CN110442113A - Abnormal driving condition intelligence pre-judging method and Intelligent terminal for Internet of things - Google Patents
Abnormal driving condition intelligence pre-judging method and Intelligent terminal for Internet of things Download PDFInfo
- Publication number
- CN110442113A CN110442113A CN201910740761.3A CN201910740761A CN110442113A CN 110442113 A CN110442113 A CN 110442113A CN 201910740761 A CN201910740761 A CN 201910740761A CN 110442113 A CN110442113 A CN 110442113A
- Authority
- CN
- China
- Prior art keywords
- driving
- data
- abnormal
- vehicle
- running data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0221—Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention provides a kind of abnormal driving condition intelligence pre-judging method and Intelligent terminal for Internet of things.The present invention is according to driver in after drinking, when drug abuse, morbid state, fatigue driving, it is likely to occur neurological progression and psychiatric disorders feature, lead to snakelike traveling, and the characteristics of generating the relative distance data of the traveling angle-data different from normal driving, vehicle and reference line, normal driving is judged whether it is by analyzing collected running data, and is compared with vehicle operation data collection to further determine whether as abnormal driving and affiliated abnormal driving condition classification.There is technical solution of the present invention reduction executive cost, comparison vehicle carried alcohol sensor test mode to be easier to popularization, not invasion of privacy;Comparison human facial expression recognition mode has saved the high advantage of the cost of image recognition, accuracy.
Description
Technical field
The present invention relates to field of vehicle safety, especially a kind of abnormal driving condition intelligence pre-judging method and Internet of Things intelligence
It can terminal.
Background technique
As vehicle is more and more, traffic police interception car and checks whether investigate and prosecute driver one by one one by one at each crossing
There are the illegal motoring offences such as drunk driving to need the manpower, material resources and financial resources put into will be more and more.In existing driving condition
In monitoring method, one is judging whether drunk driving in such a way that vehicle installs alcohol sensor, this kind of method is due to cumbersome
It is not easy to be received by car owner, and is easy to be plugged sensor acquisition port cheating, when Che Shangyou spirituosity article, is easy to produce
Erroneous judgement;One is the facial expressions of the method analysis driver using image recognition to judge that the state of driving, such method are being answered
Invasion of privacy is understood with middle, and needs to handle a large amount of image data, the at high cost while abnormal driving shape of image procossing
State and facial expression relevance are smaller, and analysis result is also not accurate enough.
In view of the above-mentioned problems, not yet proposing effective technical solution at present.
Summary of the invention
The present invention provides a kind of abnormal driving condition intelligence pre-judging method and Intelligent terminal for Internet of things, at least to solve to carry on the back
The prior art mentioned in scape technology judges abnormal driving condition invasion of privacy, is not easy to implement, image recognition
The at high cost and not accurate enough technical problem of judging result.
According to an aspect of the present invention, a kind of abnormal driving condition intelligence pre-judging method is provided, comprising the following steps:
Acquire the running data in certain period of time [t0, t1];
A possibility that driver belongs to abnormal driving condition is judged according to the running data;
Repetition judges a possibility that driver belongs to abnormal driving condition in multiple periods, if repeatedly judging driving condition
Then increase degree a possibility that driver belongs to abnormal driving condition for abnormal driving;
Wherein, the running data is since a certain moment t0, and section △ t is collected related to time t at regular intervals
Running data value composition running data sequence, the recording method of the running data value is with t0 moment collected traveling
It is worth on the basis of data value, the positive negative increment being worth on the basis of subsequent running data value.
Wherein, the running data includes: the relative distance data for travelling angle-data, vehicle and reference line, wherein institute
Stating traveling angle-data includes but is not limited to: the angle-data of the vehicle when driving of vehicle, the rotational angle data of steering wheel, vehicle
Angle data with reference line;Wherein, the relative distance data of the vehicle and reference line are within the same period, with solid
The data of the relative distance of collected vehicle and reference line on the basis of fixed reference line;The reference line includes but is not limited to vehicle
Road graticule.
