A kind of intelligent wiper starting method
Technical field
The present invention relates to a kind of starting of rain brush method, especially one kind, can not have to user manually opened and fully meet use
The intelligent wiper of family actual demand starts method.
Background technique
Rain brush is device indispensable on various vehicles, is related to vehicle in the Exploration on Train Operation Safety of rainy day, for eliminating resistance
Sleet, the dust etc. on glass are kept off, to guarantee glass transparent clearly to ensure the user visual field.Existing most of rain brush are all
User is needed to be adjusted manually, this causes the dispersion of user's attention undoubtedly in driving to be easy to cause accident, and
The gear of adjusting is limited, can not well adapt to the demand of user.There is also detect rainwater by rainfall sensor to certainly
The dynamic rain brush controlled, then precipitation rain fall sensor is usually that the principles such as infrared ray, capacitor, thermocouple is used to detect water droplet
In the presence of, need all to install many hardware devices additional in each car, cause the increase of cost, and for southern user and
Speech, the control of this principle can not often detect the presence of drizzle, and leading to user, there is still a need for hands in drizzle
It is dynamic to be operated.
There are also in such a way that image is controlled, by the feature for identifying picture, extracting picture, it is filtered etc. multiple
It can just judge whether open rain brush after processing, however this mode needs each car to be all equipped with the very powerful processing of function
Device significantly increases the cost of operation, and the selection of algorithm is very big on the influence of the correctness of result, if algorithm is not suitable with certain
The characteristic of the rainwater in area, then the result identified is likely to mistake.
Summary of the invention
Therefore, in view of the above-mentioned problems, the present invention provides a kind of intelligent wiper starting method, it can be achieved that rain brush automatically turns on
And user's actual need is fully met, the cost of excessive increase vehicle is not needed, user experience is greatly improved.
In order to achieve the above object, the invention proposes a kind of intelligent wipers to start method, comprising:
1. video acquisition;
2. data acquire;
3. obtaining image;
4. intelligence learning;
5. intelligent starting.
Above-mentioned intelligent wiper starts method, and further also meet condition: step 1 is specifically, using interior backsight is placed in
Camera near mirror position acquire in real time obtained by front windshield it is consistent with the driver visual field with time shaft mark
Video is simultaneously sent to entire car controller by the video of note in real time.
Above-mentioned intelligent wiper starts method, and further also meet condition: camera is the camera of automobile data recorder.
Above-mentioned intelligent wiper starts method, and further also meet condition: camera is powered by interior cigarette lighter plug.
Above-mentioned intelligent wiper starts method, and further also meet condition: step 2 is specifically, detection stepless speed-regulating device
Whether it is rotated, rotation initial time, rotation end time is sent to entire car controller.
Above-mentioned intelligent wiper starts method, further also meets condition: camera uses super clear camera.
Above-mentioned intelligent wiper starts method, further also meets condition: video format MPEG-4.
Intelligent wiper of the invention starts method, it is only necessary to realize video acquisition, data acquisition and be tied according to acquisition in vehicle side
The process that fruit obtains image and then uploads image does not need vehicle side and carries out excessive information collection, processing, analysis work, subtracts
The light burden of vehicle side, while Cloud Server is based on big data and carries out intelligent depth study to image, obtains and meets user demand
Neural model, and neural model software implementation is handed down to vehicle side, and then only need that software is installed in vehicle side and run can be real
Show fully automated and have the function of the rain brush intelligent starting of high user experience, rain can not only be opened in time when user needs
It brushes and the speed needed in user can be stablized.
Detailed description of the invention
Fig. 1 is a kind of intelligent wiper starting method flow diagram of the invention.
Specific embodiment
Embodiment one.
Referring to Figure 1.
A kind of intelligent wiper starts method, includes:
1. video acquisition;
2. data acquire;
3. obtaining image;
4. intelligence learning;
5. intelligent starting.
Step 1 passes through front windshield specifically, acquiring in real time using the camera being placed near room mirror position
Video is simultaneously sent to entire car controller by obtained consistent with the driver visual field video with time shaft label in real time.
For save the cost, so that scheme has more feasibility, camera can be installed in most of vehicle
The camera of automobile data recorder.In order to improve the precise degrees of image recognition, camera at least uses high-definition camera, preferably adopts
With super clear camera.For the ease of transmitting and handling, video should reach balance between clarity and size, therefore should
Using mpeg format, especially MPEG-4 format.Camera is usually powered by interior cigarette lighter plug, can also be used and additionally be set
The power supply of the devices such as battery, the solar battery set.
Step 2 is specifically, whether detection stepless speed-regulating device is rotated, by rotation initial time, rotation end time hair
Give entire car controller.
Embodiment two.
A kind of intelligent wiper starts method, which is characterized in that itself the following steps are included:
Obtained by front windshield and driver is acquired using the camera being placed near room mirror position in real time
Video is simultaneously sent to entire car controller by the consistent video with time shaft label in the visual field in real time;
Whether detection stepless speed-regulating device is rotated, and rotation initial time, rotation end time are sent to full-vehicle control
Device;
Entire car controller be based on rotation initial time retract a predetermined reaction time obtain rotation required time, band sometimes
Between image when the corresponding image of rotation required time being intercepted to obtain rotation demand in the video that marks of axis, in band
The rotation end time corresponding image is intercepted into the image at the end of being rotated in the video of having time axis label, it will
There are image when rotation demand, the image at the end of rotation to be packaged into a file, is sent out this document by telecommunication mode
Give cloud server;
Cloud server, which is received, uploads the multiple files to come from multiple entire car controllers, will there is rotation in All Files
Image when demand is grouped together into rotation and orders training picture set, by the image group at the end of rotating in All Files
It is combined to form constant speed order training picture set;Rotation is ordered each of training picture set figure by cloud server
As resolving into the subgraph being overlapped according to certain tactic multiple portions, each subgraph is input to a nervelet net
In network, the output of the nervelet network is stored in a small ordered series of numbers, all small ordered series of numbers are arranged according to certain sequence
Column obtain a big ordered series of numbers, which is input in one big neural network, so obtain can according to image judgement be
It is no that there are the first nerves controllers of rotation demand;Constant speed order is trained each of picture set image by cloud server
The subgraph being overlapped according to certain tactic multiple portions is resolved into, each subgraph is input to a nervelet network
In, the output of the nervelet network is stored in a small ordered series of numbers, all small ordered series of numbers are arranged according to certain sequence
A big ordered series of numbers is obtained, which is input in one big neural network, and then obtain to judge revolving speed according to image
Whether the nervus opticus controller of user demand has been met;
First nerves controller, nervus opticus controller difference software are melted into the first software, second soft by cloud server
Part, and the first software, the second software are issued to all entire car controllers;
Each entire car controller receives the first software, the second software and is installed;Entire car controller will have time shaft
The video of label is input to the first software in real time, when there are export rotation requirement command when rotation demand to whole for the judgement of the first software
Vehicle controller, entire car controller are immediately controlled rain brush and start to be turned with a predetermined acceleration raising speed when receiving rotation requirement command
It is dynamic, while entire car controller will no longer be input in real time the first software with the video of time shaft label, and by the band having time
The video of axis label is input to the second software in real time;It is fixed to export when the second software judges that rain brush revolving speed has met user demand
To entire car controller, entire car controller is immediately controlled rain brush when receiving constant speed instruction and is persistently rotated with present speed for speed instruction,
And entire car controller continues the video that should have time shaft label being input to the first software and the second software in real time respectively;When
There is no output reductions of speed when rotation demand to instruct to entire car controller for the judgement of first software, and entire car controller receives reduction of speed instruction
When rain brush be immediately controlled rotated with a predetermined acceleration reduction of speed, when the second software judges that rain brush revolving speed no longer meets user demand
When, instruction of raising speed is exported to entire car controller, and entire car controller is immediately controlled rain brush when receiving speed-raising instruction and makes a reservation for add with one
The rotation of speed raising speed.
Embodiment three.
A kind of intelligent wiper starts method, which is characterized in that itself the following steps are included:
Obtained by front windshield and driver is acquired using the camera being placed near room mirror position in real time
Video is simultaneously sent to entire car controller by the consistent video with time shaft label in the visual field in real time,
The position of camera appropriate should adjust so that the emphasis for the video that camera is taken and the side in the driver visual field
Emphasis is consistent, therefore, can not use the camera of automobile data recorder, and a camera is in addition arranged and enables its position
By flexibly adjustment;
Whether detection stepless speed-regulating device is rotated, and rotation initial time, rotation end time are sent to full-vehicle control
Device,
Stepless speed-regulating device for realized by artificial rotation process rain brush by stop working to work at a slow speed it is last to
The process of rapid operation, the control to rain brush rotation speed are stepless;
Entire car controller be based on rotation initial time retract a predetermined reaction time obtain rotation required time, band sometimes
Between image when the corresponding image of rotation required time being intercepted to obtain rotation demand in the video that marks of axis, in band
The rotation end time corresponding image is intercepted into the image at the end of being rotated in the video of having time axis label, it will
There are image when rotation demand, the image at the end of rotation to be packaged into a file, is sent out this document by telecommunication mode
Cloud server is given,
Due to the presence of human response's time, rotating initial time is not the time that user is actually needed that rain brush is opened,
Therefore the predetermined reaction time for subtracting characterization human response's time by being easy to the rotation initial time that detection obtains is needed to obtain
To rotation required time accurately embody user actually want to rain brush open at the time of,
Stepless speed regulation is different from traditional stage speed regulation, and stage speed regulation is substantially instantaneous, and stepless speed regulation is to deposit
In the governing time that one can not ignore, i.e. user no longer adjusts after starting speed regulation to the speed for being satisfied with speed adjusting to oneself
Show that user is satisfied to bring clarity after the rain brush work of present speed when user no longer adjusts the speed fast this period,
Due to needing to carry out screenshot so that image can to video according to rotation required time and rotation end time
The visual field of user at that time is accurately embodied, therefore should be when starting by the time of the time of camera and stepless speed-regulating device
It is synchronous,
The image transmitting at the end of image, rotation when entire car controller will only have a rotation demand to cloud server, and
The image of other times can be abandoned, do not need to store, not only reduce the burden of communication, reduce communication congestion can
Energy property, and the processing of cloud server is more succinctly facilitated,
Common telecommunication mode includes 4G, 5G, wifi;
Cloud server, which is received, uploads the multiple files to come from multiple entire car controllers, will there is rotation in All Files
Image when demand is grouped together into rotation and orders training picture set, by the image group at the end of rotating in All Files
It is combined to form constant speed order training picture set;Rotation is ordered each of training picture set figure by cloud server
As resolving into the subgraph being overlapped according to certain tactic multiple portions, each subgraph is input to a nervelet net
In network, the output of the nervelet network is stored in a small ordered series of numbers, all small ordered series of numbers are arranged according to certain sequence
Column obtain a big ordered series of numbers, which is input in one big neural network, so obtain can according to image judgement be
It is no that there are the first nerves controllers of rotation demand;Constant speed order is trained each of picture set image by cloud server
The subgraph being overlapped according to certain tactic multiple portions is resolved into, each subgraph is input to a nervelet network
In, the output of the nervelet network is stored in a small ordered series of numbers, all small ordered series of numbers are arranged according to certain sequence
A big ordered series of numbers is obtained, which is input in one big neural network, and then obtain to judge revolving speed according to image
Whether the nervus opticus controller of user demand has been met,
For each subgraph, using identical neural network weight;
First nerves controller, nervus opticus controller difference software are melted into the first software, second soft by cloud server
Part, and the first software, the second software are issued to all entire car controllers once communicated with cloud server,
The process of machine learning needs identification and the matching process of great amount of images, and conventional vehicle side controller cannot achieve,
And if the cost that can greatly improve vehicle if vehicle side upgrade controller can realize this process, it is unfavorable for technology
Popularization and application, therefore, the cloud server for being alternatively provided at a distant place realizes this process, and cloud server can be according to region
Setting, such as one cloud server is set in south, in the north, another cloud server is set, it can also be according to vehicle type
Setting, such as one cloud server is set for truck, for car, another cloud server is set,
The judgement precise degrees of first, second neuron controller should be limited, i.e., only when its accuracy rate is in a fixed limit
Just by software implementation and then entire car controller can be handed down to when being worth above;
Entire car controller receives the first software, the second software and is installed;Entire car controller will be marked with time shaft
Video be input to the first software in real time, when the first software judgement there are export when rotation demand rotate requirement command give vehicle control
Device processed, entire car controller are immediately controlled rain brush and start with predetermined acceleration raising speed rotation, together when receiving rotation requirement command
When entire car controller no longer will be input in real time the first software with the video of time shaft label, and by this with time shaft label
Video be input to the second software in real time, when the second software judges that rain brush revolving speed has met user demand export constant speed instruction
To entire car controller, entire car controller is immediately controlled rain brush when receiving constant speed instruction and is persistently rotated with present speed, and whole
Vehicle controller continues the video that should have time shaft label being input to the first software and the second software in real time respectively;When first soft
There is no output reductions of speed when rotation demand to instruct to entire car controller for part judgement, and entire car controller receives when reduction of speed instructs immediately
Control rain brush is rotated with a predetermined acceleration reduction of speed, when the second software judges that rain brush revolving speed no longer meets user demand, output
To entire car controller, rain brush is immediately controlled when receiving speed-raising instruction with a predetermined acceleration raising speed in entire car controller for speed-raising instruction
Rotation exports constant speed when the second software judges that rain brush revolving speed has met user demand and instructs to entire car controller, vehicle control
Device processed is immediately controlled rain brush when receiving constant speed instruction and is persistently rotated with present speed,
By the way that entire car controller will be handed down to after the first, second neuron controller software implementation, so that entire car controller is not required to
It wants powerful processing, calculation function that the identification function to image can be thus achieved, needs to carry out rain brush control to judge automatically out
The case where processed.
It should be noted that the above content is combine specific embodiment made for the present invention further specifically
It is bright, and it cannot be said that a specific embodiment of the invention is only limitted to this, under above-mentioned guidance of the invention, those skilled in the art can
To carry out various improvement and deformations on the basis of the above embodiments, and these are improved or deformation falls in protection model of the invention
In enclosing.