CN106696825B - A kind of method and system that auxiliary drives - Google Patents
A kind of method and system that auxiliary drives Download PDFInfo
- Publication number
- CN106696825B CN106696825B CN201610997607.0A CN201610997607A CN106696825B CN 106696825 B CN106696825 B CN 106696825B CN 201610997607 A CN201610997607 A CN 201610997607A CN 106696825 B CN106696825 B CN 106696825B
- Authority
- CN
- China
- Prior art keywords
- value
- image information
- input value
- subregion
- target
- 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.)
- Active
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R1/00—Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60T—VEHICLE BRAKE CONTROL SYSTEMS OR PARTS THEREOF; BRAKE CONTROL SYSTEMS OR PARTS THEREOF, IN GENERAL; ARRANGEMENT OF BRAKING ELEMENTS ON VEHICLES IN GENERAL; PORTABLE DEVICES FOR PREVENTING UNWANTED MOVEMENT OF VEHICLES; VEHICLE MODIFICATIONS TO FACILITATE COOLING OF BRAKES
- B60T7/00—Brake-action initiating means
- B60T7/12—Brake-action initiating means for automatic initiation; for initiation not subject to will of driver or passenger
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/30—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of image processing
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/80—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement
- B60R2300/8066—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement for monitoring rearward traffic
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Mechanical Engineering (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Transportation (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention provides a kind of method and system that auxiliary drives, this method includes：When detecting that vehicle is in transport condition, the corresponding at least one image information of ambient enviroment of vehicle is obtained；It is performed both by for each image information：The image information is divided into the crucial subregion of the first quantity, and determines the input value of each crucial subregion；Processing is optimized using the input value of the first quantity of pre-set majorized function pair, the corresponding reference value of the input value to generate first quantity；Judge whether reference value and the difference of predetermined standard value are not more than given threshold, if so, executing urgent danger prevention processing.Due to can judge from the ambient enviroment of vehicle vehicle running state, better than the only simple method judged by distance and speed, the accuracy for avoiding accident from occurring can be improved.
Description
Technical field
The present invention relates to technical field of data processing, more particularly to a kind of method and system that auxiliary drives.
Background technology
With the development of society, the improvement of people's living standards, automobile is at indispensable product in for people's lives.By
In in driving procedure, driver can adjust the distance, the judgement of speed etc. is there are error, lead to take risk avoidance measures not in time, and
And there is prodigious randomness when taking urgent danger prevention measure, inappropriate urgent danger prevention measure is taken, causing originally can be with
The traffic accident avoided, to cause the damage even injures and deaths of personnel of vehicle.
Currently, some Driving assistant systems judge distance by the distance between detection and front truck and relative velocity
And whether relative velocity is more than the threshold value set, after more than the threshold value of setting, issues the user with warning accordingly or carries out certainly
Dynamic brake.
But existing realization method generally can not hazard recognition situation completely, such as feelings that rear automobile emergency quick access is close
Condition, therefore to avoiding the accuracy that accident occurs relatively low.
Invention content
The present invention provides a kind of method and systems that auxiliary drives, and can improve the accuracy for avoiding accident from occurring.
In a first aspect, the present invention provides a kind of method that auxiliary drives, this method includes：
When detecting that vehicle is in transport condition, the corresponding at least one image letter of ambient enviroment of the vehicle is obtained
Breath；
For each described image information, it is performed both by：Described image information is divided into the crucial subregion of the first quantity, and
Determine the input value of each crucial subregion；
Optimize processing using the input value of the first quantity of pre-set majorized function pair, with generate this first
The corresponding reference value of the input value of quantity；
Judge whether the reference value and the difference of predetermined standard value are not more than given threshold, if so, executing tight
Anxious hedging processing.
Preferably, the input value using the first quantity of pre-set majorized function pair optimizes processing,
To generate the corresponding reference value of the input value of first quantity, including：
S1：For each target input value in the input value of the first quantity, it is performed both by：Using pre-set
Each first majorized function in first majorized function of the first quantity, respectively optimizes the target input value, with
Generate the corresponding objective optimization value of the target input value；It determines the corresponding target weight of the objective optimization value, and determines institute
The product for stating objective optimization value and the target weight is target output value, to complete the suboptimization to the target input value
Processing；
S2：Judge whether the number of the corresponding optimization processing of the target input value reaches given threshold, if so, executing
Otherwise S3 using the target output value as the target input value, and executes S1；
S3：According to the target output value for the first quantity determined, and predetermined second majorized function is utilized, meter
Calculate the corresponding reference value of target output value of first quantity.