It should be noted that the abnormal driving condition include: drive when intoxicated, driving of taking drugs, morbid state drives, fatigue drives
It sails, wherein it is the driving condition of the driver of the sudden state of an illness occur in driving procedure that the morbid state, which drives,;When driver is in
When abnormal driving condition, the physiology of driver, the state of mind can with it is inconsistent under normal condition, be easy to cause steering wheel control
Bad, throttle and brake control are bad, to make the opposite of the traveling angle-data in vehicle travel process, vehicle and reference line
Range data and the relative distance data comparison of traveling angle-data, vehicle and reference line under normal driving state can show
Difference;Wherein, when in drive when intoxicated state when, driver be easy to appear the visual field become smaller, blurred vision it is unstable;When in suction
When driving with poison is sailed, driver, which is easy to appear, to shake the head, is spiritual excited;When being driven in morbid state, due to being generally the sudden state of an illness, drive
The person's of sailing vehicle control ability can mutate;When being in fatigue driving, driver is easy to appear eyes regulating power and is lower very
To sleep;Therefore the classification of different abnormal driving conditions, driver also have different neurological progression and spirituality barrier
Hinder feature, to generate different running datas.
For example, the driver to drive when intoxicated, it may appear that " snakelike traveling ", i.e., suddenly left, suddenly right drift can be presented in wheelpath
Move, so as to cause vehicle track can also present it is snakelike, further with the traveling number of vehicle driving trace linear correlation
It can also be presented according to the running data curve fitted snakelike, the running data includes: traveling angle-data, vehicle and reference line
Relative distance data.
Preferably, the method for a possibility that driver belongs to abnormal driving condition is judged according to the running data, is wrapped
It includes:
The running data is fitted to a time and the relevant running data curve of running data value, and judges the traveling
Whether data and curves are serpentine curve, belong to abnormal driving possibility degree if it is, increasing;
A possibility that belonging to abnormal driving condition is judged compared with running data collection using the running data, wherein described
Running data collection includes: the relative distance data set of the traveling angle-data collection of normal driving, vehicle and reference line, abnormal to drive
The relative distance data set of the traveling angle-data collection, vehicle and reference line sailed, wherein the running data collection of abnormal driving
Classification includes but is not limited to: driving when intoxicated, driving of taking drugs, morbid state driving, fatigue driving, using the side compared with running data collection
Method can further judge the type of abnormal driving condition.
Preferably, described to judge that abnormal driving by judging whether the running data curve is serpentine curve
The method of property, comprising the following steps:
Judge all extreme points of the running data curve and extreme value, extreme value is formed into extreme value sequence;
Two adjacent extreme values of the extreme value sequence one by one in order fluctuate if meeting and subtracting each other rear absolute value in serpentine curve
In range, then it is labeled as T, if being labeled as F not in the serpentine curve fluctuation range, obtains including the first of T and F sentencing
Disconnected sequence;
Sequence is judged according to described first, if occurring judging sequence dithering threshold less than second between two T of arbitrary neighborhood
F then removes the F between two T, obtains including the second of T and F judging sequence;
Sequence is judged according to described second, if there is continuous T, it is suspicious abnormal to judge whether the number of the continuous T is greater than
Number threshold value is travelled, if then increasing the abnormal suspicious number of driving;
Continue to calculate the abnormal suspicious number of driving according to above-mentioned steps, the abnormal suspicious number of driving is more, then
A possibility that abnormal driving, degree was bigger;
Wherein, the serpentine curve fluctuation range, for setting after two extreme values adjacent in the extreme value sequence are subtracted each other
When absolute value is in a certain range, then a serpentine curve fluctuation is judged as YES;
The T, it is described for marking there are the position of the two neighboring extreme value of serpentine curve fluctuation in the running data curve
F is used to mark the position of the two neighboring extreme value fluctuated in the running data curve there is no serpentine curve;
Described second judges sequence dithering threshold, F most numbers occurs for setting to work as between two adjacent T, allows to connect
It is shaken in continuous serpentine curve fluctuation;
The suspicious abnormal travel times threshold value, for setting as at least how many continuous T, then there are snakelike songs for judgement
Line segment;
The abnormal suspicious number of driving, for recording the serpentine curve segment number, according to serpentine curve segment number
A possibility that judging abnormal driving degree.
