CN107150689A - A kind of automobile assistant driving method and system - Google Patents
A kind of automobile assistant driving method and system Download PDFInfo
- Publication number
- CN107150689A CN107150689A CN201710165457.1A CN201710165457A CN107150689A CN 107150689 A CN107150689 A CN 107150689A CN 201710165457 A CN201710165457 A CN 201710165457A CN 107150689 A CN107150689 A CN 107150689A
- Authority
- CN
- China
- Prior art keywords
- signal
- fused
- assistant driving
- strategy
- algorithm
- 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
- 238000000034 method Methods 0.000 title claims abstract description 30
- 230000004927 fusion Effects 0.000 claims abstract description 52
- 238000004458 analytical method Methods 0.000 claims abstract description 29
- 238000001514 detection method Methods 0.000 claims description 24
- 238000012360 testing method Methods 0.000 claims description 16
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 7
- 238000009434 installation Methods 0.000 claims description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 2
- 230000000875 corresponding effect Effects 0.000 description 27
- 230000006870 function Effects 0.000 description 6
- 210000002438 upper gastrointestinal tract Anatomy 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 230000009123 feedback regulation Effects 0.000 description 3
- 238000012351 Integrated analysis Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000012356 Product development Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- 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
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
-
- 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
- G06F18/25—Fusion techniques
-
- 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
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Automation & Control Theory (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of automobile assistant driving method and system, pass through multiple signals of the signal pickup assembly according to the signal acquisition parameter acquisition motor vehicle environment pre-set;Signal fused strategy according to pre-setting is merged to the multiple signal, and unlike signal is combined into the signal data after being merged by different proportion according to the signal fused parameter of signal fused strategy;The signal data after fusion is identified using automobile assistant driving intelligent algorithm and obtains corresponding recognition result;Analysis of Policy Making is carried out to the recognition result according to the Decision fusion strategy pre-set and obtains the corresponding result of decision, carries out early warning to aid in driving according to result of decision correspondence dynamic adjustment signal acquisition parameter and signal fused parameter or correspondence;The accuracy of automobile assistant driving is improved, the problem of prior art is judged by accident is avoided as far as possible, fast and accurately automobile assistant driving is realized, with good application prospect.
Description
Technical field
The present invention relates to automobile assistant driving technical field, more particularly to a kind of automobile assistant driving method and system.
Background technology
With continuing to develop for automobile industry, automobile quantity is more and more, and there is existing many automobiles auxiliary to drive at present
Function, even unmanned function.Not only position is substantially solid with angle to the signal acquisition module of existing automobile assistant driving
Fixed, and the selectable scope of angle that signal acquisition is installed is seldom, causes human pilot substantially can not be according to actual environment
The parameters such as classification, position and the angle of signal acquisition are freely adjusted, automotive accessory can not be allowed to recognize situation according to algorithm
The parameter of adaptive adjustment signal acquisition, causes auxiliary to drive function and impracticable, and it is low that auxiliary drives accuracy rate, to driver with
Inconvenience is carried out.
Also, current automobile assistant driving intelligent algorithm is substantially to be carried out respectively to signal specific or specific several signals
Identification, carries out integrated analysis, feedback and response after the completion of identification.Automobile assistant driving intelligent algorithm is substantially to specific letter
Number or specific several signals be identified respectively, integrated analysis is carried out after the completion of identification, though have to these signals carry out
Fusion treatment, also the identification situation not according to intelligent algorithm dynamic adjustment is carried out to the convergence strategy of signal with updating, lead
Cause the reliability of auxiliary driving detection low, bring inconvenience.
Thus prior art could be improved and improve.
The content of the invention
In view of in place of above-mentioned the deficiencies in the prior art, it is an object of the invention to provide a kind of automobile assistant driving method and
System, it is intended to solve existing automobile assistant driving technology and be unable to adjust automatically parameter to cause the problem of low accuracy rate of reliability is low.
In order to achieve the above object, this invention takes following technical scheme:
A kind of automobile assistant driving method, wherein, including:
A, pass through multiple signals of the signal pickup assembly according to the signal acquisition parameter acquisition motor vehicle environment pre-set;
B, according to the signal fused strategy pre-set the multiple signal is merged, according to the signal of signal fused strategy
Unlike signal is combined the signal data after being merged by different proportion by fusion parameters;
C, the signal data after fusion is identified using automobile assistant driving intelligent algorithm obtains corresponding recognition result;
The Decision fusion strategy that D, basis are pre-set carries out Analysis of Policy Making to the recognition result and obtains the corresponding result of decision,
Carry out early warning to aid in driving according to result of decision correspondence dynamic adjustment signal acquisition parameter and signal fused parameter or correspondence.
Described automobile assistant driving method, wherein, the step A is specifically included:
A1, the montant that installation one can stretch in vertical direction in the middle part of car roof, being installed in the montant upper end can be in water
Square to 360 degree of rotations and the signal pickup assembly of adjustable angle in vertical direction, the signal pickup assembly includes shooting
Head, infrared emission receiver, radar emission receiver and ultrasonic transmitter-receiver;
The signal acquisition parameter that A2, basis are pre-set, the white light video signal of the signal pickup assembly collection motor vehicle environment,
Infrared video signal, feux rouges vision signal, radar signal and ultrasonic signal.
