CN108509999A - It is a kind of indignation drive detection and safe early warning method - Google Patents
It is a kind of indignation drive detection and safe early warning method Download PDFInfo
- Publication number
- CN108509999A CN108509999A CN201810294659.0A CN201810294659A CN108509999A CN 108509999 A CN108509999 A CN 108509999A CN 201810294659 A CN201810294659 A CN 201810294659A CN 108509999 A CN108509999 A CN 108509999A
- Authority
- CN
- China
- Prior art keywords
- sample
- tested
- indignation
- angry
- classification
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
- B60W2050/143—Alarm means
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Automation & Control Theory (AREA)
- Human Computer Interaction (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Emergency Alarm Devices (AREA)
Abstract
The invention discloses a kind of indignation to drive detection and safe early warning method, and by collection vehicle driving information, including travel speed, longitudinal acceleration, transverse acceleration is established angry driving data library, the driving condition of sample to be tested is detected using KNN algorithms.When sample to be tested drive parameter is close to angry drive parameter, it is determined as angry driving, and remind driver to control the emotion by sound early warning, ensures driving safety.Invention has exploitativeness, and indignation, which drives, detects accurate feature.
Description
Technical field
The invention belongs to car steering detection fields, and in particular to the detection method of driver's fierceness driving behavior and its pre-
Alarm method.
Background technology
With the fast development of China's economy, living standards of the people improve, and vehicle guaranteeding organic quantity all keeps increasing every year, side
While the person who happens to be on hand for an errand people go on a journey and promote economic development, also more risk, traffic accident enormous amount are brought to traffic safety.It drives
People is the direct participant of traffic, and driver on traffic accident influence because accounting for major part, studies have shown that driver is because in traffic
Accounting is up to 90% or more in cause of accident, wherein indignation, which drives, accounts for 3%-5%.Metropolitan traffic problems cause driver's anger
Anger mood is apparent, causes bad steering behavior, causes serious traffic safety risk.Therefore, indignation drives detection and safe early warning
It is particularly important.
A kind of angry driving condition detection method (application number CN105496369A) of patent, by normally being driven to driver
It sails and the observation of pulse situation of change under angry driving condition and relevant comparative's experiment, the change rate of selection pulse amplitude, master
Wave trains driver's indignation and drives to the range of decrease of dicrotic wave and three features of change rate of pulse frequency using neural network algorithm
State learning evaluation model is sailed, realizes angry driving condition detection.(ten thousand is flat, Wu Chaozhong, woods heroic bearing, and is waited to be based on confidence for document 1
The driver's indignation Emotion identification model Traffic transport system engineerings and information of rule base, 2015,15 (5):96-102.) discussing
In driver's indignation Emotion identification model of the text based on confidence rule base, blood flow pulse (BVP), skin conductivity are filtered out
(SC), four characteristic quantities of brain wave δ waves and β waves establish confidence rule base inference pattern, realize angry Emotion identification.
It in above-mentioned technology, needs that various physiological detection equipment, wearing is used to be not easy, interfere normal driving, survey
It is complicated to measure equipment, hardware cost is high, implements more difficult.
Invention content
The purpose of the present invention is to provide a kind of indignation to drive detection method and safe early warning method, and vehicle is travelled speed
Degree, longitudinal acceleration, transverse acceleration, the data schemas such as lateral direction of car deflection angle enter Testing index, according to detection data
Variation detection indignation drives and takes Forewarning Measures.
Technical solution of the invention is as follows:It is a kind of indignation drive detection and safe early warning method, including
Step 1:The vehicle driving parameters under normal driving and angry driving situation are acquired, normal driving parameter library is established
C1 and angry drive parameter library C2, wherein C1=(N1,N2,...,Nn), Ni=(ni1, ni2... nij), nijFor sample NiFeature
Amount, i.e., the parameter of normally travel state, j are number of parameters;C2=(A1,A2,...,An), Ai=(ai1, ai2... aij), wherein
aijFor sample AiCharacteristic quantity, i.e., the parameter under angry transport condition, j is number of parameters.
Step 2:By normal driving parameter library C1 and angry drive parameter library C2 mergers at training sample database T, wherein
T=(T1,T2,...,T2n), Ti=(ti1, ti2... tij), tijFor the characteristic parameter of driving condition, j is number of parameters.
Step 3:Using the characteristic parameter of the method for normalizing pretreatment training sample database T of min-max;
Formula is as follows:
Step 4:Sample to be tested X, X=(x are obtained in vehicle traveling process1, x2... xj), xiFor feature vector, as
Driving parameters;With the method for normalizing of the min-max in the step 3, sample to be tested is subjected to data prediction.
Step 5:Calculated using KNN sorting algorithms the distance between training sample T of sample to be tested X and known class or
Similarity d, whereinBy sample to be tested X and all training model T=
(T1,T2,...,T2n) distance or similarity be ranked up d0≤d1≤d2≤...≤d2n。
Find distance or similarity and k nearest sample to be tested X neighbours, i.e. K training sample;According to this k training
Classification belonging to sample judges the classification of sample to be tested X:If k training sample belongs to a classification, sample to be tested
Belong to that classification;Otherwise, the power for belonging to normal driving or indignation driving of the K distance or similarity is calculated separately
Weight, sample to be tested X belong to the maximum classification of weight.
Step 6:According to the judgement that step 5 makes sample to be tested X, if belonging to indignation drives classification, makes early warning and arrange
It applies, including reminds driver to adjust mood using sound early warning;If belonging to normal driving classification, return to step four.
Further, a kind of vehicle driving parameters of the step include Vehicle Speed, and longitudinal acceleration is lateral
Acceleration, lateral direction of car are biased to acceleration.
Further, the value of the K is determined by training samples number, generally less than the square root of number of training.K values
Determination, in mathematical method, if K values are too small, classification results are easily influenced by noise;It, may packet in neighbour if K values are too big
Point containing other too many classifications.Therefore, K values are typically the empirical rule determined using crosscheck, that is, are less than training sample
The square root of this number.
Further, the K distance is calculated in the step 5 or similarity belongs to normal driving or indignation
The weight of driving, sample to be tested X belong to the maximum classification of weight, include the following steps:
Step 1:The weight for belonging to angry drive parameter library C2 of K d in the step 5 is calculated, calculation is such as
UnderWherein, sim (X, Ti) it is X and i-th of arest neighbors object i.e. training sample TiIt
Between similarity or distance;
Step 2:The weight for belonging to angry drive parameter library C1 for comparing K d is:W (X, C1)=1-W (X, C2).
The beneficial effects of the invention are as follows:By collection vehicle driving information, including travel speed, longitudinal acceleration is lateral
Acceleration establishes training sample database, and the driving condition of sample to be tested is detected using KNN algorithms.When sample to be tested drive parameter connects
When nearly indignation drive parameter, it is determined as angry driving, and remind driver to control the emotion by sound early warning, ensures to drive peace
Entirely.Invention has exploitativeness, and indignation, which drives, detects accurate feature.
Description of the drawings
Fig. 1 is that the consistent indignation of the present invention drives detection and safe early warning method flow chart.
Specific implementation mode
In the following with reference to the drawings and specific embodiments, the present invention is furture elucidated, it should be understood that these embodiments are merely to illustrate
It the present invention rather than limits the scope of the invention, after having read the present invention, those skilled in the art are to of the invention each
The modification of kind equivalent form falls within the application range as defined in the appended claims.
As shown in Figure 1, a kind of indignation drives detection and safe early warning method, including
Step 1:The vehicle driving parameters under normal driving and angry driving situation are acquired, normal driving parameter library is established
C1 and angry drive parameter library C2, wherein C1=(N1,N2,...,Nn), Ni=(ni1, ni2... nij), nijFor sample NiFeature
Amount, i.e., the parameter of normally travel state, j are number of parameters;C2=(A1,A2,...,An), Ai=(ai1, ai2... aij), wherein
aijFor sample AiCharacteristic quantity, i.e., the parameter under angry transport condition, j is number of parameters.
Step 2:By normal driving parameter library C1 and angry drive parameter library C2 mergers at training sample T, wherein T
=(T1,T2,...,T2n), Ti=(ti1, ti2... tij), tijFor the characteristic parameter of driving condition, j is number of parameters.Step
Three:Using the characteristic parameter of the method for normalizing pretreatment training sample database T of min-max;The range of different characteristic parameter is respectively not
It is identical, in the range of characteristic is converted to a standard before application KNN algorithms.Method for normalizing is min-max
Standardization, the process transform characteristics make all values for being transformed data all fall in the range of 0~1,
Formula is as follows:
Step 4:Sample to be tested X, X=(x are obtained in vehicle traveling process1, x2... xj), xiFor feature vector, as
Driving parameters;With the method for normalizing of the min-max in the step 3, sample to be tested is subjected to data prediction.
Step 5:Calculated using KNN sorting algorithms the distance between training sample T of sample to be tested X and known class or
Similarity d, whereinBy sample to be tested X and all training model T=
(T1,T2,...,T2n) distance or similarity be ranked up d0≤d1≤d2≤...≤d2n, find distance or similarity with it is to be measured
K nearest sample X neighbours, i.e. K training sample;Classification belonging to this k training sample judges sample to be tested X's
Classification:If k training sample belongs to a classification, sample to be tested belongs to that classification;Otherwise, the K is calculated separately
The weight for belonging to normal driving or indignation driving of a distance or similarity, sample to be tested X belong to the maximum classification of weight.
Step 6:According to the judgement that step 5 makes sample to be tested X, if belonging to indignation drives classification, makes early warning and arrange
It applies, including reminds driver to adjust mood using sound early warning;If belonging to normal driving classification, return to step four.
Further, the vehicle driving parameters in the step 1 include Vehicle Speed, and longitudinal acceleration is lateral
Acceleration, lateral direction of car are biased to acceleration.Speed detector detects running speed, and speed is more than to limit drive speed to go as hypervelocity
It sails.Longitudinal accelerometer detects longitudinal driving acceleration, and longitudinal acceleration is more than certain threshold value, represents anxious accelerate and emergency brake garage
For.Lateral accelerometer detects lateral deflection acceleration, and transverse acceleration is more than certain threshold value, represents and acutely turns to, urgent to become
Road.
Further, the value of the K is determined by training samples number, is less than the square root of number of training.
Further, the K distance is calculated in the step 5 or similarity belongs to normal driving or indignation
The weight of driving, sample to be tested X belong to the maximum classification of weight, include the following steps:
Step 1:The weight for belonging to angry drive parameter library C2 of K d in the step 5 is calculated, calculation is such as
Under
Wherein, sim (X, Ti) it is X and i-th of arest neighbors object i.e. training sample
This TiBetween similarity or distance;
Step 2:The weight for belonging to normal driving parameter library C1 for comparing K d is:
W (X, C1)=1-W (X, C2).
The beneficial effects of the invention are as follows:By collection vehicle driving information, including travel speed, longitudinal acceleration is lateral
Acceleration establishes training sample database, and the driving condition of sample to be tested is detected using KNN algorithms.When sample to be tested drive parameter connects
When nearly indignation drive parameter, it is determined as angry driving, and remind driver to control the emotion by sound early warning, ensures to drive peace
Entirely.Invention has exploitativeness, and indignation, which drives, detects accurate feature.
