CN105909116B - Control method, the apparatus and system of car door - Google Patents
Control method, the apparatus and system of car door Download PDFInfo
- Publication number
- CN105909116B CN105909116B CN201610274787.XA CN201610274787A CN105909116B CN 105909116 B CN105909116 B CN 105909116B CN 201610274787 A CN201610274787 A CN 201610274787A CN 105909116 B CN105909116 B CN 105909116B
- Authority
- CN
- China
- Prior art keywords
- car
- information
- door
- instruction
- door controlling
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000012544 monitoring process Methods 0.000 claims abstract description 68
- 230000008859 change Effects 0.000 claims abstract description 38
- 238000012549 training Methods 0.000 claims abstract description 26
- 230000001276 controlling effect Effects 0.000 claims description 201
- 230000003068 static effect Effects 0.000 claims description 16
- 230000002123 temporal effect Effects 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 12
- 238000010801 machine learning Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 9
- 230000008676 import Effects 0.000 claims description 7
- 230000009471 action Effects 0.000 claims description 6
- 238000004088 simulation Methods 0.000 claims 1
- 230000008569 process Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 230000006399 behavior Effects 0.000 description 4
- 230000006854 communication Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000001815 facial effect Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Classifications
-
- E—FIXED CONSTRUCTIONS
- E05—LOCKS; KEYS; WINDOW OR DOOR FITTINGS; SAFES
- E05F—DEVICES FOR MOVING WINGS INTO OPEN OR CLOSED POSITION; CHECKS FOR WINGS; WING FITTINGS NOT OTHERWISE PROVIDED FOR, CONCERNED WITH THE FUNCTIONING OF THE WING
- E05F15/00—Power-operated mechanisms for wings
- E05F15/70—Power-operated mechanisms for wings with automatic actuation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R16/00—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for
- B60R16/02—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements
- B60R16/023—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements for transmission of signals between vehicle parts or subsystems
- B60R16/0231—Circuits relating to the driving or the functioning of the vehicle
-
- E—FIXED CONSTRUCTIONS
- E05—LOCKS; KEYS; WINDOW OR DOOR FITTINGS; SAFES
- E05F—DEVICES FOR MOVING WINGS INTO OPEN OR CLOSED POSITION; CHECKS FOR WINGS; WING FITTINGS NOT OTHERWISE PROVIDED FOR, CONCERNED WITH THE FUNCTIONING OF THE WING
- E05F15/00—Power-operated mechanisms for wings
- E05F15/70—Power-operated mechanisms for wings with automatic actuation
- E05F15/73—Power-operated mechanisms for wings with automatic actuation responsive to movement or presence of persons or objects
-
- E—FIXED CONSTRUCTIONS
- E05—LOCKS; KEYS; WINDOW OR DOOR FITTINGS; SAFES
- E05Y—INDEXING SCHEME ASSOCIATED WITH SUBCLASSES E05D AND E05F, RELATING TO CONSTRUCTION ELEMENTS, ELECTRIC CONTROL, POWER SUPPLY, POWER SIGNAL OR TRANSMISSION, USER INTERFACES, MOUNTING OR COUPLING, DETAILS, ACCESSORIES, AUXILIARY OPERATIONS NOT OTHERWISE PROVIDED FOR, APPLICATION THEREOF
- E05Y2400/00—Electronic control; Electrical power; Power supply; Power or signal transmission; User interfaces
- E05Y2400/10—Electronic control
- E05Y2400/45—Control modes
- E05Y2400/456—Control modes for programming, e.g. learning or AI [artificial intelligence]
-
- E—FIXED CONSTRUCTIONS
- E05—LOCKS; KEYS; WINDOW OR DOOR FITTINGS; SAFES
- E05Y—INDEXING SCHEME ASSOCIATED WITH SUBCLASSES E05D AND E05F, RELATING TO CONSTRUCTION ELEMENTS, ELECTRIC CONTROL, POWER SUPPLY, POWER SIGNAL OR TRANSMISSION, USER INTERFACES, MOUNTING OR COUPLING, DETAILS, ACCESSORIES, AUXILIARY OPERATIONS NOT OTHERWISE PROVIDED FOR, APPLICATION THEREOF
- E05Y2900/00—Application of doors, windows, wings or fittings thereof
- E05Y2900/50—Application of doors, windows, wings or fittings thereof for vehicles
- E05Y2900/53—Type of wing
- E05Y2900/531—Doors
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Mechanical Engineering (AREA)
- Power-Operated Mechanisms For Wings (AREA)
Abstract
This application discloses the method for control car door, apparatus and system.One embodiment of methods described includes：When monitoring the transport condition change information of vehicle, the in-car monitoring information and car external monitor information of the correspondence transport condition change information are obtained；The Car's door controlling model that in-car monitoring information and car the external monitor information is imported into training in advance, which match, obtains Car's door controlling instruction；Being turned on and off for control car door is instructed according to the Car's door controlling.The embodiment ensure that the accuracy and security of car door opening or closing.
Description
Technical field
The application is related to technical field of information processing, and in particular to technical field of automobile control, more particularly to control car door
Method, apparatus and system.
Background technology
The state of vehicle can be generally divided into transport condition or inactive state.In view of safety factor, vehicle is in traveling shape
During state, car door is not allow to open, and only vehicle is in inactive state, and car door just can be opened according to circumstances.
Although car door is opened in stationary vehicle, but still can occur many accidents.For example, passenger inside the vehicle is in vehicle
It is static can only often get vehicle periphery a range of information when preparing to open car door, and can not be to moving closer to
Vehicle, other vehicles or pedestrians make accurate judgement.When the door is unlocked, other vehicles or pedestrians possibly be present at car door and beat
The position opened, thereby results in the damage of vehicle, or even jeopardizes personal safety.
The content of the invention
This application provides the control method of car door, apparatus and system, the problem of to solve to mention in background technology.
In a first aspect, this application provides a kind of method for controlling car door, methods described includes：When the row for monitoring vehicle
When sailing state change information, the in-car monitoring information and car external monitor information of the correspondence transport condition change information, institute are obtained
Stating transport condition change information is included by moving to static status information or parking waiting status information, the in-car monitoring letter
Breath includes in-car image information and in-car acoustic information, and the car external monitor information includes the outer image information of car and the outer sound letter of car
Breath；The Car's door controlling model that in-car monitoring information and car the external monitor information is imported into training in advance match obtaining car door
Control instruction, the Car's door controlling model is used to characterize pair that in-car monitoring information and car external monitor information are instructed with Car's door controlling
It should be related to, the Car's door controlling instruction includes the car door information of opening car door and the temporal information of opening car door, or closed door
Car door information and closed door temporal information；Being turned on and off for control car door is instructed according to the Car's door controlling.