It should be noted that obtained extreme value sequence is the alternate extreme value sequence of maximum value minimum in the above method,
Two i.e. adjacent extreme values are respectively maximum and minimum, can be obtained by the absolute value after taking maximum to subtract each other with minimum
To the degree of fluctuation of curve, and whether serpentine curve is the S type curve of continuous up and down or left and right fluctuation, deposited by judgment curves
It may determine that whether the running data curve is serpentine curve in continuous larger fluctuation.
Preferably, according to the second aspect of the invention, a kind of Intelligent terminal for Internet of things is provided, comprising:
Storage medium, for storing program and running data;
Main control chip, for signal processing and operation, storage program;
Gyro module, for obtaining the traveling angle-data of vehicle in real time;
Locating module is communicated, for realizing networking and positioning function for the Intelligent terminal for Internet of things;
Camera module, for clapping the image picked up the car in the process of moving, to further be obtained by the method for image recognition
Obtain the relative distance data of the vehicle and reference line, the angle-data of the vehicle and reference line;
Vehicle control data obtains module, for obtaining the rotational angle data of the steering wheel;
Pronunciation unit is used for voice broadcast.
Preferably, if it is determined that abnormal driving condition, then further judgement belongs to and drives when intoxicated, is driving of taking drugs, sick
State drives, the classification in fatigue driving, while reminding driver attentively to drive using modes such as voice broadcasts, reminding the row on periphery
It sails vehicle and pays attention to the abnormal vehicle of the driving nearby;And the section is likely to be to the geography of the vehicle of abnormal driving condition
Location information, unique identifying number information, quantity information, driver information are pushed to traffic police and investigation are assisted to drive when intoxicated, take drugs and drive
The illegal act of violating regulations such as sail;If it is determined that driver is that morbid state drives, then can contact the 110 or 120 ill drivers of help into
Row alarm and the rescue of request first-aid centre;Simultaneously by the running data of the abnormal driving condition in multiple period according to institute
Belong to the running data collection that classification is saved in the abnormal driving condition, for mentioning a possibility that abnormal driving condition to analyze
For more data sets.
Preferably, since the running data includes: the relative distance data for travelling angle-data, vehicle and reference line,
One of the relative distance data of analysis traveling angle-data, vehicle and reference line data or a variety of data can be carried out
The anticipation of abnormal driving condition is analyzed.
In the present invention, be according to driver drive when intoxicated, driving of taking drugs, morbid state driving, fatigue driving etc. is abnormal drives
When sailing state, in fact it could happen that neurological progression and psychiatric disorders feature cause vehicle to generate the traveling different from normal driving
The characteristics of relative distance data of angle-data, vehicle and reference line, by the way that collected running data is fitted to traveling number
According to curve, and according to occurring serpentine curve segment number in running data curve come a possibility that judging abnormal driving;Into one
Step, running data is compared with the running data collection under driving condition under normal driving state, abnormal to judge to belong to
A possibility that abnormal driving, and judge to belong to and drive when intoxicated, drivings of taking drugs, ill driving, which kind of classification in fatigue driving.
Therefore, executive cost, comparison alcohol sensor mode is easy to spread, it is personal hidden not invade with reducing for technical solution of the present invention
It is private;Comparison human facial expression recognition mode has saved the high advantage of the cost of image recognition, accuracy.
Detailed description of the invention
Fig. 1 is a kind of abnormal driving condition intelligent control method schematic diagram provided in an embodiment of the present invention.
Fig. 2 is provided in an embodiment of the present invention to be judged not by judging whether the running data curve is serpentine curve
The method schematic diagram of normal driving possibility.
Fig. 3 is the module diagram of the Intelligent terminal for Internet of things of one kind provided in an embodiment of the present invention.
Fig. 4 is the relative distance schematic diagram data of acquisition vehicle and reference line provided in an embodiment of the present invention.
Specific embodiment
Fig. 1 is a kind of abnormal driving condition intelligence pre-judging method according to an embodiment of the present invention, comprising the following steps:
Step S11 acquires the running data in certain period of time [t0, t1];
Step S12 judges a possibility that driver belongs to abnormal driving condition according to the running data;
Step S13, repetition judge a possibility that driver belongs to abnormal driving condition in multiple periods, if repeatedly judgement
Driving condition is that abnormal driving then increases degree a possibility that driver belongs to abnormal driving condition;
Wherein, the running data is since a certain moment t0, and section △ t is collected related to time t at regular intervals
Running data value composition running data sequence, the recording method of the running data value is with t0 moment collected traveling
It is worth on the basis of data value, the positive negative increment being worth on the basis of subsequent running data value.
Wherein, the running data includes: the relative distance data for travelling angle-data, vehicle and reference line, wherein institute
Stating traveling angle-data includes but is not limited to: the angle-data of the vehicle when driving of vehicle, the rotational angle data of steering wheel, vehicle
Angle data with reference line;Wherein, the relative distance data of the vehicle and reference line are within the same period, with solid
The data of the relative distance of collected vehicle and reference line on the basis of fixed reference line;The reference line includes but is not limited to vehicle
Road graticule.
The curve further depicted with the positively related running data of vehicle driving trace can also present it is snakelike, it is described
Running data includes: the relative distance data for travelling angle-data, vehicle and reference line.
Further, the method for a possibility that driver belongs to abnormal driving condition is judged according to the running data,
Include:
The running data is fitted to a time and the relevant running data curve of running data value, and judges the traveling
Whether data and curves are serpentine curve, belong to abnormal driving possibility degree if it is, increasing;
A possibility that belonging to abnormal driving condition is judged compared with running data collection using the running data, wherein described
Running data collection includes: the relative distance data set of the traveling angle-data collection of normal driving, vehicle and reference line, abnormal to drive
The relative distance data set of the traveling angle-data collection, vehicle and reference line sailed, wherein the running data collection of abnormal driving
Classification includes but is not limited to: driving when intoxicated, driving of taking drugs, morbid state driving, fatigue driving, using the side compared with running data collection
Method can further judge the type of abnormal driving condition.
Fig. 2 is according to an embodiment of the present invention to be judged not by judging whether the running data curve is serpentine curve
The method of normal driving possibility, comprising the following steps:
Step S21 judges all extreme points of the running data curve and extreme value, and extreme value is formed extreme value sequence;
Step S22, two adjacent extreme values of the extreme value sequence one by one, subtract each other rear absolute value snakelike if meeting in order
In curve fluctuation range, then it is labeled as T, if being labeled as F not in the serpentine curve fluctuation range, obtaining including T and F
First judge sequence;
Step S23 judges sequence according to described first, if occurring judging that sequence is trembled less than second between two T of arbitrary neighborhood
Dynamic threshold value F obtains including the second of T and F judging sequence then by the F removal between two T;
Step S24 judges sequence according to described second, if there is continuous T, judging whether the number of the continuous T is greater than can
Abnormal traveling number threshold value is doubted, if then increasing the abnormal suspicious number of driving;
Step S25 continues to calculate the abnormal suspicious number of driving according to above-mentioned steps, the abnormal suspicious number of driving
More, then degree is bigger a possibility that abnormal driving;
Wherein, the serpentine curve fluctuation range, for setting after two extreme values adjacent in the extreme value sequence are subtracted each other
When absolute value is in a certain range, then a serpentine curve fluctuation is judged as YES;
The T, it is described for marking there are the position of the two neighboring extreme value of serpentine curve fluctuation in the running data curve
F is used to mark the position of the two neighboring extreme value fluctuated in the running data curve there is no serpentine curve;
Described second judges sequence dithering threshold, F most numbers occurs for setting to work as between two adjacent T, allows to connect
It is shaken in continuous serpentine curve fluctuation;
The suspicious abnormal travel times threshold value, for setting as at least how many continuous T, then there are snakelike songs for judgement
Line segment;
The abnormal suspicious number of driving, for recording the serpentine curve segment number, according to serpentine curve segment number
A possibility that judging abnormal driving degree.