Preferably, first majorized function, including：
Wherein, f (xi) optimal value for characterizing i-th in the crucial subregion of first quantity crucial subregion；xiWith
In the input value for characterizing described i-th crucial subregion；C is used to characterize the parameter of described image information；Radom is described for characterizing
The corresponding empirical value of i-th of key subregion；
Second majorized function, including：
Wherein, SjReference value for characterizing j-th of image information at least one image information；wijFor table
Levy the default weight of i-th of crucial subregion in j-th of image information；bjFor characterizing j-th of image information
Threshold value；N is for characterizing first quantity；rand(xi) it is used to characterize the equilibrium valve of described i-th crucial subregion.
Preferably, the input value of each crucial subregion of the determination, including：
For crucial subregion described in each, which is subjected to gray processing processing, and determine in the key subregion
Including each pixel gray value, and determine that the adduction of the gray value of each pixel is the key subregion
Input value.
Preferably, further comprise：
When monitoring that the barycentre offset of the corresponding driver of the vehicle is more than the first threshold of respective settings, start
Emergency braking.
Preferably, further comprise：
The normally travel direction that the vehicle is determined according to described image information, when the current driving for monitoring the vehicle
When angle between direction and the normally travel direction is more than the second threshold of respective settings, start emergency braking.
Second aspect, the present invention provides a kind of system that auxiliary drives, which includes：Acquiring unit, determination unit,
Processing unit and judging unit, wherein
The acquiring unit, for when detecting that vehicle is in transport condition, obtaining the ambient enviroment pair of the vehicle
At least one image information answered；
The determination unit is performed both by for being directed to each described image information：Described image information is divided into first
The crucial subregion of quantity, and determine the input value of each crucial subregion；
The processing unit, for being optimized using the input value of the first quantity of pre-set majorized function pair
Processing, to generate the corresponding reference value of the input value of first quantity；
The judging unit, whether the difference for judging the reference value with predetermined standard value is no more than setting
Threshold value, if so, executing urgent danger prevention processing.
Preferably, the processing unit, including optimization subelement, triggering subelement, computation subunit, wherein
The optimization subelement, for for each target input value in the input value of the first quantity, holding
Row：Using each first majorized function in the first majorized function of pre-set first quantity, respectively to the target
Input value optimizes, to generate the corresponding objective optimization value of the target input value；Determine that the objective optimization value is corresponding
Target weight, and determine that the product of the objective optimization value and the target weight is target output value, to complete to the mesh
Mark an optimization processing of input value；
The triggering subelement, for judging whether the number of the corresponding optimization processing of the target input value reaches setting
Otherwise threshold value, using the target output value as the target input value, and triggers institute if so, triggering the computation subunit
State optimization subelement；
The computation subunit for the target output value according to the first quantity determined, and is utilized and is predefined
The second majorized function, calculate the corresponding reference value of target output value of first quantity.
Preferably, first majorized function, including：
Wherein, f (xi) optimal value for characterizing i-th in the crucial subregion of first quantity crucial subregion；xiWith
In the input value for characterizing described i-th crucial subregion；C is used to characterize the parameter of described image information；Radom is described for characterizing
The corresponding empirical value of i-th of key subregion；
Second majorized function, including：
Wherein, SjReference value for characterizing j-th of image information at least one image information；wijFor table
Levy the default weight of i-th of crucial subregion in j-th of image information；bjFor characterizing j-th of image information
Threshold value；N is for characterizing first quantity；rand(xi) it is used to characterize the equilibrium valve of described i-th crucial subregion.
Preferably, the determination unit is specifically used for, for each crucial subregion, which being carried out ash
Degreeization processing, and determine the gray value for each pixel that the key subregion includes, and determine each described pixel
The adduction of the gray value of point is the input value of the key subregion.
Preferably, further comprise：First brake unit, for when the center of gravity for monitoring the corresponding driver of the vehicle
When offset is more than the first threshold of respective settings, start emergency braking.
Preferably, the second brake unit, the normally travel direction for determining the vehicle according to described image information, when
Monitor that the angle between the current driving direction of the vehicle and the normally travel direction is more than the second threshold of respective settings
When value, start emergency braking.
The present invention provides a kind of method and systems that auxiliary drives, by when detecting that vehicle is in transport condition,
Image information is divided into the crucial subregion of the first quantity by the corresponding image information of ambient enviroment for obtaining vehicle, and determination is each
The input value of a key subregion, optimizes processing, with life using the input value of the first quantity of pre-set majorized function pair
At the corresponding reference value of the input value of first quantity, judge whether reference value and the difference of predetermined standard value are not more than
Given threshold, if so, executing urgent danger prevention processing.Due to can sentence from the ambient enviroment of vehicle to vehicle driving state
It is disconnected, better than the only simple method judged by distance and speed, the accuracy for avoiding accident from occurring can be improved.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is the present invention
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 is the flow chart for the method that a kind of auxiliary provided by one embodiment of the present invention drives；
Fig. 2 is a kind of identification model framework map provided by one embodiment of the present invention；
Fig. 3 is the flow chart for the method that another auxiliary provided by one embodiment of the present invention drives；
Fig. 4 is the schematic diagram for the system that a kind of auxiliary provided by one embodiment of the present invention drives；
Fig. 5 is the schematic diagram for the system that another auxiliary provided by one embodiment of the present invention drives.