Second aspect, this application provides a kind of device of control car door, described device includes：Monitoring information obtains single
Member, the in-car prison for when monitoring the transport condition change information of vehicle, obtaining the correspondence transport condition change information
Measurement information and car external monitor information, the transport condition change information are included by moving to static status information or parking waiting
Status information, the in-car monitoring information includes in-car image information and in-car acoustic information, and the car external monitor information includes
The outer image information of car and the outer acoustic information of car；Car's door controlling instructs acquiring unit, for by outside the in-car monitoring information and car
The Car's door controlling model of monitoring information importing training in advance, which match, obtains Car's door controlling instruction, and the Car's door controlling model is used
In characterizing the corresponding relation that in-car monitoring information and car external monitor information are instructed with Car's door controlling, the Car's door controlling instruction includes
The car door information and the temporal information of opening car door of opening car door, or the car door information of closed door and the time of closed door believe
Breath；Execution unit, being turned on and off for car door is controlled for being instructed according to the Car's door controlling.
The third aspect, this application provides a kind of system for controlling car door, the system includes the control of above-mentioned second aspect
The device of car door processed.
The method for the control car door that the application is provided, apparatus and system, change in the transport condition for monitoring vehicle first
During information, in-car monitoring information and car external monitor information are obtained, to obtain comprehensive information of vehicles；Then by in-car monitoring information
With car external monitor information importing Car's door controlling model match and obtain Car's door controlling instruction, car door can be turned on and off
Accurate judgement is made, is instructed finally according to Car's door controlling and controls being turned on and off for car door, farthest ensure that car door is opened
The accuracy and security for opening or closing.
Brief description of the drawings
By reading the detailed description made to non-limiting example made with reference to the following drawings, the application's is other
Feature, objects and advantages will become more apparent upon：
Fig. 1 a are the flow charts of the method for the control car door according to the application；
Fig. 1 b are the flow charts for setting up image recognition model according to the application；
Fig. 1 c are the flow charts for setting up voice recognition model according to the application；
Fig. 2 is a schematic diagram of the application scenarios of the method for the control car door according to the present embodiment；
Fig. 3 is a structural representation of the device of the control car door according to the application；
Fig. 4 is the structural representation of one embodiment of the terminal device according to the application.
Embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that, in order to
Be easy to description, illustrate only in accompanying drawing to about the related part of invention.
It should be noted that in the case where not conflicting, the feature in embodiment and embodiment in the application can phase
Mutually combination.Describe the application in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 a show the flow chart 100 of the method for control car door.As shown in Figure 1a, the side of the control car door of the present embodiment
Method comprises the following steps：
Step 101, when monitoring the transport condition change information of vehicle, the correspondence transport condition change information is obtained
In-car monitoring information and car external monitor information.
In motion, car door does not allow to be opened vehicle, when a vehicle is at rest, and car door can be opened.Cause
This, when vehicle is by moving to static, car door can be opened；When vehicle remains static, car door can also be opened.
It can be seen that, transport condition change information can be determined by speed monitoring equipment or gps signal.
Whether car door is opened judge when, it is necessary to consider in-car monitoring information and car external monitor information.Wherein,
In-car monitoring information includes the content spoken of occupant, for example, " I will get off ", " enabling ", " I goes down XXX "；In-car prison
Measurement information can also include in-car image information, for example, the face-image of occupant, the location drawing picture of occupant.Car
External monitor information includes the acoustic information outside car, for example, the sound of other vehicles of vehicle periphery, vehicle periphery pedestrian are (especially
The elderly and minor) sound, the sound of car owner, the sound of car owner family and friends, also can determine that according to these sound
The distance of other vehicles and pedestrian relative to vehicle and direction；Car external monitor information includes the image information outside car, for example, car owner
Location drawing picture, car owner household and ambient image residing for the location drawing picture of friend, vehicle, around other vehicles image or
The image of pedestrian.Therefore, the transport condition change information of the present embodiment is included by moving to static status information or parking etc.
Treat status information.The in-car monitoring information includes in-car image information and in-car acoustic information, the car external monitor packet
Include the outer image information of car and the outer acoustic information of car.Above-mentioned in-car monitoring information and car external monitor information can pass through vehicle-mounted pick-up
Head and sound pick-up outfit are obtained.
Step 102, the Car's door controlling model for in-car monitoring information and car the external monitor information being imported into training in advance enters
Row matching obtains Car's door controlling instruction.
Wherein, the Car's door controlling model is used to characterize in-car monitoring information and car external monitor information and Car's door controlling instruction
Corresponding relation, Car's door controlling instruction includes the car door information of opening car door and the temporal information of opening car door, or closing
The car door information and the temporal information of closed door of car door.
Car's door controlling model is got by the training of the in-car monitoring information and car external monitor information that collect, for by pair
The analysis of acoustic information and image information outside in-car car, determines the intention of car owner and related personnel, and then control car door referring to
The fixed time opens or closes.
In some optional implementations of the present embodiment, the present embodiment method also includes setting up Car's door controlling model
Step, may comprise steps of：
The first step, sets up image recognition model and sound identification model respectively.
Seen from the above description, in-car monitoring information and car external monitor information includes image information and acoustic information respectively.
Accordingly, it would be desirable to corresponding image recognition model and sound identification model be set up respectively, according to the image result and sound identified
As a result corresponding Car's door controlling instruction is determined.That is, described image identification model is used to characterize in-car image information and the outer image of car
The corresponding relation that information is instructed with Car's door controlling, the voice recognition model is used to characterize in-car acoustic information and the outer sound letter of car
The corresponding relation that breath is instructed with Car's door controlling.
Second step, is the described image identification model weights different with the configuration of sound identification model, described in after weighting
Image recognition model and the combination of sound identification model obtain Car's door controlling model.
For different car owners, the household of car owner and friend, they get on the bus or get off the motor habit that often occurs and
The characteristics of custom of speaking (including content of speaking, tone color of speaking) has oneself, also, can be obtained by some action or sound
More accurately judge.Therefore, can be corresponding image recognition model and sound identification model configuration weights, and weights can not
It is identical, it is necessary to which that a weights are big, and another weights is small, the judged result for image recognition model and sound identification model otherwise occur
When inconsistent, it is impossible to provide definite Car's door controlling instruction.
In some optional implementations of the present embodiment, such as Fig. 1 b institutes of flow chart 1021 of image recognition model are set up
Show, may comprise steps of：
Step 10211, in-car sample image is extracted from image information outside history in-car image information and history car respectively
The outer sample image information of car of information and the correspondence in-car sample image information.
(the in-car image information of history and gone through before training image identification model, it is necessary to first gather various image informations
The outer image information of history car), for example, driver's facial image information, the location drawing picture information of occupant, the action of occupant
Image information, the location drawing picture information of the outer personnel of car, the motion images information of the outer personnel of car, the image in car setpoint distance
Information (image information at the image information of such as automobile tail, automobile tire).Get after above-mentioned various image informations,
Picked out from these image informations to opening door of vehicle or related image information of closing the door as sample image information.For example, will
From personnel in the car, door opening, personnel get off, the corresponding image information of the door that cut-offs is as the sample image information got off；By people
Member is outside car, door opening, personnel get on the bus, the corresponding image information of the door that cut-offs is as the sample image information got on the bus.Can also be by
The image information at image information or tire when getting on the bus or getting off at the tailstock is further increased as sample image information
Car or the security got off.
Step 10212, filtered out respectively from sample image information outside the in-car sample image information and car and meet
The one in-car sample image characteristic information imposed a condition and the outer sample image characteristic information of car.
Wherein, described first impose a condition including at least one in time conditions, operation condition and locality condition.
The sample image information got off is got with after the sample image information got on the bus, passes through the sample image information got off
Corresponding sample image characteristic information is extracted in time corresponding with the sample image information got on the bus, action and position.For example, getting off
Time order and function order information, action change information and the change in location of process each sample image information corresponding with the process of getting on the bus
Information etc..
Step 10213, the of the outer sample image characteristic information of correspondence in-car the sample image characteristic information and car is searched
One history Car's door controlling is instructed.
Get after in-car sample image characteristic information and the outer sample image characteristic information of car, it may be determined that specifically get off
Behavior and behavior of getting on the bus, and then obtain corresponding first history Car's door controlling instruction, the first history Car's door controlling instruction bag
Include door open command or instruction of closing the door, can also include which car door specifically opened.
Step 10214, using machine learning method, based on sample image outside the in-car sample image characteristic information, car
Characteristic information and the instruction of the first history Car's door controlling, training obtain image recognition model.
By existing a variety of machine learning methods, sample image feature outside in-car sample image characteristic information and car is believed
Breath is as input information, using the instruction of the first history Car's door controlling as output information, set up in-car sample image characteristic information and
The outer sample image characteristic information of car and the corresponding relation of the first history Car's door controlling instruction, obtain image recognition model.
In some optional implementations of the present embodiment, such as Fig. 1 c institutes of flow chart 1022 of voice recognition model are set up
Show, may comprise steps of：
Step 10221, in-car sample audio is extracted from acoustic information outside history in-car acoustic information and history car respectively
The outer sample audio information of car of information and the correspondence in-car sample audio information.
Before training voice recognition model, it is necessary to first gather various acoustic informations (i.e. the in-car acoustic information of history with go through
The outer acoustic information of history car), for example, the acoustic information (including male voice, female voice, accent) of driver, the sound of in-car other staff
Information (further may determine that the position of other staff in the car accordingly), the acoustic information of in-car sound equipment or broadcast, car it is outer its
The sound of the outer non-motor vehicle of the acoustic information of his vehicle, the acoustic information of goers outside vehicle, car.Get above-mentioned various acoustic informations
Afterwards, picked out from these acoustic informations to opening door of vehicle or related acoustic information of closing the door as sample audio information.For example,
Using from personnel in the car, door opening, personnel get off, the corresponding acoustic information of the door that cut-offs is used as the sample audio information got off；Will
Personnel are outside car, door opening, personnel get on the bus, the corresponding acoustic information of the door that cut-offs is as the sample audio information got on the bus.Can be with
Using the acoustic information of other vehicles when getting on the bus or get off and the acoustic information of pedestrian as sample audio information, further increase
The security got on the bus or got off.
Step 10222, filtered out respectively from sample audio information outside the in-car sample audio information and car and meet
The two in-car sample audio characteristic informations imposed a condition and the outer sample audio characteristic information of car.
Wherein, described second impose a condition including in voice content condition, voice direction condition and equipment audio conditions
At least one of.
The sample audio information got off is got with after the sample audio information got on the bus, passes through the sample audio information got off
Corresponding with the sample audio information got on the bus voice content (" getting off ", " I goes down XXX "), voice direction and equipment sound are (empty
Voicing sound, broadcast sounds, engine sound) extract corresponding sample audio characteristic information.For example, get off process and process of getting on the bus
Voice content change information, voice direction change information and the equipment sound variation information of each corresponding sample image information
Deng.
Step 10223, the of the outer sample audio characteristic information of correspondence in-car the sample audio characteristic information and car is searched
Two history Car's door controllings are instructed.
Get after in-car sample audio characteristic information and the outer sample audio characteristic information of car, it may be determined that specifically get off
Behavior and behavior of getting on the bus, and then obtain corresponding second history Car's door controlling instruction, the second history Car's door controlling instruction bag
Include door open command or instruction of closing the door, can also include which car door specifically opened.
Step 10224, using machine learning method, based on sample audio outside the in-car sample audio characteristic information, car
Characteristic information and the instruction of the second history Car's door controlling, training obtain voice recognition model.
By existing a variety of machine learning methods, sample audio feature outside in-car sample audio characteristic information and car is believed
Breath is as input information, using the instruction of the second history Car's door controlling as output information, set up in-car sample audio characteristic information and
The outer sample audio characteristic information of car and the corresponding relation of the second history Car's door controlling instruction, obtain voice recognition model.
It is described by in-car monitoring information and car the external monitor information in some optional implementations of the present embodiment
Import training in advance Car's door controlling model carry out match obtain Car's door controlling instruction may comprise steps of：
The first step, image information outside the car of the in-car image information of the in-car monitoring information and car external monitor information is led
Enter described image identification model, obtain the instruction of the first Car's door controlling.
Obtain after above-mentioned image recognition model, image information outside current in-car image information and car is imported into described image
Identification model, obtains the instruction of the first Car's door controlling, and the instruction of the first Car's door controlling can include controlling which car door, when open and what
Shi Guan.
Second step, acoustic information outside the in-car acoustic information of the in-car monitoring information and the car of car external monitor information is led
Enter the voice recognition model, obtain the instruction of the second Car's door controlling.
The process for obtaining the instruction of the second Car's door controlling is similar with obtaining the instruction of the first Car's door controlling, and here is omitted.
3rd step, when first Car's door controlling instruction is identical with the instruction of the second Car's door controlling, then Car's door controlling is instructed
It is identical with first Car's door controlling instruction or the second Car's door controlling instruction, otherwise, Car's door controlling instruction and first car door
Weights the greater is identical during control instruction is instructed with the second Car's door controlling.
Wherein, the first Car's door controlling instruction is identical with weights the greater in the instruction of the second Car's door controlling.
The the first Car's door controlling instruction obtained by image recognition model and the second car obtained by voice recognition model
Gate control instruction may be identical, it is also possible to different, when the instruction of the first Car's door controlling is identical with the instruction of the second Car's door controlling, explanation
The possibility opened the door or closed the door is very high；When the instruction of the first Car's door controlling is different with the instruction of the second Car's door controlling, illustrate that image is believed
Breath is different with the result that acoustic information is obtained, at this time, it may be necessary to be entered according to the weights to image recognition model and sound identification model
Row judges.The size of weights determines the priority of image recognition model and sound identification model, passes through image recognition model harmony
The instruction of the first Car's door controlling and the instruction of the second Car's door controlling that sound identification model is obtained are also corresponding with the weights.When the first car door control
When system instruction is different with the instruction of the second Car's door controlling, Car's door controlling instruction Car's door controlling instruction (first car door larger with weights
Control instruction or the instruction of the second Car's door controlling) it is identical.That is, in Car's door controlling instruction and image recognition model and sound identification model
The instruction of the first Car's door controlling or the instruction of the second Car's door controlling that weights the greater is obtained are identical.
Step 103, instructed according to the Car's door controlling and control being turned on and off for car door.
Obtain after Car's door controlling instruction, the motor on car door can be controlled to control being turned on and off for car door.
In some optional implementations of the present embodiment, described instructed according to the Car's door controlling controls opening for car door
Following two situations can be included by opening and closing：
The first, when the transport condition change information is by moving to static status information, according to the car door
Control instruction opening car door, and when nobody gets on the bus or got off in the first setting time, otherwise closed door, keeps car
Door closure state.
Car's door controlling instruction generally includes opening car door and closed door, when Car's door controlling instruction is opening car door, then
Car door is opened, and when detecting that someone gets on the bus or got off, keeps car door opening state, when getting on the bus or getting off completion, car is closed
Door；When Car's door controlling instruction is closed door, because vehicle movement is into quiescing process, what car door was originally closed, because
This, keeps closing of the door state.
Second, when the transport condition change information is parking waiting status information, referred to according to the Car's door controlling
Opening car door is made, and when nobody gets on the bus or got off in the second setting time, otherwise closed door, keeps closing of the door
State.
During parking waiting state to the control process of car door with vehicle by moving to static when to the control process class of car door
Seemingly, here is omitted.
With continued reference to Fig. 2, Fig. 2 is a schematic diagram of the application scenarios of the method for the control car door according to the present embodiment.
Fig. 2 shows that automobile A goes out situation when stopping in traffic lights.As the above analysis, the technical scheme of the application is by moving
In-car monitoring information and car external monitor information can be obtained during to static and parking waiting, and then controls being turned on and off for car door.
If in parking stall parking, the first Car's door controlling instruction and second obtained according to in-car monitoring information and car external monitor information
Car's door controlling instruction identical is more many than regular meeting, easily makes accurate judgment.The present embodiment runs into traffic lights in the process of moving
Situation about stopping is illustrated to technical scheme.In traffic light, automobile A stops, and monitors automobile A traveling
State change information, now obtains in-car monitoring information and car external monitor information.Now, car external monitor information has been able to detect that
Image information and acoustic information that pedestrian quickly moves in motor vehicle environment, and other vehicles and motorcycle image information harmony
Message ceases, moreover it is possible to obtain the image of traffic lights.Now, even if detecting the acoustic information that in-car there are " getting off " etc, or
Get off motion images, the Car's door controlling instruction obtained by Car's door controlling model is also to maintain the operation of closing of the door.Similarly, when
Vehicle is dead ship condition, and it is in-car nobody when (car door now should be closed), if occurring in that it around car
His vehicles or pedestrians, though detect the outer personnel of car with the corresponding image information of enabling and acoustic information, Car's door controlling model
Obtained Car's door controlling instruction is also to maintain the operation of closing of the door.
The method that above-described embodiment of the application is provided, first when monitoring the transport condition change information of vehicle, is obtained
Monitoring information and car external monitor information in picking up the car, to obtain comprehensive information of vehicles；Then it will be supervised outside in-car monitoring information and car
Measurement information, which imports Car's door controlling model and match, obtains Car's door controlling instruction, can to car door be turned on and off make accurate
Judge, instructed finally according to Car's door controlling and control being turned on and off for car door, farthest ensure that car door opening or closing
Accuracy and security.
With further reference to Fig. 3, as the realization to method shown in above-mentioned each figure, this application provides a kind of control car door
One embodiment of device, the device embodiment is corresponding with the embodiment of the method shown in Fig. 1.
As shown in figure 3, the device 300 of the above-mentioned control car door of the present embodiment includes：Monitoring information acquiring unit 301, car
Gate control instructs acquiring unit 302 and execution unit 303.Wherein, monitoring information acquiring unit 301 is used to monitor vehicle
During transport condition change information, the in-car monitoring information and car external monitor information of the correspondence transport condition change information are obtained,
The transport condition change information is included by moving to static status information or parking waiting status information, the in-car monitoring
Information includes in-car image information and in-car acoustic information, and the car external monitor information includes the outer image information of car and the outer sound of car
Information；Car's door controlling instruction acquiring unit 302 is used to in-car monitoring information and car the external monitor information importing training in advance
Car's door controlling model carry out match obtain Car's door controlling instruction, the Car's door controlling model be used for characterize in-car monitoring information and
The corresponding relation that car external monitor information and Car's door controlling are instructed, the Car's door controlling instruction include the car door information of opening car door with
The temporal information of opening car door, or closed door car door information and the temporal information of closed door；Execution unit 303 is used for root
Being turned on and off for control car door is instructed according to the Car's door controlling.
In some optional implementations of the present embodiment, the device 300 of control car door also includes：Car's door controlling model
Construction unit (not shown), for setting up Car's door controlling model, including：Model construction subelement (not shown) and mould
Type combines subelement (not shown).Wherein, model construction subelement is used to set up image recognition model respectively and sound is known
Other model, it is corresponding that described image identification model is used to characterizing the outer image information of in-car image information and car and Car's door controlling is instructed
Relation, the voice recognition model is used to characterize the corresponding pass that in-car acoustic information and the outer acoustic information of car are instructed with Car's door controlling
System；Model group zygote unit is used to be the described image identification model weights different with the configuration of sound identification model, after weighting
Described image identification model and sound identification model combination obtain Car's door controlling model.
In some optional implementations of the present embodiment, the model construction subelement is instructed including image recognition model
Practice module (not shown), including：Sample image information extraction submodule (not shown), sample image characteristic information are carried
Submodule (not shown), the instruction of the first history Car's door controlling is taken to search submodule (not shown) and image recognition model
Train submodule (not shown).Wherein, sample image information extraction submodule is used for respectively from the in-car image information of history
With sample outside the car that in-car sample image information and the correspondence in-car sample image information are extracted in image information outside history car
Image information；Sample image feature information extraction submodule is used for respectively from sample graph outside the in-car sample image information and car
Meet sample image characteristic information, institute outside the first in-car sample image characteristic information imposed a condition and car as being filtered out in information
First is stated to impose a condition including at least one in time conditions, operation condition and locality condition；First history Car's door controlling refers to
Submodule is searched in order to be used to search the first of the outer sample image characteristic information of correspondence in-car the sample image characteristic information and car
History Car's door controlling is instructed, and the first history Car's door controlling instruction includes door open command or instruction of closing the door；Image recognition model
Training submodule is used to utilize machine learning method, based on sample image feature outside the in-car sample image characteristic information, car
Information and the instruction of the first history Car's door controlling, training obtain image recognition model.
In some optional implementations of the present embodiment, the model construction subelement is instructed including voice recognition model
Practice module (not shown), including：Sample audio information extraction submodule (not shown), sample audio characteristic information are carried
Submodule (not shown), the instruction of the second history Car's door controlling is taken to search submodule (not shown) and sound identification model
Train submodule (not shown).Wherein, sample audio information extraction submodule is used for respectively from the in-car acoustic information of history
With sample outside the car that in-car sample audio information and the correspondence in-car sample audio information are extracted in acoustic information outside history car
Acoustic information；Sample audio feature information extraction submodule is used for respectively from sample sound outside the in-car sample audio information and car
Filtered out in message breath and meet the second in-car sample audio characteristic information imposed a condition and the outer sample audio characteristic information of car, institute
Second is stated to impose a condition including at least one in voice content condition, voice direction condition and equipment audio conditions；Second goes through
It is special for searching the outer sample audio of correspondence in-car the sample audio characteristic information and car that submodule is searched in the instruction of history Car's door controlling
The second history Car's door controlling instruction of reference breath, the second history Car's door controlling instruction includes door open command or instruction of closing the door；
Voice recognition model training submodule be used for utilize machine learning method, based on the in-car sample audio characteristic information, car outside
Sample audio characteristic information and the instruction of the second history Car's door controlling, training obtain voice recognition model.
In some optional implementations of the present embodiment, the Car's door controlling instruction acquiring unit 302 includes：First
Car's door controlling instruction obtains subelement (not shown), the instruction of the second Car's door controlling and obtains subelement (not shown) and car
Gate control instructs determination subelement (not shown).Wherein, the instruction of the first Car's door controlling obtains subelement and is used for the car
The in-car image information of interior monitoring information and the outer image information of the car of car external monitor information import described image identification model, obtain
First Car's door controlling is instructed；The instruction of second Car's door controlling, which obtains subelement, to be used to believe the in-car sound of the in-car monitoring information
Breath and the outer acoustic information of the car of car external monitor information import the voice recognition model, obtain the instruction of the second Car's door controlling；Car door
Control instruction determination subelement is used for when first Car's door controlling instruction is identical with the instruction of the second Car's door controlling, then car door control
System instruction is identical with first Car's door controlling instruction or the second Car's door controlling instruction, otherwise, and Car's door controlling is instructed and described the
One Car's door controlling instructs identical with weights the greater in the instruction of the second Car's door controlling.
In some optional implementations of the present embodiment, the execution unit 303 includes first and performs subelement (figure
Not shown in) and the second execution subelement (not shown).Wherein, first subelement is performed for becoming in the transport condition
When changing information for by moving to static status information, opening car door is instructed according to the Car's door controlling, in the first setting time
When interior nobody gets on the bus or got off, otherwise closed door, keeps closing of the door state；Second, which performs subelement, is used for described
When transport condition change information is parking waiting status information, opening car door is instructed according to the Car's door controlling, in the second setting
When nobody gets on the bus or got off in time, otherwise closed door, keeps closing of the door state.
The present embodiment additionally provides a kind of system for controlling car door, and the system includes the device of above-mentioned control car door.
Below with reference to Fig. 4, it illustrates suitable for for the computer system 400 for the terminal device for realizing the embodiment of the present application
Structural representation.
As shown in figure 4, computer system 400 includes CPU (CPU) 401, it can be read-only according to being stored in
Program in memory (ROM) 402 or be loaded into program in random access storage device (RAM) 403 from storage part 408 and
Perform various appropriate actions and processing.In RAM403, the system that is also stored with 400 operates required various programs and data.
CPU401, ROM402 and RAM403 are connected with each other by bus 404.Input/output (I/O) interface 405 is also connected to bus
404。
I/O interfaces 405 are connected to lower component：Importation 406 including touch-control entr screen etc.；Including such as liquid crystal
The output par, c 407 of display (LCD) and loudspeaker etc.；Storage part 408 including flash memory, hard disk etc.；And including all
The communications portion 409 of such as NIC of LAN card, modem.Communications portion 409 via such as internet network
Perform communication process.Driver 410 is also according to needing to be connected to I/O interfaces 405.Detachable media 411, such as disk, CD,
Magneto-optic disk, semiconductor memory etc., are arranged on driver 410, in order to the computer journey read from it as needed
Sequence is mounted into storage part 408 as needed.
Especially, in accordance with an embodiment of the present disclosure, the process described above with reference to flow chart may be implemented as computer
Software program.For example, embodiment of the disclosure includes a kind of computer program product, it includes being tangibly embodied in machine readable
Computer program on medium, above computer program bag, which contains, is used for the program code of the method shown in execution flow chart.At this
In the embodiment of sample, the computer program can be downloaded and installed by communications portion 409 from network, and/or from removable
Medium 411 is unloaded to be mounted.
Flow chart and block diagram in accompanying drawing, it is illustrated that according to the system of the various embodiments of the application, method and computer journey
Architectural framework in the cards, function and the operation of sequence product.At this point, each square frame in flow chart or block diagram can generation
The part of one module of table, program segment or code, a part for above-mentioned module, program segment or code is comprising one or more
Executable instruction for realizing defined logic function.It should also be noted that in some realizations as replacement, institute in square frame
The function of mark can also be with different from the order marked in accompanying drawing generation.For example, two square frames succeedingly represented are actual
On can perform substantially in parallel, they can also be performed in the opposite order sometimes, and this is depending on involved function.Also
It is noted that the combination of each square frame in block diagram and/or flow chart and the square frame in block diagram and/or flow chart, Ke Yiyong
Perform the special hardware based system of defined function or operation to realize, or can be referred to specialized hardware with computer
The combination of order is realized.
Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard
The mode of part is realized.Described unit can also be set within a processor, for example, can be described as：A kind of processor bag
Include monitoring information acquiring unit, Car's door controlling instruction acquiring unit and execution unit.Wherein, the title of these units is in certain feelings
The restriction to the unit in itself is not constituted under condition.For example, execution unit is also described as " for performing Car's door controlling referring to
The unit of order ".
As on the other hand, present invention also provides a kind of nonvolatile computer storage media, the non-volatile calculating
Machine storage medium can be the nonvolatile computer storage media included in said apparatus in above-described embodiment；Can also be
Individualism, without the nonvolatile computer storage media in supplying terminal.Above-mentioned nonvolatile computer storage media is deposited
One or more program is contained, when said one or multiple programs are performed by an equipment so that the said equipment：Work as prison
When measuring the transport condition change information of vehicle, obtain outside the in-car monitoring information and car of the correspondence transport condition change information
Monitoring information, the transport condition change information is included by moving to static status information or parking waiting status information, institute
Stating in-car monitoring information includes in-car image information and in-car acoustic information, and the car external monitor information includes the outer image information of car
With acoustic information outside car；
The Car's door controlling model that in-car monitoring information and car the external monitor information is imported into training in advance match
To Car's door controlling instruction, the Car's door controlling model is used to characterize in-car monitoring information and car external monitor information refers to Car's door controlling
The corresponding relation of order, the Car's door controlling instruction includes the car door information of opening car door and the temporal information of opening car door, or closes
Close the car door information of car door and the temporal information of closed door；
Being turned on and off for control car door is instructed according to the Car's door controlling.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.People in the art
Member should be appreciated that invention scope involved in the application, however it is not limited to the technology of the particular combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from the inventive concept, is carried out by above-mentioned technical characteristic or its equivalent feature
Other technical schemes formed by any combination.Such as features described above has similar work(with (but not limited to) disclosed herein
The technical characteristic of energy carries out technical scheme formed by replacement mutually.
Claims (13)
1. a kind of method for controlling car door, methods described includes：
When monitoring the transport condition change information of vehicle, the in-car monitoring letter of the correspondence transport condition change information is obtained
Breath and car external monitor information, the transport condition change information are included by moving to static status information or parking waiting state
Information, the in-car monitoring information includes in-car image information and in-car acoustic information, and the car external monitor information is included outside car
Image information and the outer acoustic information of car；
The Car's door controlling model that in-car monitoring information and car the external monitor information is imported into training in advance match obtaining car
Gate control is instructed, and the Car's door controlling model is used to characterize what in-car monitoring information and car external monitor information were instructed with Car's door controlling
Corresponding relation, the Car's door controlling instruction includes the car door information of opening car door and the temporal information of opening car door, or closes car
The car door information of door and the temporal information of closed door；
Being turned on and off for control car door is instructed according to the Car's door controlling.
2. according to the method described in claim 1, it is characterised in that methods described also includes：
The step of setting up Car's door controlling model, including：
Set up image recognition model and sound identification model respectively, described image identification model be used to characterizing in-car image information and
The corresponding relation that the outer image information of car is instructed with Car's door controlling, the voice recognition model is used to characterize in-car acoustic information and car
The corresponding relation that outer acoustic information is instructed with Car's door controlling；
For the described image identification model weights different with the configuration of sound identification model, by the described image identification model after weighting
Car's door controlling model is obtained with the combination of sound identification model.
3. method according to claim 2, it is characterised in that the image recognition model of setting up includes：
In-car sample image information is extracted from image information outside the in-car image information of history and history car and correspondence is described respectively
The outer sample image information of the car of in-car sample image information；
Filtered out respectively from sample image information outside the in-car sample image information and car and meet the first car imposed a condition
The outer sample image characteristic information of interior sample image characteristic information and car, described first imposes a condition including time conditions, action bar
At least one of in part and locality condition；
Search the first history Car's door controlling of the outer sample image characteristic information of correspondence in-car the sample image characteristic information and car
Instruction, the first history Car's door controlling instruction includes door open command or instruction of closing the door；
Using machine learning method, based on sample image characteristic information and first outside the in-car sample image characteristic information, car
History Car's door controlling is instructed, and training obtains image recognition model.
4. method according to claim 2, it is characterised in that the voice recognition model of setting up includes：
In-car sample audio information is extracted from acoustic information outside the in-car acoustic information of history and history car and correspondence is described respectively
The outer sample audio information of the car of in-car sample audio information；
Filtered out respectively from sample audio information outside the in-car sample audio information and car and meet the second car imposed a condition
The outer sample audio characteristic information of interior sample audio characteristic information and car, described second imposes a condition including voice content condition, language
At least one of in sound direction condition and equipment audio conditions；
Search the second history Car's door controlling of the outer sample audio characteristic information of correspondence in-car the sample audio characteristic information and car
Instruction, the second history Car's door controlling instruction includes door open command or instruction of closing the door；
Using machine learning method, based on sample audio characteristic information and second outside the in-car sample audio characteristic information, car
History Car's door controlling is instructed, and training obtains voice recognition model.
5. method according to claim 2, it is characterised in that described by in-car monitoring information and car the external monitor information
Import training in advance Car's door controlling model carry out match obtain Car's door controlling instruction include：
Image information outside the car of the in-car image information of the in-car monitoring information and car external monitor information is imported into described image
Identification model, obtains the instruction of the first Car's door controlling；
Acoustic information outside the in-car acoustic information of the in-car monitoring information and the car of car external monitor information is imported into the sound
Identification model, obtains the instruction of the second Car's door controlling；
When first Car's door controlling instruction is identical with the instruction of the second Car's door controlling, then Car's door controlling is instructed and first car
Gate control is instructed or the instruction of the second Car's door controlling is identical, otherwise, Car's door controlling instruction and first Car's door controlling instruction and the
Weights the greater is identical in the instruction of two Car's door controllings.
6. method according to claim 2, it is characterised in that described instructed according to the Car's door controlling controls opening for car door
Open and closing includes：
When the transport condition change information is by moving to static status information, is instructed and opened according to the Car's door controlling
Car door, and when nobody gets on the bus or got off in the first setting time, otherwise closed door, keeps closing of the door state；
When the transport condition change information is parking waiting status information, opening car door is instructed according to the Car's door controlling,
And when nobody gets on the bus or got off in the second setting time, otherwise closed door, keeps closing of the door state.
7. a kind of device of control car door, described device includes：
Monitoring information acquiring unit, for when monitoring the transport condition change information of vehicle, obtaining the correspondence traveling shape
The in-car monitoring information and car external monitor information of state change information, the transport condition change information include static by moving to
Status information or parking waiting status information, the in-car monitoring information include in-car image information and in-car acoustic information, institute
Stating car external monitor information includes the outer image information of car and the outer acoustic information of car；
Car's door controlling instructs acquiring unit, the car for in-car monitoring information and car the external monitor information to be imported to training in advance
Gate simulation, which match, obtains Car's door controlling instruction, and the Car's door controlling model is used to characterize outside in-car monitoring information and car
The corresponding relation that monitoring information is instructed with Car's door controlling, the Car's door controlling instruction includes car door information and the unlatching of opening car door
The temporal information of car door, or closed door car door information and the temporal information of closed door；
Execution unit, being turned on and off for car door is controlled for being instructed according to the Car's door controlling.
8. device according to claim 7, it is characterised in that described device also includes：
Car's door controlling model construction unit, for setting up Car's door controlling model, including：
Model construction subelement, for setting up image recognition model and sound identification model respectively, described image identification model is used
In characterizing the corresponding relation that image information is instructed with Car's door controlling outside in-car image information and car, the voice recognition model is used for
Characterize the corresponding relation that in-car acoustic information and the outer acoustic information of car are instructed with Car's door controlling；
Model group zygote unit, for for the described image identification model weights different with the configuration of sound identification model, will weight
Described image identification model and the combination of sound identification model afterwards obtains Car's door controlling model.
9. device according to claim 8, it is characterised in that the model construction subelement is instructed including image recognition model
Practice module, including：
Sample image information extraction submodule, for the extraction from image information outside the in-car image information of history and history car respectively
The outer sample image information of car of in-car sample image information and the correspondence in-car sample image information；
Sample image feature information extraction submodule, for believing respectively from sample image outside the in-car sample image information and car
Filtered out in breath and meet the outer sample image characteristic information of the first in-car sample image characteristic information imposed a condition and car, described the
One imposes a condition including at least one in time conditions, operation condition and locality condition；
Submodule is searched in the instruction of first history Car's door controlling, for searching outside correspondence in-car the sample image characteristic information and car
The first history Car's door controlling instruction of sample image characteristic information, the first history Car's door controlling instruction include door open command or
Close the door instruction；
Image recognition model training submodule, for utilizing machine learning method, based on the in-car sample image characteristic information,
The outer sample image characteristic information of car and the instruction of the first history Car's door controlling, training obtain image recognition model.
10. device according to claim 8, it is characterised in that the model construction subelement includes voice recognition model
Training module, including：
Sample audio information extraction submodule, for the extraction from acoustic information outside the in-car acoustic information of history and history car respectively
The outer sample audio information of car of in-car sample audio information and the correspondence in-car sample audio information；
Sample audio feature information extraction submodule, for believing respectively from sample audio outside the in-car sample audio information and car
Filtered out in breath and meet the outer sample audio characteristic information of the second in-car sample audio characteristic information imposed a condition and car, described the
Two impose a condition including at least one in voice content condition, voice direction condition and equipment audio conditions；
Submodule is searched in the instruction of second history Car's door controlling, for searching outside correspondence in-car the sample audio characteristic information and car
The second history Car's door controlling instruction of sample audio characteristic information, the second history Car's door controlling instruction include door open command or
Close the door instruction；
Voice recognition model training submodule, for utilizing machine learning method, based on the in-car sample audio characteristic information,
The outer sample audio characteristic information of car and the instruction of the second history Car's door controlling, training obtain voice recognition model.
11. device according to claim 8, it is characterised in that the Car's door controlling instruction acquiring unit includes：
The instruction of first Car's door controlling obtains subelement, for by the in-car image information and car external monitor of the in-car monitoring information
The outer image information of the car of information imports described image identification model, obtains the instruction of the first Car's door controlling；
The instruction of second Car's door controlling obtains subelement, for by the in-car acoustic information and car external monitor of the in-car monitoring information
The outer acoustic information of the car of information imports the voice recognition model, obtains the instruction of the second Car's door controlling；
Car's door controlling instruct determination subelement, for when first Car's door controlling instruct it is identical with the instruction of the second Car's door controlling
When, then Car's door controlling instruction is identical with first Car's door controlling instruction or the second Car's door controlling instruction, and otherwise, Car's door controlling refers to
Order is identical with weights the greater in first Car's door controlling instruction and the instruction of the second Car's door controlling.
12. device according to claim 8, it is characterised in that the execution unit includes：
First perform subelement, for the transport condition change information be by moving to static status information when, according to
The Car's door controlling instructs opening car door, and when nobody gets on the bus or got off in the first setting time, closed door is no
Then, closing of the door state is kept；
Second performs subelement, for when the transport condition change information is parking waiting status information, according to the car
Gate control instructs opening car door, and when nobody gets on the bus or got off in the second setting time, otherwise closed door, keeps
Closing of the door state.
13. a kind of system for controlling car door, it is characterised in that the system includes the control described in claim any one of 7-12
The device of car door.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610274787.XA CN105909116B (en) | 2016-04-28 | 2016-04-28 | Control method, the apparatus and system of car door |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610274787.XA CN105909116B (en) | 2016-04-28 | 2016-04-28 | Control method, the apparatus and system of car door |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105909116A CN105909116A (en) | 2016-08-31 |
| CN105909116B true CN105909116B (en) | 2017-08-04 |
Family
ID=56753112
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610274787.XA Active CN105909116B (en) | 2016-04-28 | 2016-04-28 | Control method, the apparatus and system of car door |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105909116B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107415657B (en) * | 2017-06-28 | 2023-09-15 | 驭势（上海）汽车科技有限公司 | Intelligent vehicle |
| CN108564945B (en) * | 2018-03-13 | 2020-11-10 | 斑马网络技术有限公司 | Vehicle-mounted voice control method and device, electronic equipment and storage medium |
| CN110717365B (en) * | 2018-07-13 | 2022-05-31 | 杭州海康威视数字技术股份有限公司 | Method and device for obtaining picture |
| CN110287810B (en) * | 2019-06-04 | 2021-05-25 | 北京字节跳动网络技术有限公司 | Vehicle door motion detection method, device and computer readable storage medium |
| CN110593707A (en) * | 2019-08-08 | 2019-12-20 | 广汽蔚来新能源汽车科技有限公司 | Tail gate control method, device and system, computer equipment and storage medium |
| CN112418303B (en) * | 2020-11-20 | 2024-07-12 | 浙江大华技术股份有限公司 | Training method and device for identifying state model and computer equipment |
| CN112783165A (en) * | 2020-12-29 | 2021-05-11 | 新奇点智能科技集团有限公司 | Control system and method for automatically driving vehicle |
| CN113129484B (en) * | 2021-04-07 | 2022-12-13 | 广州小鹏汽车科技有限公司 | Door lock control method and device, automobile and storage medium |
| CN115223327B (en) * | 2021-07-14 | 2024-07-12 | 广州汽车集团股份有限公司 | In-vehicle living body protection method and system |
| CN114407630A (en) * | 2022-01-29 | 2022-04-29 | 上海商汤临港智能科技有限公司 | Vehicle door control method and device, electronic equipment and storage medium |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006264472A (en) * | 2005-03-23 | 2006-10-05 | Fujitsu Ten Ltd | Vehicle body equipment controlling device and vehicle body equipment controlling method |
| JP2007077652A (en) * | 2005-09-14 | 2007-03-29 | Nissan Motor Co Ltd | Control device and control method for vehicle door |
| JP2007096799A (en) * | 2005-09-29 | 2007-04-12 | Fujitsu Ten Ltd | Monitoring apparatus of vehicle-mounted electronic control network |
| JP5625178B2 (en) * | 2010-09-22 | 2014-11-19 | トヨタ車体株式会社 | Vehicle equipped with a doorway opening / closing device |
| CN102390330B (en) * | 2011-08-31 | 2013-12-25 | 浙江吉利汽车研究院有限公司 | Auxiliary getting-off monitoring device and monitoring method thereof |
| US9475369B2 (en) * | 2013-07-17 | 2016-10-25 | Aisin Seiki Kabushiki Kaisha | Vehicle door opening and closing apparatus and method of controlling the same |
| CN105041094A (en) * | 2015-08-05 | 2015-11-11 | 苏州佳世达光电有限公司 | Car door opening control system and method |
-
2016
- 2016-04-28 CN CN201610274787.XA patent/CN105909116B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN105909116A (en) | 2016-08-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105909116B (en) | Control method, the apparatus and system of car door | |
| Carvalho et al. | Exploiting the use of recurrent neural networks for driver behavior profiling | |
| CN107368890A (en) | A kind of road condition analyzing method and system based on deep learning centered on vision | |
| EP3687863A1 (en) | Multiple exposure event determination | |
| WO2019223655A1 (en) | Detection of non-motor vehicle carrying passenger | |
| CN109562763A (en) | The control method and control device of automatic driving vehicle | |
| KR101845769B1 (en) | Car rear detection system using convolution neural network, and method thereof | |
| CN113723528B (en) | Vehicle-mounted language-vision fusion multi-mode interaction method and system, equipment and storage medium | |
| CN108647708A (en) | Driver evaluation's method, apparatus, equipment and storage medium | |
| JP2015089697A (en) | Vehicular voice recognition apparatus | |
| US20190318746A1 (en) | Speech recognition device and speech recognition method | |
| CN109987102A (en) | A kind of method and apparatus of the High Precision Automatic identification driver's unsafe behaviors based on convolutional neural networks | |
| Yan et al. | Recognizing driver inattention by convolutional neural networks | |
| CN115205729A (en) | Behavior recognition method and system based on multi-mode feature fusion | |
| WO2018233300A1 (en) | Voice recognition method and voice recognition device | |
| WO2021115232A1 (en) | Arrival reminding method and device, terminal, and storage medium | |
| CN114973209A (en) | Method, device, equipment, medium and vehicle for recognizing emotion of driver | |
| CN110555346A (en) | Driver emotion detection method and device, electronic equipment and storage medium | |
| CN110009780A (en) | A kind of car door unlocking method, server and storage medium based on car networking | |
| Shaily et al. | Smart driver monitoring system | |
| CN110263664A (en) | A kind of more occupant lanes are broken rules and regulations recognition methods and device | |
| CN114360204A (en) | Block chain-based networked automobile information safety communication system | |
| US11748974B2 (en) | Method and apparatus for assisting driving | |
| JP7277511B2 (en) | car estimator | |
| JP2020093575A (en) | Control apparatus and control system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |