Embodiment
An embodiment of the present invention provides a kind of automobile data recorder, solves current automobile data recorder in vehicle travel process
The burst accident run into is difficult to the technical problem of complementary processing.
Goal of the invention, feature, advantage to enable the present invention is more obvious and understandable, below in conjunction with the present invention
Attached drawing in embodiment, is clearly and completely described the technical solution in the embodiment of the present invention, it is clear that disclosed below
Embodiment be only part of the embodiment of the present invention, and not all embodiment.Based on the embodiments of the present invention, this area
All other embodiment that those of ordinary skill is obtained without making creative work, belongs to protection of the present invention
Scope.
Referring to Fig. 1, a kind of one embodiment of automobile data recorder provided in an embodiment of the present invention includes:
Camera 11 and control mechanism 12, camera 11 and control mechanism 12 are electrically connected, and control mechanism 12 includes:
Main control module 121, mobile detection module 122 and warning module 123, mobile detection module 122 and warning module 123
It is connected with main control module 121;
Wherein, mobile detection module 122, catches for carrying out image when target object occurs according to the first prepattern
Catch, if no target object occurs, do not trigger automobile data recorder work;
Warning module 123, for the triggering by main control module 121, the vehicle aligned under steam carries out deviation
Early warning, fatigue driving early warning and overspeed warning.
In the present embodiment, by adding mobile detection module 122 and warning module 123 to control mechanism 12, moved
The picture catching of animal body, intelligent realizes trigger camera and carry out picture catching when there are objects moving, do not have that there are objects moving
When, automobile data recorder is in holding state, and warning module 123, for the triggering by main control module 121, aligns and is expert at
Vehicle in sailing carries out lane departure warning, fatigue driving early warning and the multi-functional realization of overspeed warning, solves at present
The burst accident that automobile data recorder is run into vehicle travel process is difficult to the technical problem of complementary processing.
The above is that the composition of automobile data recorder is described in detail, and will carry out detailed retouch to specific configuration below
State, referring to Fig. 2, a kind of one embodiment of automobile data recorder provided in an embodiment of the present invention includes:
Camera 21 and control mechanism 22, camera 21 and control mechanism 22 are electrically connected, and camera is dual camera mould
Formula, it can be sensed using ccd image sensor or cmos image that two cameras set camera 21 for activity adjustment angle
Device combines collection image, foregoing dual camera pattern, and a camera shoots front side scene against headstock;One shooting
Head uses common CMOS camera against in-car, the camera, and the camera against headstock uses the AR0330 of Aptina companies
Camera module, possesses high definition 1080P, wide dynamic technique, 110 ° to 170 ° wide-angles, can be the collocation resistance to height of 4G, 5G, 6G all-wave
Warm camera lens.AR0330 uses A-Pix technologies, improves quantum efficiency for feux rouges and green light, it is obtained for dim light susceptibility
Very big lifting is arrived.Present automobile data recorder all develops towards high definition direction, so image quality is user examining of needing most
Consider, the VGA cameras that the high definition sensor of AR0330 compares on the market, clarity is higher by several times, and in addition product has at the same time
Standby electronic steady image system, can compensate the image of jounce condition, be very suitable for movement image recorder and driving
Recorder.
Evening light is dark, and automobile data recorder is mainly with external light sources such as street lamp, headlight for vehicles, to obtain more light
Source.But some road surfaces do not have Street Light Illumination sometimes, only irradiated at this time by headlight for vehicles by extreme influence automobile data recorder
Areas imaging.Since the light on and off human eye of infrared lamp is insensitive, imaging sensor but has very wide photoactive spectrum scope, because
This utilizes this characteristic, can also make driving recording with auxiliary infrared light supply illumination in the case where night is without visible illumination
Instrument is clearly imaged.
Compensation is further illuminated using infrared-emitting diode (LED) infrared lamp, so as to complete night vision function.It is infrared
LED infrared lamps form illuminator by infrared light-emitting diode matrix.Infrared-emitting diode is by the high material of infrared radiation efficiency
PN junction is made in (common GaAs GaAs), and additional forward bias excites infrared light to PN junction Injection Current.Spectral power distribution is
Centre wavelength 830-950nm, half-peak bandwidth about 40nm or so, it is arrowband distribution, can be experienced for common CCD B/W camera
Scope.Its biggest advantage is that can be entirely without red sudden and violent or only faint red sudden and violent and long lifespan.
Control mechanism 22 includes:
Main control module 221, mobile detection module 222 and warning module 223, mobile detection module 222 and warning module 223
It is connected with main control module 221;
Wherein, mobile detection module 222, catches for carrying out image when target object occurs according to the first prepattern
Catch, if no target object occurs, do not trigger automobile data recorder work;
Warning module 223, for the triggering by main control module 221, the vehicle aligned under steam carries out deviation
Early warning, fatigue driving early warning and overspeed warning.
Further, control mechanism 22 further includes:
Intelligent anti-theft module 224, for carrying out automobile according to the antitheft of the second prepattern by the triggering of main control module,
And send vehicle geographical location information to external equipment by network, such as can drive a vehicle to remember by remote control control
Whether record instrument enters state of deploying troops on garrison duty.When entering state of deploying troops on garrison duty, whether program cycle detection automobile is stolen.Whether stolen to automobile
Intelligent measurement is the progress by two ways.A kind of is the output by vibrating sensor, judges whether automobile has necessarily
Vibration, whether the second position data deviation when being position data and the parking by automobile up to exceeding setting value.Pass through this
Two ways, which is combined, detects that automobile is stolen or is only knocked, and provides warning message in time.Trigger anti-theft early-warning
Afterwards, start camera in car immediately to be shot and picture is sent to car owner, while tracking display car in time by 3G network
Main vehicle GPS data, and the query link being given in google maps, for smart mobile phone, opening link can be direct
The street locations where vehicle are inquired in google maps.
Further, control mechanism 22 further includes:
Image processing module 225, is connected with main control module 221, and the image for being gathered to camera 21 is carried out in image
Object brightness and background luminance adjusting processing, and the correction process of the optical distortion of image.
The adjusting processing of foregoing object brightness and background luminance, can be due under night environment, by camera
The video pictures overall situation gray value of collection is relatively low, image detail poor contrast, noise jamming are serious, carries out evening images enhancing
Processing, can be divided into two aspect of spatial domain enhancing processing and frequency domain enhancing processing, mainly there is gray scale stretching calculation in the spatial domain
Method and histogram equalization algorithm, wherein gray scale stretching are divided into linearly or nonlinearly conversion locally or globally, pass through transforming function transformation function
The pixel value of full images is handled, this algorithm has obvious stretching to global gray value, but be easy to cause image quality
The higher place of hypersaturated state, i.e. original pixel value can expand, and the calculation amount of whole algorithm is than relatively low.Histogram method passes through system
Balanced color histogram, local histogram equalization and the histogram equalization of various conversion are done after counting the histogram distribution of source images
Algorithm such as Plateau histogram is handled, these change the noise that the algorithm being distributed be easy to cause image by statistic histogram, carry
The quality of image is reduced while high gray scale.It is divided into single scale converter technique and MEAM based on Retinex in frequency domain processing
(Method According to Aare) algorithm.Retinex is theoretical to be used to explain as visual model (HVS)
Colored constant property, this theoretical foundation is exactly that the information that HVS models are reflected for target surface is very sensitive.At this
In model, image is made of two parts, and a part is the bright brightness of object in scene, corresponding to the low frequency part of image, separately
A part is the reflecting brightness of object in scene, corresponding to the high frequency section of image, usually they be also referred to as luminance picture and
Reflected image.So if luminance picture and reflected image are isolated from given image, under conditions of constant color, just
Can by varying the ratio of luminance picture and reflected image in original image come achieve the purpose that strengthen image.Image is converted into frequency
During domain, the noise and details of high-frequency information representative image, low-frequency information contain the brightness of image, such as MEAM algorithms by carrying
Low-and high-frequency part and optimize high frequency section, realize the overall situation dynamic enhancing and ensure that the reduction of noise and the holding of details.
The correction process of the optical distortion of foregoing image, can be due to the wide-angle of camera, such as 90 degree to 170 degree,
But wide-angle angle is bigger, there are optical distortion, causes image periphery to form serious distortion, it is necessary to be corrected to pattern distortion
Processing, the correction process are that whole video frame images are divided into grid, establish standard grid chart, standard grid chart are established more
A known grid point coordinates, to the fault image absorbed, establishes distortion grid, extraction is corresponding with known grid point coordinates
Distortion grid coordinate, coordinate points matching is carried out by distortion grid coordinate and known grid point coordinates, is established geometric coordinate and is become mold changing
Type, carries out correspondingly spatial alternation, and carry out corresponding gradation of image adjustment, the image formed after correction is defeated to fault image
Go out, such as whole video frame images are divided into grid, so can use an order polynomial side for each rectangular mesh region
Journey solves its Correction Problemss, and such calculation amount is will be small very much.The distortion of radial direction is regarded as origin symmetry
A kind of distortion, only sees first quartile, it is possible to which knowing the method for other three quadrants can analogize according to symmetrical rule.
One quadrant is divided into horizontal m, Vertical n grid, it is ensured that the deformation for each rectangular area that subregion obtains is same degree, also
Lucky makes it ensure approaching for precision in the number of minimum lattice.N, m decide the number of mesh generation, n, m's
Numerical value is bigger, mesh generation it is careful, correction accuracy is namely more accurate, and quantity is more few also more inaccurate, but more
Accurate correction accuracy, the memory space for also bringing along bigger occupy, and the cost for storing transformation model will be higher.
Emergent management module 226, is connected with main control module 221, for when a vehicle is in a collision, camera to be gathered
Image is latched and sent by network to external equipment, such as when vehicle occurs colliding and produces vibrations, recorder meeting
This section shooting video is latched and (can pre-set the collision generation front and rear period), will not be when repeating to record by certainly
It is dynamic to override, to retain the safety of video evidence automatically.Meanwhile it can pre-set collision occurs whether to start 3G network and lead to
Letter, if starting 3G network, then just immediately upload to this section of video by 3G network and pre-set network storage location.
Further, the first prepattern includes:
Noise suppression preprocessing is carried out to the image of camera collection, carries out background modeling further according to image, and image is carried out
The multidomain treat-ment of region of interest and non-region of interest, carries out corresponding weighting processing, according to weighted results to region of interest or non-region of interest
Judge whether the target object in present image moves, if so, camera continuous collecting image is then triggered, if it is not, not triggering then
Automobile data recorder works, which will be described in detail in following embodiment, and details are not described herein again.
Preferably,
Second prepattern is the vibration information gathered according to vibrating sensor, is judged whether more than the second preset threshold value,
If so, then carrying out position deviation calculating to vehicle, whether position deviation is judged more than the 3rd preset threshold value, if so, then passing through control
Mechanism processed starts camera and carries out picture catching, and carries out early warning processing, second prepattern will in following embodiment into
The detailed description of row, details are not described herein again.
Preferably,
Warning module 223 specifically includes:
Lane departure warning submodule 2231, for catching present image by camera, is filtered with reference to Hough and Kalman
Ripple, judges whether vehicle deviates travel route in the process of moving, if so, early warning is then carried out, the lane departure warning submodule
2231 workflow will be described in detail in following embodiment, and details are not described herein again.
Preferably,
Warning module 223 specifically includes:
Fatigue driving early warning submodule 2232, for exceeding preset time when driving time, and is caught by camera and driven
The ocular for the person of sailing, is to the eyes closed of interpupillary distance tracking prediction driver according to the Kalman filter of neural network aiding
It is no more than the first preset threshold value, if so, then carry out fatigue driving early warning.
Warning module 223 can further include:Overspeed warning function, can be that automobile data recorder passes through sub- OBD moulds
Whether block collection vehicle instantaneous velocity, exceeded the speed limit by software design patterns voice reminder driver.User can preset three limits
Speed prompting, 120km/h are set for pressure speed limit.When speed is less than 120km/h, every default speed limit point only needs language
Sound reminds driver's current vehicle speed to have arrived at the speed;But if when speed is more than 120km/h, voice prompt is driven
The person's of sailing current vehicle speed, simultaneity factor are alarmed.
Control mechanism 21 is dsp chip, such as shown in Fig. 7, Video processing particularly video compression algorithm is to processor
Operational capability has higher requirement.The processor of some high-quality, such as PC machine, PC104 etc. can meet such requirement, but
It is that their costs are higher, is unfavorable for the popularization of product, and these processors can not adapt to the vehicle-mounted environment that jolts.Therefore,
Dsp chip must be used to meet real-time processing requirement as main control chip.
Can be that NT96650 chips are chanted as main control chip using connection, NT96650 chips are a fine definition, Gao Xing
Energy, the dsp chip that energy consumption is small, cost is low.The resolution ratio of up to 50,000,000 pixels can be obtained;It can be used for high-speed cmos image
Sensor;Complicated video processing function is realized using intrinsic function of hardware acceleration;Possess outstanding automatic white balance, automatic
Expose the functions such as adjusting, auto-focusing;H.264 coding and decoding video, the 1080 video figures of HD of hardware supported 30 frame per second are embedded
Picture;The HDTV outputs of built-in 1.3 Tx of HDMI;Possess USB2.0 interfaces, can be with high-speed uploading/download audio, video data.Collocation
The Auto WDR functions of NT96650, bright dark contrast is fine, and night 3DNR seems very excellent to reducing snowflower effect,
Night and low-light (level) are done well.
As shown in figure 8, automobile data recorder further include:
Touch-screen 23, is electrically connected with dsp chip, such as LCD touch screen, does not limit specifically herein, LCD touch screen can
To interact medium as between vehicle and driver, the information of recorder or data are intuitively fed back into driver, as system is set
Put, current time, each function module state, the GPS information of vehicle, short message communication result etc..Can also dynamically it be shown on LCD
Show the prospect situation of vehicle, or check the picture in flash card.In addition driver can pass through the LCD inputs provided or selection work(
The setting of recorder, such as operational mode or working mechanism can be changed.
TFT types liquid crystal display is with image quality is good, it is true to nature to be in bright colors, stereovision is strong, screen display reaction speed
It hurry up, the advantages that gray scale display control is accurate.10.4 cun of TFT-LCD screen LQ104V1DG11 of Sharp companies are selected, it has
The features such as resolution ratio is 640 × 480, color depth 18, interface is big, it uses the DF9BA- produced by Hirose electronics corporations
31-1V interfaces.
Power storage module 24, is electrically connected with dsp chip, and power storage module is externally connected to USB interface and/or vehicle-mounted charge
Head, as shown in Figure 8 and Figure 9, the circuit connection diagram of power storage module 24, is filled using car or Mini USB interfaces are powered, OK
Car recorder has internal battery, it is ensured that model machine works on a period of time after power-off.After access car fills, system boot simultaneously opens
Dynamic pattern of making video recording is made video recording automatically.
Vehicle power supply voltage has+12V ,+a 24V and+36 three kinds at present, wherein China's automobile power source mainly using+12V and+
Two kinds of 24V.The power supply that automobile travel recorder generally requires is+5V and+3.3V, and+5V power supplys are the power supply such as DSP, are main power source,
+ 3.3V powers for data storage, is accessory power supply.
LM2576 is used to design main power source for the switching power supply of core.The system select LM2576-5.0 and
LM2576-3.3 is power supply chip, by the storage battery DC power supply of automobile change into circuit system work normally required+5V and+
Two kinds of 3.3V.
Automobile data recorder is also equipped with memory module (shown in Fig. 6), is electrically connected with main control mechanism 21, can select SD
Card, after memory capacity is full, system will cover the information of making video recording of earliest time automatically, realize that automatic cycle is made video recording.SD card
(Secure Digital Memory Card) is a kind of memory device of new generation based on semiconductor fast-flash memory device, has body
The features such as product is small, light-weight, memory capacity is high, data transfer is quick, mobile flexibility is strong and security is good.Pass through 9 pins
Connection interface is connected with special driver, it is not necessary to extra power supply come be held on memory information.And it is one
Body solid dielectric, without any movable part, it is more difficult to because mechanical movement produces damage, be adapted to in-car electronic equipment running environment
The characteristics of severe.In addition, FAT file system is established in SD card, to facilitate compatibility of the system with PC machine.
Automobile data recorder is also equipped with voice module (shown in Fig. 6), is electrically connected with main control mechanism 21, can work as driver
During dangerous traveling behavior, respective sensor sends signal, and main control chip control high brightness red LED pipe is glittering, at the same time
Start voice alarm function, send voice warning.Meanwhile driver can also realize in-car voice by opening recording mode
Record, for example with monolithic audio record circuit ISD4004-16 as playback chip.ISD4004-16 chip operating voltages are
3.3V, monolithic recording playback time are 16 minutes, can at most divide 2400 sections, tonequality is good, suitable for mobile phone and other portable electrics
In sub- product.Chip uses CMOS technology, includes oscillator, anti-aliasing filter, smoothing filter, audio-frequency amplifier, automatic
Noise elimination and the more electrical level flash storage arrays of high density.
Preferably,
Control mechanism 21 further includes:
Vehicle-state acquisition module 227, is electrically connected with main control module 221, includes OBD submodules 2271, accelerates to pass
Sensor 2272 and vibrating sensor 2273, using vibrating sensor 2273 can be relatively reliable whether detect parked vehicle
It is stolen or is knocked.Vibration detection circuit uses the finished product module of in the market.The module is three-wire interface:Power supply, and signal
Output line.5V DC power supplies, when vibrating sensor 2273 is vibrated, its signal output only need to be provided to vibration detection module
Line can export the low level pulse of 1 second or so.Shaken by adjusting to adjust with 2273 corresponding knob of vibrating sensor
Dynamic detection sensitivity, causes to judge by accident, the meaning of acceleration transducer (G-sensor), it is one special to prevent slight vibration
High-tech component, the change of acceleration can be perceived.When acutely rocking occurs in vehicle body, G-Sensor can produce one
Signal is simultaneously transmitted to dsp chip, and so this section, which is made video recording, to be saved, not by circulation make video recording covering (when vehicle collides this
Function has fine purposes).
GPS module 228, is electrically connected with main control module 221, for gps signal to be carried out to the geography of processing acquisition vehicle
Positional information, the main task of GPS module 228 are to receive the control command for carrying out autonomous controller, capture and receive according to order
The satellite-signal of region, then carries out conversion process to gps signal, calculate longitude where automobile, latitude, the time and
Speed.Finally these data sendings are handled to master controller by it.GPS module 228 uses Taiwan Ya Quan companies
(HIMARK) GPS module produced, model ARZOIO, its main feature is that small, high reliability, interface are simple.ARZOIOGPS
Module has:The module can be transmitted information by bluetooth, can follow the trail of 12 satellite datas at the same time, and positioning time is less than
500 nanoseconds, positioning accuracy 5-15m;With good dynamic property, normal range of operation is below height 18000m, speed
Within 500m/s, acceleration be less than 4g;Can quick starting module, the time of thermal starting/startup temperature/cold start-up is 10 respectively
Second/35 seconds/60 seconds, meets the work requirements of the burglary-resisting system;Interface type is USB, RS232, baud rate 9600bps, non-
Often meet the interface requirements of embedded controller.
Mixed-media network modules mixed-media 229, is electrically connected, mixed-media network modules mixed-media is 3G communication modules, and the 3G network of use is with main control module
WCDMA.WCDMA uses newest asynchronous transfer mode and wechat member transport protocol using newest asynchronous transfer mode (atm),
It can unify on bar circuit to be carried out at the same time multiple callings again, and the place more than people is not easy to block, and in addition, also uses
Adaptive antenna and Microcell technology, greatly increase the capacity of system, using winged icepro WCDMA 3G modules, using USB
Interface mode, is inserted into Huawei MF637U unicom WCDMA wireless Internet cards (SIM card) in 3G module, can be real by USB interface
Existing communication between development board and 3G network.
Warning module 223 can further include:Overspeed warning function, can be that automobile data recorder passes through sub- OBD moulds
Whether block collection vehicle instantaneous velocity, exceeded the speed limit by software design patterns voice reminder driver.User can preset three limits
Speed prompting, 120km/h are set for pressure speed limit.When speed is less than 120km/h, every default speed limit point only needs language
Sound reminds driver's current vehicle speed to have arrived at the speed;But if when speed is more than 120km/h, voice prompt is driven
The person's of sailing current vehicle speed, simultaneity factor are alarmed.
In the present embodiment, by adding mobile detection module 222 and warning module 223 to control mechanism 22, moved
The picture catching of animal body, intelligent realizes trigger camera and carry out picture catching when there are objects moving, do not have that there are objects moving
When, automobile data recorder is in holding state, and warning module 223, for the triggering by main control module 221, aligns and is expert at
Vehicle in sailing carries out lane departure warning, fatigue driving early warning and the multi-functional realization of overspeed warning, solves at present
The burst accident that automobile data recorder is run into vehicle travel process is difficult to the technical problem of complementary processing, meanwhile, OK
To have merged the technologies such as DSP, GPS positioning, 3G communications, sensor technology and Video processing, emphasis solves video and compiles car recorder
The key technologies such as decoding, video pre-filtering, object detecting and tracking, multi-sensor information fusion, developing one kind has urgent thing
The functions such as part record, intelligent anti-theft, mobile detection, lane departure warning, fatigue driving early warning, overspeed warning, infrared night vision
Intelligent travelling crane recorder.
The process detailed description of the first preset mode processing is carried out to the mobile detection module of automobile data recorder below, please be join
Fig. 3 is read, a kind of one embodiment of the first preset mode of automobile data recorder provided in an embodiment of the present invention includes:
301st, image acquisition device background image is passed through;
After vehicle parking, judge whether target object is before, it is necessary to pass through figure when needing to record by camera
As harvester collection background image.
Foregoing image collecting device can be camera.
302nd, the pretreatment of image quality optimization is carried out to background image;
, it is necessary to carry out the pre- of image quality optimization to background image after by image acquisition device background image
Processing, for example with medium filtering plus gaussian filtering, effectively removes picture noise, and the method for then carrying out histogram equalization increases
Strong picture contrast.
303rd, image background modeling is carried out to pretreated background image according to improvement vibe algorithms;
After the pretreatment of image quality optimization is carried out to image, according to improvement vibe algorithms to pretreated background
Image carries out image background modeling.
It should be noted that foregoing vibe algorithms are known to the skilled person technology, it is just no longer superfluous in detail herein
State.
304th, will be by image acquisition device realtime graphic, and the pre- place of image quality optimization is carried out to realtime graphic
Reason;
Picture catching when carrying out target object and occurring, judges whether target object is to need to record by camera
When, it is necessary to will by image acquisition device realtime graphic, and to realtime graphic carry out image quality optimization pretreatment, example
Gaussian filtering is such as added using medium filtering, effectively removes picture noise, then carries out the method enhancing image of histogram equalization
Contrast.
305th, carry out preset picture area differentiation to realtime graphic to handle, image is divided into region of interest and non-region of interest;
When will by image acquisition device realtime graphic, and to realtime graphic carry out image quality optimization pretreatment
Afterwards, carry out preset picture area differentiation to realtime graphic to handle, image is divided into region of interest and non-region of interest, foregoing interest
Area can be the important pickup area (region of such as front side) of image collecting device, otherwise non-region of interest can be Image Acquisition
The insignificant pickup area of device, such as photographed the region on vehicle body.
306th, the pixel of all non-matching corresponding region of interest of pixel and the pixel of non-region of interest are obtained;
Handled when carrying out preset picture area differentiation to realtime graphic, after image is divided into region of interest and non-region of interest,
Need to obtain the pixel of all corresponding region of interest of non-matching pixel and the pixel of non-region of interest.
307th, corresponding weighting processing is carried out to the pixel of region of interest and non-region of interest;
When the image according to image acquisition device is defined according to preset picture area, image is divided into region of interest and non-
After region of interest, corresponding weighting processing, such as region of interest and non-interest are carried out to the pixel of region of interest and non-region of interest
The weight in area and for one, the sum of pixel weight of region of interest is 0.8, and the sum of pixel weight of non-region of interest is 0.2.
308th, the pixel total value of region of interest and non-region of interest after weighting processing is calculated;
After the pixel to region of interest and non-region of interest carries out corresponding weighting processing, after calculating weighting processing
The pixel total value of region of interest and non-region of interest.
309th, judge whether pixel total value exceedes preset threshold, if so, then performing step 310;
Whether the pixel total value of region of interest and non-region of interest after weighting processing is calculated is afterwards, it is necessary to judge pixel total value
More than preset threshold, if so, then performing step 310.
310th, determine in realtime graphic there are object movement, and trigger image collecting device continuous collecting image.
When pixel total value is contrasted with threshold function, determine to meet preset threshold, if, it is determined that realtime graphic
In there are object movement, and the image collecting device continuous collecting image of automobile data recorder is triggered, if it is not, then image collector
The automobile data recorder put is standby.
A kind of mobile detection method provided in an embodiment of the present invention is applied in automobile data recorder.
It is region of interest and non-interest by carrying out multidomain treat-ment to the image of image acquisition device in the present embodiment
Area;The pixel total value of region of interest and non-region of interest is obtained, and judges whether pixel total value meets preset threshold, if so, then true
Determine the target object movement in image, preset threshold is modeled by image background and obtained, just realized automatic decision image and adopt
Acquisition means can pickup area whether have mobile object, if then trigger image collecting device carry out image collection, solve
At present when vehicle is parked, automobile data recorder be stopped can not catch when have mobile object appear in car nearby vehicle is caused
Unnecessary infringement is other when needing the automobile data recorder to record image, automobile data recorder can not judgment object whether occur starting shooting into
The technical problem of row Image Acquisition, and preset picture area differentiation is carried out to realtime graphic and is handled, image is divided into region of interest
With non-region of interest, the judgement of more accurate object movement.
The process detailed description of the second preset mode processing is carried out to the intelligent anti-theft module of automobile data recorder below, please be join
Fig. 4 is read, a kind of one embodiment of the second preset mode of automobile data recorder provided in an embodiment of the present invention includes:
Whether the vibration information for the 401st, detecting vibrating sensor collection has vibration, if so, then performing step 402;
Can be that car owner can enter shape of deploying troops on garrison duty by remote control control automobile data recorder when vehicle, which enters, deploys troops on garrison duty state
State, whether the vibration information for first detecting vibrating sensor collection has vibration, if so, then performing step 402, foregoing vibration information
It can be accurate to judge whether vibration frequency is judged more than the second preset threshold value whether to have vibration.
402nd, carrying out vehicle has the prompting of vibration;
When the vibration information of detection vibrating sensor collection is that have vibration, then carrying out vehicle has the prompting of vibration, Ke Yishi
Prompted with short message mode, can also be that carrying out prompting vehicle on network service to timely communication software by mixed-media network modules mixed-media has
Vibration.
403rd, position deviation calculating is carried out to vehicle, and whether judges position deviation more than the 3rd preset threshold value, if so, then
Perform step 404;
, it is necessary to carry out position deviation calculating to vehicle after carrying out vehicle and having the prompting of vibration, and judge position deviation
Whether more than the 3rd preset threshold value, if so, then performing step 404, which is calculated as extraction real-time vehicle new position letter
Breath, geographical location contrast is carried out by new location information and the positional information that parks cars, if position deviation more than the 3rd preset threshold value,
Then perform step 404.
404th, carrying out vehicle has mobile prompting, and triggers camera and carry out image real-time acquisition, and is sent by network
To external equipment.
Position deviation is judged more than the 3rd preset threshold value, then carrying out vehicle has mobile prompting, and triggers camera progress
Image real-time acquisition, and sent by network to external equipment, such as carrying out vehicle has mobile short message mode to prompt, or it is logical
Cross mixed-media network modules mixed-media prompt on network service to timely communication software, and trigger camera and carry out image real-time acquisition and pass through
Network is sent to external equipment, such as car owner's mobile phone.
In the present embodiment, by the vibration information gathered according to vibrating sensor, judge whether more than the second preset threshold value,
If so, then carrying out position deviation calculating to vehicle, whether position deviation is judged more than the 3rd preset threshold value, if so, then passing through control
Mechanism processed starts camera and carries out picture catching, and carries out early warning processing, anti-theft measure when realizing vehicle away from sight, greatly
The probability that vehicle is stolen is reduced greatly, is solved when current automobile data recorder will take anti-thefting monitoring, it is necessary to long-time power consumption, 24
The technical problem of consume vehicle storage battery caused by hour work.
The course of work of the lane departure warning submodule of automobile data recorder is described in detail below, referring to Fig. 5, this hair
A kind of one embodiment of the course of work of the lane departure warning submodule for automobile data recorder that bright embodiment provides includes:
501st, the image of video frame is gathered, and adjusts the contrast of image;
When needing to carry out lane departure warning to the vehicle in traveling, the image of video frame is gathered first, and adjusts figure
The contrast of picture, such as each frame either a certain two field picture of the video to recording carry out extraction collection, to the image
The contrast of image is adjusted by image enhancement technique.
502nd, image the latter half is arranged to interest region;
When the image of collection video frame, and the contrast of image is adjusted afterwards, it is necessary to which image the latter half is arranged to emerging
Interesting region, it is experience that image the latter half is arranged to interest region, the road video image collected, and road sections are several
All concentrate on the lower half-plane of image.
503rd, Hough straight-line detections are carried out to interest region and calculates track both sides lane line;
, it is necessary to carry out Hough straight-line detection meters to interest region after image the latter half is arranged to interest region
Track both sides lane line is calculated, which is known in the art technology, does not repeat specifically herein.
504th, Kalman filter tracking lane line is carried out to interest region;
After Hough straight-line detections calculating track both sides lane line is carried out to interest region, interest region is carried out
Kalman filter tracks lane line, which is detected as techniques well known, does not repeat specifically herein.
505th, according to Hough detect both sides lane line and Kalman filter tracking lane line as a result, calculate both sides car
The first slope in road and the second slope;
, it is necessary to the both sides track detected according to Hough after Kalman filter tracking lane line is carried out to interest region
Line and Kalman filter tracking lane line as a result, calculate both sides track first slope and the second slope.
506th, by calculating the divisor of first slope and the second slope, judge whether divisor is more than the 4th preset threshold value, if
It is then to perform step 507;
When both sides lane line and Kalman filter the tracking lane line detected according to Hough is as a result, calculate both sides track
First slope and the second slope after, it is necessary to which divisor by calculating first slope and the second slope, judges whether divisor big
In the 4th preset threshold value, if so, then performing step 507.
507th, vehicle deviates travel route in the process of moving, and carries out early warning.
When the divisor by calculating first slope and the second slope, judge that divisor is greater than the 4th preset threshold value, then vehicle
Deviate travel route in the process of moving, and carry out early warning.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, may be referred to the corresponding process in preceding method embodiment, details are not described herein.
In several embodiments provided herein, it should be understood that disclosed system, apparatus and method can be with
Realize by another way.For example, device embodiment described above is only schematical, for example, the unit
Division, is only a kind of division of logic function, can there is other dividing mode, such as multiple units or component when actually realizing
Another system can be combined or be desirably integrated into, or some features can be ignored, or do not perform.It is another, it is shown or
The mutual coupling, direct-coupling or communication connection discussed can be the indirect coupling by some interfaces, device or unit
Close or communicate to connect, can be electrical, machinery or other forms.
The unit illustrated as separating component may or may not be physically separate, be shown as unit
The component shown may or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
In network unit.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, can also
That unit is individually physically present, can also two or more units integrate in a unit.Above-mentioned integrated list
Member can both be realized in the form of hardware, can also be realized in the form of SFU software functional unit.
If the integrated unit is realized in the form of SFU software functional unit and is used as independent production marketing or use
When, it can be stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially
The part to contribute in other words to the prior art or all or part of the technical solution can be in the form of software products
Embody, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, server, or network equipment etc.) performs the complete of each embodiment the method for the present invention
Portion or part steps.And foregoing storage medium includes:USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can store journey
The medium of sequence code.
The above, the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although with reference to before
Embodiment is stated the present invention is described in detail, it will be understood by those of ordinary skill in the art that:It still can be to preceding
State the technical solution described in each embodiment to modify, or equivalent substitution is carried out to which part technical characteristic;And these
Modification is replaced, and the essence of appropriate technical solution is departed from the spirit and scope of various embodiments of the present invention technical solution.