Rear vehicle speed sample sequence
Sequence of samples of speed difference between front and rear vehicles [ delta v ]10k+1，...，Δv10k+N+1]K represents the number of data sets and
22: dividing a training sample data set into a training set and a test set according to the proportion of 7: 3;
23: setting characteristic parameters of the training process, including loss function, optimizer, learning rate and training round
24: and training and optimizing the rear vehicle speed prediction model until the rear vehicle speed prediction model is converged in the loss function of the test set, stopping training, and storing the model data for later prediction.
3. The traffic information credible identification method based on speed prediction algorithm according to claim 1 or 2, characterized by: and N is 50.
4. The method for credibly identifying traffic information based on speed prediction algorithm according to claim 2, characterized in that: the loss function employs mselos.
5. The method for credibly identifying traffic information based on speed prediction algorithm according to claim 2, characterized in that: the optimizer employs Adam.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111023562.4A CN113723529B (en) | 2021-09-01 | 2021-09-01 | Traffic information credible identification method based on speed prediction algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111023562.4A CN113723529B (en) | 2021-09-01 | 2021-09-01 | Traffic information credible identification method based on speed prediction algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113723529A CN113723529A (en) | 2021-11-30 |
| CN113723529B true CN113723529B (en) | 2022-11-01 |
Family
ID=78680689
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111023562.4A Active CN113723529B (en) | 2021-09-01 | 2021-09-01 | Traffic information credible identification method based on speed prediction algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113723529B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109859469A (en) * | 2019-02-15 | 2019-06-07 | 重庆邮电大学 | A kind of vehicle flowrate prediction technique based on integrated LSTM neural network |
| CN111338385A (en) * | 2020-01-22 | 2020-06-26 | 北京工业大学 | Vehicle following method based on fusion of GRU network model and Gipps model |
| CN111391831A (en) * | 2020-02-27 | 2020-07-10 | 中南大学 | Automobile following speed control method and system based on preceding automobile speed prediction |
| CN111931905A (en) * | 2020-07-13 | 2020-11-13 | 江苏大学 | Graph convolution neural network model and vehicle track prediction method using same |
-
2021
- 2021-09-01 CN CN202111023562.4A patent/CN113723529B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109859469A (en) * | 2019-02-15 | 2019-06-07 | 重庆邮电大学 | A kind of vehicle flowrate prediction technique based on integrated LSTM neural network |
| CN111338385A (en) * | 2020-01-22 | 2020-06-26 | 北京工业大学 | Vehicle following method based on fusion of GRU network model and Gipps model |
| CN111391831A (en) * | 2020-02-27 | 2020-07-10 | 中南大学 | Automobile following speed control method and system based on preceding automobile speed prediction |
| CN111931905A (en) * | 2020-07-13 | 2020-11-13 | 江苏大学 | Graph convolution neural network model and vehicle track prediction method using same |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113723529A (en) | 2021-11-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3533681B1 (en) | Method for detecting safety of driving behavior, apparatus and storage medium | |
| CN109572550B (en) | Driving track prediction method, system, computer equipment and storage medium | |
| Jafarnejad et al. | Towards a real-time driver identification mechanism based on driving sensing data | |
| CN110077398B (en) | Risk handling method for intelligent driving | |
| CN111310583A (en) | Vehicle abnormal behavior identification method based on improved long-term and short-term memory network | |
| CN108877213B (en) | Traffic accident identification method and system | |
| CN112053589B (en) | Target vehicle lane changing behavior adaptive identification model construction method | |
| CN111461292B (en) | Unmanned aerial vehicle real-time track prediction method | |
| CN110040134B (en) | Vehicle collision time calculation method considering environmental factors | |
| CN111159642B (en) | Online track prediction method based on particle filtering | |
| CN112863245B (en) | Vehicle track change real-time prediction method based on deep neural network | |
| CN108710637A (en) | Taxi exception track real-time detection method based on time-space relationship | |
| Harkous et al. | A two-stage machine learning method for highly-accurate drunk driving detection | |
| Wang et al. | Vehicle reidentification with self-adaptive time windows for real-time travel time estimation | |
| CN116434523A (en) | Vehicle active safety control method and device based on constraint degree in information perception scene | |
| CN115797403A (en) | Traffic accident prediction method and device, storage medium and electronic device | |
| CN112319505B (en) | Automatic driving lane change judgment method, device, equipment and storage medium | |
| CN113723529B (en) | Traffic information credible identification method based on speed prediction algorithm | |
| Harkous et al. | Application of hidden Markov model on car sensors for detecting drunk drivers | |
| Zeng et al. | On the importance of contextual information for building reliable automated driver identification systems | |
| Ma et al. | Lane change analysis and prediction using mean impact value method and logistic regression model | |
| CN113705013B (en) | Traffic information credible identification method based on following scene driving behaviors | |
| CN113722982A (en) | Automobile sensor attack detection and defense method based on multi-model fusion | |
| CN117975732B (en) | Intelligent traffic control system and method for tunnel | |
| CN114814825B (en) | Vehicle track sensing and state extraction method based on radar and video fusion |
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 |