CN105527710B - A kind of intelligence head-up-display system - Google Patents
A kind of intelligence head-up-display system Download PDFInfo
- Publication number
- CN105527710B CN105527710B CN201610012601.3A CN201610012601A CN105527710B CN 105527710 B CN105527710 B CN 105527710B CN 201610012601 A CN201610012601 A CN 201610012601A CN 105527710 B CN105527710 B CN 105527710B
- Authority
- CN
- China
- Prior art keywords
- module
- voice
- information
- display
- instruction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G02—OPTICS
- G02B—OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- G02B27/00—Optical systems or apparatus not provided for by any of the groups G02B1/00 - G02B26/00, G02B30/00
- G02B27/01—Head-up displays
- G02B27/0101—Head-up displays characterised by optical features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
-
- G—PHYSICS
- G02—OPTICS
- G02B—OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- G02B27/00—Optical systems or apparatus not provided for by any of the groups G02B1/00 - G02B26/00, G02B30/00
- G02B27/01—Head-up displays
- G02B27/0101—Head-up displays characterised by optical features
- G02B2027/0141—Head-up displays characterised by optical features characterised by the informative content of the display
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Optics & Photonics (AREA)
- Traffic Control Systems (AREA)
- Navigation (AREA)
Abstract
The invention discloses a kind of intelligent head-up-display systems, including, display component, image collection assembly, natural-sounding interactive component, sensor module and processor module, the display component are connect with described image acquisition component, the sensor module is connect with the processor module, and described image acquisition component is connect with the processor module.Compared to present head-up-display system, the present invention can support more interactive controllings, and interaction uses voice scheme.All kinds of third-party applications can be installed simultaneously, extend abundant function.Further, intelligent head-up-display system of the invention carries sensor abundant, can connect external equipment.In addition, the present invention has towards interior camera module, it can identify driving behavior and state, safe driving prompt facility and function of interaction control may be implemented.
Description
Technical field
The present invention relates to head-up-display system, in particular to intelligent head-up-display system.
Background technique
Head up display HUD (Head Up Display) is generally with flight supplementary instrument on aircraft at present on aircraft.Lift
Head is meant that pilot can see ... without looking down the important information of his needs.Because of the convenience and energy of HUD
Enough improve flight safety, airliner also follow-up installation one after another.HUD is the principle using optical reflection, and important flight is related
Information is incident upon above a sheet glass.This sheet glass position what cockpit front end, height is substantially with the eyes of pilot at level, projection
Text and image adjust on the distance of focal length infinity, pilot through HUD seen toward front when, will not hamper
The running of eyes maintains to clearly indicate.
The basic framework of HUD includes two parts:Data processing unit and image display.Data processing unit be by
The Hou of the data conformity processing of each system on aircraft, is converted into preset symbol, figure is either according to the selected mode
With the kenel output of text either number.Signal processing is divided into two devices with image output by some products, but substantially
On be all similar working method.Image display is just mounted in front of cockpit, between pilot and canopy
Spatially.Image display receives the information from data processing device, is incident upon above glass.Display device and have
Control panel can reconcile the image for either changing output.
Improvement of the HUD of a new generation in terms of image is shown includes (Holographic) display mode of being photographed using full figure,
Expand the range of display image, especially increase the field-of-view angle in level, reduce the thickness of bracket to the limitation in the what visual field with
It influences, the display enhanced under different luminosity and external environment adjusts, and strengthens the clarity of image, with the output of other optical images
The aircraft forward image that infrared image video camera generates, can for example be projected directly on HUD by cooperation, provide with others
Material fusion display cooperates the use of night vision goggles and uses chromatic image display data.Improvement packet on data processing unit
The rate and efficiency for improving processing are included, and HUD is on fixation device image being incident upon in front of cockpit, when pilot rotates head
When, these images will his field range away from keyboard.The HUD of a new generation is more suitable for widely being used on automobile.
In the intrinsic notion of people, what driving should most be focused on is safety naturally, but popularizing with smart phone,
It is convenient and quick that mobile phone users do not depend on mobile phone bring all the time.The real-time communication of phone, short message, wechat, multimedia
Use, digital map navigation tool etc. these, however today increasing in " race of bowing ", mobile phone bring our convenience but
The safety that strong influence drives.The traffic accident of diversified forms be all due to car owner in driving procedure due to using hand
Machine and caused by.Automobile vendors come to realise the importance of middle control screen, along with vehicle is as maximum terminal device,
This block " screen " on vehicle is more allowed to become place contested by all strategists.However the presence of vehicle-mounted middle control screen allows driving to become more really
Safety still has the every drawback and inconvenient on vehicle-mounted middle control screen but in real experiences, can still allow driving
Member diverts one's attention.
Currently, head up display HUD also exists as follows defect:
1. most of be only able to display the information such as speed, oil mass, do not have operating function completely.
2. when in use, needing to commonly use mobile phone, then the information projection on mobile phone is shown on screen to coming back.
Summary of the invention
The technical problem to be solved by the present invention is to, provide and support more interactive controllings, may be implemented interaction using voice,
The intellective scheme of gesture.Mountable all kinds of third-party application is provided, abundant function is extended, connection external equipment may be implemented.
The driving behavior that can be identified and state are provided, safe driving prompt facility and function of interaction control may be implemented.
Above-mentioned technical problem is solved, the present invention provides a kind of intelligent head-up-display systems, including, display component, image
Acquisition component, natural-sounding interactive component, sensor module and processor module, the display component include, projection module,
Imaging device and reflection unit, the projection module, to emit light;The imaging device, to receive the projective module
The transmitting light of block, and by the way that picture is imaged after two secondary reflections, and it is emitted to reflection unit;The reflection unit is used
With by the picture imaging amplification after reimaging;The characteristics of display component, amplification imaging;In front at the virtual image, the virtual image and road
It is overlapped, reduces the switching of user's focal length.It is the screen of a direct imaging the invention shows in another implementation of component
(LCD screen) and reflection unit, without projection module.
Described image acquisition component includes the first photographic device, the second photographic device, and driver status monitors system, is driven
Sail environmental monitoring system, first photographic device, to obtain driver drives vehicle status information, second photographic device,
To obtain the status information of vehicle periphery, the driver status monitors system, to what is obtained according to the first photographic device
Information carries out driver status monitoring;The driving environment monitors system, to the vehicle week obtained according to the second photographic device
It encloses state and carries out driving environment monitoring;The natural-sounding interactive component includes microphone and speech processing module, the Mike
Wind is to transmit the natural-sounding information of driver to the speech processing module, and the speech processing module is to carry out nature
Identification, synthesis and the logical sessions of voice messaging and the wake-up of natural-sounding information;The sensor module, including, light
According to sensing device, for obtaining the illumination value in driving environment;The processor module, including, processing unit is obtained for basis
Driver drives vehicle status information is taken, image data is formed, if described image data are unsatisfactory for scheduled images of gestures standard,
The image data is not stored;If satisfied, gesture instruction is exported after then storing to described image data, and
For according to the illumination value, it is determined whether to enable compensation illumination;It irradiates if so, opening compensation light and obtains driving ring again
Image data in border;The display component is connect with described image acquisition component, the sensor module and the processor
Component connection, described image acquisition component are connect with the processor module.Processor module, for interactive voice, image is known
Deng there be effect.Further, processor module, there are also networking components, can connect WIFI network, cellular mobile network.
It further include map AM access module in intelligent head-up-display system of the invention, to be given birth to according to voice messaging interaction
At driving navigation instruction, the navigation routine of initial position and destination is established according to traffic navigation instruction, by the navigation
Route is shown that the navigation routine includes running line inquiry and traffic route planning using the mode of simplifying;When from described
Initial position starts running that when destination, the distance apart from the destination is shown using auto zoom mode;Root
Navigation circuit is shown in the way of route classification according to traffic navigation instruction.Specifically, based on the intelligence of installation
Operating system, can develop and install various application software, and navigation is one of application software.
It further include intelligent gender, the Emotion identification inspection of view-based access control model and voice in intelligent head-up-display system of the invention
Examining system carries out the Emotion identification of occupant according to facial image, and is identified according to the gender that face carries out occupant;
The Emotion identification of occupant is carried out according to the voice of people, and is identified according to the gender that voice carries out occupant;To incite somebody to action
The result of the gender identification is matched and is sent to individualized intelligent voice interactive system, and to know the mood
Other result is merged and is sent to individualized intelligent voice interactive system;According to the matching result and fusion results received
Carry out interactive voice.
The sensor module further includes acquisition unit, to detect interior illumination brightness, user preference unit, to
User preference is set, and be self-regulated unit, is self-regulated to collect light intensity signal according to above-mentioned illumination brightness;
To be self-regulated according to above-mentioned user preference setting brightness preference;Display unit, for showing self-regulation brightness.
The sensor module further includes that gesture monitors identification module, to carry out gestures detection to driver, according to institute
It states gesture identification and goes out trigger action information, audio monitoring identification module, to carry out speech message monitoring to driver, according to institute
State speech message and identify wake-up voice messaging, key monitoring modular, to be monitored to associated key, if monitor by
Key triggers information, then is matched, wake-up module, to the trigger action information or wake-up voice messaging progress
Match, if any information matches success, is waken up.
The sensor module further includes speech recognition module, to receive the voice signal of user's transmission;Inquire mould
Block, to obtain the address POI of user's input according to the voice signal;Output module is shown, to according to the address POI
It is retrieved, obtains search result;Voice interaction module waits user next time to feed back the search result
Voice signal;According to the voice signal next time, selective positioning with going out mesh, completes navigation in the result of the feedback.
The processor module further includes wake up instruction processing module, navigation instruction processing module, and telephone order handles mould
Block, musical instruction processing module, wechat command process module, navigation instruction processing module, including purpose is selected with phonetic order
It specifies, judges whether to hide congestion route instructions, navigates and come sourse instruction, driving road-condition instruction, cyberdog instruction in ground;Wake up instruction
Processing module, to wake up the head up display of suspend mode;Telephone order, capable of emitting telephone order carry out voice control and answer, dial
Phone out can be with voice selecting when called party's number of depositing is more than one;Musical instruction, according to voice operating, Ke Yibo
Put the music or broadcast station content of SD card;Wechat instruction, can log in wechat by barcode scanning in advance, have when receiving wechat
Whether voice prompting is broadcasted, and is converted into asking text by voice input, identification when reply.
It further include the external equipment by wireless connection or wired connection in intelligent head-up-display system of the invention,
The external equipment includes intelligent mobile terminal, automobile data recorder, automobile OBD equipment.Intelligent mobile terminal by wireless or
The mode of bluetooth and intelligent head-up-display system keep connecting.The automobile equipment OBD can monitor the operation of engine at any time
The working condition of situation and exhaust gas aftertreatment system can issue police once discovery is possible to cause to discharge exceeded situation at once
Show.When system breaks down, emergency warning lamp is bright, while OBD system for trouble light (MIL) or inspection engine (Check Engine)
Fault message can be stored in memory, the diagnostic instrments of standard and diagnose interface can be read in the form of error code it is related
Information.According to the prompt of error code, maintenance personal can quickly and accurately determine property and the position of failure.
The sensor module further includes direction sensor, acceleration transducer, GPS, temperature sensor and earth magnetism
Sensor, to incude interior temperature and radiate, the geomagnetic sensor is configured for detecting the temperature sensor
Vehicle and vehicle cab recognition, the direction sensor to judge vehicle advance or fall back direction and test running car away from
From braking, starting detection of the acceleration transducer to vehicle, the GPS connect to position vehicle location and map
Enter.
The reflection unit includes radiation shield, and the radiation shield is the optical lens of two sides curvature having the same, and interior
The reflectivity of cambered surface plated film is higher than the reflectivity of extrados plated film;The imaging device includes:First transmitting mirror, the second reflecting mirror
And the exit of the light, second reflecting mirror and first hair is arranged in imaging film, first mirror tilt
Mirror splicing is penetrated, is equally obliquely installed, the imaging film splices along the edge of side and second reflecting mirror.
Beneficial effects of the present invention:
1) since the natural-sounding interactive component includes that microphone and speech processing module, the microphone is to pass
The natural-sounding information of driver is passed to the speech processing module, the speech processing module is to carry out natural-sounding information
Identification, synthesis and logical sessions and natural-sounding information wake-up.So that intelligent head-up-display system can be realized it is more
Voice interactive function is taken turns, to complete all inputs using voice mode completely.
2) since the display component includes, projection module, imaging device and reflection unit, the projection module, to
Emit light;The imaging device, to receive the transmitting light of the projection module, and by after two secondary reflections by picture into
Row imaging, and it is emitted to reflection unit;The reflection unit, to by reimaging after picture imaging amplification, imaging is shown
In vehicle front certain distance so that intelligent head-up-display system can be realized the display of a variety of on-vehicle informations.
3) since described image acquisition component includes, the first photographic device, the second photographic device, driver status monitoring system
System, driving environment monitor system, first photographic device, to obtain driver drives vehicle status information, second camera shooting
Device, to obtain the status information of vehicle periphery, the driver status monitors system, to be obtained according to the first photographic device
The information taken carries out driver status monitoring;The driving environment monitors system, to the vehicle obtained according to the second photographic device
Ambient state carries out driving environment monitoring.Intelligent head-up-display system is enabled to identify driving behavior and state, it can be with
Realize safe driving prompt facility and function of interaction control.Concrete function includes:Fatigue detecting, deviation prompt, front truck touch
Hit detection etc..
4) since the processor module includes processor, memory, memory, for running intelligent operating system, intelligence
Operation has types of functionality program in operating system.Such as:Processing unit, for according to acquisition driver drives vehicle status information, shape
At image data, if described image data are unsatisfactory for scheduled images of gestures standard, the image data is not carried out
Storage;If satisfied, exporting gesture instruction after then storing to described image data, and for sentencing according to the illumination value
It is disconnected whether to open compensation illumination;It irradiates if so, opening compensation light and obtains the image data in driving environment again.So that intelligence
Energy head-up-display system has automatic brightness control function, can be achieved at the same time daytime, night is freely adjusted.
5) since the display component may include, it is provided with LCD display device on the upside of the pedestal, to show vehicle
Information image, and information image is projected to the reflecting mirror, the reflecting mirror is relative to the LCD display device in water
It square is inclined to set upwards, to be reflected after receiving the information image, reflection is provided on the left of the pedestal
Screen, to amplify and show information image., can be anti-by optical path progress side by above-mentioned structure, it can effectively shorten product
Length, meanwhile, the working depth of HUD entirety can be effectively reduced, so that product can be adapted to more vehicles.
6) front camera retrieval actual scene traffic events and traffic signals based on HUD, and it is shown in navigation interface
On, realize that scene and navigation display combine in the present invention.
Detailed description of the invention
Fig. 1 is the intelligent head-up-display system structural schematic diagram in one embodiment of the invention.
Fig. 2 is the structural schematic diagram of the display component in Fig. 1.
Fig. 3 is the structural schematic diagram of image collection assembly in Fig. 1.
Fig. 4 is the structural schematic diagram of sensor module in Fig. 1.
Fig. 5 is the structural schematic diagram of processor module in Fig. 1.
Fig. 6 is the structural schematic diagram of natural-sounding interactive component in Fig. 1.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with specific embodiment, and reference
Attached drawing, the present invention is described in more detail.
Referring to FIG. 1, being the intelligent head-up-display system structural schematic diagram in one embodiment of the invention.
Intelligent head-up-display system in the present embodiment, including, display component 101, image collection assembly 102, nature
Interactive voice component 105, sensor module 103 and processor module 104, the display component 101 are acquired with described image
Component 102 connects, to show the image information in image collection assembly.The sensor module 103 and the place
It manages device assembly 104 to connect, the signal to detect sensor module is transferred into processor module 104 and handles.
Described image acquisition component 102 is connect with the processor module 104, the image information collected is converted to image
Signal is transferred into processor module 104 and is handled.Specifically, display component 101, driver need not bow, so that it may
See that running information, such as speed, navigation can be all shown in the pocket of front windshield.Avoid dispersion to road ahead
Attention.The display component 101 is able to carry out amplification imaging, forms the virtual image in front so that the virtual image on radiation shield and
Carriage way is overlapped, and reduces the focal length switching of user's vision.Specifically, described image acquisition component 102, collects driver
Face, gesture, iris image, and those image informations are compared in relevant database, and then carry out subsequent
Identification.Specifically, the natural-sounding interactive component 105 can identify the voice messaging of driver, obtained knowledge
Other result carries out more wheel natural-sounding interactions, obtains corresponding moving operation instruction.Specifically, the sensor module 103, energy
Multiple sensors are enough carried, such as:The sensors such as direction, acceleration, GPS, microphone.Specifically, processor module 104, packet
It includes, processor, memory and memory, by can be used for running intelligent operating system after matching api interface, in intelligent operation system
Types of functionality program can be run on system.As preferred in the present embodiment, the complete machine of intelligent head-up-display system has one
Cooling system, entire cooling system is by fan, cooling fin, air duct composition.
Intelligent head-up-display system in the present embodiment further includes map AM access module, to be handed over according to voice messaging
Alternate establishes the navigation routine of initial position and destination according to traffic navigation instruction at driving navigation instruction, will be described
Navigation routine is shown that the navigation routine includes running line inquiry and traffic route planning using the mode of simplifying;When from
The initial position starts running that when destination, the distance apart from the destination is shown using auto zoom mode
Show;Navigation circuit is shown in the way of route classification according to traffic navigation instruction.Specifically, the map essence
Simple mode is:By in the navigation routine initial position and destination carry out position positioning, due in initial position and purpose
Not being between ground is linear distance, needs the geographical environment around building or corresponding position, positions to position.According to institute
Rheme sets positioning and obtains GPS coordinate, and GPS coordinate information can be directly acquired on map, for example, indicating the mansion of a prince on map
Well Applied in Business Pedestrian Street, the then GPS coordinate information parsed are:North latitude 39.9, east longitude 116.4.It is obtained by above-mentioned GPS coordinate
Position coordinates point is drawn on the traffic navigation map according to the position coordinates point and generates travel, indicates driver
The navigation routine of member's traveling.Using Google Maps API, Amap API, MapBox API or use Cloudmade API.
User can selectively be shown according to the object in far and near to map.Google and most maps provide commercial city and mention automatically
This function, such as neighbouring street and highway are supplied.The drafting generates vehicle line, for default or driver
It is customized.It is preset as fixed factory-said value, the customized determination for increasing driver to position coordinate points of driver.
Specifically, the step of being shown in the present embodiment with auto zoom mode be:When from initial position to purpose
In ground driving process, according to travel speed, navigation routine scale bar in traffic navigation map described in adjust automatically.In view of working as vapour
When the speed of vehicle varies widely, user may need different map denotations to experience.Such as when speed is slower, Yong Huxu
Want the scale bar of map to amplify, with facilitate see road conditions beside oneself parking stall and point of interest (Point of Interest,
POI) information;When speed is very fast, user needs the scale compression of map, to see more information of overall importance.Meanwhile
When by complex crossing, user needs to amplify current scale bar more clearly to show current crossing situation;And it crosses
Complex crossing, user need the scale compression of map, to see more information of overall importance.Pass through row described in adjust automatically
Navigation routine scale bar in vehicle navigation map, is able to solve above-mentioned problem.The travel speed, is obtained by navigation software
Two o'clock longitude and latitude obtain the distance of point-to-point transmission, then made with the distance divided by the time spent by the two o'clock obtained result
For the vehicle present speed of acquisition.To be connected with the control system of vehicle itself and can obtain vehicle from navigation software itself
Present speed, obtains more convenient, and the change on hardware is smaller.For example, first obtain current vehicle position, then root
Judge vehicle whether close to complex crossing according to current vehicle position;If so, showing current map with the first display scale ruler;If
It is no, then it needs to obtain vehicle present speed.Further, the scale bar of corresponding present speed is searched as the second display scale
Then ruler shows current map again with the second display scale ruler.By aforesaid operations, vehicle close to complex crossing (or
Person marks close to speed limit, camera shooting labeling head, the aggregation such as traffic lights information mark ground) when, i.e., adjust automatically current map is with the
One display scale ruler shown, and when being not close to complex crossing, then adjust automatically current map is current with vehicle
The corresponding second display scale ruler of speed is shown.In varied situations, it can achieve auto zoom navigation map and show ratio
Example, facilitate user to watch, and operate repeatedly without user.And the distance according to the next navigation hint point in front, automatically
Adjust navigation routine scale bar in the traffic navigation map;It is looked by the above-mentioned speed proportional ruler table of comparisons (i.e. preset table)
The scale bar of corresponding present speed is found as the second display scale ruler, the mapping of other speed and scale bar can also be passed through
Relationship is searched.Further, the speed proportional ruler table of comparisons may be to obtain according to user setting, so as to side
Just user is arranged under different speeds according to the demand of oneself shows map with the second display scale ruler.Above-mentioned complex crossing is
It is obtained according to filling information determination;The filling information is the information of each point between starting point and destination in navigation path planning;
Or the complex crossing can for direction of advance can not by the crossing that guide of prompt of turning left to prompt or turn right, according to this into
Row judgement determines.Larger proportion ruler correspondence includes more multi-class point of interest in the scale bar point of interest POI classification table of comparisons.
For example, the smallest scale bar can show the point of interest of 30 classifications, and maximum scale bar can show the emerging of 80 classifications
Interesting point.As preferred in the present embodiment, the current map of the display includes interest point information.The point of interest category foundation
The first display scale ruler or the second display scale ruler are searched to obtain.When the current map is with the first display scale
When ruler is shown, the point of interest category is searched to obtain according to the first display scale ruler;When the current map be with
When second display scale ruler is shown, the point of interest category is searched to obtain according to the second display scale ruler.Described
Next navigation hint point is that turn marks, speed limit label, camera shooting labeling head, traffic lights information flag, nearby lodging marks, is attached
Nearly diet label, the label that nearby refuels, nearby one or more of shopping label.
Intelligent head-up-display system in the present embodiment further includes intelligent gender, the mood knowledge of view-based access control model and voice
Other detection system carries out the Emotion identification of occupant according to facial image, and the gender of occupant is carried out according to face
Identification;The Emotion identification of occupant is carried out according to the voice of people, and is identified according to the gender that voice carries out occupant;With
Matched and be sent to individualized intelligent voice interactive system with the result for identifying the gender, and to by the feelings
The result of thread identification is merged and is sent to individualized intelligent voice interactive system;According to the matching result and fusion received
As a result interactive voice is carried out.
Mood and the gender identification based on image can be according to " face action organization system " (FACS) come will be each
The expression decomposition of people is many Facial action units (Action Units), while using being automatically analyzed, identified with computer
Facial expression is an extremely complex problem, and key is to establish reasonable human emotion's model and by it and face
Facial characteristics and the variation characteristic of expression connect.Generally speaking, in order to which mood is recognized accurately, mood can be divided into 5
Class:It is bored, pleasant, surprised, baffle or indignation, sad or pain.In some embodiments, the voice-based mood and property
Other identification module 101, for example need to comprehensively consider the attention level to face, if the information for obtaining face changes in faces is endless
It is whole, then expression compensation can be carried out using compensation way.For another example, face familiarity, first is that the characteristic amplitude extracted, second is that
The human face three-dimensional model of foundation.For another example, it needs in view of influence of the extraneous factors to image such as illumination.In some embodiments
In, it, can be using the two kinds of gender identification methods provided in the contrib of OpenCV when carrying out gender identification:EigenFace
And FisherFace.In addition, voice-based mood and gender identification, to carry out the mood of occupant according to the voice of people
Identification, and identified according to the gender that voice carries out occupant;As a result Fusion Module 103 is inputted;The voice according to people
The Emotion identification of occupant is carried out, including:" key acoustical features " in voice, then by these critical sound features with set
Fixed categorizing system is compareed, to judge the mood of speaker.5 kinds can be divided into altogether by the Emotion identification that voice carries out
Basic emotion:It is happy, sad, gentle, frightened and angry.
Carrying out fusion to result includes that the result to identify the gender is matched and is sent to individualized intelligent
Voice interactive system, and to be merged the result of the Emotion identification and be sent to individualized intelligent interactive voice system
System;Individualized intelligent interactive voice is carried out after fusion;Fusion when by by pass through speech recognition mood and gender with pass through
The mood and gender result of Expression Recognition are merged, and individualized intelligent interactive voice system can be sent to after obtained fusion results
System carries out so promoting gender/Emotion identification precision to carry out next step interactive voice.For example, being based on voice
Mood and gender identification in the result that detects be gender:Male, mood:It is happy, in mood and gender knowledge based on image
The result that detection obtains in not is gender:Male, mood:It is pleasant, then it is assumed that gender is consistent with the identification of mood, and fusion results are
It is consistent, individualized intelligent interactive voice can be carried out.For example, the knot detected in voice-based mood and gender identification
Fruit is gender:Male, mood:It is gentle, and the result detected in the mood and gender identification based on image is gender:
Female, mood:Gentle, then fusion results are not consistent, without interactive voice.When carrying out individualized intelligent interactive voice, according to
The matching result and fusion results received carries out interactive voice, and carrying out fused result will be with the individualized intelligent voice
Interactive voice information in interactive result is matched.If the judgement result to current emotional states is unhealthy emotion shape
State, then start it is in individualized intelligent interactive voice for example, music unit, according to the sound preset in personalized music library
Melody mesh plays out, and the unhealthy emotion state of driver is adjusted to benign emotional state by music, promotes to drive indirectly
Member is using the driving behavior for tending to safety, to realize the function of actively assisting driving safety.As in the present embodiment preferably, than
Such as, intelligent sound interactive unit can also be used, according to the mood talk context of setting, by using personalized speech service into
Market thread is dredged, and the unhealthy emotion state of driver is adjusted to benign emotional state.
It, can be using the preposition camera in car-mounted terminal, to retrieve actual field as preferred in the present embodiment
Scape traffic events and traffic signals, and be shown on navigation interface and realize that scene and navigation display combine.Specifically, in some realities
It applies in example, the lane being presently in is identified according to acquisition, lane position is matched in navigation map, and navigation refers to
It enables, provides user and remind more accurately, for example, navigation instruction front needs to be driven out to from right-side outlet, if detected current
Vehicle lane on the right does not need prompt doubling to the right then.If detecting that current vehicle in left-hand lane, should remind doubling
Operation.If detecting vehicle in leftmost side lane, it should apart from crossing farther out when just remind doubling.Pass through preposition camera shooting
Head, can real-time detection upcoming traffic event and traffic signals, intelligent reminding driver carries out and road, turning etc..Some
In embodiment, when vehicle driving is to a traffic light intersection, the state according to traffic lights collected by camera, prompting is driven
The person of sailing waits or traveling.When the traffic light status changes, driver is reminded to execute specific operation.Pass through above-mentioned mode
It can effectively overcome in visible navigation realization at present, not account for the traffic light status, can be potentially encountered in red light
When hear the prompt of " please keep straight on ", cause navigation can not the defect that combines of actual situation.
Fig. 2 is the structural schematic diagram of the display component in Fig. 1.
In this example it is shown that component includes, and projection module 1011, imaging device 1012 and reflection unit 1013, institute
Projection module 1011 is stated, to emit light;The imaging device 1012, to receive the transmitting light of the projection module 1011
Line, and by the way that picture is imaged after two secondary reflections, and it is emitted to reflection unit 1013;The reflection unit 1013, to
By reimaging after picture imaging amplification.Due in imaging device 1012, by the way that picture is imaged after two secondary reflections,
And it is emitted to reflection unit 1013, the length of product can be effectively shortened, meanwhile, the working depth of HUD entirety can be effectively reduced,
So that product can be adapted to more vehicles.Realize the projection module i.e. micro optical-mechanical in reflection unit by secondary reflection
In back permeable membrane on be imaged.Specifically, in the present embodiment, the reflection unit 1013 may include radiation shield, wherein described
Radiation shield is the optical lens of two sides curvature having the same, and the reflectivity of intrados plated film is higher than the reflection of extrados plated film
Rate.As preferred in the present embodiment, the reflectivity of the intrados of the radiation shield is 30%, the reflectivity 1% of extrados, is protected
Card driver sees outside vehicle the normal images for having 70% light transmittance, meanwhile, there is 30% light to be reflected on the intrados and drives
The picture can be imaged and zoom into the virtual image by the person's of sailing eyes.As preferred in the present embodiment, the packet of imaging device 1012
It includes:The exit of the light source, institute is arranged in first transmitting mirror, the second reflecting mirror and imaging film, first mirror tilt
It states the second reflecting mirror and first transmitting mirror is spliced, be equally obliquely installed.Since the imaging device 1012 includes:First hair
Mirror, the second reflecting mirror and imaging film are penetrated, wherein imaging film uses special stack-design, has taken into account daytime and evening so not
It is required with brightness demand, while being avoided that user can see the background color of imaging film.The imaging film along side edge with
The second reflecting mirror splicing, wherein stating imaging film includes:Gum plate, optical reflecting lens, optical clear offset plate, diffusion barrier,
After the optical reflecting lens are bonded with optical clear offset plate, fixation, the optical reflection are pressed by gum plate and diffusion barrier
Mirror surface is the sheet glass or PET reflecting piece to adjust height, and the optical reflecting lens are in the side towards the diffusion barrier
It has set up reflection plated film or the diffusion barrier is back projection imaging film.In some embodiments, the projection module 1011
For micro projector, miniature video camera instrument.
Fig. 3 is the structural schematic diagram of image collection assembly in Fig. 1.
Described image acquisition component includes the first photographic device 1021, the second photographic device 1022, driver status monitoring
System 1023, driving environment monitor system 1024, first photographic device 1021, to obtain driver drives vehicle state letter
Breath, second photographic device 1022, to obtain the status information of vehicle periphery, the driver status monitors system
1023, the information to be obtained according to the first photographic device 1022 carries out driver status monitoring;Driving environment monitoring system
System 1023, the vehicle periphery state to be obtained according to the second photographic device 1022 carry out driving environment monitoring.
Specifically, the first photographic device 1021 in the present embodiment, to obtain driver drives vehicle status information, second is taken the photograph
As device 1022, to obtain the status information of vehicle periphery, driver status monitors system 1024:It may include gesture identification
Module, driver identity identification module, fatigue driving detection module, the information to be obtained according to the first photographic device are driven
The person's of sailing condition monitoring;The gesture recognition module identifies to the gesture to driver, and the gesture of driver includes but not
It is limited to:The five fingers palm (opening) index finger, is clenched fist, the static shape of gestures such as scissors hand, the five fingers palm (closing up), " OK " gesture
State.By the gesture, can be realized free incoming call answering and perhaps refuse incoming call and play or switching Music Radio, reply or
Person checks the chat softwares such as wechat.The driver identity identification module, to identify the identity information of driver, identity information
Include:Driver whether be car owner oneself, the gender of driver, driver driving habit (height, the distance at seat etc.).
The fatigue driving detection module can first carry out driver identity and recognize for detecting whether driver is carrying out fatigue driving
Card, according to driver present period video image, by recognition of face, to the driver identity for currently driving vehicle
It is authenticated;It is accumulative to be synchronously carried out driving time, according to the identity authentication result of driver, obtains the driving time of driver
Record;Further include that emotional state extracts, according to driver in the video image of present period, extracts driver in present period
Emotional state;Further include that limbs state is extracted, according to driver in the video image of present period, extracts driver and working as
The limbs state of preceding period;It further include that traffic information is collected, according to the video image that scene camera is shot in present period,
Obtain the environmental information that driver drives vehicle-surroundings;Finally carry out the extraction of vehicle performance state, combining road condition information and vehicle
Driving condition, extract driver in present period to the manipulation state of vehicle;To sum up, driving time is added up with present period
As driver's emotional state, the timestamp of limbs state and vehicle performance state, tracking drivers working states variation is updated
Data, analyze more new data in driver state change, judge whether current time driver is in fatigue driving.Pass through
Recognition of face tracks driver's facial expression and limb action over time, shows and becomes from normal condition to fatigue state
Change, for example closed-eye time is elongated, and the frequency of bowing increases etc.;Tracking driver vehicle manipulates whether state declines at any time, for example
Steering wheel rotation variance becomes larger, and detects whether driver is in fatigue driving state with this.
Specifically, driving environment monitors system 1023 in the present embodiment:It may include whether detection current vehicle deviates
Whether lane module, detection driving front have the running distance of pedestrian's module, front truck to whether there is collision distance internal module, to
Driving environment monitoring is carried out according to the vehicle periphery state that the second photographic device obtains;Whether the detection current vehicle deviates vehicle
Road module can monitor system according to the blind area BLIS and be examined to detect whether the vehicle in driving process deviates from lane
It surveys, and has a doubling attention gatter by being arranged on the pillar of rearview mirror and remind driver.Whether detection driving front has
Pedestrian's module 106, to carry out pedestrian's Distance Judgment according to collision distance, if more than collision distance, then without early warning, if
Less than collision distance, then need to carry out early warning.The running distance of the front truck whether there is collision distance internal module, to basis
Collision distance carries out leading vehicle distance calculating, and carries out early warning, can acquire the information of front truck by camera, and can be with
Other way is cooperated.
It further, in the present embodiment can be according to mood and sex-screening as a result, carrying out individualized content recommendation.It is described
Individualized content is recommended to be based on multi-channel feedback, is not limited to voice.
For example, recognition result " man's bicycle master, fatigue ", then can by with intelligent wearable device or setting seat in the car
On device carry out vibration adjusting, to alleviate the physiological fatigue state of driver.Or recognition result " woman's bicycle master, fatigue ",
Then the fragrance of a variety of fragrances can be provided to alleviate driver's mood by the way that flavor-generating device in the car is arranged.
Fig. 4 is the structural schematic diagram of sensor module in intelligent head-up-display system in Fig. 1.
Sensor module 103 in the present embodiment includes:Illumination sensing device 1031, for obtaining in driving environment
Illumination value;It wherein further include acquisition unit 1032, to detect interior illumination brightness, user preference unit 1033, to be arranged
User preference, be self-regulated unit 1034, is self-regulated to collect light intensity signal according to above-mentioned illumination brightness
And to be self-regulated according to above-mentioned user preference setting brightness preference;Display unit 1035, for showing self-regulation
Brightness.
Those skilled in the art can be illustrated, the illumination sensing device 1031, for obtaining the illumination in driving environment
Value;Those skilled in the art can be illustrated, and illumination sensing device 1031 can use illumination inductor or light-sensitive element.
The sensor module 103 further includes that gesture monitors identification module 1036, to carry out gesture inspection to driver
It surveys, trigger action information is gone out according to the gesture identification, audio monitoring identification module 1037 disappears to carry out voice to driver
Breath is monitored, and identifies wake-up voice messaging according to the speech message, key monitoring modular 1038, to associated key into
Row monitoring is matched, wake-up module 1039 if monitoring key triggering information, to the trigger action information or
Person wakes up voice messaging and matches, if any information matches success, is waken up.
The sensor module 103 further includes speech recognition module 10311, to receive the voice signal of user's transmission;
Enquiry module 10312, to obtain the address POI of user's input according to the voice signal;It shows output module 10313, uses
To be retrieved according to the address POI, search result is obtained;Voice interaction module 10314, to by the search result into
Row feedback waits user's voice signal next time;According to the voice signal next time, it is fixed to select in the result of the feedback
With going out mesh, complete navigation in position.The sensor module 103 further includes, direction sensor 10315, acceleration transducer 10316,
GPS10319, temperature sensor 10317 and geomagnetic sensor 10318, the temperature sensor 10317 is to incude car
Temperature simultaneously radiates, and the geomagnetic sensor 10318 is to detection direction, and the direction sensor 10315 is to judge vehicle
Advance or fall back direction and test running car distance, the acceleration transducer 10316 to vehicle braking, open
Dynamic detection, the GPS10319 is to position vehicle location and map access.
Fig. 5 is the structural schematic diagram of processor module in Fig. 1.
The processor module in intelligent head-up-display system in the present embodiment includes processing unit 1041, is used for root
According to driver drives vehicle status information is obtained, image data is formed, if described image data are unsatisfactory for scheduled images of gestures mark
Standard does not store the image data then;Refer to if satisfied, exporting gesture after then storing to described image data
It enables, and for according to the illumination value, it is determined whether to enable compensation illumination;It irradiates and obtains again if so, opening compensation light
Take the image data in driving environment.The processing unit 1041 can provide the processing capacity of high speed, and the processing of 4 core of ARM can be used
Device unit, while micro SD memory card maximum being supported to support 32GB.HUD 805, to provide the carrier of above-mentioned apparatus.
In the present embodiment, specifically, the stationary state of gesture is identified based on two-dimentional hand-type;Two-dimentional hand-type identifies
Based on two-dimentional level, need to regard the two-dimensional signal without depth information as input during processing.Just as usually
It is the same that resulting photograph of taking pictures just contains two-dimensional signal, it is only necessary to which the two dimensional image for using single camera to capture is as defeated
Enter, then analyzed by two dimensional image of the computer vision technique to input, information is obtained, to realize gesture identification.
Those skilled in the art can be illustrated, in computer vision (Computer Vision, CV), the processing technique master of visual information
Image processing method is depended on, it includes image enhancement, data encoding and transmission, smooth, edge sharpening, segmentation, feature pumping
It takes, the contents such as image recognition and understanding.The quality that image is exported after these processing obtains considerable degree of improvement, both improves
The visual effect of image, and image is analyzed, handled and identified convenient for computer.For example, being obtained by Image Acquisition
Two-dimentional hand-type image can carry out image enhancement to two-dimentional hand-type image, such as can be converted by histogram and enhance image pair
Than degree, realizes single channel image enhancing, image grayscale threshold value is stretched to 0-255.Then data encoding and transmission are carried out again, this
Step is to compress to image, and image smoothing main purpose is to denoise, and is removed probably due to environmental factor (vehicle
Jolt, turn, the factors such as dark) caused by image fault.Completing edge sharpening can use《Figure based on edge detection
As sharpening method》The method of bright was once praised.After completing above-mentioned operation, feature extraction can be carried out again, can use karhunen-Le
The linear transformation carried out based on dimension expansion.Or nonlinear mapping method is used, such as multidimensional scaling method and parameter mapping
Method.Eventually complete the identification of image.Further, input obtains the first figure after obtaining the two-dimensional signal on the two-dimentional hand-type
Picture;Available two-dimensional signal after above-mentioned two-dimentional hand-type is obtained, the first obtained image is the image after image procossing,
Match cognization is carried out with preset gesture again;Preset gesture includes the images of gestures of all single, double hands, i.e., right-hand man or
Person's list branch hand.Trigger action instructs if finding with the second image of first images match;Second image is
The images of gestures prestored can trigger corresponding instruction, such as static gesture " 1 " if match cognization success, can corresponding instruction
Music is played, then head up display is controlled according to matched result, plays out music.Such as static gesture " fist
Head ", can correspond to unlatching navigation feature, then be controlled according to matched result head up display, after completing to wake up, open
Beginning navigates.Specifically, when interior illumination deficiency, head up display can automatically turn on compensation illumination, and prompt driver
Hand-type operation is carried out again, or when driver does not make instruction hand-type operation also, is opened compensation illumination in advance, avoided secondary
Operation.The optical path mode of above-mentioned adjusting can be used《Based on physical light according to the intelligent dimming algorithm research of reacting condition》Old middle silver
Light modulation algorithm.
The processor module 104 further includes wake up instruction processing module 1042, navigation instruction processing module 1043, electricity
Words command process module 1044, musical instruction processing module 1045, wechat command process module 1046, processor module 104
Function is as follows:With phonetic order selection destination instruction, judge whether to hide congestion route instructions, navigation come sourse instruction, driving
Road conditions instruction, cyberdog instruction;Wake up instruction processing module 1042, to wake up the head up display of suspend mode;Telephone order, can
It issues telephone order progress voice control to answer, dial number, when called party's number of depositing is more than one, can be selected with voice
It selects;Musical instruction can play the music or broadcast station content of SD card according to voice operating;Wechat instruction, can shift to an earlier date
Wechat is logged in by barcode scanning, has whether voice prompting is broadcasted when receiving wechat, is converted by voice input, identification when reply
Text.Above-mentioned instruction belongs to the operational order based on head up display:Those skilled in the art can be illustrated, and be referred to voice
Enable selection destination specified including but not limited to, the direct navigation of destination, or the address inquiring method based on POI.It is described
Navigation carrys out sourse instruction and includes but is not limited to the map supply quotient for the access for selecting map, for example can choose Gao De or Baidu
Map is accessed.Navigation instruction processing module 1043 includes but is not limited to handle driving road-condition instruction, if stifled
The road conditions of vehicle, if the traffic signals for having red light, taking pictures, if whether can have pedestrian etc. with curb parking, front.The electronics
Dog instruction, the including but not limited to anti-velocity radar of full range, GPS cyberdog, GPS radar electric dog.Effect is to remind car owner in advance
The presence of electronic eyes or velocity radar can prevent from being imposed a fine and being deducted points because of hypervelocity or violation, driver is allowed to have using up for defence
Enjoy driving pleasure.Wake up instruction, to wake up the head up display of suspend mode;Those skilled in the art can be illustrated, can be by hand
Gesture is associated in advance with the wake up instruction, in this way after making gesture, so that it may realize the wake-up to head up display.Electricity
Words command process module 1044 carries out voice control and answers, dials number to execute telephone order, capable of emitting telephone order, when
It, can be with voice selecting when called party's number of depositing is more than one;It is external such as after mobile phone and head up display bluetooth connection
, can be directly by the stationary state of gesture when incoming call, such as " palm ", the also motion state of gestures available, such as " clench fist to
Right sliding ", to refuse or receive the logical incoming call.Musical instruction processing module 1045 is to execute musical instruction, according to voice
Operation, can play the music or broadcast station content of SD card;For example when using broadcast station content, can directly it pass through
The stationary state of gesture, such as " scissors hand ", the also motion state of gestures available, such as " clench fist and slide to the left ", to switch sound
Happy, increase sound etc..Wechat command process module 1046 can log in wechat by barcode scanning in advance, receive to handle wechat instruction
Have whether voice prompting is broadcasted when to wechat, when reply is converted into asking text by voice input, identification.Can directly it pass through
The motion state of gesture, such as " sliding index finger to the right " send wechat information.
Fig. 6 is the structural schematic diagram of natural-sounding interactive component in Fig. 1.
The natural-sounding interactive component 105 in intelligent head-up-display system in the present embodiment includes 1051 He of microphone
Speech processing module 1052, the microphone 1051 is to transmit the natural-sounding information of driver to the speech processing module
1052, identification, synthesis and logical sessions of the speech processing module 1052 to carry out natural-sounding information, and it is natural
The wake-up of voice messaging.
Specifically, the identification of natural-sounding information is carried out, synthesis includes:Voice interaction module, to tie the retrieval
Fruit is fed back, and user's voice signal next time is waited;According to the voice signal next time, selected in the result of the feedback
It selects with orienting mesh, completes navigation.Voice signal next time, or voice signal for the first time, can be according to customized personalization
Answer method is preset.Before the use, the rules of competence and content of automatic-answering back device are set, and possible rule includes:It provides
The contacts list of automatic-answering back device service provides the period of automatic-answering back device service, each contact person institute energy for each contact person
Received automatic-answering back device service range.Then authenticating caller identity, if it is determined that it has permission is obtained by automatic answering system
It wins the confidence breath, then carries out subsequent step;Caller identities include:Personal information, pre-set data etc..Data store specific
Realization, which can be divided into, to be stored in local data base or server-side database.The voice number that further receiving caller's issue
According to, use automatic speech recognition module carry out speech recognition;The conversation content and dialog process.It of management and caller, according to exhaling
The data content of the problem of person of crying inquires and owner's setting, automatically analyzes out response content.The module can realize beyond the clouds,
Mobile terminal is interacted with cloud;It can also independently realize on mobile terminals.Further according to speech recognition result, semanteme point is used
Analysis method is analyzed caller and is intended to;Further it is intended to according to the caller that analysis obtains, uses pre-set automatic-answering back device
Rules and contents, or access third party's data and program determine the content of text of response or right using semantic analysis
Mobile terminal data executes corresponding operation;Finally, response content of text is converted into voice data using phoneme synthesizing method
It is sent to caller.
Specifically, the logical sessions of the natural-sounding information in the present embodiment, can be grasped in accordance with the following steps
Make:
1) voice signal that user sends is received to need to pre-process device when receiving the voice signal of user;
Pretreated step mainly includes:HUD under in a dormant state is waken up, the mode of wake-up includes but not
It is limited to, wakes up manually, voice control wakes up and is waken up using remote controler.The principle of wake-up includes but is not limited to broadcast
The wake-up of signal, the wake-up of speech chip.HUD can be used to receive the voice signal of user upon awakening, wherein this field skill
Art personnel can be illustrated, and voice signal can include but is not limited to, and disyllabic word converges, such as " starting, start " or with useful
The customized multisyllable vocabulary in family, such as " radish, starting ".But according to monosyllabic vocabulary, such as " ", " ", " beauty "
Deng, it is be easy to cause the inaccuracy of speech recognition, or cause operand excessive processing unit, it is slower so as to cause HUD reaction.
It is specific to can be used《The design and implementation of instruction interactive system based on speech recognition and text segmentation methods》Zhang Wenjie floods
Just, it is realized.
2) address POI of user's input is obtained according to the voice signal;Voice signal is parsed, to be needed
The address POI wanted;
POI is the abbreviation of " Point Of Interest ", and each POI includes four aspect information, title, classification, longitude latitude
Degree, neighbouring business information, may be collectively referred to as " navigation map information ".Business information includes near described:Food and drink, hotel, amusement,
Bus station, subway station, gas station, parking lot, sight spot, bank, pharmacy's information.According to voice signal mesh can be obtained with intelligent extraction
Keyword is marked, the target keyword includes but is not limited to place word, modal particle, connection relationship word etc..Carrying out target critical
Word also needs that " time parameter ", " person (name) parameter " is arranged when extracting." time parameter " etc.." time parameter ", " person
(name) parameter ", " weather parameters ", " time parameter " can be, " morning, noon, afternoon ", and " person (name) parameter " can be with
Mr. Wang, Miss Wang, king two, Wang Yi, or in driver's mobile phone contact person and contact method be associated, including
But be not limited to phoneme, syllable, word or sentence etc..
3) it is retrieved according to the address POI, obtains search result;Selectively the address POI is called,
For example, voice is " Wangfujing ", then the address POI is then title;For another example voice is " market shopping mall ", then POI
Address is then classification.Voice is that " north latitude 39.9, east longitude 116.4 ", then the address POI is then latitude, longitude, for another example language for another example
Sound is " going neighbouring KFC ", then the address POI is then neighbouring business information.
4) search result is fed back, waits user's voice signal next time;The search result of the feedback can
It can include multiple search results, need to wait the selection of user's voice signal progress next time again;
For example, the voice signal of the first round is " the KFC dining room that meet in the morning with Miss Wang ", obtained result is anti-
The search result of feedback, may include:
" Zhong Guan-cun KFC dining room "
" village Hai Dianhuang KFC dining room "
" People's University KFC dining room "
User's voice signal next time is waited, user, which can choose, such as " checks schedule table " to query result and day
Information in journey calendar carries out after cross-searching feedback result again, for example records and have with Miss Wang in schedule table
Guan Cun meeting, then can feed back to user for query result.
5) according to the voice signal next time, selective positioning goes out destination in the result of the feedback, completes navigation.
The voice signal destination last to determination next time includes but is not limited in voice signal next time:Instruction is directly tied
The END instruction of beam dialogue, carries out the selection instruction of selection again.
Specifically, the wake-up of the natural-sounding information includes the following steps:
Speech message monitoring is carried out to driver, wake-up voice messaging is identified according to the speech message, it can be according to
Following mode is operated:Establish voice activation library by self-defined message, the self-defined message includes, it is monosyllabic or
Polysyllabic word if listening to matched self-defined message, and meets the wake-up voice messaging condition of setting, is then directly waken up
After wait.Further, as preferred in the present embodiment, voice is inputted in the case where not proposing to inquire to user and is transmitted
To the voice activation library in automatic speech recognition system, to generate language text (i.e. the correspondence character translation of voice).It obtains
Take voice input can be according to the detection device of vehicle interior, such as the radio reception wheat with the signal processing apparatus for being connected in downstream
Gram wind receives the voice input of user.After being converted to the first digital information by the voice for issuing driver, by the first number
Information is sent in the storage element for being previously stored with voice document data base, passes through the voice data being arranged in server
Library identifies obtained voice, by voice data lab setting in special, so voice document data base is deposited
Storage capacity is no longer limited by vehicle-mounted memory, and the memory capacity of storage element can extend, and avoid vehicle-mounted storage
The occupancy of memory storage space is caused due to storing the navigation map of multi-medium data and onboard navigation system in device
The further insufficient defect of the memory space of storaged voice document data base, so that can be as more as possible in voice document data base
The different accents of storage driver voice data, so increasing the identification for issuing voice to different accent drivers may
Property, improve the practicability of vehicle-mounted voice identification interactive system.ARM4 core CPU, memory 1G RAM, Neng Goubao are configured in HUD
Demonstrate,prove the processing speed identified to above-mentioned voice data.In addition, the 8G ROM of HUD configuration, and can support Micro SD (TF)
Memory card, maximum support 32,64,128G, provide guarantee to the storage of voice document data base.As excellent in the present embodiment
Choosing, natural-sounding interactive component 105 further includes noise reduction module 1053.Specifically, the noise reduction module 1053 includes dual microphone
Noise reduction, Lou Shi high s/n ratio silicon wheat enable microphone itself to mention by the way that ADC (analog-digital converter) to be integrated into microphone
For numeral output, to reduce noise jamming.
Those of ordinary skills in the art should understand that:More than, described is only specific embodiments of the present invention, and
It is not used in the limitation present invention, all within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done,
It should be included within protection scope of the present invention.
Claims (8)
1. a kind of intelligence head-up-display system, which is characterized in that including, display component, image collection assembly, natural-sounding interaction
Component, sensor module and processor module,
The display component includes projection module, imaging device and reflection unit, the projection module, to emit light;Institute
Imaging device is stated, to receive the transmitting light of the projection module, and by the way that picture is imaged after two secondary reflections, concurrently
It is mapped to reflection unit;The reflection unit, to reimaging after amplifying picture imaging;
Described image acquisition component includes the first photographic device, the second photographic device, and driver status monitors system, drives ring
Border monitors system, first photographic device, to obtain driver drives vehicle status information, second photographic device, to
The status information of vehicle periphery is obtained, the driver status monitors system, to the information obtained according to the first photographic device
Carry out driver status monitoring;The driving environment monitors system, to the vehicle periphery shape obtained according to the second photographic device
State carries out driving environment monitoring;
The natural-sounding interactive component includes that microphone and speech processing module, the microphone is to transmit driver's
Natural-sounding information is to the speech processing module, and the speech processing module is to carry out the identification of natural-sounding information, close
At and logical sessions and natural-sounding information wake-up;
The sensor module, including, illumination sensing device, for obtaining the illumination value in driving environment;
The sensor module further includes that gesture monitors identification module, to carry out gestures detection to driver, according to the hand
Gesture identifies trigger action information, audio monitoring identification module, to carry out speech message monitoring to driver, according to institute's predicate
Sound message identifies wake-up voice messaging, key monitoring modular, to be monitored to associated key, if monitoring key touching
Photos and sending messages are then matched, wake-up module, to be matched to the trigger action information or wake-up voice messaging, if
Any information matches success, then waken up;
The processor module, including, processing unit, for forming image data according to driver drives vehicle status information is obtained,
If described image data are unsatisfactory for scheduled images of gestures standard, the image data is not stored;If satisfied,
Gesture instruction is exported after then storing to described image data, and for according to the illumination value, it is determined whether to enable benefits
Repay illumination;It irradiates if so, opening compensation light and obtains the image data in driving environment again;
The display component is connect with described image acquisition component, and the sensor module is connect with the processor module, institute
Image collection assembly is stated to connect with the processor module;
It further include map AM access module, to generate traffic navigation instruction according to voice messaging interaction, according to the traffic navigation
The navigation routine of initial position and destination is established in instruction, and the navigation routine is shown using the mode of simplifying, described to lead
Air route line includes running line inquiry and traffic route planning;It starts running when destination, adopts when from the initial position
It is shown with auto zoom mode;Navigation circuit is shown in the way of route classification according to traffic navigation instruction
Show.
2. intelligence head-up-display system according to claim 1, which is characterized in that further include the intelligence of view-based access control model and voice
Energy gender, Emotion identification detection system, individualized intelligent voice interactive system carry out the mood of occupant according to facial image
Identification, and identified according to the gender that face carries out occupant;The Emotion identification of occupant is carried out according to the voice of people, with
And it is identified according to the gender that voice carries out occupant;Result to identify the gender is matched and is sent to individual character
Change intelligent speech interactive system, and to be merged the result of the Emotion identification and be sent to individualized intelligent voice
Interactive system;Interactive voice is carried out according to the matching result and fusion results received.
3. intelligence head-up-display system according to claim 1, which is characterized in that the sensor module further includes adopting
Collect unit, to detect interior illumination brightness, user preference unit, user preference is arranged, be self-regulated unit, to basis
Above-mentioned illumination brightness collects light intensity signal and carries out self-regulation and to bright according to above-mentioned user preference setting
Degree preference is self-regulated;Display unit, for showing self-regulation brightness.
4. intelligence head-up-display system according to claim 1, which is characterized in that the sensor module further includes language
Sound identification module, to receive the voice signal of user's transmission;Enquiry module, it is defeated to obtain user according to the voice signal
The address POI entered;Show that output module obtains search result to be retrieved according to the address POI;Interactive voice mould
Block waits user's voice signal next time to feed back the search result;According to the voice signal next time,
Selective positioning with going out mesh, completes navigation in the result of the feedback.
5. intelligence head-up-display system according to claim 1, which is characterized in that the processor module further includes calling out
It wakes up command process module, navigation instruction processing module, telephone order processing module, musical instruction processing module, at wechat instruction
Module is managed, including instructed with phonetic order selection destination, judge whether to hide congestion route instructions, navigation come sourse instruction, row
The instruction of bus or train route condition, cyberdog instruction;Wake up instruction processing module, to wake up the head up display of suspend mode;Telephone order can be sent out
Telephone order progress voice control is answered, is dialed number out, when called party's number of depositing is more than one, can be selected with voice
It selects;Musical instruction can play the music or broadcast station content of SD card according to voice operating;Wechat instruction, can shift to an earlier date
Wechat is logged in by barcode scanning, has whether voice prompting is broadcasted when receiving wechat, is converted by voice input, identification when reply
Text.
6. intelligence head-up-display system system according to claim 1, which is characterized in that further include by being wirelessly connected or
The external equipment of person's wired connection, the external equipment include intelligent mobile terminal, automobile data recorder, automobile OBD equipment.
7. intelligence head-up-display system according to claim 1, which is characterized in that the sensor module further includes side
To sensor, acceleration transducer, GPS, temperature sensor and geomagnetic sensor, the temperature sensor is to incude car
Temperature and radiate, the geomagnetic sensor to detection direction, the direction sensor advance judging vehicle or
The direction of retroversion and test running car distance, braking, starting detection of the acceleration transducer to vehicle are described
GPS is to position vehicle location and map access.
8. intelligence head-up-display system according to claim 1, which is characterized in that the display component includes pedestal, instead
Screen, LCD display device and reflecting mirror are penetrated, is provided with LCD display device on the upside of the pedestal, to show the information of vehicle
Image, and information image is projected to the reflecting mirror, the reflecting mirror relative to the LCD display device in the horizontal direction
It is inclined to set, to be reflected after receiving the information image, radiation shield is provided on the left of the pedestal, to put
Greatly and show information image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610012601.3A CN105527710B (en) | 2016-01-08 | 2016-01-08 | A kind of intelligence head-up-display system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610012601.3A CN105527710B (en) | 2016-01-08 | 2016-01-08 | A kind of intelligence head-up-display system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105527710A CN105527710A (en) | 2016-04-27 |
CN105527710B true CN105527710B (en) | 2018-11-20 |
Family
ID=55770035
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610012601.3A Active CN105527710B (en) | 2016-01-08 | 2016-01-08 | A kind of intelligence head-up-display system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105527710B (en) |
Families Citing this family (36)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106226905B (en) | 2016-08-23 | 2019-08-23 | 北京乐驾科技有限公司 | A kind of head-up display device |
CN106335454A (en) * | 2016-09-29 | 2017-01-18 | 北京汽车股份有限公司 | Vehicle and setting method of vehicle driving habit of driver |
CN106347221B (en) * | 2016-09-30 | 2019-04-16 | 广东威创视讯科技股份有限公司 | Vehicle-mounted head-up display device |
CN108116309A (en) * | 2016-11-07 | 2018-06-05 | 法乐第(北京)网络科技有限公司 | Interior reading lamp method of adjustment, device, system and electronic equipment |
CN106740473A (en) * | 2016-12-13 | 2017-05-31 | 中国航空工业集团公司洛阳电光设备研究所 | A kind of vehicle-mounted small-sized HUD head-up-display systems |
CN106707512B (en) * | 2016-12-26 | 2023-10-27 | 中科海微(北京)科技有限公司 | Low-power consumption intelligent AR system and intelligent AR glasses |
CN107885810A (en) * | 2017-01-24 | 2018-04-06 | 问众智能信息科技(北京)有限公司 | The method and apparatus that result for vehicle intelligent equipment interactive voice is shown |
CN106767887A (en) * | 2017-02-13 | 2017-05-31 | 上海荧瑞光电科技有限公司 | A kind of HUD onboard navigation systems |
CN106950696A (en) * | 2017-04-21 | 2017-07-14 | 苏州车萝卜汽车电子科技有限公司 | The head-up display device and its implementation of a kind of split type installation |
CN107719306A (en) * | 2017-09-30 | 2018-02-23 | 深圳市创康安科技有限公司 | A kind of intelligent vehicle-mounted system |
WO2019114426A1 (en) * | 2017-12-15 | 2019-06-20 | 蔚来汽车有限公司 | Vehicle-mounted music matching method and apparatus, and vehicle-mounted intelligent controller |
CN108229345A (en) * | 2017-12-15 | 2018-06-29 | 吉利汽车研究院(宁波)有限公司 | A kind of driver's detecting system |
CN108171673B (en) * | 2018-01-12 | 2024-01-23 | 京东方科技集团股份有限公司 | Image processing method and device, vehicle-mounted head-up display system and vehicle |
CN108181992A (en) * | 2018-01-22 | 2018-06-19 | 北京百度网讯科技有限公司 | Voice awakening method, device, equipment and computer-readable medium based on gesture |
CN108279500A (en) * | 2018-02-02 | 2018-07-13 | 深圳市恒晨电器有限公司 | Embedded head up display based on laser light source |
CN108459520B (en) * | 2018-02-02 | 2022-02-15 | 斑马网络技术有限公司 | Automatic display method for vehicle and system thereof |
CN108594698B (en) * | 2018-03-14 | 2021-08-31 | 深圳市火乐科技发展有限公司 | Projection control method and device adaptive to projectors of different platforms |
CN108334871A (en) * | 2018-03-26 | 2018-07-27 | 深圳市布谷鸟科技有限公司 | The exchange method and system of head-up display device based on intelligent cockpit platform |
CN108759854A (en) * | 2018-04-28 | 2018-11-06 | 苏州车萝卜汽车电子科技有限公司 | Method for processing navigation information and device, virtual reality head-up display device |
CN110620840A (en) * | 2018-06-20 | 2019-12-27 | 阿里巴巴集团控股有限公司 | Call processing method, device, terminal equipment and storage medium |
CN109050396A (en) * | 2018-07-16 | 2018-12-21 | 浙江合众新能源汽车有限公司 | A kind of vehicle intelligent robot |
CN112513708B (en) * | 2018-07-26 | 2023-02-21 | 宝马股份公司 | Apparatus and method for use with a vehicle |
CN111124198A (en) * | 2018-11-01 | 2020-05-08 | 广州汽车集团股份有限公司 | Animation playing and interaction method, device, system and computer equipment |
CN109598948A (en) * | 2019-01-16 | 2019-04-09 | 谢宝建 | A kind of new vehicle automatic segmentation speed limit solution |
CN109633911B (en) * | 2019-01-18 | 2020-10-30 | 黄山徽岭电子科技有限公司 | Teaching experience device based on VR technique and experience system thereof |
CN110213730B (en) * | 2019-05-22 | 2022-07-15 | 未来(北京)黑科技有限公司 | Method and device for establishing call connection, storage medium and electronic device |
CN110194108A (en) * | 2019-05-29 | 2019-09-03 | 中国第一汽车股份有限公司 | Display color regulation method, head-up-display system and the vehicle of head-up-display system |
CN111591223B (en) * | 2020-04-26 | 2021-12-07 | 中国第一汽车股份有限公司 | Height adjusting method and system for head-up display image and vehicle |
CN111696548A (en) * | 2020-05-13 | 2020-09-22 | 深圳追一科技有限公司 | Method and device for displaying driving prompt information, electronic equipment and storage medium |
CN111696561A (en) * | 2020-05-27 | 2020-09-22 | 一汽奔腾轿车有限公司 | Voice interaction system and method based on auditory, visual and olfactory feedback |
CN114365214A (en) | 2020-08-14 | 2022-04-15 | 海思智财控股有限公司 | System and method for superimposing virtual image on real-time image |
EP4073572A1 (en) | 2020-09-03 | 2022-10-19 | HES IP Holdings, LLC | Systems and methods for improving binocular vision |
CN116420104A (en) | 2020-09-30 | 2023-07-11 | 海思智财控股有限公司 | Virtual image display system for a virtual reality and augmented reality device |
CN112861677A (en) * | 2021-01-28 | 2021-05-28 | 上海商汤临港智能科技有限公司 | Method and device for detecting actions of rail transit driver, equipment, medium and tool |
CN114454814B (en) * | 2022-01-26 | 2023-08-11 | 深圳时空数字科技有限公司 | Human-computer interaction method and device for augmented reality |
CN116923425B (en) * | 2023-08-01 | 2024-06-04 | 深圳市哲思特科技有限公司 | New energy automobile intelligent cabin with intelligent sensing system and control method thereof |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8514101B2 (en) * | 2011-12-02 | 2013-08-20 | GM Global Technology Operations LLC | Driving maneuver assist on full windshield head-up display |
CN102707801B (en) * | 2012-05-07 | 2015-08-19 | 广东好帮手电子科技股份有限公司 | Vehicle-mounted control system for identifying and control method thereof |
CN102910130B (en) * | 2012-10-24 | 2015-08-05 | 浙江工业大学 | Forewarn system is assisted in a kind of driving of real enhancement mode |
CN203544376U (en) * | 2013-06-24 | 2014-04-16 | 惠州市华阳多媒体电子有限公司 | Split head-up display |
CN104348851A (en) * | 2013-07-25 | 2015-02-11 | 惠州市华阳多媒体电子有限公司 | Interconnection system of head up display and mobile terminal |
CN104567897A (en) * | 2013-10-16 | 2015-04-29 | 大陆汽车投资(上海)有限公司 | Road condition forecast combined path planning method and navigation device |
KR20150100452A (en) * | 2014-02-25 | 2015-09-02 | 최해용 | High brightness head-up display device |
CN205720871U (en) * | 2016-01-08 | 2016-11-23 | 北京乐驾科技有限公司 | A kind of intelligence head-up-display system |
-
2016
- 2016-01-08 CN CN201610012601.3A patent/CN105527710B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN105527710A (en) | 2016-04-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105527710B (en) | A kind of intelligence head-up-display system | |
CN205720871U (en) | A kind of intelligence head-up-display system | |
US10875525B2 (en) | Ability enhancement | |
US11335210B2 (en) | Apparatus and method for analyzing images | |
US20230396704A1 (en) | Systems, devices, and methods for generating messages | |
US11366513B2 (en) | Systems and methods for user indication recognition | |
US10462568B2 (en) | Terminal and vehicle control method of mobile terminal using machine learning | |
CN109416733B (en) | Portable personalization | |
WO2020134858A1 (en) | Facial attribute recognition method and apparatus, electronic device, and storage medium | |
US7792328B2 (en) | Warning a vehicle operator of unsafe operation behavior based on a 3D captured image stream | |
KR20190030731A (en) | Command processing using multimode signal analysis | |
US9255813B2 (en) | User controlled real object disappearance in a mixed reality display | |
CN105509761B (en) | A kind of more wheel interactive voice navigation methods and systems | |
KR20190084789A (en) | Electric terminal and method for controlling the same | |
US20200286450A1 (en) | Agent device, method of controlling agent device, and storage medium | |
US8422693B1 (en) | Geo-coded spatialized audio in vehicles | |
CN111750885B (en) | Control device, control method, and storage medium storing program | |
US20230314156A1 (en) | Information presentation method, information presentation system, and computer-readable medium | |
CN111746435B (en) | Information providing apparatus, information providing method, and storage medium | |
CN112193255A (en) | Human-computer interaction method, device, equipment and storage medium of vehicle-machine system | |
JP2022103675A (en) | Information processing device, information processing method, and program | |
WO2023236691A1 (en) | Control method based on vehicle external audio system, vehicle intelligent marketing method, electronic apparatus, and storage medium | |
KR20160025840A (en) | System and method for reporting the violation of traffic regulations by wearable glass device | |
JP2023152707A (en) | Information presentation method, information presentation system, and program | |
KR20160014822A (en) | System and method for checking information about taxi boarding by wearable glass device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 102208 Beijing city Changping District Huilongguan Longyu street 1 hospital floor A loe Center No. 1 floor 5 Room 518 Applicant after: BEIJING LEJIA TECHNOLOGY CO., LTD. Address before: 100193 Beijing City, northeast of Haidian District, South Road, No. 29, building 3, room 3, room 3558 Applicant before: BEIJING LEJIA TECHNOLOGY CO., LTD. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |