CN112991731A - Teaching method based on dangerous driving behavior evaluation model - Google Patents
Teaching method based on dangerous driving behavior evaluation model Download PDFInfo
- Publication number
- CN112991731A CN112991731A CN202110223054.4A CN202110223054A CN112991731A CN 112991731 A CN112991731 A CN 112991731A CN 202110223054 A CN202110223054 A CN 202110223054A CN 112991731 A CN112991731 A CN 112991731A
- Authority
- CN
- China
- Prior art keywords
- driving
- behavior
- value
- vehicle
- driving behavior
- 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.)
- Granted
Links
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
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/06—Alarms for ensuring the safety of persons indicating a condition of sleep, e.g. anti-dozing alarms
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B5/00—Electrically-operated educational appliances
- G09B5/04—Electrically-operated educational appliances with audible presentation of the material to be studied
Abstract
The invention discloses a teaching method based on a dangerous driving behavior evaluation model, which comprises the following steps: the driving behavior evaluation model is arranged in the vehicle and used for acquiring driving behavior video information of a driver in real time during the running of the vehicle, identifying dangerous behaviors of the running video and setting each dangerous behavior to correspond to a preset behavior value; summing the preset behavior values corresponding to all the recognized dangerous behaviors to obtain a behavior risk value; the server acquires the result of the driving behavior evaluation model, sets a behavior risk value threshold, judges the driving behavior if the evaluation value of the result breaks through the threshold, and the judgment result comprises: the driving behavior needs to be reminded and corrected. The invention can realize real-time supervision of driving behaviors and information acquisition so as to carry out targeted teaching.
Description
Technical Field
The invention relates to the technical field of driving behavior analysis, in particular to a teaching method based on a dangerous driving behavior evaluation model.
Background
In past research, video education has been mainly adopted as a safe driving education mode, and such education inevitably shows some disadvantages such as: the process is too lengthy, the content is difficult to absorb, and exercise is lacking. However, as the economic and technical levels continue to advance, various driving education techniques are also being increasingly utilized in education. For example, dangerous accidents possibly occurring in the next scene are predicted in real time through driving simulation operation, and the prediction capability of the driver on the dangerous accidents and the operation capability of the driver can be effectively improved through the education.
The above-mentioned education methods are usually performed before or after driving, and cannot evaluate, refer to and perform teaching correction in a targeted manner according to the real-time driving habits of the driver.
Disclosure of Invention
The invention aims to provide a teaching method based on a dangerous driving behavior evaluation model.
The purpose of the invention can be realized by the following technical scheme: a teaching method based on a dangerous driving behavior assessment model comprises the following steps:
the driving behavior evaluation model is arranged in the vehicle and used for acquiring driving behavior video information of a driver in real time during the running of the vehicle, identifying dangerous behaviors of the running video and setting each dangerous behavior to correspond to a preset behavior value; summing the preset behavior values corresponding to all the recognized dangerous behaviors to obtain a behavior risk value;
the server acquires the result of the driving behavior evaluation model, sets a behavior risk value threshold, judges the driving behavior if the evaluation value of the result breaks through the threshold, and the judgment result comprises: driving behaviors need to be reminded and corrected;
the judgment rule is as follows: respectively marking the numerical values corresponding to the current driving time length, the total driving time length and the behavior risk value as M1, M2 and M3;
using formulas
Obtaining an evaluation value PG; wherein d1, d2 and d3 are preset proportionality coefficients, and λ is a correction factor and takes the value of 0.8457; setting an evaluation value threshold, if the result breaks through the threshold, indicating that the driving behavior needs to be reminded, otherwise indicating that the driving behavior needs to be corrected;
the server sends an instructive instruction to the vehicle terminal according to the judgment result, sends out a reminding voice for the driving behavior needing to be reminded, records the reminding voice in a library, and changes the driving behavior needing to be reminded into the driving behavior needing to be corrected if the driving behavior needing to be reminded occurs more than N times in continuous driving time;
for the driving behavior needing to be corrected, firstly, a reminding voice is sent out and recorded in the server, and after the driving behavior is finished, a driver is required to go to a designated unit for correction learning;
the method also comprises a corrected evaluation model, wherein standard driving behaviors are stored in the model aiming at the driving behaviors to be corrected, the standard behaviors in the model are compared with the corrected driving behaviors, and the comparison result is an evaluation result.
Preferably, the calculation of the behavioral risk value comprises the steps of: determining independence of driving behaviors, setting a screening radius R by taking a driving vehicle as a center, defining the vehicle in the radius R as a related vehicle, identifying a lane line in the radius R, and monitoring the driving behaviors of the related vehicle through video information in real time, wherein the driving behaviors comprise: the use of a turn signal, the turning of the vehicle head, the speed of turning, the acceleration of the vehicle and the speed difference between the associated vehicle and the vehicle; the influence model of the associated vehicle behavior on the driving behavior of the vehicle is trained, the independence of the driving behavior of the vehicle is judged, if the influence model is influenced, the independence is judged, and if the influence model is not influenced, the independence is judged, and a risk value needs to be calculated.
Preferably, the specific steps of the server obtaining the evaluation model result are as follows:
the method comprises the following steps: acquiring a registration terminal in a server, sending a communication connection instruction by the server, carrying out communication connection with the registration terminal, and marking the successfully connected registration terminal as a preferred terminal;
step two: calculating the time difference between the position of the preferred terminal and the position of the server to obtain a transmission distance and marking the transmission distance as G1; marking the terminal value and the identification value of the preferred terminal as G2 and G3 respectively;
step three: normalizing the transmission distance, the terminal value and the identification value of the preferred terminal, and taking the values, and obtaining the line position value GF of the preferred terminal by using a formula GF ═ 1/G1 (x b1+ G2 x b2+ G3 x b 3; wherein b1, b2 and b3 are all preset proportionality coefficients;
step four: marking the preferred terminal with the maximum value at the row as a selected terminal;
step five: calculating the time difference between the video sending start time and the video finishing end time to obtain the single video processing durationWhen the single video processing time length is less than the set processing threshold value; subtracting the single video processing time length from the set processing threshold to obtain the advanced time length, extracting the numerical value of the advanced time length and marking the numerical value as QX, and using a formula QB (QX)22-1.63 obtaining a single processing value QB of the selected terminal; and summing all the single processing values of the preferred terminal to obtain the identification value of the selected terminal, and increasing the total processing times of the selected terminal once.
Compared with the prior art, the invention has the beneficial effects that:
the invention sets an evaluation model to carry out risk evaluation on the behavior of a driver in a vehicle terminal through video information, and the evaluation result is classified: the driving behavior needing to be reminded and the driving behavior needing to be corrected are specifically guided according to the two results, particularly the driving behavior needing to be corrected is used for reminding a driver to perform necessary correction teaching, and the method can be applied to correction teaching of comprehensive driving quality of the driver by a traffic supervision department or a driving school.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood 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.
A teaching method based on a dangerous driving behavior evaluation model is used in a vehicle-mounted terminal and comprises the following steps:
the driving behavior evaluation model is arranged in the vehicle and used for acquiring driving behavior video information of a driver in real time during the running of the vehicle, identifying dangerous behaviors of the running video and setting each dangerous behavior to correspond to a preset behavior value; summing the preset behavior values corresponding to all the recognized dangerous behaviors to obtain a behavior risk value;
the calculation of the behavioral risk value includes the steps of: determining independence of driving behaviors, setting a screening radius R by taking a driving vehicle as a center, defining the vehicle in the radius R as a related vehicle, identifying a lane line in the radius R, and monitoring the driving behaviors of the related vehicle through video information in real time, wherein the driving behaviors comprise: the use of a turn signal, the turning of the vehicle head, the speed of turning, the acceleration of the vehicle and the speed difference between the associated vehicle and the vehicle; the influence model of the associated vehicle behavior on the driving behavior of the vehicle is trained, the independence of the driving behavior of the vehicle is judged, if the influence model is influenced, the independence is judged, and if the influence model is not influenced, the independence is judged, and a risk value needs to be calculated. The main point of the introduction of the driving behavior independence determination here is that although some driving behaviors or risk-oriented behaviors may be caused by behaviors of the associated vehicle, for example, sudden steering and acceleration of the associated vehicle may cause the host vehicle to perform sudden braking operation, and if the behaviors are the behaviors, the behaviors should not be considered as risk behaviors.