Claims (4)
1. a kind of indignation drives detection and safe early warning method, it is characterised in that:Including
Step 1:Acquire the vehicle driving parameters under normal driving and angry driving situation, establish normal driving parameter library C1 and
Angry drive parameter library C2, wherein C1=(N1,N2,...,Nn), Ni=(ni1, ni2... nij), nijFor sample NiCharacteristic quantity,
That is the parameter of normally travel state, j are number of parameters;C2=(A1,A2,...,An), Ai=(ai1, ai2... aij), wherein aij
For sample AiCharacteristic quantity, i.e., the parameter under angry transport condition, j is number of parameters;
Step 2:By normal driving parameter library C1 and angry drive parameter library C2 mergers at training sample database T, T=(T1,
T2,...,T2n), wherein training sample Ti=(ti1, ti2... tij), tijFor the characteristic parameter of driving condition, j is number of parameters;
Step 3:Using the characteristic parameter in the method for normalizing pretreatment training sample database T of min-max;
Formula is as follows:
Step 4:Sample to be tested X, X=(x are obtained in vehicle traveling process1, x2... xj), xiFor feature vector, as traveling ginseng
Number;With the method for normalizing of the min-max in the step 3, sample to be tested is subjected to data prediction;
Step 5:The distance between sample to be tested X and the training sample of known class or similarity are calculated using KNN sorting algorithms
D, the wherein calculation of d are:By sample to be tested X and all training samples
T=(T1,T2,...,T2n) distance or similarity be ranked up, obtain d0≤d1≤d2≤...≤d2n,
Selected distance or similarity and k nearest sample to be tested X neighbours, i.e. K training sample;According to this k training sample
Affiliated classification judges the classification of sample to be tested X:If k training sample belongs to a classification, sample to be tested X belongs to
That classification;Otherwise, calculate separately it is described K distance or similarity belong to normal driving parameter library C1 or indignation drive ginseng
The weight of number library C2, sample to be tested X belong to the maximum classification of weight;
Step 6:According to the judgement that step 5 makes sample to be tested X, if belonging to indignation drives classification, Forewarning Measures are made,
Including reminding driver to adjust mood using sound early warning;If belonging to normal driving classification, return to step four.
2. a kind of indignation according to claim 1 drives detection and safe early warning method, it is characterised in that:The step 1
The vehicle driving parameters of kind include Vehicle Speed, longitudinal acceleration, transverse acceleration, lateral direction of car deviation acceleration.
3. a kind of indignation according to claim 1 drives detection and safe early warning method, it is characterised in that:The value of the K
It is determined by training samples number, is less than the square root of number of training.
4. a kind of indignation according to claim 1 drives detection and safe early warning method, it is characterised in that:The step 5
In calculate separately the K distance or similarity belong to normal driving parameter library C1 from or angry drive parameter library C2 power
Weight, sample to be tested X belong to the maximum classification of weight, include the following steps:
Step 1:The weight for belonging to angry drive parameter library C2 of K d in the step 5 is calculated, calculation is as follows
Wherein, sim (X, Ti) it is X and i-th of arest neighbors object i.e. training sample Ti
Between similarity or distance;
Step 2:The weight for belonging to angry drive parameter library C1 for comparing K d is:
W (X, C1)=1-W (X, C2).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810294659.0A CN108509999A (en) | 2018-03-30 | 2018-03-30 | It is a kind of indignation drive detection and safe early warning method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810294659.0A CN108509999A (en) | 2018-03-30 | 2018-03-30 | It is a kind of indignation drive detection and safe early warning method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108509999A true CN108509999A (en) | 2018-09-07 |
Family
ID=63380187
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810294659.0A Pending CN108509999A (en) | 2018-03-30 | 2018-03-30 | It is a kind of indignation drive detection and safe early warning method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108509999A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109407504A (en) * | 2018-11-30 | 2019-03-01 | 华南理工大学 | A kind of personal safety detection system and method based on smartwatch |
CN109498041A (en) * | 2019-01-15 | 2019-03-22 | 吉林大学 | Driver road anger state identification method based on brain electricity and pulse information |
CN111383362A (en) * | 2018-12-29 | 2020-07-07 | 北京骑胜科技有限公司 | Safety monitoring method and device |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105496369A (en) * | 2015-10-19 | 2016-04-20 | 南京邮电大学 | Angry driving state detection method |
CN107235045A (en) * | 2017-06-29 | 2017-10-10 | 吉林大学 | Consider physiology and the vehicle-mounted identification interactive system of driver road anger state of manipulation information |
-
2018
- 2018-03-30 CN CN201810294659.0A patent/CN108509999A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105496369A (en) * | 2015-10-19 | 2016-04-20 | 南京邮电大学 | Angry driving state detection method |
CN107235045A (en) * | 2017-06-29 | 2017-10-10 | 吉林大学 | Consider physiology and the vehicle-mounted identification interactive system of driver road anger state of manipulation information |
Non-Patent Citations (1)
Title |
---|
商强等: "基于谱聚类与RS-KNN的城市快速路交通状态判别", 《华南理工大学学报(自然科学版)》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109407504A (en) * | 2018-11-30 | 2019-03-01 | 华南理工大学 | A kind of personal safety detection system and method based on smartwatch |
CN111383362A (en) * | 2018-12-29 | 2020-07-07 | 北京骑胜科技有限公司 | Safety monitoring method and device |
CN109498041A (en) * | 2019-01-15 | 2019-03-22 | 吉林大学 | Driver road anger state identification method based on brain electricity and pulse information |
CN109498041B (en) * | 2019-01-15 | 2021-04-16 | 吉林大学 | Driver road rage state identification method based on electroencephalogram and pulse information |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Ma et al. | A comparative study of aggressive driving behavior recognition algorithms based on vehicle motion data | |
Chu et al. | Curve speed model for driver assistance based on driving style classification | |
Tang et al. | Driver lane change intention recognition of intelligent vehicle based on long short-term memory network | |
CN103531042A (en) | Rear-end collision pre-warning method based on driver types | |
CN110796207A (en) | Fatigue driving detection method and system | |
CN108509999A (en) | It is a kind of indignation drive detection and safe early warning method | |
CN106022561A (en) | Driving comprehensive evaluation method | |
CN111311093B (en) | Road intersection risk assessment and early warning method based on driver physiological data | |
CN103471865A (en) | Train suspension system failure isolation method based on LDA method | |
CN108769104B (en) | Road condition analysis and early warning method based on vehicle-mounted diagnosis system data | |
CN109229108A (en) | A kind of driving behavior safe evaluation method based on driving fingerprint | |
CN113581188A (en) | Commercial vehicle driver driving style identification method based on Internet of vehicles data | |
CN104598993A (en) | Blink time based driver fatigue driving prediction method | |
Wang et al. | A probabilistic approach to measuring driving behavior similarity with driving primitives | |
Harkous et al. | A two-stage machine learning method for highly-accurate drunk driving detection | |
CN114037015A (en) | Driving behavior safety analysis method based on driving mode primitive | |
CN113989534B (en) | Bus inter-station load identification method and system based on multi-source operation data | |
CN112215044A (en) | Driving tendency identification method based on probabilistic neural network | |
Wang et al. | Recognition of trip-based aggressive driving: A system integrated with Gaussian mixture model structured of factor-analysis, and hierarchical clustering | |
CN116092037B (en) | Vehicle type identification method integrating track space-semantic features | |
Anil et al. | Driver behavior analysis using K-means algorithm | |
CN110525446A (en) | A kind of automobile pressure lane-change decision safe early warning method considering mood | |
Li et al. | Modeling and verification of heavy-duty truck drivers’ car-following characteristics | |
Schmidt | Tire Pressure Monitoring using Weighted Horizontal Visibility Graphs | |
Sun et al. | Effects of Individual Differences on Measurements’ Drowsiness-Detection Performance |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180907 |
|
RJ01 | Rejection of invention patent application after publication |