CN108694407A - A kind of driving behavior recognition methods based on mobile terminal - Google Patents
A kind of driving behavior recognition methods based on mobile terminal Download PDFInfo
- Publication number
- CN108694407A CN108694407A CN201710232230.4A CN201710232230A CN108694407A CN 108694407 A CN108694407 A CN 108694407A CN 201710232230 A CN201710232230 A CN 201710232230A CN 108694407 A CN108694407 A CN 108694407A
- Authority
- CN
- China
- Prior art keywords
- behavior
- time
- driving behavior
- mobile phone
- network
- 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- Withdrawn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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/285—Selection of pattern recognition techniques, e.g. of classifiers in a multi-classifier system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Telephone Function (AREA)
Abstract
The present invention provides a kind of method based on smart mobile phone automatic identification driving behavior, the method includes:Using the real-time 3-axis acceleration data obtained from mobile phone sensor, after being pre-processed behavior switching point is determined using end-point detection algorithm, pass through sliding window extract real-time time serial message and the time and frequency domain characteristics of sequence of calculation segment, after choosing validity feature, fusion primitive behavior information establishes input terminal of the complete time sequence section as limited Boltzmann machine with feature, hidden layer is converted to the identifiable bernoulli distribution mode of network, more hidden layers of optimization parameter preset are limited Boltzmann machine and are extracted to the feature for inputting client information, eventually by DBN(Deep Belief Network, deep belief network)Realize the identification of driving behavior.The experimental results showed that the deep belief network driving behavior recognizer entirety discrimination of improved sliding window Fusion Features is 85.2%, the identification of driving behavior can be effectively carried out.
Description
Technical field
The present invention relates to intelligent terminal technical field, more particularly to a kind of Activity recognition method and mobile terminal.
Background technology
Nowadays the popularity rate of automobile is higher and higher, also more and more intelligent.The combination of automobile and mobile terminal is one
Good market applies hot spot, mobile terminal that can provide auxiliary information for driver, helps user to carry out safer driving, obtains
Better user experience, such as after handset identity be in driving condition to user, connection on-vehicle Bluetooth receives calls automatically,
And map is automatically opened, inquiry user will go to where, and start to navigate, and obtain automobile present speed and give in an overspeed situation
Prompt, or prompt user to slow down after user brings to a halt and drive.
In existing technology, on-vehicle Bluetooth is connected to receive calls if necessary to mobile phone, is needed mobile phone after getting on the bus
Mode setting is driving pattern;If necessary to Mobile Telephone Gps, user opens map APP after getting on the bus, and inputs customer objective
Ground, map APP can navigate, traffic information prompt and safe driving prompt.It needs to terminate after user terminates to drive, get off
Navigation, and map APP is closed, mobile phone is adjusted to general mode, releases the connection with on-vehicle Bluetooth.The prior art there is
Some limitations, need that driving pattern is set in advance, and open navigation manually, and human-computer interaction seems not smart enough simple.If can be certainly
When dynamic identification user starts to drive, and automatic to carry out on-vehicle Bluetooth connection and open navigation, automatic identification user has got off, from
Dynamic closing driving pattern and navigation system, the user experience being achieved in that will be more preferable.
By the retrieval discovery to the prior art, existing driving behavior at present identifies that patent has following a few classes:1, it uses
Image recognition algorithm distinguishes fatigue driving and normal driving behavior;2, the combination sensors such as accelerometer or gyroscope are installed,
Abnormal driving behavior is identified using machine learning algorithm;3, using the sensor carried in mobile terminal, machine learning is used
Algorithm identifies abnormal driving behavior;Existing patent is to consider from a safety viewpoint, identifies that abnormal driving behavior, this patent are known
Such as the igniting of other normal behaviour drives and stops working, it is therefore intended that provides better usage experience to the user.
Invention content
The technical problem to be solved in the present invention is to provide a kind of method based on smart mobile phone automatic identification driving behavior, profits
Information is acquired with the built-in acceleration sensor on smart mobile phone, Activity recognition is carried out by deep learning algorithm so that is moved
Dynamic terminal can obtain the behavior of active user, judge the behaviors such as the igniting of user, driving, flame-out.
In order to solve the above technical problems, the embodiment of the present invention provides a kind of judgment method, including:
Since in driving procedure, igniting and flame-out sample number are considerably less, and behavior is not easily distinguishable, shallow structure sorting algorithm point
The relatively low problem of class accuracy proposes a kind of improved deep belief network driving behavior identification side based on sliding window Fusion Features
Method.It is true using end-point detection algorithm after being pre-processed using the real-time 3-axis acceleration data obtained from mobile phone sensor
Determine behavior switching point, has by sliding window extract real-time time serial message and the time and frequency domain characteristics of sequence of calculation segment, selection
After imitating feature, fusion primitive behavior information establishes input terminal of the complete time sequence section as limited Boltzmann machine with feature,
Hidden layer is converted to the identifiable bernoulli distribution mode of network, and the more hidden layers for optimizing parameter preset are limited Boltzmann machine to input
The feature of client information extracts, eventually by DBN(Deep Belief Network, deep belief network)Realize driving behavior
Identification.The experimental results showed that the deep belief network driving behavior recognizer of improved sliding window Fusion Features integrally identifies
Rate is 85.2%, can effectively carry out the identification of driving behavior.
In order to solve the above technical problems, the embodiment of the present invention also provides a kind of mobile terminal, mobile terminal can carry
On the body of user, or place in the car, including:
APP is developed on smart mobile phone, can obtain the information of mobile phone built-in acceleration meter, the data meeting acquired by sensor
By noise jamming, original acceleration information is pre-processed, the disposal of gentle filter can be selected, by collected data
The matrix a=(a for the 100*3 being processed intox, ay, az), wherein axIndicate the acceleration information in mobile phone coordinate system x-axis, ayIndicate y
Acceleration information on axis, azIndicate the acceleration information in z-axis, matrix a is pressed to mobile phone coordinate system x, y, z variation successively is
The row vector b of 1*300.
Information interception is carried out based on sliding window, in order to judge that speed is fast, sliding window length is 2s, and interception is primary per 0.5s.
The above-mentioned technical proposal of the present invention has the beneficial effect that:
In said program, driving behavior identification is carried out using smart mobile phone, new mobile unit is not needed to buy, implements more square
Just.Behavior switching point is determined using end-point detection algorithm, by sliding window extract real-time time series, carries out feature extraction, and
By DBN algorithms realize driving behavior identification, recognition speed is fast, recognition accuracy is high, thus the present invention be highly suitable for into
The identification of row driving mode can provide the driving information of user, so that mobile phone provides to the user more just for various applications on mobile phone
Prompt service enhances user experience.
Description of the drawings
Fig. 1 is the driving behavior identification model based on deep belief network;
Fig. 2 is the timing distribution schematic diagram of behavior switching point in driving procedure;
Fig. 3 is characterized degree of the deeply convinceing network structure model of fusion;
Fig. 4 is the acceleration schematic diagram of four kinds of typicalness.
Specific implementation mode
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although showing the disclosure in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Completely it is communicated to those skilled in the art.
The present invention in said program, carries out driving behavior identification using smart mobile phone, does not need to buy in the prior art
New mobile unit implements more convenient.Behavior switching point is determined using end-point detection algorithm, passes through sliding window extract real-time
Time series carries out feature extraction, and realizes driving behavior identification by DBN algorithms, and recognition speed is fast, recognition accuracy is high,
Therefore the present invention is highly suitable for carrying out the identification of driving mode, and the driving letter of user can be provided for various applications on mobile phone
Breath, more easily services so that mobile phone provides to the user, enhances user experience.
First embodiment:
Referring to Fig. 1, the driving behavior identification model includes:
Step 11 acquires for data, and the acceleration information of vehicle is obtained using the mobile phone placed in the car;Including following several rows
For:Static, igniting starts, traveling, brakes and stop working;The present embodiment is using the smart mobile phone of arm processor as embedded system
System hardware platform, is based on 2.3 systems of Android, Samsung emerging in the smart mobile phone of acceleration transducer using being equipped with, HTC
Deng building driving behavior data collector, data acquisition carried out to the real time status of driving behavior, vehicle platform is Chevrolet match
Europe, manual gear are tested the result of processing through Bluetooth feedback to mobile phone, the real-time display current state on mobile phone.
Experimental data includes the acceleration information of two cars, and driving behavior pattern includes starting, lighting a fire, giving it the gun, just
Often seven kinds of behaviors such as traveling, lane change traveling, brake, stopping, covering the several modes of driving behavior, for each row substantially
For user location is mainly:It drives, copilot, left back seat, right back seat, mobile phone placement location is divided into:Trouser pocket, hand
In, the direction of estrade, wherein mobile phone under different behaviors includes traverse, keeps flat, and experiment is in different location and side in mobile phone
In the case of, 2100, sample is acquired altogether, and for each driving behavior acceleration information, the duration acquired every time is
10 seconds, the sampling period was 20ms.
Step 12, noise reduction is filtered to pre-process and normalize;During actual acquired data, what sensor was acquired
Data can be by noise jamming, therefore to carry out the disposal of gentle filter to raw acceleration data, while being input to degree of deeply convinceing
Network first has to pre-process data before being trained and testing.The square for the 100*3 that collected data are processed into
Battle array a=(ax, ay, az), wherein axIndicate the acceleration information in mobile phone coordinate system x-axis, ayIndicate the acceleration information in y-axis,
azIt indicates the acceleration information in z-axis, matrix a is pressed to the row vector b that mobile phone coordinate system x, y, z variation is 1*300 successively.
Step 13, since the transient state driving behavior event such as startup, igniting, brake, flame-out is only in a bit of time series
There are obvious characteristic variations, and behavior similarity is higher within remaining period, while cannot accurately be extracted in data acquisition
Behavior valid data section and reduce discrimination, therefore using end-point detection algorithm detection driving behavior event effective time sequence
Section, chooses its time and frequency domain characteristics while inputting primitive behavior real value data and carries out combinatory analysis.
Step 14, it is merged using raw information with characteristic and establishes complete time sequence section as the input of deep belief network
Realize the identification of driving behavior, and by classification results Real-time Feedback to intelligent terminal.
In the present embodiment, in order to detect continuous driving behavior, mobile phone sensor obtains corresponding acceleration information, simultaneously
By the estimation of end-point detection algorithm and the relevant time series signal of driving behavior.In end-point detection algorithm, sliding window is used
Sampled data is organized, for each window, sample energy estimator is:
Wherein,Indicate the energy of each window, s[k]For the value of corresponding points in each window,For in window data it is equal
Value,The standard deviation of these data is represented, m is window size.Igniting and flame-out driving behavior characteristic are when shorter
The setting of interior completion, and the substantially changeing there are acceleration peak value in a bit of time series, this paper thresholdings then passes through instruction
Form of energy observed by during practicing determines, for distinguishing current state, and determines that behavior next stage is, answers
Real-time and recent behavior can be embodied.
Please referring to Fig. 2, the timing distribution schematic diagram of behavior switching point in driving procedure, wherein time indicates the time,
Accelerator indicates acceleration.
Referring to Fig. 3, the present embodiment is improved degree of deeply convinceing Learning Algorithms, a kind of Fusion Features are proposed
(FFDBN)Deep belief network, during identifying driving behavior, input signal is acceleration information, and driving behavior also can be with
It the time and changes, the complexity with height, different driving behavior processes have different characteristics, detect that each state passes
There is the probability of occurrence for feeling information certain regularity, acceleration time series also will present the spy of corresponding dynamic consecutive variations
Point.
The present embodiment designs two layers of RBM and builds network learning model, and FFDBN network models are as shown in figure 3, its structure is n-
100-100-7.The network is arranged one by input terminal RBM, two layers of hidden layer RBM that one layer of degree of freedom is n, output top layer
Softmax graders constitute a NN, wherein for each driving behavior, degree of freedom n is a variable.
It please refers to Fig. 4, in the present embodiment, has counted the 3-axis acceleration value of typical four kinds of driving behaviors, and draw song
Line, to driving behavior sequential piecewise analysis:
Figure 41 is static, and the time-domain curve of stationary state is a smooth straight line, and resultant acceleration value is attached most importance to close to 10
Power acceleration, when the vehicle is still, there is no variations by a relatively large margin within a sampling period.
Figure 42 is igniting, and fired state exists in regular hour early period tract shakes, and there are one for central acceleration value
A more apparent mutation peak segment.
Figure 43 is brake, and the acceleration value of braking state is by acute variation to gentle, and the Energy distribution of time series is by close
Collection can use peak value or energy diacritical point fire, is flame-out with other driving behaviors to gentle.
Figure 44 is normally travel, and there are certain periodicity for the changing rule of normally travel state, and peak value is all more
Obviously.
The above is the preferred embodiment of the present invention, it is noted that for those skilled in the art
For, without departing from the principles of the present invention, it can also make several improvements and retouch, these improvements and modifications
It should be regarded as protection scope of the present invention.
Claims (6)
1. a kind of method based on smart mobile phone automatic identification driving behavior, the method includes:In on smart mobile phone
Acceleration transducer acquisition information is set, Activity recognition is carried out by deep learning algorithm so that mobile terminal can obtain currently
The behavior of user judges the igniting, driving, flame-out behavior of user.
2. the method as described in claim 1, which is characterized in that using the real-time 3-axis acceleration obtained from mobile phone sensor
Data determine behavior switching point after being pre-processed using end-point detection algorithm, are believed by sliding window extract real-time time series
The time and frequency domain characteristics of simultaneously sequence of calculation segment are ceased, after choosing validity feature, when fusion primitive behavior information establishes complete with feature
Between input terminal of the tract as limited Boltzmann machine, hidden layer is converted to the identifiable bernoulli distribution mode of network, optimizes
More hidden layers of parameter preset are limited Boltzmann machine and are extracted to the feature for inputting client information, eventually by DBN(Deep
Belief Network, deep belief network)Realize the identification of driving behavior.
3. the method as described in claim 1, which is characterized in that utilize acceleration transducer acquisition letter built-in on smart mobile phone
Breath, and carry out the disposal of gentle filter;The matrix a=(a for the 100*3 that collected data are processed intox, ay, az), wherein axTable
Show the acceleration information in mobile phone coordinate system x-axis, ayIndicate the acceleration information in y-axis, azIndicate the acceleration information in z-axis,
Matrix a is pressed to the row vector b that mobile phone coordinate system x, y, z variation is 1*300 successively.
4. the method as described in claim 1, which is characterized in that due to the transient state driving behavior such as startup, igniting, brake, flame-out
There are obvious characteristic variations only in a bit of time series for event, and behavior similarity is higher within remaining period, simultaneously number
Discrimination is reduced according to cannot accurately extract behavior valid data section in gatherer process, therefore is driven using the detection of end-point detection algorithm
The effective time tract for sailing behavior event is chosen its time and frequency domain characteristics while inputting primitive behavior real value data and is carried out
Combinatory analysis.
5. the method as described in claim 1, which is characterized in that merge raw information with characteristic and establish full time sequence
Row section realizes the identification of driving behavior as the input of deep belief network, and by classification results Real-time Feedback to intelligent terminal.
6. the method as described in claim 1, which is characterized in that two layers of RBM builds network learning model, FFDBN network models
As shown in figure 3, its structure is n-100-100-7;The network is defeated by the input terminal RBM that one layer of degree of freedom is n, two layers of hidden layer RBM
Go out top layer and one softmax graders one NN of composition is set, wherein for each driving behavior, degree of freedom n is a variable.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710232230.4A CN108694407A (en) | 2017-04-11 | 2017-04-11 | A kind of driving behavior recognition methods based on mobile terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710232230.4A CN108694407A (en) | 2017-04-11 | 2017-04-11 | A kind of driving behavior recognition methods based on mobile terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108694407A true CN108694407A (en) | 2018-10-23 |
Family
ID=63843476
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710232230.4A Withdrawn CN108694407A (en) | 2017-04-11 | 2017-04-11 | A kind of driving behavior recognition methods based on mobile terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108694407A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109720353A (en) * | 2018-12-27 | 2019-05-07 | 南京航空航天大学 | A kind of driving behavior detection method based on smart phone |
| CN110006438A (en) * | 2019-02-15 | 2019-07-12 | 腾讯大地通途（北京）科技有限公司 | Navigation control method, device and computer equipment |
| CN110287838A (en) * | 2019-06-17 | 2019-09-27 | 韶关市启之信息技术有限公司 | A kind of monitoring method and system for driving to play mobile phone behavior |
| CN110765122A (en) * | 2019-11-07 | 2020-02-07 | 深圳鼎然信息科技有限公司 | Method, device and system for realizing data acquisition and driving evaluation based on SDK |
| CN111126438A (en) * | 2019-11-22 | 2020-05-08 | 北京理工大学 | Driving behavior recognition method and system |
| CN111860661A (en) * | 2020-07-24 | 2020-10-30 | 中国平安财产保险股份有限公司 | Data analysis method and device based on user behavior, electronic equipment and medium |
| CN114970705A (en) * | 2022-05-20 | 2022-08-30 | 深圳市有一说一科技有限公司 | Driving state analysis method, device, equipment and medium based on multi-sensing data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102156204A (en) * | 2010-02-11 | 2011-08-17 | 希姆通信息技术（上海）有限公司 | Method for measuring automobile acceleration by utilizing mobile phone |
| CN103871123A (en) * | 2014-03-28 | 2014-06-18 | 深圳市成为智能交通系统有限公司 | Vehicle traveling data recorder with driving behavior optimization function and use method of data recorder |
| CN104269026A (en) * | 2014-09-25 | 2015-01-07 | 同济大学 | Fatigue driving real-time monitoring and early warning method based on Android platform |
| CN105389984A (en) * | 2015-11-16 | 2016-03-09 | 北京智视信息科技有限公司 | Driving behavior identification method based on mobile terminal sensing information fusion |
-
2017
- 2017-04-11 CN CN201710232230.4A patent/CN108694407A/en not_active Withdrawn
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102156204A (en) * | 2010-02-11 | 2011-08-17 | 希姆通信息技术（上海）有限公司 | Method for measuring automobile acceleration by utilizing mobile phone |
| CN103871123A (en) * | 2014-03-28 | 2014-06-18 | 深圳市成为智能交通系统有限公司 | Vehicle traveling data recorder with driving behavior optimization function and use method of data recorder |
| CN104269026A (en) * | 2014-09-25 | 2015-01-07 | 同济大学 | Fatigue driving real-time monitoring and early warning method based on Android platform |
| CN105389984A (en) * | 2015-11-16 | 2016-03-09 | 北京智视信息科技有限公司 | Driving behavior identification method based on mobile terminal sensing information fusion |
Non-Patent Citations (1)
| Title |
|---|
| 王忠民等: "基于滑动窗特征融合的深信度网络驾驶行为识别", 《计算机应用研究》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109720353B (en) * | 2018-12-27 | 2020-11-17 | 南京航空航天大学 | Driving behavior detection method based on smart phone |
| CN109720353A (en) * | 2018-12-27 | 2019-05-07 | 南京航空航天大学 | A kind of driving behavior detection method based on smart phone |
| CN110006438A (en) * | 2019-02-15 | 2019-07-12 | 腾讯大地通途（北京）科技有限公司 | Navigation control method, device and computer equipment |
| CN110287838A (en) * | 2019-06-17 | 2019-09-27 | 韶关市启之信息技术有限公司 | A kind of monitoring method and system for driving to play mobile phone behavior |
| CN110287838B (en) * | 2019-06-17 | 2021-12-14 | 青岛民航凯亚系统集成有限公司 | Method and system for monitoring behaviors of driving and playing mobile phone |
| CN110765122A (en) * | 2019-11-07 | 2020-02-07 | 深圳鼎然信息科技有限公司 | Method, device and system for realizing data acquisition and driving evaluation based on SDK |
| CN110765122B (en) * | 2019-11-07 | 2022-05-24 | 深圳鼎然信息科技有限公司 | Method, device and system for realizing data acquisition and driving evaluation based on SDK |
| CN111126438A (en) * | 2019-11-22 | 2020-05-08 | 北京理工大学 | Driving behavior recognition method and system |
| CN111126438B (en) * | 2019-11-22 | 2023-11-14 | 北京理工大学 | Driving behavior recognition method and system |
| CN111860661A (en) * | 2020-07-24 | 2020-10-30 | 中国平安财产保险股份有限公司 | Data analysis method and device based on user behavior, electronic equipment and medium |
| CN111860661B (en) * | 2020-07-24 | 2024-04-30 | 中国平安财产保险股份有限公司 | Data analysis method and device based on user behaviors, electronic equipment and medium |
| CN114970705A (en) * | 2022-05-20 | 2022-08-30 | 深圳市有一说一科技有限公司 | Driving state analysis method, device, equipment and medium based on multi-sensing data |
| CN114970705B (en) * | 2022-05-20 | 2024-05-07 | 深圳市有一说一科技有限公司 | Running state analysis method, device, equipment and medium based on multi-sensing data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108694407A (en) | A kind of driving behavior recognition methods based on mobile terminal | |
| EP3533681B1 (en) | Method for detecting safety of driving behavior, apparatus and storage medium | |
| CN108989541A (en) | Session initiation device, system, vehicle and method based on situation | |
| CN105867179A (en) | Vehicle-borne voice control method, device and equipment | |
| CN106448050B (en) | A kind of smart mobile phone traffic hazard method for early warning and system based on vehicle noise | |
| CN107848478A (en) | The automatic identification of low speed collision and assessment | |
| CN107472247A (en) | A kind of constant-speed-cruise control method, apparatus, controller and automobile | |
| CN109285547A (en) | A kind of voice awakening method, apparatus and system | |
| CN106878303B (en) | A kind of vehicle-mounted T Box Information Security Defending Systems and method for teleinstruction | |
| CN102529885A (en) | Fingerprint-based speed limiting device of automatic transmission automobile, and control method thereof | |
| CN106476805A (en) | A kind of control method of safe driving of vehicle and terminal | |
| CN109636924A (en) | Vehicle multi-mode formula augmented reality system based on real traffic information three-dimensional modeling | |
| KR101473957B1 (en) | Apparatus and method for determining insurance premium based on driving pattern recognition | |
| CN108803623B (en) | Method for personalized driving of automatic driving vehicle and system for legalization of driving | |
| CN105957523A (en) | Vehicular system control method and device | |
| CN110143202A (en) | A kind of dangerous driving identification and method for early warning and system | |
| CN108437993A (en) | A kind of road anger vehicle drive automatically control system and method | |
| KR20100090048A (en) | The system for collecting and analyzing information related to driver's automobile manipulation | |
| CN111688700A (en) | Driving mode switching system, method and device and storage medium | |
| CN106427771A (en) | Sound control method and device | |
| CN109720353B (en) | Driving behavior detection method based on smart phone | |
| CN109835280B (en) | System for displaying vehicle state and driving behavior through voice recognition and vehicle | |
| CN108921977A (en) | A kind of vehicle carried driving person's abnormal driving behavioral value device and detection method | |
| CN108099785A (en) | A kind of traffic control method applied in intelligent vehicle | |
| CN112015261A (en) | Intelligent terminal driving mode identification method |
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: 20181023 |
|
| WW01 | Invention patent application withdrawn after publication |