Further, there are some unusual behaviors that may not be problematic from a stand alone perspective, but the host vehicle has an effect on the associated vehicle, such as a forced lane change, a solid line crossing, and the like. Then the risk behavior should be identified
The server acquires the result of the driving behavior evaluation model, sets a behavior risk value threshold, judges the driving behavior if the evaluation value of the result breaks through the threshold, and the judgment result comprises: driving behaviors need to be reminded and corrected;
the judgment rule is as follows: respectively marking the numerical values corresponding to the current driving time length, the total driving time length and the behavior risk value as M1, M2 and M3;
using formulas
Obtaining an evaluation value PG; wherein d1, d2 and d3 are preset proportionality coefficients, and λ is a correction factor and takes the value of 0.8457; setting an evaluation value threshold, if the result breaks through the threshold, indicating that the driving behavior needs to be reminded, otherwise indicating that the driving behavior needs to be corrected; a driving time length factor is introduced into the evaluation value PG, whether certain behaviors of a driver are caused by fatigue driving or driving habits are judged through the factor, if the behaviors are caused by the fatigue driving, prompt reminding can be carried out, and if the behaviors are caused by the fatigue driving, prompt reminding can be carried outCorrection is required as a result of driving habits.
The server sends an instructive instruction to the vehicle terminal according to the judgment result, sends out a reminding voice for the driving behavior needing to be reminded, records the reminding voice in a library, and changes the driving behavior needing to be reminded into the driving behavior needing to be corrected if the driving behavior needing to be reminded occurs more than N times in continuous driving time; if it is long-term fatigue driving, this behavior should also be classified as corrective driving behavior.
For the driving behavior needing to be corrected, firstly, a reminding voice is sent out and recorded in the server, and after the driving behavior is finished, a driver is required to go to a designated unit for correction learning;
the method also comprises a corrected evaluation model, wherein standard driving behaviors are stored in the model aiming at the driving behaviors to be corrected, the standard behaviors in the model are compared with the corrected driving behaviors, and the comparison result is an evaluation result.
The server in the above should be distributed over a plurality of terminals, such as a plurality of driving schools or traffic regulators. The specific steps of the server for obtaining the evaluation model result are as follows:
the method comprises the following steps: acquiring a registration terminal in a server, sending a communication connection instruction by the server, carrying out communication connection with the registration terminal, and marking the successfully connected registration terminal as a preferred terminal;
step two: calculating the time difference between the position of the preferred terminal and the position of the server to obtain a transmission distance and marking the transmission distance as G1; marking the terminal value and the identification value of the preferred terminal as G2 and G3 respectively; the terminal value is the performance attribute of the server terminal itself, such as the carrying capacity.
Step three: normalizing the transmission distance, the terminal value and the identification value of the preferred terminal, and taking the values, and obtaining the line position value GF of the preferred terminal by using a formula GF ═ 1/G1 (x b1+ G2 x b2+ G3 x b 3; wherein b1, b2 and b3 are all preset proportionality coefficients;
step four: marking the preferred terminal with the maximum value at the row as a selected terminal;
step five: finishing the video transmission starting time and the video finishing ending timeCalculating time difference at any moment to obtain single video processing time length, and when the single video processing time length is smaller than a set processing threshold value; subtracting the single video processing time length from the set processing threshold to obtain the advanced time length, extracting the numerical value of the advanced time length and marking the numerical value as QX, and using a formula QB (QX)22-1.63 obtaining a single processing value QB of the selected terminal; and summing all the single processing values of the preferred terminal to obtain the identification value of the selected terminal, and increasing the total processing times of the selected terminal once.
Through the steps, a most suitable server is selected, namely a most suitable teaching unit is selected.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise forms disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (3)
1. A teaching method based on a dangerous driving behavior evaluation model is used in a vehicle-mounted terminal and comprises the following steps:
the driving behavior evaluation model is arranged in the vehicle and used for acquiring driving behavior video information of a driver in real time during the running of the vehicle, identifying dangerous behaviors of the running video and setting each dangerous behavior to correspond to a preset behavior value; summing the preset behavior values corresponding to all the recognized dangerous behaviors to obtain a behavior risk value;
the server acquires the result of the driving behavior evaluation model, sets a behavior risk value threshold, judges the driving behavior if the evaluation value of the result breaks through the threshold, and the judgment result comprises: driving behaviors need to be reminded and corrected;
the judgment rule is as follows: respectively marking the numerical values corresponding to the current driving time length, the total driving time length and the behavior risk value as M1, M2 and M3;
using formulas
Obtaining an evaluation value PG; wherein d1, d2 and d3 are preset proportionality coefficients, and λ is a correction factor and takes the value of 0.8457; setting an evaluation value threshold, if the result breaks through the threshold, indicating that the driving behavior needs to be reminded, otherwise indicating that the driving behavior needs to be corrected;
the server sends an instructive instruction to the vehicle terminal according to the judgment result, sends out a reminding voice for the driving behavior needing to be reminded, records the reminding voice in a library, and changes the driving behavior needing to be reminded into the driving behavior needing to be corrected if the driving behavior needing to be reminded occurs more than N times in continuous driving time;
for the driving behavior needing to be corrected, firstly, a reminding voice is sent out and recorded in the server, and after the driving behavior is finished, a driver is required to go to a designated unit for correction learning;
the method also comprises a corrected evaluation model, wherein standard driving behaviors are stored in the model aiming at the driving behaviors to be corrected, the standard behaviors in the model are compared with the corrected driving behaviors, and the comparison result is an evaluation result.
2. The dangerous driving behavior evaluation model-based teaching method according to claim 1, wherein the calculation of the behavior risk value comprises the following steps: determining independence of driving behaviors, setting a screening radius R by taking a driving vehicle as a center, defining the vehicle in the radius R as a related vehicle, identifying a lane line in the radius R, and monitoring the driving behaviors of the related vehicle through video information in real time, wherein the driving behaviors comprise: the use of a turn signal, the turning of the vehicle head, the speed of turning, the acceleration of the vehicle and the speed difference between the associated vehicle and the vehicle; the influence model of the associated vehicle behavior on the driving behavior of the vehicle is trained, the independence of the driving behavior of the vehicle is judged, if the influence model is influenced, the independence is judged, and if the influence model is not influenced, the independence is judged, and a risk value needs to be calculated.
3. The teaching method based on the dangerous driving behavior assessment model as claimed in claim 1, wherein the specific steps of the server obtaining the assessment model result are:
the method comprises the following steps: acquiring a registration terminal in a server, sending a communication connection instruction by the server, carrying out communication connection with the registration terminal, and marking the successfully connected registration terminal as a preferred terminal;
step two: calculating the time difference between the position of the preferred terminal and the position of the server to obtain a transmission distance and marking the transmission distance as G1; marking the terminal value and the identification value of the preferred terminal as G2 and G3 respectively;
step three: normalizing the transmission distance, the terminal value and the identification value of the preferred terminal, and taking the values, and obtaining the line position value GF of the preferred terminal by using a formula GF ═ 1/G1 (x b1+ G2 x b2+ G3 x b 3; wherein b1, b2 and b3 are all preset proportionality coefficients;
step four: marking the preferred terminal with the maximum value at the row as a selected terminal;
step five: calculating the time difference between the video sending starting time and the video finishing time to obtain the single video processing time length, and when the single video processing time length is smaller than a set processing threshold value; subtracting the single video processing time length from the set processing threshold to obtain the advanced time length, extracting the numerical value of the advanced time length and marking the numerical value as QX, and using a formula QB (QX)22-1.63 obtaining a single processing value QB of the selected terminal; and summing all the single processing values of the preferred terminal to obtain the identification value of the selected terminal, and increasing the total processing times of the selected terminal once.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110223054.4A CN112991731B (en) | 2021-02-26 | 2021-02-26 | Teaching method based on dangerous driving behavior evaluation model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110223054.4A CN112991731B (en) | 2021-02-26 | 2021-02-26 | Teaching method based on dangerous driving behavior evaluation model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112991731A true CN112991731A (en) | 2021-06-18 |
| CN112991731B CN112991731B (en) | 2022-04-29 |
Family
ID=76351443
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110223054.4A Active CN112991731B (en) | 2021-02-26 | 2021-02-26 | Teaching method based on dangerous driving behavior evaluation model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112991731B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113506012A (en) * | 2021-07-22 | 2021-10-15 | 中冶南方城市建设工程技术有限公司 | Driving behavior risk index judgment method based on mobile phone Internet of vehicles data |
| CN114148338A (en) * | 2021-11-30 | 2022-03-08 | 支付宝(杭州)信息技术有限公司 | Driving correction processing method and device |
| CN114446126A (en) * | 2021-12-03 | 2022-05-06 | 广州小鹏汽车科技有限公司 | Safe driving guiding method and device, electronic equipment and readable medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102717765A (en) * | 2012-07-09 | 2012-10-10 | 湖南赛格导航技术研究有限公司 | Fatigue driving detection method and anti-fatigue driving auxiliary device |
| JP5705361B1 (en) * | 2014-09-02 | 2015-04-22 | アジア航測株式会社 | Vehicle damage risk assessment device |
| CN104732785A (en) * | 2015-01-09 | 2015-06-24 | 杭州好好开车科技有限公司 | Driving behavior analyzing and reminding method and system |
| CN104933865A (en) * | 2015-06-08 | 2015-09-23 | 厦门金龙联合汽车工业有限公司 | Monitoring method and system for preventing driver from fatigue driving |
| CN105206078A (en) * | 2015-08-26 | 2015-12-30 | 宇龙计算机通信科技(深圳)有限公司 | Driving information prompting method, driving information prompting apparatus, and wearable equipment |
| CN105303830A (en) * | 2015-09-15 | 2016-02-03 | 成都通甲优博科技有限责任公司 | Driving behavior analysis system and analysis method |
| CN107618512A (en) * | 2017-08-23 | 2018-01-23 | 清华大学 | Driving behavior safe evaluation method based on people's car environment multi-data source |
| US20180157802A1 (en) * | 2016-12-01 | 2018-06-07 | Fujitsu Limited | Risk evaluation method, risk evaluation device, and storage medium |
| CN110933147A (en) * | 2019-11-15 | 2020-03-27 | 广州深卓信息科技有限公司 | Information technology analysis system based on cloud computing |
| US20200231184A1 (en) * | 2019-01-22 | 2020-07-23 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for measuring user acceptance of autonomous vehicle, and electronic device |
-
2021
- 2021-02-26 CN CN202110223054.4A patent/CN112991731B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102717765A (en) * | 2012-07-09 | 2012-10-10 | 湖南赛格导航技术研究有限公司 | Fatigue driving detection method and anti-fatigue driving auxiliary device |
| JP5705361B1 (en) * | 2014-09-02 | 2015-04-22 | アジア航測株式会社 | Vehicle damage risk assessment device |
| CN104732785A (en) * | 2015-01-09 | 2015-06-24 | 杭州好好开车科技有限公司 | Driving behavior analyzing and reminding method and system |
| CN104933865A (en) * | 2015-06-08 | 2015-09-23 | 厦门金龙联合汽车工业有限公司 | Monitoring method and system for preventing driver from fatigue driving |
| CN105206078A (en) * | 2015-08-26 | 2015-12-30 | 宇龙计算机通信科技(深圳)有限公司 | Driving information prompting method, driving information prompting apparatus, and wearable equipment |
| CN105303830A (en) * | 2015-09-15 | 2016-02-03 | 成都通甲优博科技有限责任公司 | Driving behavior analysis system and analysis method |
| US20180157802A1 (en) * | 2016-12-01 | 2018-06-07 | Fujitsu Limited | Risk evaluation method, risk evaluation device, and storage medium |
| CN107618512A (en) * | 2017-08-23 | 2018-01-23 | 清华大学 | Driving behavior safe evaluation method based on people's car environment multi-data source |
| US20200231184A1 (en) * | 2019-01-22 | 2020-07-23 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for measuring user acceptance of autonomous vehicle, and electronic device |
| CN110933147A (en) * | 2019-11-15 | 2020-03-27 | 广州深卓信息科技有限公司 | Information technology analysis system based on cloud computing |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113506012A (en) * | 2021-07-22 | 2021-10-15 | 中冶南方城市建设工程技术有限公司 | Driving behavior risk index judgment method based on mobile phone Internet of vehicles data |
| CN114148338A (en) * | 2021-11-30 | 2022-03-08 | 支付宝(杭州)信息技术有限公司 | Driving correction processing method and device |
| CN114446126A (en) * | 2021-12-03 | 2022-05-06 | 广州小鹏汽车科技有限公司 | Safe driving guiding method and device, electronic equipment and readable medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112991731B (en) | 2022-04-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112991731B (en) | Teaching method based on dangerous driving behavior evaluation model | |
| EP3533681B1 (en) | Method for detecting safety of driving behavior, apparatus and storage medium | |
| EP3796112A1 (en) | Virtual vehicle control method, model training method, control device and storage medium | |
| CN111325230B (en) | Online learning method and online learning device for vehicle lane change decision model | |
| Wandtner et al. | Non-driving related tasks in highly automated driving-effects of task modalities and cognitive workload on take-over performance | |
| CN112009397B (en) | Automatic driving drive test data analysis method and device | |
| CN113753059B (en) | Method for predicting takeover capacity of driver under automatic driving system | |
| CN110705101A (en) | Network training method, vehicle driving method and related product | |
| CN112288023A (en) | Modeling method for aggressive driving recognition based on simulated driver and SVM algorithm | |
| CN112418646A (en) | Vehicle comfort evaluation method and device and readable storage medium | |
| CN108682157A (en) | Video analysis and method for early warning and system | |
| CN111723835A (en) | Vehicle movement track distinguishing method and device and electronic equipment | |
| CN115366891A (en) | Driving style recognition method, system and storage medium | |
| CN116563604A (en) | End-to-end target detection model training, image target detection method and related equipment | |
| CN116011225A (en) | Scene library generation method, test method, electronic device and storage medium | |
| CN112818236A (en) | Learning content recommendation method and system based on scene | |
| CN112434573A (en) | Method and device for evaluating spatial perception capability of driver | |
| CN111932829A (en) | Fatigue driving prevention facility utility testing method and system | |
| CN110991788A (en) | Method and device for acquiring learning feedback information of live course | |
| CN113129184B (en) | Volume model training, volume method and device and computer storage medium | |
| CN111209796B (en) | Driving behavior detection method and device, electronic equipment and medium | |
| CN114792049A (en) | Method for identifying and predicting impact risk influencing factors of automatic driving takeover on highway | |
| CN115866340B (en) | On-line training data processing method and system | |
| CN116167900B (en) | Score display analysis system and method based on artificial intelligence | |
| CN112232158B (en) | Training cheating verification system and method based on driving behavior characteristics |
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 |