For example, being worth on the basis of the t0 moment since the t0 moment, if a reference value is 0;Every 500ms from the Internet of Things
The gyroscope of intelligent terminal obtains the traveling angle value of a vehicle, wherein the traveling angle value is relative to the benchmark
The increment of value arrives the t1 moment, acquires 9s altogether, obtain sequence:
[0, 0, 2, 3, 4, 3, 3.1, 0, 40, 19,20,22,-20, 20, -20, 20, -20, 20];
According to above-mentioned sequence fit at traveling data and curves, and extreme value is calculated, obtains extreme value sequence:
[0,4,3,3.1,0,40,19,22,-20,20,-20,20,-20,20];
If serpentine curve fluctuation range is [10,50], the two neighboring extreme value of extreme value sequence is subtracted each other in order, for example, the 1st
The absolute value that a extreme value and the 2nd extreme value are subtracted each other is 4, not in serpentine curve fluctuation range, is labeled as F;2nd extreme value and
The absolute value that 3 extreme values are subtracted each other is 1, not in serpentine curve fluctuation range, is labeled as F;13rd extreme value and the 14th extreme value
The absolute value subtracted each other is 40, in serpentine curve fluctuation range, is labeled as T;Finally obtain the first judgement sequence:
[F,F,F,F,F,F,F,T,F,F,T,T,T,T,T];
If second judges sequence dithering threshold for 2, i.e., when occurring judge that sequence dithering threshold is a less than second between two neighboring T
When F, then F is removed, obtains the second judgement sequence:
[F,F,F,F,F,F,F,T,T,T,T,T,T];
If the initial abnormal suspicious number of driving is 0, if suspicious abnormal travel times threshold value is 5, above-mentioned second judgement is judged
There is the continuously number of a T and continuous T to be greater than the number of suspicious abnormal travel times threshold value being 1 in sequence, therefore this is sentenced
It is disconnected to obtain that abnormal to drive suspicious number be finally 1;
Continue to record the suspicious number of the abnormal driving according to above-mentioned steps and add up, the abnormal suspicious number of driving is got over
More, then degree is bigger a possibility that abnormal driving.
Fig. 3 is a kind of Intelligent terminal for Internet of things according to the present embodiment, comprising:
Storage medium 32, for storing program and running data;
Main control chip 31, for signal processing and operation, storage program;
Gyro module 33, for obtaining the traveling angle-data of vehicle in real time;
Locating module 34 is communicated, for realizing networking and positioning function for the Intelligent terminal for Internet of things;
Camera module 35, for clapping the image picked up the car in the process of moving, to further pass through the method for image recognition
Obtain the relative distance data of the vehicle and reference line, the angle-data of the vehicle and reference line;
Vehicle control data obtains module 36, for obtaining the rotational angle data of the steering wheel;
Pronunciation unit 37 is used for voice broadcast.
It should be noted that being generally provided with the biography of the rotational angle data of acquisition steering wheel in the control system of vehicle
Sensor obtains module by vehicle control data and vehicle control system communicates, can obtain the rotational angle of the steering wheel
Data.
Fig. 4 is the relative distance schematic diagram data for acquiring vehicle and reference line, wherein 41 be vehicle, and 42 be benchmark line, i.e.,
Traffic lane line, 43 be the relative distance of vehicle 41 and reference line 42, and 44 be the driving trace of snakelike traveling, passes through image recognition
Vehicle lane graticule can be identified and be calculated the relative distance of vehicle 41 Yu reference line 42 by method.Acquire vehicle and reference line
When relative distance data, to be worth on the basis of the relative distance of t0 moment collected vehicle 41 and reference line 42, trailer record value
For the positive negative increment relative to a reference value.It should be noted that acquisition vehicle and reference line angle data and acquisition vehicle with
The relative distance data of reference line are similar, do not illustrate here.
Further, if it is determined that abnormal driving condition, then further judgement belong to drive when intoxicated, driving of taking drugs,
Classification in morbid state driving, fatigue driving, while reminding driver attentively to drive using modes such as voice broadcasts, reminding periphery
Driving vehicle pays attention to the abnormal vehicle of the driving nearby;And the section is likely to be to the ground of the vehicle of abnormal driving condition
Reason location information, unique identifying number information, quantity information, driver information are pushed to traffic police and investigation are assisted to drive when intoxicated, take drugs
The illegal acts of violating regulations such as driving;If it is determined that driver is that morbid state drives, then the ill driver of 110 or 120 helps can be contacted
It is alarmed and first-aid centre is requested to rescue;Simultaneously by the running data of the abnormal driving condition in multiple period according to
Generic is saved in the running data collection of the abnormal driving condition, for being a possibility that analyzing abnormal driving condition
More data sets are provided.
In the present invention, be according to driver drive when intoxicated, driving of taking drugs, morbid state driving, fatigue driving etc. is abnormal drives
When sailing state, in fact it could happen that neurological progression and psychiatric disorders feature cause vehicle to generate the traveling different from normal driving
The characteristics of relative distance data of angle-data, vehicle and reference line, by the way that collected running data is fitted to traveling number
According to curve, and according to occurring serpentine curve segment number in running data curve come a possibility that judging abnormal driving;Into one
Step, running data is compared with the running data collection under driving condition under normal driving state, abnormal to judge to belong to
A possibility that abnormal driving, and judge to belong to and drive when intoxicated, drivings of taking drugs, ill driving, which kind of classification in fatigue driving.
Therefore, executive cost, comparison alcohol sensor mode is easy to spread, it is personal hidden not invade with reducing for technical solution of the present invention
It is private;Comparison human facial expression recognition mode has saved the high advantage of the cost of image recognition, accuracy.
The preferred embodiment of the present invention has been described in detail above.It should be appreciated that those skilled in the art without
It needs creative work according to the present invention can conceive and makes many modifications and variations.Therefore, all technologies in the art
Personnel are available by logical analysis, reasoning, or a limited experiment on the basis of existing technology under this invention's idea
Technical solution, all should be within the scope of protection determined by the claims.
Claims (7)
1. a kind of abnormal driving condition intelligence pre-judging method, which comprises the following steps:
Acquire the running data in certain period of time [t0, t1];
A possibility that driver belongs to abnormal driving condition is judged according to the running data;
Repetition judges a possibility that driver belongs to abnormal driving condition in multiple periods, if repeatedly judging driving condition
Then increase degree a possibility that driver belongs to abnormal driving condition for abnormal driving;
Wherein, the running data is since a certain moment t0, and section △ t is collected related to time t at regular intervals
Running data value composition running data sequence, the recording method of the running data value is with t0 moment collected traveling
It is worth on the basis of data value, the positive negative increment being worth on the basis of subsequent running data value.
2. a kind of abnormal driving condition intelligence pre-judging method as described in claim 1, which is characterized in that the running data
It include: the relative distance data for travelling angle-data, vehicle and reference line, wherein the traveling angle-data includes but unlimited
In: the angle-data of the vehicle when driving of vehicle, the rotational angle data of steering wheel, the angle data of vehicle and reference line;Its
In, the relative distance data of the vehicle and reference line are to be collected on the basis of fixed reference line within the same period
Vehicle and reference line relative distance data;The reference line includes but is not limited to traffic lane line.
3. a kind of abnormal driving condition intelligence pre-judging method as described in claim 1, which is characterized in that described abnormal to drive
The state of sailing include: drive when intoxicated, driving of taking drugs, morbid state drive, fatigue driving, wherein it is described morbid state drive be driving procedure in
There is the driving condition of the driver of the sudden state of an illness;When driver is in abnormal driving condition, the physiology of driver, essence
Refreshing state can with it is inconsistent under normal condition, be easy to cause steering wheel control bad, throttle and brake control it is bad, to make vehicle
The relative distance data of traveling angle-data, vehicle and reference line in driving process and the traveling angle under normal driving state
The relative distance data comparison of degree evidence, vehicle and reference line can show difference;Wherein, when in drive when intoxicated state when,
Driver be easy to appear the visual field become smaller, blurred vision it is unstable;When driving in drug abuse, driver, which is easy to appear, to shake the head, is smart
Mind is excited;When driving in morbid state, due to being generally the sudden state of an illness, driver vehicle's control ability can mutate;When
When in fatigue driving, driver, which is easy to appear eyes regulating power and is lower, even to sleep;Therefore different abnormal driving shape
The classification of state, driver also has different neurological progression and psychiatric disorders feature, to generate different running datas.
4. a kind of abnormal driving condition intelligence pre-judging method as described in claim 1, which is characterized in that according to the traveling
The method that data judge a possibility that driver belongs to abnormal driving condition, comprising:
The running data is fitted to a time and the relevant running data curve of running data value, and judges the traveling
Whether data and curves are serpentine curve, belong to abnormal driving possibility degree if it is, increasing;
A possibility that belonging to abnormal driving condition is judged compared with running data collection using the running data, wherein described
Running data collection includes: the relative distance data set of the traveling angle-data collection of normal driving, vehicle and reference line, abnormal to drive
The relative distance data set of the traveling angle-data collection, vehicle and reference line sailed, wherein the running data collection of abnormal driving
Classification includes but is not limited to: driving when intoxicated, driving of taking drugs, morbid state driving, fatigue driving, using the side compared with running data collection
Method can further judge the type of abnormal driving condition.
5. a kind of abnormal driving condition intelligence pre-judging method as described in claim 1, which is characterized in that described to pass through judgement
Whether the running data curve is serpentine curve to judge the abnormal method for driving possibility, comprising the following steps:
Judge all extreme points of the running data curve and extreme value, extreme value is formed into extreme value sequence;
Two adjacent extreme values of the extreme value sequence one by one in order fluctuate if meeting and subtracting each other rear absolute value in serpentine curve
In range, then it is labeled as T, if being labeled as F not in the serpentine curve fluctuation range, obtains including the first of T and F sentencing
Disconnected sequence;
Sequence is judged according to described first, if occurring judging sequence dithering threshold less than second between two T of arbitrary neighborhood
F then removes the F between two T, obtains including the second of T and F judging sequence;
Sequence is judged according to described second, if there is continuous T, it is suspicious abnormal to judge whether the number of the continuous T is greater than
Number threshold value is travelled, if then increasing the abnormal suspicious number of driving;
Continue to calculate the abnormal suspicious number of driving according to above-mentioned steps, the abnormal suspicious number of driving is more, then
A possibility that abnormal driving, degree was bigger;
Wherein, the serpentine curve fluctuation range, for setting after two extreme values adjacent in the extreme value sequence are subtracted each other
When absolute value is in a certain range, then a serpentine curve fluctuation is judged as YES;
The T, it is described for marking there are the position of the two neighboring extreme value of serpentine curve fluctuation in the running data curve
F is used to mark the position of the two neighboring extreme value fluctuated in the running data curve there is no serpentine curve;
Described second judges sequence dithering threshold, F most numbers occurs for setting to work as between two adjacent T, allows to connect
It is shaken in continuous serpentine curve fluctuation;
The suspicious abnormal travel times threshold value, for setting as at least how many continuous T, then there are snakelike songs for judgement
Line segment;
The abnormal suspicious number of driving, for recording the serpentine curve segment number, according to serpentine curve segment number
A possibility that judging abnormal driving degree.
6. a kind of Intelligent terminal for Internet of things characterized by comprising
Storage medium, for storing program and running data;
Main control chip, for signal processing and operation, storage program;
Gyro module, for obtaining the traveling angle-data of vehicle in real time;
Locating module is communicated, for realizing networking and positioning function for the Intelligent terminal for Internet of things;
Camera module, for clapping the image picked up the car in the process of moving, to further be obtained by the method for image recognition
Obtain the relative distance data of the vehicle and reference line, the angle-data of the vehicle and reference line;
Vehicle control data obtains module, for obtaining the rotational angle data of the steering wheel;
Pronunciation unit is used for voice broadcast.
7. a kind of abnormal driving condition intelligence pre-judging method as described in claim 1, which is characterized in that if it is determined that not
Normal driving state, then further judgement belong to drive when intoxicated, drivings of taking drugs, ill driving, the classification in fatigue driving, simultaneously
Notice that the abnormal vehicle of the driving exists using the driving vehicle that the modes such as voice broadcast remind driver attentively to drive, remind periphery
Near;And the section is likely to be to geographical location information, the unique identifying number information, quantity of the vehicle of abnormal driving condition
Information, driver information be pushed to traffic police assist investigate and prosecute drive when intoxicated, takes drugs drive etc. illegal act of violating regulations;If it is determined that driving
Member drives for morbid state, then can contact the ill driver of 110 or 120 helps and alarm and first-aid centre is requested to rescue;Simultaneously
The running data of abnormal driving condition in multiple period is saved in the abnormal driving shape according to generic
The running data collection of state, for providing more data sets a possibility that abnormal driving condition to analyze.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910740761.3A CN110442113A (en) | 2019-08-12 | 2019-08-12 | Abnormal driving condition intelligence pre-judging method and Intelligent terminal for Internet of things |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910740761.3A CN110442113A (en) | 2019-08-12 | 2019-08-12 | Abnormal driving condition intelligence pre-judging method and Intelligent terminal for Internet of things |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110442113A true CN110442113A (en) | 2019-11-12 |
Family
ID=68434673
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910740761.3A Pending CN110442113A (en) | 2019-08-12 | 2019-08-12 | Abnormal driving condition intelligence pre-judging method and Intelligent terminal for Internet of things |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110442113A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112398814A (en) * | 2020-10-26 | 2021-02-23 | 易显智能科技有限责任公司 | Driving behavior data tamper-proofing method and device based on big data |
CN113380038A (en) * | 2021-07-06 | 2021-09-10 | 深圳市城市交通规划设计研究中心股份有限公司 | Vehicle dangerous behavior detection method, device and system |
CN114841679A (en) * | 2022-06-29 | 2022-08-02 | 陕西省君凯电子科技有限公司 | Intelligent management system for vehicle running data |
-
2019
- 2019-08-12 CN CN201910740761.3A patent/CN110442113A/en active Pending
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112398814A (en) * | 2020-10-26 | 2021-02-23 | 易显智能科技有限责任公司 | Driving behavior data tamper-proofing method and device based on big data |
CN113380038A (en) * | 2021-07-06 | 2021-09-10 | 深圳市城市交通规划设计研究中心股份有限公司 | Vehicle dangerous behavior detection method, device and system |
CN114841679A (en) * | 2022-06-29 | 2022-08-02 | 陕西省君凯电子科技有限公司 | Intelligent management system for vehicle running data |
CN114841679B (en) * | 2022-06-29 | 2022-10-18 | 陕西省君凯电子科技有限公司 | Intelligent management system for vehicle running data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Singh et al. | Analyzing driver behavior under naturalistic driving conditions: A review | |
Arumugam et al. | A survey on driving behavior analysis in usage based insurance using big data | |
CN110442113A (en) | Abnormal driving condition intelligence pre-judging method and Intelligent terminal for Internet of things | |
US20180165531A1 (en) | Systems and methods for near-crash determination | |
EP3564086A1 (en) | Managing drive modes of a vehicle | |
JP4888761B2 (en) | Virtual lane display device | |
CN105564436A (en) | Advanced driver assistance system | |
CN112389448A (en) | Abnormal driving behavior identification method based on vehicle state and driver state | |
Feng et al. | An on-board system for detecting driver drowsiness based on multi-sensor data fusion using Dempster-Shafer theory | |
Ziakopoulos et al. | A critical overview of driver recording tools | |
US20190202477A1 (en) | Providing location and driving behavior based alerts | |
CN110286667A (en) | Abnormal driving condition intelligent control method and Intelligent terminal for Internet of things | |
JP4622749B2 (en) | Vehicle data collection device, vehicle driving support device, and vehicle safe driving support system | |
Tavakoli et al. | HARMONY: A human-centered multimodal driving study in the wild | |
JPWO2018179392A1 (en) | System, information management server, and method | |
Russell et al. | Naturalistic study of Level 2 driving automation functions | |
Dua et al. | Drowsiness detection and alert system | |
US20190193753A1 (en) | Providing relevant alerts to a driver of a vehicle | |
Ziegler et al. | Computer vision on the road: A lane departure and drowsy driver warning system | |
Beggiato et al. | Sequence analysis of glance patterns to predict lane changes on urban arterial roads | |
CN115107786A (en) | Driving behavior correction system and method for intelligent automobile | |
Soultana et al. | Context-awareness in the smart car: Study and analysis | |
JP2005006966A (en) | Support apparatus | |
Riera et al. | Detecting and tracking unsafe lane departure events for predicting driver safety in challenging naturalistic driving data | |
Klauer et al. | How risky is it |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20191112 |