Specific implementation mode
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments, based on the embodiments of the present invention, those of ordinary skill in the art
The every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
As shown in Figure 1, an embodiment of the present invention provides a kind of method that auxiliary drives, this method may include following step
Suddenly：
Step 101：When detecting that vehicle is in transport condition, the ambient enviroment corresponding at least one of the vehicle is obtained
A image information.
Step 102：For each described image information, it is performed both by：Described image information is divided into the pass of the first quantity
Key subregion, and determine the input value of each crucial subregion.
Step 103：Processing is optimized using the input value of the first quantity of pre-set majorized function pair, with life
At the corresponding reference value of the input value of first quantity.
Step 104：Judge whether the reference value and the difference of predetermined standard value are not more than given threshold, if
It is to execute step 105.
Step 105：Execute urgent danger prevention processing.
In the embodiment shown in fig. 1, by when detecting that vehicle is in transport condition, obtaining the ambient enviroment of vehicle
Image information is divided into the crucial subregion of the first quantity by corresponding image information, and determines the input value of each crucial subregion,
Processing is optimized using the input value of the first quantity of pre-set majorized function pair, to generate the input value of first quantity
Corresponding reference value, judges whether reference value and the difference of predetermined standard value are not more than given threshold, if so, executing tight
Anxious hedging processing.Due to can judge from the ambient enviroment of vehicle vehicle driving state, better than only simple dependence away from
From the method judged with speed, the accuracy for avoiding accident from occurring can be improved.
It is worth noting that high-speed camera can be arranged on vehicle, the image to shoot vehicle periphery in real time is believed
Breath, therefore the corresponding at least one image information of the ambient enviroment of the vehicle got can be front, rear, the left side of vehicle
At least one of side, the corresponding image information in right side side and top.
In an embodiment of the invention, described to utilize pre-set optimization letter in order to ensure the reliability of reference value
Several input values to the first quantity optimize processing, to generate the corresponding reference of the input value of first quantity
Value, including：
S1：For each target input value in the input value of the first quantity, it is performed both by：Using pre-set
Each first majorized function in first majorized function of the first quantity, respectively optimizes the target input value, with
Generate the corresponding objective optimization value of the target input value；It determines the corresponding target weight of the objective optimization value, and determines institute
The product for stating objective optimization value and the target weight is target output value, to complete the suboptimization to the target input value
Processing；
S2：Judge whether the number of the corresponding optimization processing of the target input value reaches given threshold, if so, executing
Otherwise S3 using the target output value as the target input value, and executes S1；
S3：According to the target output value for the first quantity determined, and predetermined second majorized function is utilized, meter
Calculate the corresponding reference value of target output value of first quantity.
Include input in the identification model in this embodiment it is possible to build identification model as shown in Figure 2 in advance
Layer, hidden layer and output layer three parts.Wherein, input layer is used for for inputting determining input value, hidden layer to the defeated of input
Enter value to optimize, output layer is used to export the optimal value after hidden layer optimization.And data can be added in the identification model
Filtering technique so that the data sample to go against accepted conventions is just eliminated later in the seldom number of optimization, and the data to go against accepted conventions are eliminated in advance, than
Optimization number just finds that data are unreasonable more intelligent after reaching threshold value.
In fig. 2, x1、x2、…、xrFor characterizing the input value being input in identification model, o1、o2、…、orFor characterizing
The optimal value generated after the first majorized function carries out a suboptimization being input in identification model.
In an embodiment of the invention, in order to further ensure that the reliability of reference value, first majorized function, packet
It includes：
Wherein, f (xi) optimal value for characterizing i-th in the crucial subregion of first quantity crucial subregion；xiWith
In the input value for characterizing described i-th crucial subregion；C is used to characterize the parameter of described image information；Radom is described for characterizing
The corresponding empirical value of i-th of key subregion；
Second majorized function, including：
Wherein, SjReference value for characterizing j-th of image information at least one image information；wijFor table
Levy the default weight of i-th of crucial subregion in j-th of image information；bjFor characterizing j-th of image information
Threshold value；N is for characterizing first quantity；rand(xi) it is used to characterize the equilibrium valve of described i-th crucial subregion.