Described automobile assistant driving method, wherein, the step B is specifically included:
B1, the unlike signal of motor vehicle environment is gathered under various environment in advance and analysis test is carried out, obtain optimal statistical knowledge
Rule, forms the signal fused strategy of acquiescence;
B2, according to the signal fused strategy pre-set the multiple signal is merged, according to the letter of signal fused strategy
Unlike signal is combined the signal data after being merged by different proportion by number fusion parameters;
B3, by after fusion signal data store, by signal data with meet algorithm input form be stored in different fixations
Region, externally only provides data pointer interface, so that corresponding automobile assistant driving intelligent algorithm is called.
Described automobile assistant driving method, wherein, the step C is specifically included:
C1, the signal data after fusion is identified respectively according to the automobile assistant driving intelligent algorithm obtains corresponding knowledge
Other result;Wherein, the automobile assistant driving intelligent algorithm includes scene environment evaluation algorithm, lane shift detection algorithm, preceding
Car anticollision algorithm, rear car anticollision algorithm and pedestrian detection algorithm.
Described automobile assistant driving method, wherein, the step D is specifically included:
D1, the unlike signal of motor vehicle environment is gathered under various environment in advance and analysis test is carried out, obtain optimal reliability and know
Other result, forms corresponding Decision fusion strategy;
D2, according to Decision fusion analysis of strategies recognition result and feedback adjustment signal acquisition parameter and signal fused parameter or
Reliability highest recognition result carries out early warning reaction to aid in driving under selection current environment.
A kind of automobile assistant driving system, wherein, including:
Signal acquisition module, for by signal pickup assembly according to the signal acquisition parameter acquisition motor vehicle environment pre-set
Multiple signals;
Signal fused module, for being merged according to the signal fused strategy pre-set to the multiple signal, according to letter
Unlike signal is combined the signal data after being merged by different proportion by the signal fused parameter of number convergence strategy;
Signal identification module, is obtained pair for the signal data after fusion to be identified using automobile assistant driving intelligent algorithm
The recognition result answered;
Signal decision-making module, is obtained for carrying out Analysis of Policy Making to the recognition result according to the Decision fusion strategy pre-set
The corresponding result of decision, is carried out pre- according to result of decision correspondence dynamic adjustment signal acquisition parameter and signal fused parameter or correspondence
Warn to aid in driving.
Described automobile assistant driving system, wherein, the signal acquisition module includes:
Device setting unit, for installing a montant that can be stretched in vertical direction in the middle part of car roof, in the montant
Upper end install can in the horizontal direction 360 degree rotate and the signal pickup assembly of adjustable angle in vertical direction, the signal is adopted
Acquisition means include camera, infrared emission receiver, radar emission receiver and ultrasonic transmitter-receiver;
Signal gathering unit, for according to the signal acquisition parameter pre-set, the signal pickup assembly to gather motor vehicle environment
White light video signal, infrared video signal, feux rouges vision signal, radar signal and ultrasonic signal.
Described automobile assistant driving system, wherein, the signal fused module includes:
Setting unit is merged, for gathering under various environment the unlike signal of motor vehicle environment in advance and carrying out analysis test, is obtained
Optimal statistical knowledge rule, forms the signal fused strategy of acquiescence;
Signal fused unit, for being merged according to the signal fused strategy pre-set to the multiple signal, according to letter
Unlike signal is combined the signal data after being merged by different proportion by the signal fused parameter of number convergence strategy;
Memory cell is merged, for the signal data after fusion to be stored, signal data is deposited with the form for meeting algorithm input
Storage externally only provides data pointer interface, so that corresponding automobile assistant driving intelligent algorithm is called in different FX.
Described automobile assistant driving system, wherein, the signal identification module includes:
Signal identification unit, for being known respectively to the signal data after fusion according to the automobile assistant driving intelligent algorithm
Corresponding recognition result is not obtained;Wherein, the automobile assistant driving intelligent algorithm is inclined comprising scene environment evaluation algorithm, track
Move detection algorithm, front truck anticollision algorithm, rear car anticollision algorithm and pedestrian detection algorithm.
Described automobile assistant driving system, wherein, the signal decision-making module includes:
Decision-making setting unit, for gathering under various environment the unlike signal of motor vehicle environment in advance and carrying out analysis test, is obtained
Optimal reliability recognition result, forms corresponding Decision fusion strategy;
Signal decision package, for recognition result and feedback adjustment signal acquisition parameter according to Decision fusion analysis of strategies and
Reliability highest recognition result carries out early warning reaction to aid in driving under signal fused parameter or selection current environment.
The automobile assistant driving method and system provided compared to prior art, the present invention, according to automobile assistant driving intelligence
The identification situation of energy algorithm carries out dynamic adjustment and renewal to the convergence strategy of signal so that auxiliary drives the reliability of detection
Height, can preferably detect target, and to driver's early warning, reduce that prior art False Rate high reliability is low to ask as far as possible
Topic, realizes fast and accurately automobile assistant driving, with good application prospect, brings great convenience.
Brief description of the drawings
The method flow diagram for the automobile assistant driving method that Fig. 1 provides for the present invention.
The signal pickup assembly scheme of installation that Fig. 2 provides for the present invention.
The structured flowchart for the automobile assistant driving system Application Example that Fig. 3 provides for the present invention.
Embodiment
The present invention provides a kind of automobile assistant driving method and system.To make the purpose of the present invention, technical scheme and effect
Clearer, clear and definite, the present invention is described in more detail for the embodiment that develops simultaneously referring to the drawings.It should be appreciated that this place is retouched
The specific embodiment stated only to explain the present invention, is not intended to limit the present invention.
The present invention provides a kind of automobile assistant driving method, referring to Fig. 1, the automobile assistant driving method, including with
Lower step:
S100, pass through multiple signals of the signal pickup assembly according to the signal acquisition parameter acquisition motor vehicle environment pre-set;
S200, according to the signal fused strategy pre-set the multiple signal is merged, according to signal fused strategy
Unlike signal is combined the signal data after being merged by different proportion by signal fused parameter;
S300, using automobile assistant driving intelligent algorithm the signal data after fusion is identified and to obtain corresponding identification knot
Really;
The Decision fusion strategy that S400, basis are pre-set carries out Analysis of Policy Making to the recognition result and obtains corresponding decision-making knot
Really, carry out early warning to aid in driving according to result of decision correspondence dynamic adjustment signal acquisition parameter and signal fused parameter or correspondence
Sail.
Above-mentioned steps are described in detail with reference to specific embodiment.
In the step S100, by signal pickup assembly according to the signal acquisition parameter acquisition automobile week pre-set
The multiple signals enclosed.Specifically, a montant that can be stretched in vertical direction can be installed in the middle part of car roof, described perpendicular
Bar upper end is installed can 360 degree of rotations and the in vertical direction signal pickup assembly of adjustable angle, the signal in the horizontal direction
Harvester includes camera, infrared emission receiver, radar emission receiver and ultrasonic transmitter-receiver.Then, according to
The signal acquisition parameter pre-set, the signal pickup assembly gathers white light video signal, the infrared video of motor vehicle environment
Signal, feux rouges vision signal, radar signal and ultrasonic signal.
In practical application, as shown in Fig. 2 by the middle part of roof, installing a pole that can be stretched upwards.On this pole
End is installed by the signal picker in signal pickup assembly, signal pickup assembly(Camera or radar emission receiver, multiple signals
Collector can be arranged on same direction also in different directions when installation)Can the rotation of 360 degree of horizontal direction, vertical direction can
Adjust certain angle.Automobile is interacted by the cable in bar and signal picker, the signal number that transmission order, return are collected
According to.360 degree of rotations of signal picker, collection specific direction, such as data all around, and by the cable in pole number
According on the display screen of display in the car.Multiple signals of signal pickup assembly collection include white light video signal, infrared video
Signal, feux rouges vision signal, radar signal and ultrasonic signal etc..
In step s 200, the multiple signal is merged according to the signal fused strategy pre-set, according to letter
Unlike signal is combined the signal data after being merged by different proportion by the signal fused parameter of number convergence strategy.Tool
For body, the convergence strategy after signal acquisition is combined unlike signal data by different proportion, such as, infrared figure
Picture data are A, and White-light image data are B, it is assumed that A is consistent with B size(If inconsistent, it can reduce, be allowed to by amplification
Size is consistent), then infrared data is merged with obtaining new data C, C=a*A+a b*B, wherein a, b point after white light data
Not Wei infrared data and white light data weight, determined by prior largely test statisticses(I.e. a large amount of test results show weight
When taking this value, preferably, weight situation cited below is similar for algorithm effect).The signal to signal data can also be used
The convergence strategy that feature is merged, such as the feature for extracting infrared data above is X, and the feature of the white light data of extraction is Y,
X weights x, y different from Y are assigned respectively and form new characteristic Z, i.e. Z=x*X+y*Y, and different weights x, y are measured greatly by advance
Examination statistics is determined.
Further, the step S200 is specifically included:
S201, the unlike signal of motor vehicle environment is gathered under various environment in advance and analysis test is carried out, obtain optimal statistics and know
Know rule, form the signal fused strategy of acquiescence;
S202, according to the signal fused strategy pre-set the multiple signal is merged, according to signal fused strategy
Unlike signal is combined the signal data after being merged by different proportion by signal fused parameter;
S203, by after fusion signal data store, by signal data with meet algorithm input form be stored in different consolidate
Determine region, data pointer interface is externally only provided, so that corresponding automobile assistant driving intelligent algorithm is called.
Specifically, in practical application, due to each signal all only reflect or characterize varying environment under the conditions of it is to be checked
Certain aspect feature of the automobile of survey, in varying environment, such as greasy weather, the image information of vehicle is typically just obvious without radar, evening
On then white light figure information typically just not as infrared light figure information it is clear.So the automobile for more efficient detection above, then
Foregut fermenters algorithm answers preferential or emphasis to use so that preferentially making under target to be detected obvious clearly signal, i.e. foggy environment
With radar signal, preferentially use infrared signal in the evening.The present invention by gathering the unlike signal under various environment in advance, to this
A little signals carry out analysis test, obtain optimal statistical knowledge rule, that is, form the signal fused strategy of acquiescence(Follow-up difference
Decision fusion strategy drawn also by similar approach)., can be according to the picture of the image in a period of time on environment evaluation algorithm
Plain statistical information judges varying environment, such as, intermediate region directly over statistics white light figure(I.e. 1/6 to picture altitude is prolonged in top,
Region between the 1/3 to 2/3 of picture traverse from left to right)If average gray is less than the ash of the acquiescence counted in advance
Spend threshold value, then it is assumed that be evening environment, other environment are similar to be judged.So, just can be according to the signal fused plan kept in advance
Slightly, multiple signals are merged.
Preferably, in practical application, on the signal data after fusion, will also be sent to memory module and be stored.Deposit
Storage is transmitted through the signal data after next fusion from acquisition module.Signal data is stored in difference with the form for meeting algorithm input
FX, externally only provide data pointer interface, for correspondence automobile assistant driving intelligent algorithm call.Preferably, it is described
Also there are signal acquisition parameter and signal fused parameter in memory module, so that subsequent step carries out feedback regulation.
In the step S300, the signal data after fusion is identified using automobile assistant driving intelligent algorithm
To corresponding recognition result.Specifically, the automobile assistant driving intelligent algorithm is inclined comprising scene environment evaluation algorithm, track
Move detection algorithm, front truck anticollision algorithm, rear car anticollision algorithm, pedestrian detection algorithm and aid parking algorithm;Then according to described
Automobile assistant driving intelligent algorithm is identified to the signal data after fusion obtains corresponding recognition result respectively.
In practical application, automobile assistant driving intelligent algorithm comprising lane shift detection algorithm, front truck anticollision algorithm, after
Car anticollision algorithm, pedestrian detection algorithm etc..Wherein, lane shift detection algorithm, generally by the car first detected on road
The cut-off rule in road, judges that this car crosses over cut-off rule.And front truck anticollision algorithm is that whether have vehicle in front of the detection visual field, and apart from this
Car it is how far, if distance is in the range of some, it is likely that bump against, this information is uploaded to system, allows system to make instead
Should.And rear car anticollision algorithm, then similar front truck anticollision algorithm, but detected behind this car.It is similar on pedestrian detection algorithm
Front truck anticollision algorithm, but be detection pedestrian.
Each intelligent algorithm calls the signal data of FX in memory module(Pass through pointer).Herein, there are two kinds
Embodiment, one is serial mode, and one is parallel mode.Exemplified by a serial fashion, a period of time in, continuous adjusting parameter with
Strategy, is identified.Adjusting parameter and the method for convergence strategy herein, be according to product development during training in advance with
What test was got, effectively to be adjusted.The input data of all kinds of intelligent algorithms is white light video signal data, infrared light is regarded
The signal datas such as frequency signal data, feux rouges video signal data, radar signal data, ultrasonic signal data it is a kind of, several
Or fusion etc., and the parameter of recognizer in itself and structure can be updated after memory module reading data.
In practical application, Foregut fermenters algorithm calls the signal data of FX in memory module(Pass through pointer).
Lane detection algorithm detection lane information is first passed through, by feeding back angle lenses adjusting parameter corresponding by lane position information
(The table of comparisons for making a lane position and camera lens adjusting parameter can be counted in advance), signal pickup assembly is passed to, camera lens is adjusted
Angle so that straight lane line is symmetrical on image, is so convenient for Foregut fermenters.Scene environment is called to judge
Algorithm(Judge whether be evening, whether the greasy weather, whether rainy day), the strategy with preserving in advance is judged according to different environment,
May be selected by the convergence strategy, the convergence strategy of feature, Foregut fermenters algorithm of unlike signal parameter, change so as to realize
Become Foregut fermenters algorithm structure, characteristic morphology, parameter, and then improve Foregut fermenters algorithm detection efficiency.
In the step S400, Analysis of Policy Making is carried out to the recognition result according to the Decision fusion strategy pre-set
The corresponding result of decision is obtained, is entered according to result of decision correspondence dynamic adjustment signal acquisition parameter and signal fused parameter or correspondingly
Row early warning with aid in drive.Specifically, the present invention gathers under various environment the unlike signal of motor vehicle environment and divided in advance
Analysis test, obtains optimal reliability recognition result, forms corresponding Decision fusion strategy.Then, according to Decision fusion strategy
Analyze under the recognition result and feedback adjustment signal acquisition parameter and signal fused parameter or selection current environment reliability most
High recognition result carries out early warning reaction to aid in driving.
In practical application, Decision fusion strategy, also similar with above-mentioned signal fused strategy, i.e. different intelligent algorithm or same
The difference of one intelligent algorithm realizes that the result that module is drawn is inconsistent or not quite identical, at this time how to be judged, according to
General knowledge, it should select Reliability comparotive high, and which result Reliability comparotive under which kind of environment is high, is measured greatly by advance
Examination statistics is determined.If for example example one, algorithm(It is designated as algorithm 1)Input and used in vain than simple for the recognition effect of infrared signal
The effect of light figure is good, here it is the corresponding result of decision.Some ginseng in algorithm is found after example two, such as operation a period of time
Number(It is designated as parameter 1)Value b is adjusted to by a, its recognition effect more preferably, this is the corresponding result of decision.
Then judge it is to need to carry out early warning reaction according to the result of decision, it is desired nonetheless to adjusting parameter.If the result of decision
More preferably, reliability is higher for corresponding effect, then follow-up just feedback regulation parameter and strategy.For example, decision-making is carried out to example one
After analysis, the relevant parameter in memory module, convergence strategy are fed back to signal acquisition module, the i.e. input data of algorithm 1 and determined
For infrared signal data.Example two is carried out after Analysis of Policy Making, the relevant parameter in feedback adjustment memory module, i.e., algorithm
The value of parameter 1 is revised as b.If that is, the corresponding situation of the result of decision is very urgent, for example having reached the threshold value bar of early warning
Part, then immediate response, early warning, such as front truck anti-collision early warning, giving fatigue pre-warning and pedestrian's early warning etc. are carried out to driver.Such as basis
Alarm warning decision-making, carries out early warning to driver, in emergency circumstances, directly takes car such as emergency brake operations.Certainly, also deposit
In nonreactive situation.
On feedback regulation parameter, common dynamic adjustment signal acquisition parameter and signal fused parameter.The signal acquisition
Parameter:Species including signal acquisition(It is white light video signal, infrared video signal, feux rouges vision signal, radar signal, super
Acoustic signals etc.), signal acquisition angle(If camera, this is the angle in camera vertical and horizontal direction)Deng.And
Signal fused parameter includes two aspects, and one is the parameter of particular variables(The ratio that for example unlike signal is merged), two are whether
Using the Rule of judgment of some algorithm, such as some parameter P values use algorithm 1, algorithm 2 are used when P values are 2 when being 1.
The automobile assistant driving method that the present invention is provided, in car running process, based on scene environment, according to intelligent calculation
Method recognizes situation, and the parameter such as classification, position, angle, the camera lens of signal acquisition can be automatically adjusted, the signal fused after collection
Strategy can be also automatically adjusted, moreover it is possible to carry out the adjust automatically of algorithm parameter or structure, and the present invention can enter from actual scene
Row study, so as to change relevant parameter, improves automobile assistant driving level
The automobile assistant driving method provided based on above-described embodiment, the present invention also provides a kind of automobile assistant driving system.Please
Refering to Fig. 3, the automobile assistant driving system includes:
Signal acquisition module 10, for by signal pickup assembly according to the signal acquisition parameter acquisition motor vehicle environment pre-set
Multiple signals;Specifically as described in step S100;
Signal fused module 20, for being merged according to the signal fused strategy pre-set to the multiple signal, according to
Unlike signal is combined the signal data after being merged by different proportion by the signal fused parameter of signal fused strategy;
Specifically as described in step S200;
Signal identification module 30, is obtained for the signal data after fusion to be identified using automobile assistant driving intelligent algorithm
Corresponding recognition result;Specifically as described in step S300;
Signal decision-making module 40, is obtained for carrying out Analysis of Policy Making to the recognition result according to the Decision fusion strategy pre-set
To the corresponding result of decision, carried out according to result of decision correspondence dynamic adjustment signal acquisition parameter and signal fused parameter or correspondence
Early warning with aid in drive;Specifically as described in step S400.
Further, the signal acquisition module 10 includes:
Device setting unit, for installing a montant that can be stretched in vertical direction in the middle part of car roof, in the montant
Upper end install can in the horizontal direction 360 degree rotate and the signal pickup assembly of adjustable angle in vertical direction, the signal is adopted
Acquisition means include camera, infrared emission receiver, radar emission receiver and ultrasonic transmitter-receiver;
Signal gathering unit, for according to the signal acquisition parameter pre-set, the signal pickup assembly to gather motor vehicle environment
White light video signal, infrared video signal, feux rouges vision signal, radar signal and ultrasonic signal.
Further, the signal fused module 20 includes:
Setting unit is merged, for gathering under various environment the unlike signal of motor vehicle environment in advance and carrying out analysis test, is obtained
Optimal statistical knowledge rule, forms the signal fused strategy of acquiescence;
Signal fused unit, for being merged according to the signal fused strategy pre-set to the multiple signal, according to letter
Unlike signal is combined the signal data after being merged by different proportion by the signal fused parameter of number convergence strategy;
Memory cell is merged, for the signal data after fusion to be stored, signal data is deposited with the form for meeting algorithm input
Storage externally only provides data pointer interface, so that corresponding automobile assistant driving intelligent algorithm is called in different FX.
Further, the signal identification module 30 includes:
Signal identification unit, for being known respectively to the signal data after fusion according to the automobile assistant driving intelligent algorithm
Corresponding recognition result is not obtained;Wherein, the automobile assistant driving intelligent algorithm is inclined comprising scene environment evaluation algorithm, track
Move detection algorithm, front truck anticollision algorithm, rear car anticollision algorithm and pedestrian detection algorithm.
Further, the signal decision-making module 40 includes:
Decision-making setting unit, for gathering under various environment the unlike signal of motor vehicle environment in advance and carrying out analysis test, is obtained
Optimal reliability recognition result, forms corresponding Decision fusion strategy;
Signal decision package, for recognition result and feedback adjustment signal acquisition parameter according to Decision fusion analysis of strategies and
Reliability highest recognition result carries out early warning reaction to aid in driving under signal fused parameter or selection current environment.
Because the concrete principle and detail technical features of the automobile assistant driving system are in above-mentioned automobile assistant driving side
Elaborate, will not be repeated here in method embodiment.
The division of above-mentioned functions module is only used to for example, in actual applications, can be as needed by above-mentioned functions
Distribution is completed by different functional modules, that is, different functional modules is divided into, to complete all or part of foregoing description
Function.
One of ordinary skill in the art will appreciate that all or part of flow in above-described embodiment method, can be by
Computer(Or mobile terminal)Program come instruct correlation hardware complete, described computer(Or mobile terminal)Program can be stored
In a computer(Or mobile terminal)In read/write memory medium, program is upon execution, it may include the embodiment of above-mentioned each method
Flow.Storage medium therein can be magnetic disc, CD, read-only memory(ROM)Or random access memory(RAM)
Deng.
In summary, a kind of automobile assistant driving method and system for providing of the present invention, by signal pickup assembly according to
Multiple signals of the signal acquisition parameter acquisition motor vehicle environment pre-set;According to the signal fused strategy pre-set to described
Multiple signals are merged, and are combined unlike signal by different proportion according to the signal fused parameter of signal fused strategy
Signal data after being merged;The signal data after fusion is identified using automobile assistant driving intelligent algorithm and obtained pair
The recognition result answered;Analysis of Policy Making is carried out to the recognition result according to the Decision fusion strategy pre-set and obtains corresponding determine
Plan result, carries out early warning to aid according to result of decision correspondence dynamic adjustment signal acquisition parameter and signal fused parameter or correspondence
Drive;The accuracy of automobile assistant driving is improved, the problem of prior art is judged by accident is avoided as far as possible, it is quick, accurate to realize
Automobile assistant driving, with good application prospect, bring great convenience.
It is understood that for those of ordinary skills, can be with technique according to the invention scheme and its hair
Bright design is subject to equivalent substitution or change, and all these changes or replacement should all belong to the guarantor of appended claims of the invention
Protect scope.
Claims (10)
1. a kind of automobile assistant driving method, it is characterised in that including:
A, pass through multiple signals of the signal pickup assembly according to the signal acquisition parameter acquisition motor vehicle environment pre-set;
B, according to the signal fused strategy pre-set the multiple signal is merged, according to the signal of signal fused strategy
Unlike signal is combined the signal data after being merged by different proportion by fusion parameters;
C, the signal data after fusion is identified using automobile assistant driving intelligent algorithm obtains corresponding recognition result;
The Decision fusion strategy that D, basis are pre-set carries out Analysis of Policy Making to the recognition result and obtains the corresponding result of decision,
Carry out early warning to aid in driving according to result of decision correspondence dynamic adjustment signal acquisition parameter and signal fused parameter or correspondence.
2. automobile assistant driving method according to claim 1, it is characterised in that the step A is specifically included:
A1, the montant that installation one can stretch in vertical direction in the middle part of car roof, being installed in the montant upper end can be in water
Square to 360 degree of rotations and the signal pickup assembly of adjustable angle in vertical direction, the signal pickup assembly includes shooting
Head, infrared emission receiver, radar emission receiver and ultrasonic transmitter-receiver;
The signal acquisition parameter that A2, basis are pre-set, the white light video signal of the signal pickup assembly collection motor vehicle environment,
Infrared video signal, feux rouges vision signal, radar signal and ultrasonic signal.
3. automobile assistant driving method according to claim 2, it is characterised in that the step B is specifically included:
B1, the unlike signal of motor vehicle environment is gathered under various environment in advance and analysis test is carried out, obtain optimal statistical knowledge
Rule, forms the signal fused strategy of acquiescence;
B2, according to the signal fused strategy pre-set the multiple signal is merged, according to the letter of signal fused strategy
Unlike signal is combined the signal data after being merged by different proportion by number fusion parameters;
B3, by after fusion signal data store, by signal data with meet algorithm input form be stored in different fixations
Region, externally only provides data pointer interface, so that corresponding automobile assistant driving intelligent algorithm is called.
4. automobile assistant driving method according to claim 3, it is characterised in that the step C is specifically included:
C1, the signal data after fusion is identified respectively according to the automobile assistant driving intelligent algorithm obtains corresponding knowledge
Other result;Wherein, the automobile assistant driving intelligent algorithm includes scene environment evaluation algorithm, lane shift detection algorithm, preceding
Car anticollision algorithm, rear car anticollision algorithm and pedestrian detection algorithm.
5. automobile assistant driving method according to claim 4, it is characterised in that the step D is specifically included:
D1, the unlike signal of motor vehicle environment is gathered under various environment in advance and analysis test is carried out, obtain optimal reliability and know
Other result, forms corresponding Decision fusion strategy;
D2, according to Decision fusion analysis of strategies recognition result and feedback adjustment signal acquisition parameter and signal fused parameter or
Reliability highest recognition result carries out early warning reaction to aid in driving under selection current environment.
6. a kind of automobile assistant driving system, it is characterised in that including:
Signal acquisition module, for by signal pickup assembly according to the signal acquisition parameter acquisition motor vehicle environment pre-set
Multiple signals;
Signal fused module, for being merged according to the signal fused strategy pre-set to the multiple signal, according to letter
Unlike signal is combined the signal data after being merged by different proportion by the signal fused parameter of number convergence strategy;
Signal identification module, is obtained pair for the signal data after fusion to be identified using automobile assistant driving intelligent algorithm
The recognition result answered;
Signal decision-making module, is obtained for carrying out Analysis of Policy Making to the recognition result according to the Decision fusion strategy pre-set
The corresponding result of decision, is carried out pre- according to result of decision correspondence dynamic adjustment signal acquisition parameter and signal fused parameter or correspondence
Warn to aid in driving.
7. automobile assistant driving system according to claim 6, it is characterised in that the signal acquisition module includes:
Device setting unit, for installing a montant that can be stretched in vertical direction in the middle part of car roof, in the montant
Upper end install can in the horizontal direction 360 degree rotate and the signal pickup assembly of adjustable angle in vertical direction, the signal is adopted
Acquisition means include camera, infrared emission receiver, radar emission receiver and ultrasonic transmitter-receiver;
Signal gathering unit, for according to the signal acquisition parameter pre-set, the signal pickup assembly to gather motor vehicle environment
White light video signal, infrared video signal, feux rouges vision signal, radar signal and ultrasonic signal.
8. automobile assistant driving system according to claim 7, it is characterised in that the signal fused module includes:
Setting unit is merged, for gathering under various environment the unlike signal of motor vehicle environment in advance and carrying out analysis test, is obtained
Optimal statistical knowledge rule, forms the signal fused strategy of acquiescence;
Signal fused unit, for being merged according to the signal fused strategy pre-set to the multiple signal, according to letter
Unlike signal is combined the signal data after being merged by different proportion by the signal fused parameter of number convergence strategy;
Memory cell is merged, for the signal data after fusion to be stored, signal data is deposited with the form for meeting algorithm input
Storage externally only provides data pointer interface, so that corresponding automobile assistant driving intelligent algorithm is called in different FX.
9. automobile assistant driving system according to claim 8, it is characterised in that the signal identification module includes:
Signal identification unit, for being known respectively to the signal data after fusion according to the automobile assistant driving intelligent algorithm
Corresponding recognition result is not obtained;Wherein, the automobile assistant driving intelligent algorithm is inclined comprising scene environment evaluation algorithm, track
Move detection algorithm, front truck anticollision algorithm, rear car anticollision algorithm and pedestrian detection algorithm.
10. automobile assistant driving system according to claim 9, it is characterised in that the signal decision-making module includes:
Decision-making setting unit, for gathering under various environment the unlike signal of motor vehicle environment in advance and carrying out analysis test, is obtained
Optimal reliability recognition result, forms corresponding Decision fusion strategy;
Signal decision package, for recognition result and feedback adjustment signal acquisition parameter according to Decision fusion analysis of strategies and
Reliability highest recognition result carries out early warning reaction to aid in driving under signal fused parameter or selection current environment.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710165457.1A CN107150689A (en) | 2017-03-20 | 2017-03-20 | A kind of automobile assistant driving method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710165457.1A CN107150689A (en) | 2017-03-20 | 2017-03-20 | A kind of automobile assistant driving method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107150689A true CN107150689A (en) | 2017-09-12 |
Family
ID=59792367
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710165457.1A Pending CN107150689A (en) | 2017-03-20 | 2017-03-20 | A kind of automobile assistant driving method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107150689A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110053629A (en) * | 2019-05-07 | 2019-07-26 | 广州小鹏汽车科技有限公司 | Interaction control method, device, electronic equipment and storage medium |
CN110187410A (en) * | 2019-06-18 | 2019-08-30 | 武汉中海庭数据技术有限公司 | Human body detection device and method in a kind of automatic Pilot |
CN112287801A (en) * | 2020-10-23 | 2021-01-29 | 北京嘀嘀无限科技发展有限公司 | Vehicle-mounted data processing method and device, server and readable storage medium |
WO2021024017A1 (en) * | 2019-08-03 | 2021-02-11 | Zhang Chuanrui | Advanced display and control system for driving assistance |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN100572159C (en) * | 2006-01-19 | 2009-12-23 | 通用汽车环球科技运作公司 | Have the deviation warning of warning correction standard and avoid system |
CN101782646A (en) * | 2009-01-19 | 2010-07-21 | 财团法人工业技术研究院 | All-round environment sensing system and method |
EP2594446A2 (en) * | 2011-11-15 | 2013-05-22 | Robert Bosch Gmbh | Apparatus and method for operating a vehicle |
CN104290745A (en) * | 2014-10-28 | 2015-01-21 | 奇瑞汽车股份有限公司 | Semi-automatic driving system for vehicle and method thereof |
CN106379319A (en) * | 2016-10-13 | 2017-02-08 | 上汽大众汽车有限公司 | Automobile driving assistance system and control method |
WO2017021119A1 (en) * | 2015-08-03 | 2017-02-09 | Volkswagen Aktiengesellschaft | Method and device in a motor vehicle for improved data fusion in an environment detection |
-
2017
- 2017-03-20 CN CN201710165457.1A patent/CN107150689A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN100572159C (en) * | 2006-01-19 | 2009-12-23 | 通用汽车环球科技运作公司 | Have the deviation warning of warning correction standard and avoid system |
CN101782646A (en) * | 2009-01-19 | 2010-07-21 | 财团法人工业技术研究院 | All-round environment sensing system and method |
EP2594446A2 (en) * | 2011-11-15 | 2013-05-22 | Robert Bosch Gmbh | Apparatus and method for operating a vehicle |
CN104290745A (en) * | 2014-10-28 | 2015-01-21 | 奇瑞汽车股份有限公司 | Semi-automatic driving system for vehicle and method thereof |
WO2017021119A1 (en) * | 2015-08-03 | 2017-02-09 | Volkswagen Aktiengesellschaft | Method and device in a motor vehicle for improved data fusion in an environment detection |
CN106379319A (en) * | 2016-10-13 | 2017-02-08 | 上汽大众汽车有限公司 | Automobile driving assistance system and control method |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110053629A (en) * | 2019-05-07 | 2019-07-26 | 广州小鹏汽车科技有限公司 | Interaction control method, device, electronic equipment and storage medium |
CN110187410A (en) * | 2019-06-18 | 2019-08-30 | 武汉中海庭数据技术有限公司 | Human body detection device and method in a kind of automatic Pilot |
WO2021024017A1 (en) * | 2019-08-03 | 2021-02-11 | Zhang Chuanrui | Advanced display and control system for driving assistance |
CN112287801A (en) * | 2020-10-23 | 2021-01-29 | 北京嘀嘀无限科技发展有限公司 | Vehicle-mounted data processing method and device, server and readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107150689A (en) | A kind of automobile assistant driving method and system | |
US10423164B2 (en) | Object position measurement with automotive camera using vehicle motion data | |
CN104657735B (en) | Method for detecting lane lines, system, lane departure warning method and system | |
US9384401B2 (en) | Method for fog detection | |
EP3784505A1 (en) | Device and method for determining a center of a trailer tow coupler | |
CN105892471A (en) | Automatic automobile driving method and device | |
CN112487905B (en) | Method and system for predicting danger level of pedestrian around vehicle | |
CN114454809A (en) | Intelligent light switching method, system and related equipment | |
CN109190488B (en) | Front vehicle door opening detection method and device based on deep learning YOLOv3 algorithm | |
CN114572183A (en) | Automobile pavement self-adaptive vehicle control method and equipment | |
CN114781479A (en) | Traffic incident detection method and device | |
CN113449650A (en) | Lane line detection system and method | |
CN115503747A (en) | Road condition identification and reminding system based on intelligent automobile steer-by-wire system | |
US11580695B2 (en) | Method for a sensor-based and memory-based representation of a surroundings, display device and vehicle having the display device | |
CN102610057B (en) | Vehicle-mounted information intelligent processing system and method | |
Sezgin et al. | Safe autonomous driving in adverse weather: Sensor evaluation and performance monitoring | |
CN113657161A (en) | Non-standard small obstacle detection method and device and automatic driving system | |
CN113954836A (en) | Segmented navigation lane changing method and system, computer equipment and storage medium | |
CN111881748A (en) | Lane line visual identification method and system based on VBAI platform modeling | |
CN108062528A (en) | A kind of lane recognition system and method based on Streaming Media inside rear-view mirror system | |
CN112241004B (en) | Object recognition device | |
CN110531339A (en) | Detection method, device and the computer readable storage medium of laser radar | |
CN112633055A (en) | General automatic driving navigation system based on pavement disease detection | |
CN116331220B (en) | Lane departure early warning method and early warning system for automatic driving vehicle | |
CN113139493B (en) | Unmanned road obstacle recognition system |
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 | ||
DD01 | Delivery of document by public notice |
Addressee: Xue Liantong Document name: Notice of commencement of preservation procedure |
|
DD01 | Delivery of document by public notice |