CN104954738A - Mobile detecting method and mobile detecting device - Google Patents
Mobile detecting method and mobile detecting device Download PDFInfo
- Publication number
- CN104954738A CN104954738A CN201510217838.0A CN201510217838A CN104954738A CN 104954738 A CN104954738 A CN 104954738A CN 201510217838 A CN201510217838 A CN 201510217838A CN 104954738 A CN104954738 A CN 104954738A
- Authority
- CN
- China
- Prior art keywords
- image
- pixel
- interest
- region
- realtime graphic
- 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.)
- Pending
Links
Landscapes
- Traffic Control Systems (AREA)
Abstract
An embodiment of the invention discloses a mobile detecting method and a mobile detecting device. The mobile detecting method includes: subjecting a real-time image acquired by an image acquisition device and a background model corresponding to the background image to pixel point matching, confirming non-matched pixel points, and if the non-matched pixel points exceed a preset threshold value, confirming that object moving exists in the real-time image and triggering the image acquisition device to acquire images continuously. The mobile detecting method and the mobile detecting device solve the technical problem of inconvenience in operation of an existing driving recorder which triggers image acquisition manually, and further avoid the technical problem of driving dangerousness caused by image acquisition operated during driving.
Description
Technical field
The present invention relates to field of computer technology, particularly relate to a kind of mobile detection method and device.
Background technology
Drive recorder and registration of vehicle travel the instrument of the relevent informations such as image in way and sound.After drive recorder is installed, image and the sound of running car overall process can be recorded, can be traffic accident and produce evidence.
Traditional drive recorder can only record driving states, the for example speed of a motor vehicle, mileage number etc., be commonly called as " automobile black box; but; only can record driving states, but, when vehicle is parked; drive recorder quit work cannot catch when have mobile object appear near car to vehicle cause unnecessary infringement or other need drive recorder document image time, whether drive recorder cannot occur starting shooting and carries out the technical problem of IMAQ by judgment object.
Summary of the invention
Embodiments provide a kind of mobile detection method and device, solve at present when vehicle is parked, drive recorder quit work cannot catch when have mobile object appear near car to vehicle cause unnecessary infringement or other need drive recorder document image time, whether drive recorder cannot occur starting shooting and carries out the technical problem of IMAQ by judgment object.
A kind of mobile detection method that the embodiment of the present invention provides, comprising:
The background model corresponding with background image by the realtime graphic of image acquisition device is carried out pixel coupling, determine non-matching pixel, if described non-matching pixel exceedes preset threshold value, then determine that the object that exists in described realtime graphic moves, and trigger described image collecting device continuous collecting image.
Preferably,
The background model corresponding with background image by the realtime graphic of image acquisition device is carried out pixel coupling, determine non-matching pixel, if described non-matching pixel exceedes preset threshold value, then determine that the object that exists in described realtime graphic moves, and also comprise before triggering described image collecting device continuous collecting image:
By background image described in described image acquisition device;
According to improvement vibe algorithm, image background modeling is carried out to pretreated described background image.
Preferably,
Also comprise before according to improvement vibe algorithm image background modeling being carried out to pretreated described background image:
Described background image is carried out to the preliminary treatment of image quality optimization.
Preferably,
The background model corresponding with background image by the realtime graphic of image acquisition device is carried out pixel coupling, determine non-matching pixel, if described non-matching pixel exceedes preset threshold value, then determine that the object that exists in described realtime graphic moves, and also comprise before triggering described image collecting device continuous collecting image:
By realtime graphic described in described image acquisition device, and the preliminary treatment of image quality optimization will be carried out to described realtime graphic;
Preset picture area differentiating and processing is carried out to described realtime graphic, described image is divided into described region of interest and described non-region of interest.
Preferably,
The background model corresponding with background image by the realtime graphic of image acquisition device is carried out pixel coupling, determine non-matching pixel, if described non-matching pixel exceedes preset threshold value, then determine that the object that exists in described realtime graphic moves, and trigger described image collecting device continuous collecting image and specifically comprise:
The background model corresponding with background image by the realtime graphic of image acquisition device is carried out pixel coupling, determines described non-matching pixel;
Obtain the pixel of the corresponding described region of interest of all described non-matching pixels and the pixel of described non-region of interest;
Weighting process corresponding is with it carried out to the pixel of described region of interest and the pixel of described non-region of interest;
Calculate the pixel total value of the described region of interest after weighting process and described non-region of interest;
Judge whether described pixel total value exceedes described preset threshold, if so, then determine that the object that exists in described realtime graphic moves, and trigger described image collecting device continuous collecting image.
A kind of movement detection device that the embodiment of the present invention provides, comprising:
Judging unit, for the background model corresponding with background image by the realtime graphic of image acquisition device is carried out pixel coupling, determine non-matching pixel, if described non-matching pixel exceedes preset threshold value, then determine that the object that exists in described realtime graphic moves, and trigger described image collecting device continuous collecting image.
Preferably,
Described movement detection device also comprises:
Image acquisition units, for passing through background image described in described image acquisition device;
Modeling unit, for carrying out image background modeling according to improvement vibe algorithm to pretreated described background image.
Preferably,
Described movement detection device also comprises:
First graphics processing unit, for carrying out the preliminary treatment of image quality optimization to described image.
Preferably,
Described movement detection device also comprises:
Second image acquisition units, for by realtime graphic described in described image acquisition device, and carrying out the preliminary treatment of image quality optimization to described realtime graphic;
Zoning unit, for carrying out preset picture area differentiating and processing to described realtime graphic, is divided into described region of interest and described non-region of interest by described image.
Preferably,
Judging unit specifically comprises:
Matching unit, for the background model corresponding with background image by the realtime graphic of image acquisition device is carried out pixel coupling, determines described non-matching pixel;
Acquiring unit, for the pixel of the pixel and described non-region of interest that obtain the corresponding described region of interest of all described non-matching pixels;
Weighting subelement, for carrying out weighting process corresponding with it to the pixel of described region of interest and the pixel of described non-region of interest;
Computation subunit, for calculating the pixel total value of the described region of interest after weighting process and described non-region of interest;
Judgment sub-unit, for judging whether described pixel total value exceedes described preset threshold, if so, then determines that the object that exists in described realtime graphic moves, and triggers described image collecting device continuous collecting image.
As can be seen from the above technical solutions, the embodiment of the present invention has the following advantages:
A kind of mobile detection method that the embodiment of the present invention provides and device, mobile detection method comprises: the background model corresponding with background image by the realtime graphic of image acquisition device is carried out pixel coupling, determine non-matching pixel, if not matched pixel point exceedes preset threshold value, then determine that the object that exists in realtime graphic moves, and trigger image harvester continuous collecting image.In the present embodiment, the background model that the realtime graphic of image acquisition device is corresponding with background image carries out pixel coupling, determine non-matching pixel, if not matched pixel point exceedes preset threshold value, then determine that the object that exists in realtime graphic moves, and trigger image harvester continuous collecting image, whether what just achieve automatic decision image collecting device pickup area can have mobile object, if then trigger image harvester carries out the collection of image, solve at present when vehicle is parked, drive recorder quit work cannot catch when have mobile object appear near car to vehicle cause unnecessary infringement or other need drive recorder document image time, whether drive recorder cannot occur starting shooting and carries out the technical problem of IMAQ by judgment object.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
The schematic flow sheet of an embodiment of a kind of mobile detection method that Fig. 1 provides for the embodiment of the present invention;
The schematic flow sheet of another embodiment of a kind of mobile detection method that Fig. 2 provides for the embodiment of the present invention;
The structural representation of an embodiment of a kind of movement detection device that Fig. 3 provides for the embodiment of the present invention;
The structural representation of another embodiment of a kind of movement detection device that Fig. 4 provides for the embodiment of the present invention;
The structural representation being applied in drive recorder of a kind of movement detection device that Fig. 5 provides for the embodiment of the present invention.
Embodiment
Embodiments provide a kind of mobile detection method and device, solve at present when vehicle is parked, drive recorder quit work cannot catch when have mobile object appear near car to vehicle cause unnecessary infringement or other need drive recorder document image time, whether drive recorder cannot occur starting shooting and carries out the technical problem of IMAQ by judgment object.
For making goal of the invention of the present invention, feature, advantage can be more obvious and understandable, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, the embodiments described below are only the present invention's part embodiments, and the embodiment of not all.Based on the embodiment in the present invention, those of ordinary skill in the art, not making other embodiments all obtained under creative work prerequisite, belong to the scope of protection of the invention.
Refer to Fig. 1, an embodiment of a kind of mobile detection method that the embodiment of the present invention provides comprises:
101, the background model corresponding with background image by the realtime graphic of image acquisition device is carried out pixel coupling, determine non-matching pixel;
When carrying out picture catching when having target object to occur, judge target object whether for needs by camera record time, need the background model corresponding with background image by the realtime graphic of image acquisition device to carry out pixel coupling, determine non-matching pixel.
Aforesaid image collecting device can be camera.
If not 102 matched pixel points exceed preset threshold value, then determine that the object that exists in realtime graphic moves, and trigger image harvester continuous collecting image.
When the background model corresponding with background image by the realtime graphic of image acquisition device is carried out pixel coupling, after determining non-matching pixel, if not need matched pixel point to exceed preset threshold value, then determine that the object that exists in realtime graphic moves, and trigger image harvester continuous collecting image.
A kind of mobile detection method that the embodiment of the present invention provides is applied in drive recorder.
In the present embodiment, the background model that the realtime graphic of image acquisition device is corresponding with background image carries out pixel coupling, determine non-matching pixel, if not matched pixel point exceedes preset threshold value, then determine that the object that exists in realtime graphic moves, and trigger image harvester continuous collecting image, whether what just achieve automatic decision image collecting device pickup area can have mobile object, if then trigger image harvester carries out the collection of image, solve at present when vehicle is parked, drive recorder quit work cannot catch when have mobile object appear near car to vehicle cause unnecessary infringement or other need drive recorder document image time, whether drive recorder cannot occur starting shooting and carries out the technical problem of IMAQ by judgment object.
The above is described in detail the process of mobile detection method, below by judging that the process whether pixel total value meets preset threshold is described in detail, refer to Fig. 2, another embodiment of a kind of mobile detection method that the embodiment of the present invention provides comprises:
201, by image acquisition device background image;
After vehicle parking, judge target object whether for needs are by before during camera record, need by image acquisition device background image.
Aforesaid image collecting device can be camera.
202, background image is carried out to the preliminary treatment of image quality optimization;
After passing through image acquisition device background image, need preliminary treatment background image being carried out to image quality optimization, such as adopt medium filtering to add gaussian filtering, effectively remove picture noise, the method for then carrying out histogram equalization strengthens picture contrast.
203, according to improvement vibe algorithm, image background modeling is carried out to pretreated background image;
After preliminary treatment image being carried out to image quality optimization, according to improvement vibe algorithm, image background modeling is carried out to pretreated background image.
It should be noted that, aforesaid vibe algorithm is known to the skilled person technology, is just no longer described in detail herein.
204, by image acquisition device realtime graphic, and the preliminary treatment of image quality optimization will be carried out to realtime graphic;
When carrying out picture catching when having target object to occur, judge target object whether for needs by camera record time, needs will by image acquisition device realtime graphic, and realtime graphic is carried out to the preliminary treatment of image quality optimization, medium filtering is such as adopted to add gaussian filtering, effective removal picture noise, the method for then carrying out histogram equalization strengthens picture contrast.
205, preset picture area differentiating and processing is carried out to realtime graphic, image is divided into region of interest and non-region of interest;
When will by image acquisition device realtime graphic, and after realtime graphic being carried out to the preliminary treatment of image quality optimization, preset picture area differentiating and processing is carried out to realtime graphic, image is divided into region of interest and non-region of interest, aforesaid region of interest can be the important pickup area (region as front side) of image collecting device, otherwise non-region of interest can be the insignificant pickup area of image collecting device, as photographed the region on vehicle body.
206, the pixel of the corresponding region of interest of all non-matching pixels and the pixel of non-region of interest is obtained;
When carrying out preset picture area differentiating and processing to realtime graphic, after image being divided into region of interest and non-region of interest, need to obtain the corresponding pixel of region of interest of all non-matching pixels and the pixel of non-region of interest.
207, weighting process corresponding is with it carried out to the pixel of region of interest and non-region of interest;
When the image according to image acquisition device defines according to preset picture area, after image being divided into region of interest and non-region of interest, weighting process corresponding is with it carried out to the pixel of region of interest and non-region of interest, the weight of such as region of interest and non-region of interest and be one, the pixel weight sum of region of interest is 0.8, and the pixel weight sum of non-region of interest is 0.2.
208, the pixel total value of the region of interest after weighting process and non-region of interest is calculated;
After the pixel of region of interest and non-region of interest being carried out to weighting process corresponding with it, calculate the pixel total value of the region of interest after weighting process and non-region of interest.
209, judge whether pixel total value exceedes preset threshold, if so, then perform step 210;
After the pixel total value of the region of interest after calculating weighting process and non-region of interest, need to judge whether pixel total value exceedes preset threshold, if so, then execution step 210.
210, determine that the object that exists in realtime graphic moves, and trigger image harvester continuous collecting image.
When pixel total value and threshold function are contrasted, determine to meet preset threshold, if, then determine that the object that exists in realtime graphic moves, and trigger the image collecting device continuous collecting image of drive recorder, if not, then the drive recorder of image collecting device is standby.
A kind of mobile detection method that the embodiment of the present invention provides is applied in drive recorder.
In the present embodiment, be region of interest and non-region of interest by carrying out multidomain treat-ment to the image of image acquisition device, obtain the pixel total value of region of interest and non-region of interest, and judge whether pixel total value meets preset threshold, if, then determine that the target object in image moves, preset threshold is obtained by image background modeling, whether what just achieve automatic decision image collecting device pickup area can have mobile object, if then trigger image harvester carries out the collection of image, solve at present when vehicle is parked, drive recorder quit work cannot catch when have mobile object appear near car to vehicle cause unnecessary infringement or other need drive recorder document image time, whether drive recorder cannot occur starting shooting and carries out the technical problem of IMAQ by judgment object, and preset picture area differentiating and processing is carried out to realtime graphic, image is divided into region of interest and non-region of interest, the more accurate judgement of object movement.
Refer to Fig. 3, an embodiment of a kind of movement detection device provided in the embodiment of the present invention comprises:
Judging unit 301, for the background model corresponding with background image by the realtime graphic of image acquisition device is carried out pixel coupling, determine non-matching pixel, if not matched pixel point exceedes preset threshold value, then determine that the object that exists in realtime graphic moves, and trigger image harvester continuous collecting image.
In the present embodiment, carrying out multidomain treat-ment by the image of judging unit 301 pairs of image acquisition device is region of interest and non-region of interest, obtain the pixel total value of region of interest and non-region of interest, and judge whether pixel total value meets preset threshold, if, then determine that the target object in image moves, preset threshold is obtained by image background modeling, whether what just achieve automatic decision image collecting device pickup area can have mobile object, if then trigger image harvester carries out the collection of image, solve at present when vehicle is parked, drive recorder quit work cannot catch when have mobile object appear near car to vehicle cause unnecessary infringement or other need drive recorder document image time, whether drive recorder cannot occur starting shooting and carries out the technical problem of IMAQ by judgment object, and preset picture area differentiating and processing is carried out to realtime graphic, image is divided into region of interest and non-region of interest, the more accurate judgement of object movement.
The above is described in detail each unit of movement detection device, and will be described in detail extra cell below, and refer to Fig. 4, another embodiment of a kind of movement detection device provided in the embodiment of the present invention comprises:
Image acquisition units 401, for passing through image acquisition device background image;
First graphics processing unit 402, for carrying out the preliminary treatment of image quality optimization to image.
Modeling unit 403, for carrying out image background modeling according to improvement vibe algorithm to pretreated background image.
Second image acquisition units 404, for by image acquisition device realtime graphic, and carrying out the preliminary treatment of image quality optimization to realtime graphic;
Zoning unit 405, for carrying out preset picture area differentiating and processing to realtime graphic, is divided into region of interest and non-region of interest by image.
Judging unit 406, for the background model corresponding with background image by the realtime graphic of image acquisition device is carried out pixel coupling, determine non-matching pixel, if not matched pixel point exceedes preset threshold value, then determine that the object that exists in realtime graphic moves, and trigger image harvester continuous collecting image.
Judging unit 406 specifically comprises:
Coupling subelement 4061, for the background model corresponding with background image by the realtime graphic of image acquisition device is carried out pixel coupling, determines non-matching pixel;
Obtain subelement 4062, for the pixel of the pixel and non-region of interest that obtain the corresponding region of interest of all non-matching pixels;
Weighting subelement 4063, for carrying out weighting process corresponding with it to the pixel of region of interest and the pixel of non-region of interest;
Computation subunit 4064, for calculating the pixel total value of the region of interest after weighting process and non-region of interest;
Judgment sub-unit 4065, for judging whether pixel total value exceedes preset threshold, if so, then determines that the object that exists in realtime graphic moves, and trigger image harvester continuous collecting image.
In the present embodiment, carrying out multidomain treat-ment by the image of judging unit 401 pairs of image acquisition device is region of interest and non-region of interest, obtain the pixel total value of region of interest and non-region of interest, and judge whether pixel total value meets preset threshold, if, then determine that the target object in image moves, preset threshold is obtained by image background modeling, whether what just achieve automatic decision image collecting device pickup area can have mobile object, if then trigger image harvester carries out the collection of image, solve at present when vehicle is parked, drive recorder quit work cannot catch when have mobile object appear near car to vehicle cause unnecessary infringement or other need drive recorder document image time, whether drive recorder cannot occur starting shooting and carries out the technical problem of IMAQ by judgment object, and zoning unit 405 pairs of realtime graphics carry out preset picture area differentiating and processing, image is divided into region of interest and non-region of interest, the more accurate judgement of object movement.
The above is described in detail the composition of movement detection device, below by movement detection device, the structure be applied in drive recorder is described in detail, refer to Fig. 5, an embodiment of a kind of drive recorder that the embodiment of the present invention provides comprises:
Camera 21 and controlling organization 22, camera 21 and controlling organization 22 are electrically connected, camera is dual camera pattern, two cameras are that to arrange camera 21 can be use ccd image sensor or cmos image sensor to combine to gather image to activity adjustment angle, aforesaid dual camera pattern, a camera, facing to headstock, takes front side scene; A camera is facing in car, and this camera adopts common CMOS camera, and the camera facing to headstock adopts the AR0330 camera module of Aptina company, have high definition 1080P, wide dynamic technique, 110 ° to 170 ° wide-angles can be the high temperature resistant camera lenses of collocation 4G, 5G, 6G all-wave.AR0330 adopts A-Pix technology, improves quantum efficiency, make it obtain very large lifting for low light level susceptibility for ruddiness and green glow.Present drive recorder is all towards high definition future development, so the consideration that image quality is user to be needed most, the VGA camera that the high definition transducer of AR0330 is compared on the market, definition exceeds several times, product possesses electronic steady image system simultaneously in addition, can compensate the image of jounce condition, be very suitable for motion image recorder and drive recorder.
Evening, light was dark, drive recorder mainly with the external light source such as street lamp, headlight for vehicles, for obtaining more light source.But some road surface does not have Street Light Illumination sometimes, now only irradiate the areas imaging of extreme influence drive recorder by headlight for vehicles.Because the light on and off human eye of infrared lamp is insensitive, imageing sensor but has very wide photoactive spectrum scope, therefore utilizes this characteristic, can when night without visible illumination, also can make drive recorder imaging clearly with the illumination of auxiliary infrared light supply.
Further employing infrared-emitting diode (LED) infrared lamp carries out illumination compensation, thus completes night vision function.Infrared LED infrared lamp forms luminous element by infrarede emitting diode matrix.Infrared-emitting diode makes PN junction by the material (conventional GaAs GaAs) that infrared radiation efficiency is high, and additional forward bias excites infrared light to PN junction Injection Current.Wavelength 830-950nm centered by spectral power distribution, half-peak bandwidth is about about 40nm, and it is arrowband distribution, is the scope that common CCD B/W camera can be experienced.Its maximum advantage is can completely without cruelly red or only have faint red sudden and violent and the life-span is long.
Controlling organization 22 comprises:
Main control module 221, mobile detection module 222 and warning module 223, mobile detection module 222 is all connected with main control module 221 with warning module 223;
Wherein, mobile detection module 222 is movement detection device, be region of interest and non-region of interest for carrying out multidomain treat-ment to the image of image acquisition device, obtain the pixel total value of region of interest and non-region of interest, and judge whether pixel total value meets preset threshold, if so, then determine that the target object in image moves, preset threshold is obtained by image background modeling;
Warning module 223, for the triggering by main control module 221, the vehicle aligned under steam carries out lane departure warning, fatigue driving early warning and overspeed warning.
Further, controlling organization 22 also comprises:
Intelligent anti-theft module 224, for being carried out antitheft according to the second prepattern of automobile by the triggering of main control module, and vehicle geographical location information is sent to external equipment by network, can be such as can control drive recorder by remote controller whether to enter the state of deploying troops on garrison duty.When entering the state of deploying troops on garrison duty, whether program cycle detects automobile stolen.The Intelligent Measurement whether stolen to automobile is by the carrying out of two kinds of modes.Be the output by vibrating sensor, judge whether automobile has certain vibration, whether second be to be reached with position data deviation when stopping by the position data of automobile to exceed set point.Combined by these two kinds of modes and detect that automobile is stolen or is only knocked, and provide warning message in time.After triggering anti-theft early-warning, start camera in car immediately to carry out taking and picture being sent to car owner by 3G network, the host vehicle of tracking in time display simultaneously gps data, and the query link be given in google map, for smart mobile phone, open the street locations that link just directly can inquire vehicle place in google map.
Further, controlling organization 22 also comprises:
Image processing module 225, is connected with main control module 221, and the image for gathering camera 21 carries out the adjustment process of object brightness in image and background luminance, and the correction process of the optical distortion of image.
The adjustment process of aforesaid object brightness and background luminance, can be due under night environment, video pictures overall situation gray value through camera collection is lower, image detail poor contrast, noise jamming is serious, carry out the process of evening images enhancing, can be divided into spatial domain to strengthen process and frequency domain enhancing process two aspect, mainly contain gray scale stretching algorithm and histogram equalization algorithm in the spatial domain, wherein gray scale stretches and is divided into the linear or nonlinear transformation of local or the overall situation, by the pixel value of transforming function transformation function process full images, the gray value of this algorithm to the overall situation has obvious stretching, but easily cause the hypersaturated state of image quality, namely the place that original pixel value is higher can expand, the amount of calculation of whole algorithm is lower.The histogram equalization algorithm such as Plateau histogram process of color histogram equilibrium, local histogram equalization and various conversion is done after the histogram distribution of histogram method by Statistic Source image, these algorithms relying on statistic histogram to change distribution easily cause the noise of image, reduce the quality of image while improving gray scale.The single scale converter technique based on Retinex and MEAM (Method According to Aare is divided in frequency domain process
) algorithm.Retinex theoretical as visual model (HVS) for explaining colored constant character, this theory according to being exactly that the information that reflects for target surface of HVS model is very responsive.In this model, image is made up of two parts, and a part is the bright brightness of object in scene, corresponding to the low frequency part of image, another part is the reflecting brightness of object in scene, and corresponding to the HFS of image, they are also referred to as luminance picture and reflected image usually.If therefore isolate luminance picture and reflected image from given image, under the condition of constant color, just reach the object strengthening image by change luminance picture and the ratio of reflected image in original image.When image converts frequency domain to, the noise of high-frequency information representative image and details, low frequency information contains the brightness of image, and such as MEAM algorithm optimizes HFS by improving low frequency part, achieves the Dynamic contrast enhance of the overall situation and ensure that the reduction of noise and the maintenance of details.
The correction process of the optical distortion of aforesaid image, it can be the wide-angle due to camera, as 90 degree to 170 degree, but wide-angle angle is larger, there is optical distortion, image periphery is caused to form serious distortion, need to carry out correction process to picture distortion, this correction process is for be divided into grid by whole video frame images, Criterion grid chart, multiple known grid point coordinate is set up to standard network trrellis diagram, to absorbing the fault image arrived, set up distortion grid, extract the distortion grid coordinate corresponding with known grid point coordinate, distortion grid coordinate is carried out coordinate points with known grid point coordinate mate, set up geometric coordinate transformation model, correspondingly spatial alternation is carried out to fault image, and carry out corresponding gradation of image adjustment, form the image after correcting to export, such as whole video frame images is divided into grid, its Correction Problems can be solved like this with an order polynomial equation for each rectangular mesh region, such amount of calculation is will be little a lot.The distortion of radial direction is regarded as a kind of distortion of origin symmetry, only see first quartile, just can know that the method for other three quadrants just can be analogized according to symmetrical rule.First quartile is divided into horizontal m, a Vertical n grid, guarantees that the distortion of each rectangular area that subregion obtains is same degree, also make it in the number of minimum point grid, ensure approaching of precision with regard to lucky.N, m decide the number of stress and strain model, and the numerical value of n, m is larger, stress and strain model careful, correction accuracy is namely more accurate, the fewer also more inaccuracy of quantity, but more accurate correction accuracy, larger memory space also can be brought to occupy, and the cost of store transformed model will be higher.
Emergency treatment module 226, be connected with main control module 221, for when a vehicle is in a collision, the image of camera collection is carried out latching and being sent to external equipment by network, such as when vehicle occurs collision and produces vibrations, this section of capture video can carry out latching (can pre-set the time period that front and back occur in collision) by recorder, automatically can not be override, automatically to retain the safety of video evidence when repeating record.Meanwhile, can pre-set collision and occur whether start 3G network communication, if start 3G network, so instant being uploaded to by this section of video by 3G network pre-sets network storage location.
Preferably,
Second prepattern is the vibration information gathered according to vibrating sensor, judge whether more than the second preset threshold value, if, then position deviation calculating is carried out to vehicle, judge that whether position deviation is more than the 3rd preset threshold value, if, then start camera by controlling organization and carry out picture catching, and carrying out early warning process, this second prepattern will be described in detail in subsequent embodiment, repeat no more herein.
Preferably,
Warning module 223 specifically comprises:
Lane departure warning submodule 2231, for catching present image by camera, in conjunction with Hough and Kalman filter, judge whether vehicle departs from travel route in the process of moving, if, then carry out early warning, the workflow of this lane departure warning submodule 2231 will be described in detail in subsequent embodiment, repeat no more herein.
Preferably,
Warning module 223 specifically comprises:
Fatigue driving early warning submodule 2232, for exceeding preset time when driving time, and the ocular of driver is caught by camera, according to the Kalman filter of neural network aiding to the eyes closed of interpupillary distance tracking prediction driver whether more than the first preset threshold value, if so, then fatigue driving early warning is carried out.
Warning module 223 can further include: overspeed warning function, can be drive recorder by sub-OBD module acquires vehicle instantaneous velocity, whether exceeded the speed limit by software design patterns voice reminder driver.User can preset three speed limit promptings, and 120km/h is arranged for forcing speed limit.When the speed of a motor vehicle is less than 120km/h time, every default speed limit point only needs voice reminder driver current vehicle speed to arrive this speed; But if time the speed of a motor vehicle is more than 120km/h, voice message driver current vehicle speed, simultaneity factor is reported to the police.
Controlling organization 21 is dsp chip, such as Video processing particularly the operational capability of video compression algorithm to processor have higher requirement.The processor of some high-quality, such as PC, PC104 etc. can meet such requirement, but their costs are higher, are unfavorable for the popularization of product, and these processors can not adapt to the vehicle-mounted environment that jolts.Therefore, dsp chip must be adopted could to meet real-time processing requirement as main control chip.
Can be adopt connection to chant NT96650 chip as main control chip, NT96650 chip be a high definition, high-performance, power consumption is little, cost is low dsp chip.The resolution up to 5,000 ten thousand pixels can be obtained; May be used for high-speed cmos imageing sensor; Intrinsic function of hardware acceleration is utilized to realize complicated video processing function; Have the functions such as outstanding Automatic white balance, automatic exposure adjustment, auto-focusing; Embedded H.264 coding and decoding video, HD 1080 video image of hardware supports 30 frames per second; The HDTV of built-in HDMI 1.3 Tx exports; Have USB2.0 interface, can high-speed uploading/download audio, video data.The Auto WDR function of collocation NT96650, bright dark contrast is fine, and night, 3DNR seemed very excellent to reduction snowflower effect, and night and low-light (level) are done well.
Drive recorder also comprises:
Touch-screen, be electrically connected with dsp chip, such as LCD touch screen, does not specifically limit herein, and LCD touch screen can as the mutual medium between vehicle and driver, the information of recorder or data are fed back to driver intuitively, as Operation system setting, current time, each functional module state, the GPS information of vehicle, short message communication result etc.Also can on LCD the prospect situation of Dynamic Announce vehicle, or check the picture in flash card.The setting of driver's input that can be provided by LCD or selection function amendment record instrument in addition, as operational mode or working mechanism etc.
TFT type LCDs has the advantages such as image quality is good, true to nature, the stereovision of being in bright colors is strong, screen display reaction speed is fast, gray scale display and control is accurate.Features such as having selected 10.4 cun of TFT-LCD of Sharp company to shield LQ104V1DG11, it has, and resolution is 640 × 480, color depth 18, interface are large, its uses the DF9BA-31-1V interface produced by Hirose electronics corporation.
Power storage module, be electrically connected with dsp chip, power storage module is externally connected to USB interface and/or vehicle-mounted charge head, and power storage module uses car to fill or Mini USB interface is powered, drive recorder has internal battery, and after can ensureing power-off, model machine works on a period of time.After access car fills, system boot also starts pattern of making video recording and automatically makes video recording.
Current vehicle power supply voltage has+12V ,+24V and+36 three kinds, and wherein China's automobile power source mainly adopts+12V and+24V two kinds.The power supply of automobile travel recorder General Requirements is+5V and+3.3V ,+5V power supply is the power supplies such as DSP, and be main power source ,+3.3V is that data storage is powered, and is accessory power supply.
LM2576 is adopted to be that the switching power supply of core is to design main power source.Native system selects LM2576-5.0 and LM2576-3.3 to be power supply chip, the storage battery DC power supply of automobile is changed into circuit system and normally to work required+5V and+3.3V two kinds.
Drive recorder also possesses memory module, is electrically connected with main control mechanism 21, can be select SD card, and after memory capacity is full, system will cover the information of making video recording of earliest time automatically, realizes automatic cycle and makes video recording.SD card (Secure Digital Memory Card) is a kind of memory device of new generation of based semiconductor fast-flash memory device, has that volume is little, lightweight, memory capacity is high, transfer of data is quick, mobile flexibility is strong and the feature such as fail safe is good.Be connected with special driver by the connection interface of 9 pins, do not need extra power supply to keep the information of memory on it.And it is integrated solid body medium, without any movable part, more difficult because of mechanical movement generation damage, be applicable to the feature that car inner electronic equipment running environment is severe.In addition, SD card is set up FAT file system, to facilitate system with the compatibility of PC.
Drive recorder also possesses voice module, is electrically connected with main control mechanism 21, can be when the dangerous traveling behavior of driver, respective sensor sends signal, it is glittering that main control chip controls high brightness red LED pipe, starts voice alarm function simultaneously, send voice warning.Meanwhile, driver also can realize the recording of voice in car by opening recording mode, such as, adopt monolithic audio record circuit ISD4004-16 as playback chip.ISD4004-16 chip operating voltage is 3.3V, and the monolithic recording playback time is 16 minutes, can divide 2400 sections at most, and tonequality is good, is applicable in mobile phone and other portable type electronic product.Chip adopts CMOS technology, includes oscillator, anti-aliasing filter, smoothing filter, audio frequency amplifier, automatic silencing and high density many electrical level flash storage array.
Preferably,
Controlling organization 21 also comprises:
Vehicle-state acquisition module 227, is electrically connected with main control module 221, includes OBD submodule 2271, acceleration sensor 2272 and vibrating sensor 2273, adopts vibrating sensor 2273 can detect that whether the vehicle parked is stolen or be knocked more reliably.Vibration detection circuit adopts the finished product module on market.This module is three-wire interface: power supply, and output line.Only need provide 5V DC power supply to vibration detection module, when vibrating sensor 2273 is subject to vibrating, namely its output line can export the low level pulse of about 1 second.Vibration detection sensitivity can be regulated by regulating the knob corresponding with vibrating sensor 2273, in case slight vibration causes erroneous judgement, the meaning of acceleration transducer (G-sensor), it is special high-tech components and parts, can perceive the change of accelerative force.When acutely rocking appears in vehicle body, G-Sensor can produce a signal and pass to dsp chip, and this section is made video recording and will be saved like this, is not recycled covering of making video recording (this function has fine purposes when collision happens).
GPS module 228, be electrically connected with main control module 221, the geographical location information obtaining vehicle is processed for being carried out by gps signal, the main task of GPS module 228 is the control commands receiving autonomous controller, catch according to order and receive the satellite-signal of region, then conversion process is carried out to gps signal, calculate the longitude at automobile place, latitude, time and the speed of a motor vehicle.Finally sending to master controller to be processed by it these data.The GPS module that GPS module 228 adopts Taiwan Ya Quan company (HIMARK) to produce, model is ARZOIO, is characterized in that volume is little, high reliability, interface are simple.ARZOIOGPS module has: this module carries out transmission information by bluetooth, can follow the trail of 12 satellite datas simultaneously, be less than for 500 nanoseconds positioning time, and positioning precision is 5-15m; Have good dynamic property, normal range of operation is within height below 18000m, speed 500m/s, acceleration is lower than 4g; Can start module fast, the time of warm start/startup temperature/cold start-up is 10 seconds/35 seconds/60 seconds respectively, meets the work requirements of this burglary-resisting system; Interface type is USB, RS232, and baud rate is 9600bps, meets very much the interface requirements of embedded controller.
Mixed-media network modules mixed-media 229, is electrically connected with main control module, and mixed-media network modules mixed-media is 3G communication module, and the 3G network of employing is WCDMA.WCDMA adopts up-to-date asynchronous transfer mode (atm) to adopt up-to-date asynchronous transfer mode and micro-cell transmission agreement, can unify again bar circuit carries out multiple calling simultaneously, and be not easy blocking in the place that people is many, in addition, additionally use adaptive antenna and Microcell technology, greatly increase the capacity of system, employing flies to insult WCDMA 3G module, adopt usb mode, 3G module is inserted Huawei MF637U UNICOM WCDMA wireless Internet card (SIM card), the communication between development board and 3G network can be realized by USB interface.
Warning module 223 can further include: overspeed warning function, can be drive recorder by sub-OBD module acquires vehicle instantaneous velocity, whether exceeded the speed limit by software design patterns voice reminder driver.User can preset three speed limit promptings, and 120km/h is arranged for forcing speed limit.When the speed of a motor vehicle is less than 120km/h time, every default speed limit point only needs voice reminder driver current vehicle speed to arrive this speed; But if time the speed of a motor vehicle is more than 120km/h, voice message driver current vehicle speed, simultaneity factor is reported to the police.
The mobile detection module 222 mentioned in the present embodiment is movement detection device, and its working method and structure can be consistent with any one of the embodiment of Fig. 1 to Fig. 4.
Those skilled in the art can be well understood to, and for convenience and simplicity of description, the system of foregoing description, the specific works process of device and unit, with reference to the corresponding process in preceding method embodiment, can not repeat them here.
In several embodiments that the application provides, should be understood that, disclosed system, apparatus and method, can realize by another way.Such as, device embodiment described above is only schematic, such as, the division of described unit, be only a kind of logic function to divide, actual can have other dividing mode when realizing, such as multiple unit or assembly can in conjunction with or another system can be integrated into, or some features can be ignored, or do not perform.Another point, shown or discussed coupling each other or direct-coupling or communication connection can be by some interfaces, and the indirect coupling of device or unit or communication connection can be electrical, machinery or other form.
The described unit illustrated as separating component or can may not be and physically separates, and the parts as unit display can be or may not be physical location, namely can be positioned at a place, or also can be distributed in multiple network element.Some or all of unit wherein can be selected according to the actual needs to realize the object of the present embodiment scheme.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, also can be that the independent physics of unit exists, also can two or more unit in a unit integrated.Above-mentioned integrated unit both can adopt the form of hardware to realize, and the form of SFU software functional unit also can be adopted to realize.
If described integrated unit using the form of SFU software functional unit realize and as independently production marketing or use time, can be stored in a computer read/write memory medium.Based on such understanding, the part that technical scheme of the present invention contributes to prior art in essence in other words or all or part of of this technical scheme can embody with the form of software product, this computer software product is stored in a storage medium, comprising some instructions in order to make a computer equipment (can be personal computer, server, or the network equipment etc.) perform all or part of step of method described in each embodiment of the present invention.And aforesaid storage medium comprises: USB flash disk, portable hard drive, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. various can be program code stored medium.
The above, above embodiment only in order to technical scheme of the present invention to be described, is not intended to limit; Although with reference to previous embodiment to invention has been detailed description, those of ordinary skill in the art is to be understood that: it still can be modified to the technical scheme described in foregoing embodiments, or carries out equivalent replacement to wherein portion of techniques feature; And these amendments or replacement, do not make the essence of appropriate technical solution depart from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (10)
1. a mobile detection method, is characterized in that, comprising:
The background model corresponding with background image by the realtime graphic of image acquisition device is carried out pixel coupling, determine non-matching pixel, if described non-matching pixel exceedes preset threshold value, then determine that the object that exists in described realtime graphic moves, and trigger described image collecting device continuous collecting image.
2. mobile detection method according to claim 1, it is characterized in that, the background model corresponding with background image by the realtime graphic of image acquisition device is carried out pixel coupling, determine non-matching pixel, if described non-matching pixel exceedes preset threshold value, then determine that the object that exists in described realtime graphic moves, and also comprise before triggering described image collecting device continuous collecting image:
By background image described in described image acquisition device;
According to improvement vibe algorithm, image background modeling is carried out to pretreated described background image.
3. mobile detection method according to claim 2, is characterized in that, also comprises before carrying out image background modeling according to improvement vibe algorithm to pretreated described background image:
Described background image is carried out to the preliminary treatment of image quality optimization.
4. mobile detection method according to claim 3, it is characterized in that, the background model corresponding with background image by the realtime graphic of image acquisition device is carried out pixel coupling, determine non-matching pixel, if described non-matching pixel exceedes preset threshold value, then determine that the object that exists in described realtime graphic moves, and also comprise before triggering described image collecting device continuous collecting image:
By realtime graphic described in described image acquisition device, and the preliminary treatment of image quality optimization will be carried out to described realtime graphic;
Preset picture area differentiating and processing is carried out to described realtime graphic, described image is divided into described region of interest and described non-region of interest.
5. mobile detection method according to claim 4, it is characterized in that, the background model corresponding with background image by the realtime graphic of image acquisition device is carried out pixel coupling, determine non-matching pixel, if described non-matching pixel exceedes preset threshold value, then determine that the object that exists in described realtime graphic moves, and trigger described image collecting device continuous collecting image and specifically comprise:
The background model corresponding with background image by the realtime graphic of image acquisition device is carried out pixel coupling, determines described non-matching pixel;
Obtain the pixel of the corresponding described region of interest of all described non-matching pixels and the pixel of described non-region of interest;
Weighting process corresponding is with it carried out to the pixel of described region of interest and the pixel of described non-region of interest;
Calculate the pixel total value of the described region of interest after weighting process and described non-region of interest;
Judge whether described pixel total value exceedes described preset threshold, if so, then determine that the object that exists in described realtime graphic moves, and trigger described image collecting device continuous collecting image.
6. a movement detection device, is characterized in that, comprising:
Judging unit, for the background model corresponding with background image by the realtime graphic of image acquisition device is carried out pixel coupling, determine non-matching pixel, if described non-matching pixel exceedes preset threshold value, then determine that the object that exists in described realtime graphic moves, and trigger described image collecting device continuous collecting image.
7. movement detection device according to claim 6, is characterized in that, described movement detection device also comprises:
Image acquisition units, for passing through background image described in described image acquisition device;
Modeling unit, for carrying out image background modeling according to improvement vibe algorithm to pretreated described background image.
8. movement detection device according to claim 7, is characterized in that, described movement detection device also comprises:
First graphics processing unit, for carrying out the preliminary treatment of image quality optimization to described image.
9. movement detection device according to claim 8, is characterized in that, described movement detection device also comprises:
Second image acquisition units, for by realtime graphic described in described image acquisition device, and carrying out the preliminary treatment of image quality optimization to described realtime graphic;
Zoning unit, for carrying out preset picture area differentiating and processing to described realtime graphic, is divided into described region of interest and described non-region of interest by described image.
10. movement detection device according to claim 9, is characterized in that, judging unit specifically comprises:
Coupling subelement, for the background model corresponding with background image by the realtime graphic of image acquisition device is carried out pixel coupling, determines described non-matching pixel;
Obtain subelement, for the pixel of the pixel and described non-region of interest that obtain the corresponding described region of interest of all described non-matching pixels;
Weighting subelement, for carrying out weighting process corresponding with it to the pixel of described region of interest and the pixel of described non-region of interest;
Computation subunit, for calculating the pixel total value of the described region of interest after weighting process and described non-region of interest;
Judgment sub-unit, for judging whether described pixel total value exceedes described preset threshold, if so, then determines that the object that exists in described realtime graphic moves, and triggers described image collecting device continuous collecting image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510217838.0A CN104954738A (en) | 2015-04-30 | 2015-04-30 | Mobile detecting method and mobile detecting device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510217838.0A CN104954738A (en) | 2015-04-30 | 2015-04-30 | Mobile detecting method and mobile detecting device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104954738A true CN104954738A (en) | 2015-09-30 |
Family
ID=54169037
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510217838.0A Pending CN104954738A (en) | 2015-04-30 | 2015-04-30 | Mobile detecting method and mobile detecting device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104954738A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105611252A (en) * | 2015-12-31 | 2016-05-25 | 浙江大华技术股份有限公司 | Video recording method and device |
| WO2017084075A1 (en) * | 2015-11-19 | 2017-05-26 | 深圳市锐明技术股份有限公司 | Method and apparatus for switching region of interest |
| CN108492335A (en) * | 2018-03-27 | 2018-09-04 | 长春理工大学 | A kind of double camera perspective distortion bearing calibration and system |
| CN110675527A (en) * | 2019-09-28 | 2020-01-10 | 孔华 | On-site prevention device for porcelain collision behavior |
| CN111063146A (en) * | 2019-12-18 | 2020-04-24 | 浙江大华技术股份有限公司 | Defense method and equipment for monitoring picture and storage device |
| CN111080985A (en) * | 2018-10-19 | 2020-04-28 | Tcl新技术（惠州）有限公司 | Wearable device based anti-fatigue alarm method, wearable device and storage medium |
| TWI695343B (en) * | 2019-05-06 | 2020-06-01 | 中華電信股份有限公司 | Automatic labeling method for detecting moving objects |
| WO2020151083A1 (en) * | 2019-01-24 | 2020-07-30 | 北京明略软件系统有限公司 | Region determination method and device, storage medium and processor |
| TWI746947B (en) * | 2018-05-04 | 2021-11-21 | 瑞典商安訊士有限公司 | A method for detecting motion in a video sequence, computer-readable medium, motion detecting component and camera |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1731855A (en) * | 2005-08-26 | 2006-02-08 | 北京中星微电子有限公司 | Movement detecting method |
| US20120194357A1 (en) * | 2003-05-05 | 2012-08-02 | American Traffic Solutions, Inc. | Traffic violation detection, recording, and evidence processing systems and methods |
| CN103956055A (en) * | 2014-05-15 | 2014-07-30 | 山西中创伟业科技有限公司 | Vehicle image capturing device and image capturing control method thereof |
| CN204117215U (en) * | 2014-09-15 | 2015-01-21 | 杭州雄迈信息技术有限公司 | Drive recorder |
| CN104574562A (en) * | 2013-10-29 | 2015-04-29 | 大连生容享科技有限公司 | Automobile data recorder |
-
2015
- 2015-04-30 CN CN201510217838.0A patent/CN104954738A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120194357A1 (en) * | 2003-05-05 | 2012-08-02 | American Traffic Solutions, Inc. | Traffic violation detection, recording, and evidence processing systems and methods |
| CN1731855A (en) * | 2005-08-26 | 2006-02-08 | 北京中星微电子有限公司 | Movement detecting method |
| CN104574562A (en) * | 2013-10-29 | 2015-04-29 | 大连生容享科技有限公司 | Automobile data recorder |
| CN103956055A (en) * | 2014-05-15 | 2014-07-30 | 山西中创伟业科技有限公司 | Vehicle image capturing device and image capturing control method thereof |
| CN204117215U (en) * | 2014-09-15 | 2015-01-21 | 杭州雄迈信息技术有限公司 | Drive recorder |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017084075A1 (en) * | 2015-11-19 | 2017-05-26 | 深圳市锐明技术股份有限公司 | Method and apparatus for switching region of interest |
| CN105611252A (en) * | 2015-12-31 | 2016-05-25 | 浙江大华技术股份有限公司 | Video recording method and device |
| CN105611252B (en) * | 2015-12-31 | 2019-05-24 | 浙江大华技术股份有限公司 | A kind of kinescope method and equipment of video |
| CN108492335A (en) * | 2018-03-27 | 2018-09-04 | 长春理工大学 | A kind of double camera perspective distortion bearing calibration and system |
| CN108492335B (en) * | 2018-03-27 | 2020-10-20 | 长春理工大学 | Method and system for correcting perspective distortion of double cameras |
| TWI746947B (en) * | 2018-05-04 | 2021-11-21 | 瑞典商安訊士有限公司 | A method for detecting motion in a video sequence, computer-readable medium, motion detecting component and camera |
| CN111080985A (en) * | 2018-10-19 | 2020-04-28 | Tcl新技术（惠州）有限公司 | Wearable device based anti-fatigue alarm method, wearable device and storage medium |
| WO2020151083A1 (en) * | 2019-01-24 | 2020-07-30 | 北京明略软件系统有限公司 | Region determination method and device, storage medium and processor |
| TWI695343B (en) * | 2019-05-06 | 2020-06-01 | 中華電信股份有限公司 | Automatic labeling method for detecting moving objects |
| CN110675527A (en) * | 2019-09-28 | 2020-01-10 | 孔华 | On-site prevention device for porcelain collision behavior |
| CN111063146A (en) * | 2019-12-18 | 2020-04-24 | 浙江大华技术股份有限公司 | Defense method and equipment for monitoring picture and storage device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104952121B (en) | A kind of automobile data recorder | |
| CN104952209A (en) | Driving prewarning method and device | |
| CN104954738A (en) | Mobile detecting method and mobile detecting device | |
| US11891023B1 (en) | Using camera data to manage a vehicle parked outside in cold climates | |
| CN110796834B (en) | Vehicle flooding alarm method and system, vehicle and readable storage medium | |
| CN101656023B (en) | Management method of indoor car park in video monitor mode | |
| CA3087048A1 (en) | Multiple operating modes to expand dynamic range | |
| CN100507970C (en) | Red light overriding detection system and method based on digital video camera | |
| US11140334B1 (en) | 940nm LED flash synchronization for DMS and OMS | |
| CN105306796A (en) | Night vision equipment with regular infrared illumination function and global shutter CMOS (Complementary Metal Oxide Semiconductor) sensor | |
| CN104134352A (en) | Video vehicle characteristic detection system and detection method based on combination of long exposure and short exposure | |
| US11659154B1 (en) | Virtual horizontal stereo camera | |
| CN106585530A (en) | Vehicle-mounted snapshooting device and control method thereof | |
| CN204883859U (en) | Intelligence theftproof vehicle event data recorder | |
| CN208538328U (en) | A kind of convolutional neural networks road condition monitoring device | |
| CN103632543A (en) | Intelligent cloud vehicle management system device | |
| US20220100795A1 (en) | Systems and methods for image retrieval | |
| CN204883858U (en) | Multi -functional vehicle event data recorder | |
| CN204883857U (en) | Driving recorder | |
| CN111277956A (en) | Method and device for collecting vehicle blind area information | |
| CN117376712A (en) | Method, device, equipment and storage medium for adjusting shooting parameters of vehicle-mounted camera | |
| CN112889271B (en) | Image processing method and device | |
| CN110866462A (en) | Behavior recognition system and method integrated in intelligent police car | |
| CN205809936U (en) | A kind of Vehicular intelligent control loop | |
| CN114445988A (en) | Unattended electronic sentinel capable of realizing intelligent control and working method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150930 |