In this embodiment, existing majorized function isIn order to monitor the connection between every suboptimization
System, adds memory function in identification model.Then majorized function is made that on the basis of present majorized function and is changed
Into, that is, using the 3 times optimum results currently optimized as memory value, be added in the majorized function currently optimized, therefore
The first majorized function is just obtained.
In an embodiment of the invention, in order to accurately analyze image information, the determination each
The input value of the key subregion, including：
For crucial subregion described in each, which is subjected to gray processing processing, and determine in the key subregion
Including each pixel gray value, and determine that the adduction of the gray value of each pixel is the key subregion
Input value.
In this embodiment it is possible to by the sum of gray value of each pixel included in the key subregion as corresponding
Input value, can also be using the average value of the gray value of each pixel included in the key subregion as inputting accordingly
Value.And the gray value Gray of pixel can be calculate by the following formula：
Wherein, R is for characterizing red, and G is for characterizing green, and B is for characterizing blue, and 0.299 for characterizing red power
Value, 0.587 weights for characterizing green, 0.144 for characterizing red weights.
In an embodiment of the invention, in order to further ensure that the safety of driving, the method which drives can be with
Further comprise：When monitoring that the barycentre offset of the corresponding driver of the vehicle is more than the first threshold of respective settings,
Start emergency braking.
In this embodiment, due in case of emergency, the generation that the body of driver can can't help is mobile or offset,
It, can be with so as to cause the change of position of centre of gravity, therefore when monitoring that driver's barycentre offset is more than the first threshold of setting
Start emergency braking.Other urgent danger preventions can also be but taken to handle, for example, starting alarm sounds etc..
In an embodiment of the invention, in order to further ensure that the safety of driving, the method which drives can be with
Further comprise：The normally travel direction that the vehicle is determined according to described image information, when monitoring the current of the vehicle
When angle between travel direction and the normally travel direction is more than the second threshold of respective settings, start emergency braking.
In this embodiment, due in case of emergency, when driver drives vehicle may offset setting route, work as prison
When measuring angle between the current driving direction of vehicle and normally travel direction and being more than the second threshold of respective settings, Ke Yiqi
Dynamic emergency braking.Other urgent danger preventions can also be but taken to handle, for example, starting alarm sounds etc..
As shown in figure 3, an embodiment of the present invention provides a kind of method that auxiliary drives, this method may include following step
Suddenly：
Step 301：When detecting that vehicle is in transport condition, the corresponding at least one figure of ambient enviroment of vehicle is obtained
As information.
In this step, the image that can shoot vehicle periphery in real time by the way that high-speed camera is arranged on vehicle is believed
Breath, can be front, rear, left side side, right side side and the top of vehicle.
Step 302：Image information is divided into the crucial subregion of the first quantity.
It in this embodiment, can be to image in order to ensure can to improve the accuracy rate of things identification in identification process
Information carries out division operation, which can carry out being divided into several regions to image information, can be believed according to image
The gray value of pixel carrys out subregion in breath, for example, including a toy car in the image information, then can be by the wheel of toy car
Son is as a crucial subregion, using the vehicle body of toy car as a crucial subregion.
Step 303：Determine the input value of each crucial subregion.
In this step, corresponding input value can be determined according to the gray value of included pixel in crucial subregion.
In this embodiment it is possible to by the sum of gray value of each pixel included in the key subregion as corresponding
Input value.It is worth noting that can also be by the average value of the gray value of each pixel included in the key subregion
As corresponding input value.
Step 304：Determine the first majorized function of the first quantity identical with input value number.
In this step, in order to realize to whether including causing the things of traffic accident in image information, it is thus necessary to determine that with
First majorized function of identical first quantity of input value number.Assuming that in step 302, image information is divided into r pass
Key subregion, then just it needs to be determined that r the first majorized functions.
In this embodiment, due to it needs to be determined that r the first majorized functions, you can to obtain r corresponding first optimizations
Function, and each majorized function determined imparts the empirical value of first three suboptimization, to obtain r, to differ first excellent
Change function.
Step 305：For each target input value in the input value of the first quantity, distinguished using the first majorized function
Target input value is optimized, to generate the corresponding objective optimization value of target input value；Determine the corresponding mesh of objective optimization value
Weight is marked, and determines that the product of objective optimization value and target weight is target output value, to complete to the primary of target input value
Optimization processing.
In this step, identification model as shown in Figure 2 can be built in advance, the identification model include input layer,
Hidden layer and output layer three parts.
In the initial state, the input value of input layer input is each input value determined in step 303.For example, input
It is respectively x to the input value in identification model1、x2、x3、…、xr。
Can be optimal value and the optimization of the output of identification model last time in the input value of subsequent process, input layer input
It is worth the product of corresponding weights.It can also be the optimal value of identification model last time output.
In hidden layer, each round frame included by middle hidden layer is please referred to Fig.2, corresponding one the in each round frame
One majorized function, and be handled as follows in each round frame：Using corresponding first majorized function of the round frame respectively to r
Input value is calculated, and includes r objective optimization value to get one group of numerical value, in the group.
Such as：The first majorized function in hidden layer corresponding to second round frame is following formula：
Wherein, a, b, c are three empirical values.So, include for the processing that second round frame is carried out in hidden layer：It will
Input value x1、x2、x3、…、xrIt is updated in above formula respectively, obtains being directed to the corresponding r objective optimization value f of second round frame
(x1)、f(x2)、f(x3)、…、f(xr)。
Step 306：Judge whether the number of the corresponding optimization processing of target input value reaches given threshold, if so, executing
307, otherwise, using target output value as target input value, and execute 305.
In this step, threshold value is set based on experience value, can also need sets itself according to user.For example,
It it is 62 times, 90 is inferior.
Step 307：Optimize letter according to the target output value for the first quantity determined, and using predetermined second
Number, calculates the corresponding reference value of target output value of first quantity.
In this embodiment, target output value can be one group, which includes each objective optimization value and corresponding mesh
Mark the product of weights, which can also be one, for each optimization input value and respective objects weights product it
Sum afterwards.The form of the target output value can be determined according to the form of standard value.
And following formula can be utilized to calculate reference value：
Wherein, SjReference value for characterizing j-th of image information at least one image information；wijFor table
Levy the default weight of i-th of crucial subregion in j-th of image information；bjFor characterizing j-th of image information
Threshold value；N is for characterizing first quantity；rand(xi) it is used to characterize the equilibrium valve of described i-th crucial subregion.
Such as：In this embodiment, target output value is one, then r crucial subregion is corresponding with r target output value,
Respectively f (x1)、f(x2)、f(x3)、…、f(xr), then reference value Sj=w1×f(x1)+w2×f(x2)+w3×f(x3)+…+wr
×f(xr)+bj+rand(xi)。
Step 308：Judge whether reference value and the difference of predetermined standard value are not more than given threshold, if so, holding
Row urgent danger prevention is handled, and otherwise, terminates current process.
In this step, urgent danger prevention processing can be braking deceleration, can also be to give a warning sound, can also be other
Hedging processing.
As shown in figure 4, an embodiment of the present invention provides a kind of DAS (Driver Assistant System), which may include：
Acquiring unit 401, determination unit 402, processing unit 403 and judging unit 404, wherein
The acquiring unit 401, for when detecting that vehicle is in transport condition, obtaining the ambient enviroment of the vehicle
Corresponding at least one image information；
The determination unit 402 is performed both by for being directed to each described image information：Described image information is divided into
The crucial subregion of first quantity, and determine the input value of each crucial subregion；
The processing unit 403, for being carried out using the input value of the first quantity of pre-set majorized function pair
Optimization processing, to generate the corresponding reference value of the input value of first quantity；
The judging unit 404, for judging whether the reference value and the difference of predetermined standard value are not more than
Given threshold, if so, executing urgent danger prevention processing.
As shown in figure 5, in an embodiment of the invention, in order to ensure the reliability of reference value, the processing unit
403, including optimization subelement 4031, triggering subelement 4032, computation subunit 4033, wherein
The optimization subelement 4031, each target input value for being directed in the input value of the first quantity,
It is performed both by：Using each first majorized function in the first majorized function of pre-set first quantity, respectively to described
Target input value optimizes, to generate the corresponding objective optimization value of the target input value；Determine the objective optimization value pair
The target weight answered, and determine that the product of the objective optimization value and the target weight is target output value, to complete to institute
State an optimization processing of target input value；
The triggering subelement 4032, for judging whether the number of the corresponding optimization processing of the target input value reaches
Given threshold, if so, the computation subunit 4033 is triggered, otherwise, using the target output value as the target input value,
And trigger the optimization subelement 4031；
The computation subunit 4033, for the target output value according to the first quantity determined, and using in advance
The second determining majorized function calculates the corresponding reference value of target output value of first quantity.
In this embodiment, by building identification model in advance, input value is repeatedly optimized, after reaching optimization number
Target output value is generated, and calculates reference value, improves the reliability of reference value.
In an embodiment of the invention, in order to further ensure that the reliability of reference value, first majorized function, packet
It includes：
Wherein, f (xi) optimal value for characterizing i-th in the crucial subregion of first quantity crucial subregion；xiWith
In the input value for characterizing described i-th crucial subregion；C is used to characterize the parameter of described image information；Radom is described for characterizing
The corresponding empirical value of i-th of key subregion；
Second majorized function, including：
Wherein, SjReference value for characterizing j-th of image information at least one image information；wijFor table
Levy the default weight of i-th of crucial subregion in j-th of image information；bjFor characterizing j-th of image information
Threshold value；N is for characterizing first quantity；rand(xi) it is used to characterize the equilibrium valve of described i-th crucial subregion.
In an embodiment of the invention, in order to accurately analyze image information, the determination unit, tool
Body is used to, for each crucial subregion, which is carried out gray processing processing, and determine and wrap in the key subregion
The gray value of each pixel included, and determine that the adduction of the gray value of each pixel is the key subregion
Input value.
In an embodiment of the invention, referring to FIG. 5, in order to further ensure that the safety of driving, further comprise：
First brake unit 501, for when monitoring that the barycentre offset of the corresponding driver of the vehicle is more than the of respective settings
When one threshold value, start emergency braking.
In an embodiment of the invention, referring to FIG. 5, in order to further ensure that the safety of driving, further comprise：
Second brake unit 502, the normally travel direction for determining the vehicle according to described image information, when monitoring the vehicle
Current driving direction and the normally travel direction between angle when being more than the second threshold of respective settings, start urgent
Braking.
The contents such as the information exchange between each unit, implementation procedure in above system, due to implementing with the method for the present invention
Example is based on same design, and particular content can be found in the narration in the method for the present invention embodiment, and details are not described herein again.
To sum up, various embodiments of the present invention at least have the advantages that：
1, in an embodiment of the present invention, by when detecting that vehicle is in transport condition, obtaining surrounding's ring of vehicle
Image information is divided into the crucial subregion of the first quantity by the corresponding image information in border, and determines the input of each crucial subregion
Value, optimizes processing, to generate the defeated of first quantity using the input value of the first quantity of pre-set majorized function pair
Enter and be worth corresponding reference value, judge whether reference value and the difference of predetermined standard value are not more than given threshold, if so, holding
Row urgent danger prevention is handled.Due to can judge from the ambient enviroment of vehicle vehicle driving state, better than it is only simple according to
The method judged by distance and speed can improve the accuracy for avoiding accident from occurring.
2, in an embodiment of the present invention, by building identification model, the input value of crucial subregion is set according to user
Optimization number repeatedly optimized, the reliability of the target output value made improves.And data mistake is added in the identification model
Filter technology so that the data sample to go against accepted conventions is optimizing seldom number later with regard to eliminating, and the data to go against accepted conventions is eliminated in advance, than excellent
Change after number reaches threshold value and just finds that data are illegal more intelligent.
3, in an embodiment of the present invention, image information is analyzed by the first majorized function and the second majorized function
Identification increases the reliability for the reference value for calculating gained, to increase the reliability of judging result.
4, in an embodiment of the present invention, the offset spy of the centre-of gravity shift and vehicle of driver is detected by using sensor
Property, to realize urgent early warning, so as to further increase the accuracy rate that accident occurs for prediction vehicle so that driver is as early as possible
It takes measures or the probability of accident occurs for emergency brake of vehicle, reduction.
It should be noted that herein, such as first and second etc relational terms are used merely to an entity
Or operation is distinguished with another entity or operation, is existed without necessarily requiring or implying between these entities or operation
Any actual relationship or order.Moreover, the terms "include", "comprise" or its any other variant be intended to it is non-
It is exclusive to include, so that the process, method, article or equipment including a series of elements includes not only those elements,
But also include other elements that are not explicitly listed, or further include solid by this process, method, article or equipment
Some elements.In the absence of more restrictions, the element limited by sentence " including a 〃 ", is not arranged
Except there is also other identical factors in the process, method, article or apparatus that includes the element.
One of ordinary skill in the art will appreciate that：Realize that all or part of step of above method embodiment can pass through
The relevant hardware of program instruction is completed, and program above-mentioned can be stored in computer-readable storage medium, the program
When being executed, step including the steps of the foregoing method embodiments is executed；And storage medium above-mentioned includes：ROM, RAM, magnetic disc or light
In the various media that can store program code such as disk.
Finally, it should be noted that：The foregoing is merely presently preferred embodiments of the present invention, is merely to illustrate the skill of the present invention
Art scheme, is not intended to limit the scope of the present invention.Any modification for being made all within the spirits and principles of the present invention,
Equivalent replacement, improvement etc., are included within the scope of protection of the present invention.
Claims (8)
1. a kind of method that auxiliary drives, which is characterized in that including：
When detecting that vehicle is in transport condition, the corresponding at least one image information of ambient enviroment of the vehicle is obtained；
For each described image information, it is performed both by：Described image information is divided into the crucial subregion of the first quantity, and is determined
The input value of each crucial subregion；
Processing is optimized using the input value of the first quantity of pre-set majorized function pair, to generate first quantity
The corresponding reference value of the input value；
Judge whether the reference value is not more than the difference threshold of setting with the difference of predetermined standard value, if so, executing
Urgent danger prevention is handled；
The input value using the first quantity of pre-set majorized function pair optimizes processing, with generate this first
The corresponding reference value of the input value of quantity, including：
S1：For each target input value in the input value of the first quantity, it is performed both by：Utilize pre-set first
Each first majorized function in first majorized function of quantity, respectively optimizes the target input value, to generate
The corresponding objective optimization value of the target input value；It determines the corresponding target weight of the objective optimization value, and determines the mesh
The product for marking optimal value and the target weight is target output value, to complete to a suboptimization of the target input value
Reason；
S2：Judge whether the number of the corresponding optimization processing of the target input value reaches the frequency threshold value of setting, if so, executing
Otherwise S3 using the target output value as the target input value, and executes S1；
S3：According to the target output value for the first quantity determined, and predetermined second majorized function is utilized, calculating should
The corresponding reference value of target output value of first quantity.
2. according to the method described in claim 1, it is characterized in that,
First majorized function, including：
Wherein, f (xi) optimal value for characterizing i-th in the crucial subregion of first quantity crucial subregion；xiFor table
Levy the input value of described i-th crucial subregion；C is used to characterize the parameter of described image information；Radom is for characterizing described i-th
The corresponding empirical value of a key subregion；
Second majorized function, including：
Wherein, SjReference value for characterizing j-th of image information at least one image information；wijFor characterizing
State the default weight of i-th of crucial subregion in j-th of image information；bjThreshold value for characterizing j-th of image information；
N is for characterizing first quantity；rand(xi) it is used to characterize the equilibrium valve of described i-th crucial subregion.
3. according to the method described in claim 1, it is characterized in that,
The input value of each crucial subregion of the determination, including：
For crucial subregion described in each, which is subjected to gray processing processing, and determines that the key subregion includes
Each pixel gray value, and determine that the adduction of the gray value of each pixel is the defeated of the key subregion
Enter value.
4. according to any method in claims 1 to 3, which is characterized in that
Further comprise：
When monitoring that the barycentre offset of the corresponding driver of the vehicle is more than the first threshold of respective settings, start urgent
Braking；
And/or
Further comprise：
The normally travel direction that the vehicle is determined according to described image information, when the current driving direction for monitoring the vehicle
When angle between the normally travel direction is more than the second threshold of respective settings, start emergency braking.
5. a kind of system that auxiliary drives, which is characterized in that including：Acquiring unit, determination unit, processing unit and judgement are single
Member, wherein
The acquiring unit, for when detecting that vehicle is in transport condition, the ambient enviroment for obtaining the vehicle to be corresponding
At least one image information；
The determination unit is performed both by for being directed to each described image information：Described image information is divided into the first quantity
Crucial subregion, and determine the input value of each crucial subregion；
The processing unit, for optimizing place using the input value of the first quantity of pre-set majorized function pair
Reason, to generate the corresponding reference value of the input value of first quantity；
The judging unit, whether the difference for judging the reference value with predetermined standard value is no more than the difference set
It is worth threshold value, if so, executing urgent danger prevention processing；
The processing unit, including optimization subelement, triggering subelement, computation subunit, wherein
The optimization subelement, for for each target input value in the input value of the first quantity, being performed both by：Profit
With each first majorized function in the first majorized function of pre-set first quantity, respectively to the target input value
It optimizes, to generate the corresponding objective optimization value of the target input value；Determine the corresponding target power of the objective optimization value
Weight, and determine that the product of the objective optimization value and the target weight is target output value, to complete to input the target
Optimization processing of value；
The triggering subelement, for judging whether the number of the corresponding optimization processing of the target input value reaches time of setting
Otherwise number threshold value, using the target output value as the target input value, and triggers if so, triggering the computation subunit
The optimization subelement；
The computation subunit for according to the target output value of the first quantity determined, and utilizes predetermined the
Two majorized functions calculate the corresponding reference value of target output value of first quantity.
6. the system that auxiliary according to claim 5 drives, which is characterized in that
First majorized function, including：
Wherein, f (xi) optimal value for characterizing i-th in the crucial subregion of first quantity crucial subregion；xiFor table
Levy the input value of described i-th crucial subregion；C is used to characterize the parameter of described image information；Radom is for characterizing described i-th
The corresponding empirical value of a key subregion；
Second majorized function, including：
Wherein, SjReference value for characterizing j-th of image information at least one image information；wijFor characterizing
State the default weight of i-th of crucial subregion in j-th of image information；bjThreshold value for characterizing j-th of image information；
N is for characterizing first quantity；rand(xi) it is used to characterize the equilibrium valve of described i-th crucial subregion.
7. the system that auxiliary according to claim 5 drives, which is characterized in that
The determination unit is specifically used for, for each crucial subregion, which being carried out gray processing processing, and
Determine the gray value for each pixel that the key subregion includes, and determine the gray value of each pixel
Adduction is the input value of the key subregion.
8. according to the system that any auxiliary drives in claim 5 to 7, which is characterized in that
Further comprise：First brake unit monitors that the barycentre offset of the corresponding driver of the vehicle is more than for working as
When the first threshold of respective settings, start emergency braking；
And/or
Further comprise：Second brake unit, the normally travel direction for determining the vehicle according to described image information, when
Monitor that the angle between the current driving direction of the vehicle and the normally travel direction is more than the second threshold of respective settings
When value, start emergency braking.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610997607.0A CN106696825B (en) | 2016-11-11 | 2016-11-11 | A kind of method and system that auxiliary drives |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610997607.0A CN106696825B (en) | 2016-11-11 | 2016-11-11 | A kind of method and system that auxiliary drives |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106696825A CN106696825A (en) | 2017-05-24 |
| CN106696825B true CN106696825B (en) | 2018-10-19 |
Family
ID=58939803
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610997607.0A Active CN106696825B (en) | 2016-11-11 | 2016-11-11 | A kind of method and system that auxiliary drives |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106696825B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112835048B (en) * | 2021-01-04 | 2023-12-15 | 海门市帕源路桥建设有限公司 | Automatic positioning control method for construction space |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102074014B (en) * | 2011-02-23 | 2012-12-12 | 山东大学 | Stereo matching method by utilizing graph theory-based image segmentation algorithm |
| CN103745241A (en) * | 2014-01-14 | 2014-04-23 | 浪潮电子信息产业股份有限公司 | Intelligent driving method based on self-learning algorithm |
| US9248832B2 (en) * | 2014-01-30 | 2016-02-02 | Mobileye Vision Technologies Ltd. | Systems and methods for detecting traffic signal details |
-
2016
- 2016-11-11 CN CN201610997607.0A patent/CN106696825B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN106696825A (en) | 2017-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020052436A1 (en) | Vehicle overload alarming method and apparatus, electronic device, and storage medium | |
| CN107833312A (en) | Driving dangerousness coefficient appraisal procedure and device based on multi-modal information | |
| US9082285B2 (en) | System and method for determining vehicle driving status information-based driving concentration | |
| CN104827963B (en) | A kind of method, control system and control device for collision prevention of vehicle intelligent early-warning | |
| WO2019178851A1 (en) | Deep learning-based manhole cover loss detection system and method | |
| CN110321916A (en) | Learning data production method, learning method, risk prediction method and device, program storage medium | |
| CN107004347A (en) | Drive decision maker and detection means | |
| WO2018046015A1 (en) | Alarm method, device and terminal for vehicle | |
| CN111846046B (en) | System, method and device for detecting safety of bicycle | |
| JP6318785B2 (en) | Vehicle information processing system | |
| CN110435672A (en) | One kind is based on scene anticipation safe driving householder method and its system | |
| CN112477854A (en) | Monitoring and early warning device and method based on vehicle blind area | |
| CN104766445A (en) | Vehicle-mounted early warning, warning and distress system | |
| KR101857554B1 (en) | External data intrusion detection apparatus and method for vehicles | |
| US9978249B1 (en) | Method, device, and system for monitoring taxi | |
| JP2024009828A (en) | Program, information processing method, and information processing system | |
| CN106696825B (en) | A kind of method and system that auxiliary drives | |
| CN110705416B (en) | Safe driving early warning method and system based on driver face image modeling | |
| CN116524396A (en) | Vehicle Appearance Abnormality Detection Method and Device, Electronic Equipment, and Storage Medium | |
| CN107358678B (en) | A driving event detection and recognition method | |
| CN112418000B (en) | Bad driving behavior detection method and system based on monocular camera | |
| KR20160089933A (en) | Apparatus and method for preventing vehicle collision | |
| CN102043941A (en) | Dynamic real-time relative relationship recognition method and system | |
| CN114841483A (en) | Safety monitoring method and system for logistics freight vehicle | |
| CN117392841A (en) | Traffic accident handling method and device based on wireless perception and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |