WO2016024680A1 - Vehicle black box capable of real-time recognition of license plate of moving vehicle - Google Patents

Vehicle black box capable of real-time recognition of license plate of moving vehicle Download PDF

Info

Publication number
WO2016024680A1
WO2016024680A1 PCT/KR2015/001760 KR2015001760W WO2016024680A1 WO 2016024680 A1 WO2016024680 A1 WO 2016024680A1 KR 2015001760 W KR2015001760 W KR 2015001760W WO 2016024680 A1 WO2016024680 A1 WO 2016024680A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
license plate
image
information
data
Prior art date
Application number
PCT/KR2015/001760
Other languages
French (fr)
Korean (ko)
Inventor
이감연
Original Assignee
주식회사 엠브레인
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 주식회사 엠브레인 filed Critical 주식회사 엠브레인
Publication of WO2016024680A1 publication Critical patent/WO2016024680A1/en

Links

Images

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B62LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
    • B62DMOTOR VEHICLES; TRAILERS
    • B62D41/00Fittings for identifying vehicles in case of collision; Fittings for marking or recording collision areas
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60RVEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R1/00Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
    • B60R1/02Rear-view mirror arrangements
    • B60R1/04Rear-view mirror arrangements mounted inside vehicle
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/40Analysis of texture

Definitions

  • the present invention relates to a vehicle black box capable of real-time license plate recognition of a driving vehicle, and more particularly, to digital video using high-resolution digital video uncompressed data generated in real time when the license plate of a driving vehicle traveling on a road is photographed.
  • the present invention relates to a vehicle black box capable of real-time license plate recognition of a driving vehicle that improves the license plate recognition efficiency of a driving vehicle by extracting license plate information of the driving vehicle before compressing the file format.
  • Such a vehicle black box can record information before and after a crash in case of a traffic accident and provide information necessary to understand the situation. Also, it is equipped with a recording image storage function, a high pass function, and an emergency rescue signal function for convenience in real life. Providing.
  • the communication module is mounted on the vehicle black box, and the vehicle license plate information is extracted by using the digital video compressed data acquired from the vehicle black box and the license plate recognition technology of the parking control system, and the extracted license plate information is controlled. Efforts have been made to implement a technique for transmitting to the center.
  • the license plate photographed image of a running vehicle photographed in a black box has a problem that it is difficult to recognize a license plate of a criminal vehicle because the resolution is significantly lower than that of a stationary vehicle photographed by a parking control system.
  • a lens distortion phenomenon occurs as the lens frame goes closer to the frame of the captured image, and the resolution decreases.
  • a compressed image frame that is compressed and preserved in a digital video file format In the case of I-frame, the peripheral image of the frame, which has relatively more change than the frame center image, has a large amount of information of image data. Therefore, the loss of information amount of image data increases rapidly when compressing the image. There is a problem that it is difficult to recognize the license plate of the driving vehicle because the information amount of the image data necessary for the license plate recognition of the driving vehicle is insufficient.
  • the present invention has been made to solve the above problems, the present invention, by using the high-resolution digital video uncompressed data generated in real time by photographing the license plate of the vehicle, the vehicle of the driving vehicle before compression to a digital video file format It is an object of the present invention to provide a vehicle black box capable of real-time license plate recognition, which improves the license plate recognition efficiency of a running vehicle, compared to a technology of extracting license plate information by using digital video compressed data by extracting license plate information.
  • a vehicle black box capable of real-time license plate recognition of a driving vehicle is a vehicle black box attached to a specific vehicle having a camera lens and photographing a specific vehicle periphery, photographed through the camera lens.
  • An image sensor converting one image information into an electrical signal to generate a digital image signal;
  • An image processor which processes the digital image signal generated by the image sensor to generate digital video uncompressed data having an information amount corresponding to the image information around a specific vehicle;
  • a vehicle license plate information generating device for analyzing the digital video uncompressed data generated by the image processor to generate vehicle license plate information of a non-specified vehicle traveling around a specific vehicle; Combining driving information of a specific vehicle including vehicle license plate information of an unspecified vehicle generated by the vehicle license plate information generating device with the digital video uncompressed data generated by the image processor to generate driving video data of a specific vehicle, and the vehicle black
  • a controller for controlling the overall operation of the box;
  • An encoder for compressing the driving video data generated by the controller into a digital video file format
  • the apparatus for generating license plate information corresponds to a region of interest for extracting license plate information from each uncompressed image frame constituting the digital video uncompressed data generated by the image processor, and includes a color image image and a binary image image.
  • a ROI data selection unit for selecting one or more ROI data; And sequentially extracting a vehicle area, a license plate area, and a text area corresponding to the license plate information from the one or more ROI data selected by the ROI data selection unit, and then applying a character recognition algorithm to the text area and applying the characters constituting the license plate. It may include; ROI data processing unit for recognizing and generating license plate information consisting of text data.
  • the ROI data selection unit increases the license plate recognition speed by removing ROI data that is not necessary to generate vehicle license plate information when selecting one or more ROI data from each uncompressed image frame constituting the digital video uncompressed data. You can.
  • ROI data that is not necessary to generate the license plate information includes ROI data arranged above the horizon consisting of horizontal lines of vanishing points where lanes meet on each uncompressed image frame; ROI data including a text area having a text size of less than 15 pixels; And ROI data including a text area corresponding to the license plate information generated in the previous frame.
  • the ROI data processing unit compares the color image image constituting the ROI data selected by the ROI data selection unit with the feature points of the pre-analyzed vehicle and selects a vehicle region on each uncompressed image frame constituting the digital video uncompressed data.
  • a vehicle region extraction unit for extracting;
  • a license plate area extraction unit for extracting a license plate area using a binary image image constituting ROI data in the vehicle area extracted by the vehicle area extraction unit;
  • a character area recognition unit for separating a character area using a histogram from the number plate area extracted by the license plate area extraction unit;
  • a character code generator for generating a character code for text data corresponding to the license plate information by applying a character recognition algorithm to the character region extracted by the character region recognition unit.
  • the license plate area recognition unit compares the feature points of the binary image image with the pre-analyzed license plate, and the aspect ratio of the computed image and the pre-analyzed license plate obtained by sequentially performing a morphology operation and a BLOB operation on the binary image image.
  • the license plate area may be extracted by any of the methods of comparing the two.
  • the ROI data processor may further include a vehicle number tracking unit that tracks ROI data corresponding to the license plate information by using feature points of a previous frame and a current frame.
  • the ROI data processor may further include a character area restoration unit capable of restoring a character area including license plate information by applying a super resolution technique to a plurality of uncompressed image frames that are difficult to identify.
  • the control unit transmits the license plate information generated by the vehicle license plate information generating apparatus to the control center located at a remote location through the communication module or the crime vehicle information received from the control center and the unspecified vehicle generated by the vehicle license plate information generating apparatus. By comparing the license plate information of the crime can lookup the vehicle in real time.
  • a vehicle black box capable of real-time license plate recognition of a driving vehicle includes a memory for storing driving video digital compression data generated by the encoder;
  • a GPS module which communicates with a GPS satellite to obtain location information, time information, and route information included in driving information of the specific vehicle;
  • a touch panel unit which displays a driving screen of the specific vehicle and a playback screen of the driving video digital compression data stored in the memory, and an input menu for inputting emergency signals in case of a hit-off vehicle or emergency;
  • a shock detection signal is transmitted to the control unit so that the control unit stores driving information for a predetermined time and driving video digital compression data corresponding to the driving information in real time in the memory. part;
  • a calibration unit which checks and adjusts a horizontal state by using the acceleration sensor when the vehicle is attached.
  • the present invention provides a license plate information generating apparatus for extracting license plate information by using high-resolution digital video uncompressed data generated at the time of shooting. It is possible to prevent the lack of information of the lost image data, thereby improving the license plate recognition efficiency of the driving vehicle, and it is effective to provide a vehicle black box that can easily extract the vehicle number information using the photographed image while driving. .
  • the present invention has an effect of easily extracting the vehicle number information from the image taken while driving at high speed with an image processing unit for correcting the high-resolution digital video uncompressed data generated at the time of shooting to an optimal image.
  • the present invention provides a vehicle license plate by providing a ROI data selection unit inside the vehicle number generation device for selecting ROI data excluding the unnecessary area for recognizing the vehicle license plate of the driving vehicle among the frame areas constituting the high-resolution digital video uncompressed data Since it is possible to reduce the size of the ROI data required to recognize the license plate, it is possible to reduce the time required to recognize the license plate, thereby enabling the license plate recognition of the driving vehicle in real time.
  • the present invention by combining a plurality of frames difficult to identify by using a super resolution technique, a character area restoring unit capable of restoring a character corresponding to the vehicle number is provided inside the ROI data processing unit constituting the vehicle number generation device. It is effective to improve the license plate recognition efficiency.
  • the present invention includes a vehicle number tracking unit that tracks the frame coordinates of the ROI data from which the license plate information is recognized, each time the frame changes, to the ROI data processing unit constituting the vehicle license plate information generating apparatus. Since the specific area can be deleted from the ROI data selection target, the size of the ROI data selected by the ROI data selection unit can be reduced, thereby improving the license plate recognition speed of the driving vehicle.
  • the present invention is equipped with a communication module that can be connected to the mobile communication network, when the crime vehicle is inquired or hit by a short-distance accident in the near-by, when the immediate response is necessary to transmit the vehicle number information in real time to the control center It works.
  • FIG. 1 is a view showing the overall configuration of a vehicle black box capable of real-time license plate recognition of the driving vehicle according to an embodiment of the present invention.
  • FIG. 2 is a detailed configuration diagram of a vehicle license plate information generating device constituting the vehicle black box shown in FIG. 1.
  • FIG. 3 is a view for explaining ROI data removed by the ROI data selecting unit constituting the vehicle license plate information generating apparatus shown in FIG. 2.
  • FIG. 4 is a diagram illustrating separating a character area using a histogram in a character area recognition unit of the ROI data processor of the vehicle license plate information generating device shown in FIG. 2.
  • first and second are intended to distinguish one component from another component, and the scope of rights should not be limited by these terms.
  • first component may be named a second component, and similarly, the second component may also be named a first component.
  • an identification code (e.g., a, b, c, etc.) is used for convenience of description, and the identification code does not describe the order of the steps, and each step clearly indicates a specific order in context. Unless stated otherwise, they may occur out of the order noted. That is, each step may occur in the same order as specified, may be performed substantially simultaneously, or may be performed in the reverse order.
  • a vehicle black box capable of real-time license plate recognition of a driving vehicle relates to a vehicle black box attached to a specific vehicle with a camera lens and photographing the vicinity of the specific vehicle.
  • the license plate recognition efficiency of the driving vehicle can be improved by extracting the license plate information of the driving vehicle before compressing it into a digital video file format by using the high resolution digital video uncompressed data generated in real time during shooting.
  • the vehicle black foil capable of real-time license plate recognition of the driving vehicle according to the present invention because it can send and receive vehicle license plate information and criminal vehicle information in real time with the control centers such as police station, fire department and security company in real-time crime vehicle inquiry or emergency Can respond in real time in situations.
  • the region of interest described in the specification according to the present invention indicates a region necessary for image processing, and the data of the region corresponding to the region of interest is referred to as ROI data (region of interest).
  • the ROI is used when image processing is performed only on a specific area of the required part without applying image processing to the whole image, and a desired result can be obtained.In this case, only the partial area is processed instead of the whole area of the image. The time taken for image processing can be shortened.
  • the ROI is mainly extracted from the uncompressed image frame constituting the digital video uncompressed data.
  • the region of interest is specifically limited to the rectangular shape using the XY coordinate range.
  • various types of information may be additionally extracted and used as necessary.
  • FIG. 1 is a view showing the overall configuration of a vehicle black box capable of real-time license plate recognition of the driving vehicle according to an embodiment of the present invention.
  • the vehicle black box capable of real-time license plate recognition of the driving vehicle according to an embodiment of the present invention
  • the image sensor 10 the image processing unit 20, the vehicle number determination generating apparatus 100, the control unit 30, the encoder 40, and the communication module 50 may be included.
  • the image sensor 10 may generate a digital image signal by converting image information around the vehicle photographed through a camera lens of a vehicle black box into an electrical signal.
  • the image sensor 10 applied to the embodiment of the present invention serves to photograph a high-resolution image of the surroundings of the vehicle while driving, and can capture 20 frames or more per second at a HD level of 900,000 pixels or more.
  • the image sensor 10 used in the embodiment of the present invention may be a CMOS image sensor.
  • the CMOS image sensor is characterized in that the generation of electrical noise is reduced by reading the light-converted electrical signal, and the CCD image having a high voltage analog circuit is possible because it can be mass-produced compared to the CCD image sensor.
  • the manufacturing cost is low and the device size is small, so the power consumption is low.
  • a logic circuit can be manufactured in the same process so that the image processing circuit can be turned on-chip.
  • CMOS image sensor In the embodiment of the present invention, a CMOS image sensor is used, but a CMOS camera, a Charged Coupled Device (CCD) camera, or other imaging apparatus may be used depending on the purpose of use.
  • CCD Charged Coupled Device
  • the image processing unit 20 is a place for correcting and sharply processing an image captured in a high speed driving state by using an image processing technique, and processing a digital image signal generated by the image sensor 10 while driving.
  • the digital video uncompressed data having a relatively high resolution compared to the compressed state having an information amount corresponding to the image information around the specific vehicle.
  • the image processor 20 may use various image processing techniques as follows to overcome a phenomenon in which an image shakes when a moving object is photographed at a high speed in a driving vehicle.
  • the image processing unit 20 includes a camera control function for controlling the setting of the image sensor 10 and the aperture and the filter, and includes a function for controlling the automatic exposure to perform camera exposure according to the amount of light. It can be optimally controlled, and it can be adjusted to look the same regardless of the light source even if the color of the object is affected by the light source, including automatic color adjustment function.
  • the color of the license plate can be an important factor in determining the license plate area to be described later, it is possible to improve the license plate recognition rate by preventing the color change according to the light source with the automatic color control function.
  • the image processing unit 20 has a sensor dynamic range amplifier function, and when the relatively dark and bright areas exist simultaneously in the captured image, the dark areas are lighter and the bright areas are slightly darker. The area can be clearly seen at the same time, and this can be image processing to make the relatively dark portion of the license plate brighter because the license plate of the vehicle running in front of the backlight can be shaded and the recognition rate can be reduced.
  • the image processing unit 20 may have a noise suppression function.
  • the analog signal of the image sensor 10 may be amplified and used in order to secure a clear image in a low light environment, and since the unwanted noise is also amplified together, the quality of the acquired image may be significantly degraded.
  • a digital signal processing technology for suppressing noise may be used.
  • the image processing unit 20 may include a sharpness improving function to emphasize the outline of the photographed object. In general, if the noise is removed for noise suppression, the contour may disappear together.
  • the camera lens used in the vehicle black box as in the embodiment of the present invention uses a wide-angle lens having an angle of view of 100 degrees or more, when using a wide-angle lens, the geometric distortion occurs as the distance from the center of the lens becomes difficult to recognize the image. can do.
  • the amount of light passing through the lens center portion and the lens outer portion may be darker than the lens center.
  • the image processor 20 includes a function of correcting lens distortion, and may correct brightness according to distance toward the outside of the lens from the center of the lens.
  • the image processing unit 20 applied to the embodiment of the present invention has a function of automatically setting various parameters to automatically obtain an optimal image by automatically recognizing an environment such as backlight, nighttime, and rainy weather, and performing the automatic operation. It may be formed of an ISP (Image Signal Proceesor).
  • ISP Image Signal Proceesor
  • the vehicle black box according to the embodiment of the present invention includes an image processing unit for correcting high-resolution digital video uncompressed data generated during shooting to an optimal image, thereby easily obtaining vehicle number information from an image taken while driving at high speed. Can be extracted.
  • the vehicle license plate information generating apparatus 100 analyzes the digital video uncompressed data generated by the image processing unit 20 to drive around a specific vehicle or vehicle license plate information of an adjacent unspecified vehicle. Can be generated.
  • the vehicle license plate information generating apparatus 100 may recognize the vehicle number using a specific uncompressed image frame constituting the digital video uncompressed data generated by the image processor 20. Compared to image analysis based on I-frames (JPEG) constituting the compressed image frame, the vehicle number can be easily recognized because of the relatively high resolution and a large amount of information of the image information.
  • JPEG I-frames
  • the control unit 30 serves to control the overall operation of the vehicle black box according to an embodiment of the present invention, and generates the license plate information in the digital video uncompressed data generated by the image processing unit 20.
  • the driving video data of the specific vehicle may be generated by combining driving information of the specific vehicle including the license plate information of the unspecified vehicle generated by the apparatus 100.
  • control unit 30 transmits the license plate information generated by the vehicle license plate information generating apparatus 100 to the control center located at a remote location through the communication module 50 or the crime vehicle information received from the control center and the criminal vehicle search can be performed in real time by comparing the license plate information of the unspecified vehicle generated by the license plate information generating device.
  • the encoder 40 may generate driving video digital compression data by compressing the driving video data generated by the control unit 30 into a digital video file format.
  • the communication module 50 transmits the driving moving picture digital compression data generated by the encoder 40 to a remote control center or receives crime vehicle information from the remote control center under the control of the controller 30. can do.
  • the communication module 50 may transmit the license plate information to the remote control center, and can receive and receive various control signal information from the remote control center, wired communication module and One or more of the wireless communication modules can be implemented to communicate with the control center.
  • the communication module 50 may be implemented as a communication module for mobile communication supporting the LTE modem method or the CDMA method.
  • the black box for a vehicle includes a communication module that can be connected to a mobile communication network, and when a crime vehicle is inquired or a hit-and-shoot accident occurs in a short distance, an immediate response is required in a control center. Vehicle number information can be transmitted.
  • the vehicle black box capable of real-time license plate recognition of the driving vehicle according to an embodiment of the present invention
  • the unit 90 may further include a calibration unit 200.
  • the memory 60 may store driving video digital compression data generated by the encoder 40, and the GPS module 70 communicates with a GPS satellite to include in driving information of a specific vehicle.
  • the location information, time information, and route information can be obtained.
  • the memory 60 may serve as a storage space for storing various data and a control program for controlling the vehicle black box as well as a moving video.
  • the touch panel unit 80 may display a driving screen of a specific vehicle, a playback screen of the moving video digital compression data stored in the memory, and an input menu for inputting an emergency signal in case of an emergency vehicle or an emergency vehicle.
  • the touch panel unit 80 may display a vehicle number recognized as a crime vehicle under the control of the controller 30, and may be implemented as an LCD display device and an LED display screen interlocked with a separate input device. have.
  • the shock detection unit 90 includes an impact sensor to generate an event when it detects a shock greater than a predetermined reference value and transmits an impact detection signal to the control unit 30 to cause the control unit 30 to perform a memory 60 in real time. ) May store the driving information for a predetermined time and the driving video digital compression data corresponding to the driving information.
  • the calibration unit 200 may check the horizontal state by using the acceleration sensor when the vehicle is attached.
  • the calibration unit 200 may serve to inform the user of a horizontal state by using an acceleration sensor so that license plate recognition can be performed at an optimal state when the camera is installed.
  • the calibration unit 200 extracts camera parameters inside and outside the camera and outputs them to the touch panel by using lane intervals or vehicle widths of the driving video digital compression data stored in the memory.
  • the character can be adjusted in a state where it can be recognized.
  • FIG. 2 is a detailed configuration diagram of a vehicle license plate information generating device constituting the vehicle black box shown in FIG. 1.
  • the vehicle license plate information generating device 100 constituting a vehicle black box capable of real-time license plate recognition of the driving vehicle according to an embodiment of the present invention
  • ROI data selection unit 110 and ROI data processing unit 120 may be provided.
  • the ROI data selector 110 may include one or more ROI data shown in FIG. 3 described below in each uncompressed image frame constituting the digital video uncompressed data generated by the image processor 20. You can choose.
  • the ROI data which indicates a region of interest for extracting the license plate information, includes a color image image and a binary image image and may be extracted from each uncompressed image frame.
  • the RO data selection unit 110 may perform various operations for improving the accuracy in reducing the amount of calculation and extracting and recognizing license plate information in the ROI data processing unit 120 to be described later.
  • the ROI data selection unit 110 may change the size of the captured image, change the color image into a GRAY image as necessary, perform image binarization, and extract the outline. It may serve to perform preprocessing on ROI data obtained from uncompressed data.
  • the ROI data selector 110 may additionally extract lanes from the ROI data obtained from the uncompressed video data, track license plate information identified in a previous image, extract vanishing points, and configure an image.
  • the non-road area can be removed from the background area.
  • the ROI data selection unit 110 an optical element required for the camera lens and the image sensor to calculate the coordinate position and size in the image in order to correct the installation position corresponding to the lens of various angles of view and ensure the camera vision Can be extracted or calculated.
  • the ROI data that is not necessary to generate the license plate information in the ROI data selection unit 110 may be removed, and a detailed description thereof will be described later with reference to FIG. 3.
  • the ROI data processor 120 may sequentially extract a vehicle area, a license plate area, and a character area corresponding to the vehicle license plate information from one or more ROI data selected by the ROI data selector 110.
  • the ROI data processor 120 may recognize a character constituting the license plate by applying a character recognition algorithm to the character region sequentially extracted, and may generate vehicle license plate information consisting of text data.
  • the ROI data processing unit 120 as shown in the figure, vehicle area extraction unit 121, license plate area extraction unit 122, character area recognition unit 123, character code generation unit 124, The vehicle number tracking unit 125 and the character area restoration unit 126 may be included.
  • the vehicle region extraction unit 121 compares the color image image constituting the ROI data selected by the ROI data selection unit 110 with the feature points of the pre-analyzed vehicle and compares the digital video uncompressed data.
  • a vehicle region corresponding to reference numeral ROI-1 of FIG. 3 may be extracted on each of the uncompressed image frames.
  • the vehicle region extracting unit 121 may extract only a vehicle region as an XY coordinate range of a frame by judging only whether a vehicle is present and extract only a single vehicle region as a representative vehicle when the vehicle region is repeatedly extracted at an adjacent point. have.
  • the license plate area extraction unit 122 uses a binary image image constituting the ROI data in the vehicle area extracted by the vehicle area extraction unit 121 and corresponds to the reference plate ROI-2 of FIG. 3. The area can be extracted.
  • the license plate area recognition unit 122 a method for comparing the feature points of the binary image image and the pre-analyzed license plate, and the operation image and pre-analyzed license plate obtained by sequentially performing a morphology operation and a BLOB operation on the binary image image
  • the license plate area may be extracted by any of the methods of comparing the aspect ratios of.
  • the license plate area recognition unit 122 may use an algorithm for extracting whether the license plate is recognized using a pedestrian recognition (HOG), a face recognition (HAAR), or a slope.
  • HOG pedestrian recognition
  • HAAR face recognition
  • slope a slope
  • the character area recognition unit 123 may separate the character area from the license plate area extracted by the license plate area recognition unit 122 using a histogram, which will be described in detail later with reference to FIG. 4.
  • the character code generation unit 124 may generate a character code for text data corresponding to the vehicle license plate information by applying a character recognition algorithm to the character area extracted by the character area recognition unit 123.
  • the vehicle number tracking unit 125 shown in the drawing is configured to reduce ROI data required for license plate recognition, and uses CAM SHIFT and OPTICAL FLOWER algorithms using reference points of previous and current frames constituting an uncompressed image frame. Can be used to track the ROI data corresponding to the license plate information.
  • the vehicle number tracking unit 125 tracks the ROI data by calculating the amount of movement information of the license plate area in the previous frame and the current frame, and checks the movement amount of each pixel constituting the frame after inspecting the movement area of the reference point. Can be calculated.
  • the character area restoring unit 126 may restore a character area including license plate information by applying a super resolution technique to a plurality of uncompressed image frames that are difficult to identify.
  • the vehicle black box according to the embodiment of the present invention can extract the license plate information by using the digital video uncompressed data, thereby preventing the lack of information of the missing image data and easily extracting the vehicle number information.
  • a character area restoring unit capable of restoring a character corresponding to the vehicle number may be provided inside the ROI data processing unit constituting the vehicle number generation device to improve license plate recognition efficiency.
  • FIG. 2 The apparatus for generating license plate information shown in FIG. 2 will be described in more detail with reference to FIGS. 3 to 4 as follows.
  • FIG. 3 is a view for explaining ROI data removed by the ROI data selecting unit constituting the vehicle license plate information generating apparatus shown in FIG. 2.
  • a plurality of ROIs may be present in each of the uncompressed image frames constituting the digital video uncompressed data generated by the image processor 20 of FIG. 1. have.
  • the ROI may be recognized only if the ROI is located within a specific range due to the characteristics of the vehicle black box having the wide-angle camera lens.
  • the ROI data selection unit 110 selects the ROI data from each uncompressed image frame constituting the digital video uncompressed data, if the ROI data that is not necessary to generate the license plate information can be removed, the license plate recognition is performed. You can increase the speed.
  • a region of interest ROI which is not necessary for generating license plate information, is disposed in the vehicle number tracking unit 125 of FIG.
  • the vehicle number tracking unit 125 of FIG. By tracking to the region of interest already recognized in the previous frame, and located in a position outside the limit line that can be identified by the license plate has a size of less than 15 pixels difficult to recognize as a character code in the character code generation unit 124 of FIG. to be.
  • the ROI data which is not necessary for generating the license plate information in the ROI data selection unit 110, is disposed above the horizon line consisting of horizontal lines of vanishing points where the lanes meet on each uncompressed image frame.
  • the ROI data may include ROI data, a ROI data including a character area having a character size of less than 15 pixels, and ROI data including a character area corresponding to vehicle license plate information generated in a previous frame.
  • the vehicle black box capable of real-time license plate recognition of the driving vehicle includes ROI data necessary for recognizing the license plate except for unnecessary areas among frame regions constituting high-resolution digital video uncompressed data.
  • the size of the ROI data selected by the ROI data selection unit can be reduced by tracking the frame coordinates of the ROI data in which the license plate information is recognized, and changing the frame. Can be.
  • FIG. 4 is a diagram illustrating separating a character area using a histogram in a character area recognition unit of the ROI data processor of the vehicle license plate information generating device shown in FIG. 2.
  • the character area recognition unit 123 of FIG. 2 may separate a character area using a histogram from the license plate area ROI-2 of FIG. 3 extracted by the license plate area extraction unit 122. Can be.
  • the upper and lower character areas of the license plate area can be separated by the reference numeral Yb, and then the individual character areas for each number can be separated by the reference numerals a to m.
  • the character code generation unit 124 of FIG. 2 may generate a character code for text data corresponding to the license plate information by applying a character recognition algorithm to the character area extracted by the character area recognition unit 123. .
  • the character code generation unit 124 generates a character code corresponding to the license plate information by using a conventional character recognition method used in the parking control system, or the separated character area neural network, SVM, HMM, etc. Character recognition can be performed using the algorithm of, and can be provided with a function to check whether the recognized character meets the character standard of the license plate.
  • the present invention is provided by a vehicle license plate information generating apparatus for extracting license plate information by using high-resolution digital video uncompressed data generated at the time of shooting, which is lost when the captured image is compressed into a digital movie file format.
  • the lack of information amount of the image data can be prevented, thereby improving the license plate recognition efficiency of the driving vehicle, thereby providing a vehicle black box that can easily extract the vehicle number information using the photographed image of the driving state.
  • the present invention has an effect of easily extracting the vehicle number information from the image taken while driving at high speed with an image processing unit for correcting the high-resolution digital video uncompressed data generated at the time of shooting to an optimal image.
  • the present invention provides a vehicle license plate by providing a ROI data selection unit inside the vehicle number generation device for selecting ROI data excluding the unnecessary area for recognizing the vehicle license plate of the driving vehicle among the frame areas constituting the high-resolution digital video uncompressed data Since it is possible to reduce the size of the ROI data required to recognize the license plate, it is possible to reduce the time required to recognize the license plate, thereby enabling the license plate recognition of the driving vehicle in real time.
  • the present invention by combining a plurality of frames difficult to identify by using a super resolution technique, a character area restoring unit capable of restoring a character corresponding to the vehicle number is provided inside the ROI data processing unit constituting the vehicle number generation device. It is effective to improve the license plate recognition efficiency.
  • the present invention includes a vehicle number tracking unit that tracks the frame coordinates of the ROI data from which the license plate information is recognized, each time the frame changes, to the ROI data processing unit constituting the vehicle license plate information generating apparatus. Since the specific area can be deleted from the ROI data selection target, the size of the ROI data selected by the ROI data selection unit can be reduced, thereby improving the license plate recognition speed of the driving vehicle.
  • the present invention is equipped with a communication module that can be connected to the mobile communication network, when the crime vehicle is inquired or hit by a short-distance accident in the near-by, when the immediate response is necessary to transmit the vehicle number information in real time to the control center It works.
  • the present invention can be used in the field of manufacturing a vehicle black box.

Abstract

The present invention relates to a vehicle black box capable of real-time recognition of a license plate of a moving vehicle and, more particularly, to a vehicle black box capable of real-time recognition of a license plate of a moving vehicle, the black box comprising: an image processing unit for processing a digital image signal generated by an image sensor to thereby generate non-compressed digital video data having an information quantity corresponding to image information of the surroundings of a specific vehicle; a vehicle license plate information generating device for analyzing the non-compressed digital video data generated by the image processing unit to thereby generate vehicle license plate information of a non-specific vehicle which is driven in the surroundings of, or is adjacent to the specific vehicle; and a control unit for combining the non-compressed digital video data generated by the image processing unit with driving information of the specific vehicle including the vehicle license plate information of the non-specific vehicle generated by the vehicle license plate information generating device, to thereby generate driving video data of the specific vehicle. The vehicle black box extracts vehicle license plate information of a moving vehicle, prior to compression in digital video file format, using high resolution non-compressed digital video data, generated in real time when photographing a license plate of a moving vehicle traveling on the road, thereby increasing recognition efficiency of a license plate of a moving vehicle.

Description

주행차량의 번호판 인식이 실시간으로 가능한 차량용 블랙박스Vehicle black box for real-time license plate recognition
본 발명은 주행차량의 번호판 인식이 실시간으로 가능한 차량용 블랙박스에 관한 것으로서, 더욱 상세하게는, 도로에서 주행하는 주행차량의 번호판 촬영시 실시간으로 생성되는 고해상도의 디지털동영상 비압축데이터를 이용하여 디지털동영상 파일 포맷으로 압축하기 전에 주행차량의 차량번호판정보를 추출함으로써 주행중인 차량의 번호판 인식효율을 향상시킨 주행차량의 번호판 인식이 실시간으로 가능한 차량용 블랙박스에 관한 것이다.The present invention relates to a vehicle black box capable of real-time license plate recognition of a driving vehicle, and more particularly, to digital video using high-resolution digital video uncompressed data generated in real time when the license plate of a driving vehicle traveling on a road is photographed. The present invention relates to a vehicle black box capable of real-time license plate recognition of a driving vehicle that improves the license plate recognition efficiency of a driving vehicle by extracting license plate information of the driving vehicle before compressing the file format.
최근들어 교통사고발생시 정확한 피해원인을 도출하기 위하여 자동차용 영상 사고기록장치(EDR ; Event Data Recoder)로 사용되는 블랙박스가 차량에 장착되는 것이 보편화되고 있다.Recently, in order to derive the exact cause of damage in a traffic accident, it is common to mount a black box which is used as an event data recorder (EDR) for a vehicle.
이와 같은 차량용 블랙박스는 교통사고를 당할경우 충돌 전후의 사고를 기록해 사고 정황 파악에 필요한 정보를 제공할 수 있고, 촬영영상저장 기능, 하이패스 기능, 및 긴급구조신호 기능을 구비하여 실생활에 편의를 제공하고 있다.Such a vehicle black box can record information before and after a crash in case of a traffic accident and provide information necessary to understand the situation. Also, it is equipped with a recording image storage function, a high pass function, and an emergency rescue signal function for convenience in real life. Providing.
한편, 최근들어 차량용 블랙박스에 저장된 디지털동영상 압축데이터를 이용하여 범죄차량을 조회하거나 파악하는 기술이 제안되고 있다. On the other hand, recently, a technique for searching or identifying a criminal vehicle using digital video compressed data stored in a vehicle black box has been proposed.
그런데, 종래기술에 따른 차량용 블랙박스를 이용하여 범죄차량을 조회하거나 파악하는 경우에는, 촬영된 디지털동영상 압축데이터를 메모리에 기록하여 보존한 다음 범죄차량의 자동차 번호를 숙지하고 보존된 데이터와 일일이 비교하여 수동으로 판독하기 때문에 지근거리에서 뺑소니 사고가 발생하거나 주행중에 범죄차량이 지나가더라도 즉각적인 대응이 어렵고 외부충격에 의한 데이터 손상시에 데이터 판독이 불가능한 문제점이 있었다.However, in the case of querying or grasping a criminal vehicle using a black box for a vehicle according to the prior art, recorded and stored digital video compressed data is stored in a memory, and the car number of the criminal vehicle is known and compared with the stored data. Because it is read manually, it is difficult to immediately respond even if a hit accident occurs at close range or a crime vehicle passes while driving, and it is impossible to read data in case of data damage due to external shock.
이를 극복하기 위하여 차량용 블랙박스에 통신모듈을 장착한 다음, 차량용 블랙박스에서 획득한 디지털동영상 압축데이터와 주차관제시스템의 번호판 인식기술을 이용하여 차량번호판정보를 추출하고, 추출된 차량번호판정보를 관제센터로 전송하는 기술을 구현하기 위한 노력이 시도되고 있다.In order to overcome this problem, the communication module is mounted on the vehicle black box, and the vehicle license plate information is extracted by using the digital video compressed data acquired from the vehicle black box and the license plate recognition technology of the parking control system, and the extracted license plate information is controlled. Efforts have been made to implement a technique for transmitting to the center.
그러나, 블랙박스에서 촬영한 주행중인 차량의 번호판 촬영영상은 주차관제시스템에서 촬영되는 정지된 차량의 번호판 촬영영상에 비해 해상도가 현저히 떨어지기 때문에 범죄차량의 번호판을 인식하기 어려운 문제점이 있었다.However, the license plate photographed image of a running vehicle photographed in a black box has a problem that it is difficult to recognize a license plate of a criminal vehicle because the resolution is significantly lower than that of a stationary vehicle photographed by a parking control system.
또한, 차량용 블랙박스는 통상적으로 100도가 넘는 화각의 광각렌즈를 사용하므로 촬영영상의 프레임 주변으로 갈수록 렌즈왜곡 현상이 발생하여 해상도가 떨어지게 되고, 이때, 디지털동영상 파일포맷으로 압축 보존되는 압축이미지프레임(I-프레임)의 경우에 프레임 중앙영상보다 상대적으로 변화량이 많은 프레임의 주변영상은 영상데이터의 정보량이 많기 때문에 영상압축시 영상데이터의 정보량 손실이 중앙대비 급격히 많아지고 결과적으로 차량용 블랙박스의 좌우측으로 주행하는 차량의 번호판인식에 필요한 영상데이터의 정보량이 부족하여 주행차량의 번호판을 인식하기 어려운 문제점이 있었다. In addition, since a vehicle black box typically uses a wide-angle lens having an angle of view of more than 100 degrees, a lens distortion phenomenon occurs as the lens frame goes closer to the frame of the captured image, and the resolution decreases. In this case, a compressed image frame that is compressed and preserved in a digital video file format ( In the case of I-frame), the peripheral image of the frame, which has relatively more change than the frame center image, has a large amount of information of image data. Therefore, the loss of information amount of image data increases rapidly when compressing the image. There is a problem that it is difficult to recognize the license plate of the driving vehicle because the information amount of the image data necessary for the license plate recognition of the driving vehicle is insufficient.
한편, 앞서 상술한 번호인식에 필요한 영상데이터의 정보량부족 문제를 해결하기 위해서는 최대한 많은 프레임에 해당하는 디지털동영상 압축데이터를 확보해야 하지만, 이와 같이 많은 수의 프레임에 해당하는 디지털동영상 압축데이터를 이용할 경우에 차량번호판정보를 추출하는데 오랜시간이 걸려 실시간으로 주행차량의 차량번호판정보를 인식하기 어려운 문제점이 있었다. On the other hand, in order to solve the problem of lack of information of the image data required for the above-mentioned number, it is necessary to secure the digital video compressed data corresponding to as many frames as possible, but when using the digital video compressed data corresponding to a large number of frames as described above It took a long time to extract the license plate information on the vehicle, it was difficult to recognize the license plate information of the driving vehicle in real time.
따라서, 주행중인 차량의 번호판에 대한 차량번호 인식효율을 높일 수 있으면서 실시간으로 범죄차량의 차량번호조회를 가능하게 하는 현실적이고도 적용이 가능한 차량용 블랙박스에 관한 기술이 절실히 요구되고 있는 실정이다.Therefore, there is an urgent need for a technology related to a realistic and applicable vehicle black box that enables vehicle number lookup of a criminal vehicle in real time while improving vehicle number recognition efficiency of a license plate of a driving vehicle.
본 발명은 상기 문제점을 해결하기 위하여 안출된 것으로서, 본 발명은, 주행차량의 번호판을 촬영하여 실시간으로 생성되는 고해상도의 디지털동영상 비압축데이터를 이용하여 디지털동영상 파일 포맷으로 압축하기 전에 주행차량의 차량번호판정보를 추출함으로써 디지털동영상 압축데이터를 이용하여 차량번호판정보를 추출하는 기술에 비해 주행중인 차량의 번호판 인식효율을 향상시킨 주행차량의 번호판 인식이 실시간으로 가능한 차량용 블랙박스를 제공하는데 목적이 있다.The present invention has been made to solve the above problems, the present invention, by using the high-resolution digital video uncompressed data generated in real time by photographing the license plate of the vehicle, the vehicle of the driving vehicle before compression to a digital video file format It is an object of the present invention to provide a vehicle black box capable of real-time license plate recognition, which improves the license plate recognition efficiency of a running vehicle, compared to a technology of extracting license plate information by using digital video compressed data by extracting license plate information.
본 발명의 실시예에 따른 주행차량의 번호판 인식이 실시간으로 가능한 차량용 블랙박스는, 카메라렌즈를 구비한 채 특정차량에 부착되어 특정차량주변을 촬영하는 차량용 블랙박스에 있어서, 상기 카메라렌즈를 통하여 촬영한 영상정보를 전기적 신호로 변환하여 디지털영상신호를 생성하는 이미지센서와; 상기 이미지센서에서 생성된 디지털영상신호를 가공하여 특정차량주위의 영상정보에 대응되는 정보량을 갖는 디지털동영상 비압축데이터를 생성하는 영상처리부와; 상기 영상처리부에서 생성된 디지털동영상 비압축데이터를 분석하여 특정차량주위에서 주행하거나 인접한 불특정차량의 차량번호판정보를 생성하는 차량번호판정보 생성장치와; 상기 영상처리부에서 생성된 디지털동영상 비압축데이터에 상기 차량번호판정보 생성장치에서 생성된 불특정차량의 차량번호판정보를 포함하는 특정차량의 주행정보를 결합하여 특정차량의 주행동영상 데이터를 생성하고, 차량용 블랙박스의 전체동작을 제어하는 제어부와; 상기 제어부에서 생성된 주행동영상 데이터를 디지털동영상 파일포맷으로 압축하여 주행동영상 디지털압축데이터를 생성하는 엔코더부; 및 상기 제어부의 제어에 따라 상기 엔코더부에서 생성된 주행동영상 디지털압축데이터를 원격의 관제센터로 전송하거나 상기 원격의 관제센터로부터 범죄차량정보를 수신하는 통신모듈;을 포함할 수 있다.A vehicle black box capable of real-time license plate recognition of a driving vehicle according to an embodiment of the present invention is a vehicle black box attached to a specific vehicle having a camera lens and photographing a specific vehicle periphery, photographed through the camera lens. An image sensor converting one image information into an electrical signal to generate a digital image signal; An image processor which processes the digital image signal generated by the image sensor to generate digital video uncompressed data having an information amount corresponding to the image information around a specific vehicle; A vehicle license plate information generating device for analyzing the digital video uncompressed data generated by the image processor to generate vehicle license plate information of a non-specified vehicle traveling around a specific vehicle; Combining driving information of a specific vehicle including vehicle license plate information of an unspecified vehicle generated by the vehicle license plate information generating device with the digital video uncompressed data generated by the image processor to generate driving video data of a specific vehicle, and the vehicle black A controller for controlling the overall operation of the box; An encoder for compressing the driving video data generated by the controller into a digital video file format to generate driving video digital compression data; And a communication module for transmitting the driving moving picture digital compression data generated by the encoder to a remote control center or receiving crime vehicle information from the remote control center under the control of the controller.
상기 차량번호판정보 생성장치는, 상기 영상처리부에서 생성된 디지털동영상 비압축데이터를 구성하는 각각의 비압축이미지프레임에서 차량번호판정보를 추출하기 위한 관심영역에 대응되며 컬러영상이미지와 이진영상이미지를 포함하는 하나 이상의 ROI데이터를 선택하는 ROI데이터 선택부; 및 상기 ROI데이터 선택부에서 선택된 하나 이상의 ROI데이터로부터 차량번호판정보에 대응되는 차량영역, 번호판영역, 및 문자영역을 순차적으로 추출한 다음 상기 문자영역에 문자인식알고리즘을 적용하고 차량번호판을 구성하는 문자를 인식하여 텍스트데이터로 이루어진 차량번호판정보를 생성하는 ROI데이터 처리부;를 포함할 수 있다.The apparatus for generating license plate information corresponds to a region of interest for extracting license plate information from each uncompressed image frame constituting the digital video uncompressed data generated by the image processor, and includes a color image image and a binary image image. A ROI data selection unit for selecting one or more ROI data; And sequentially extracting a vehicle area, a license plate area, and a text area corresponding to the license plate information from the one or more ROI data selected by the ROI data selection unit, and then applying a character recognition algorithm to the text area and applying the characters constituting the license plate. It may include; ROI data processing unit for recognizing and generating license plate information consisting of text data.
상기 ROI데이터 선택부는, 상기 디지털동영상 비압축데이터를 구성하는 각각의 비압축이미지프레임에서 하나 이상의 ROI데이터를 선택하는 경우에 차량번호판정보를 생성하는데 필요하지 않은 ROI데이터를 제거하여 번호판 인식 속도를 증가시킬 수 있다.The ROI data selection unit increases the license plate recognition speed by removing ROI data that is not necessary to generate vehicle license plate information when selecting one or more ROI data from each uncompressed image frame constituting the digital video uncompressed data. You can.
상기 차량번호판정보를 생성하는데 필요하지 않은 ROI데이터는, 상기 각각의 비압축이미지프레임상에서 차선이 만나는 소실점의 수평선으로 이루어지는 지평선의 상측으로 배치되는 ROI데이터와; 문자크기가 15픽셀 미만인 문자영역을 포함하는 ROI데이타; 및 이전프레임에서 생성된 차량번호판정보에 대응되는 문자영역을 포함하는 ROI데이터;를 포함할 수 있다.ROI data that is not necessary to generate the license plate information includes ROI data arranged above the horizon consisting of horizontal lines of vanishing points where lanes meet on each uncompressed image frame; ROI data including a text area having a text size of less than 15 pixels; And ROI data including a text area corresponding to the license plate information generated in the previous frame.
상기 ROI데이터 처리부는, 상기 ROI데이터 선택부에서 선택된 ROI데이터를 구성하는 컬러영상이미지와 사전분석된 차량의 특징점을 비교하여 상기 디지털동영상 비압축데이터를 구성하는 각각의 비압축이미지프레임상에서 차량영역을 추출하는 차량영역추출부와; 상기 차량영역추출부에 의해 추출된 차량영역 내에서 ROI데이터를 구성하는 이진영상이미지를 이용하여 번호판영역을 추출하는 번호판영역추출부와; 상기 번호판영역추출부에 의해 추출된 번호판영역에서 히스토그램을 사용하여 문자영역을 분리하는 문자영역인식부; 및 상기 문자영역인식부에 의해 추출된 문자영역에 문자인식알고리즘을 적용하여 차량번호판정보에 해당하는 텍스트데이터용 문자코드를 생성하는 문자코드생성부;를 포함할 수 있다.The ROI data processing unit compares the color image image constituting the ROI data selected by the ROI data selection unit with the feature points of the pre-analyzed vehicle and selects a vehicle region on each uncompressed image frame constituting the digital video uncompressed data. A vehicle region extraction unit for extracting; A license plate area extraction unit for extracting a license plate area using a binary image image constituting ROI data in the vehicle area extracted by the vehicle area extraction unit; A character area recognition unit for separating a character area using a histogram from the number plate area extracted by the license plate area extraction unit; And a character code generator for generating a character code for text data corresponding to the license plate information by applying a character recognition algorithm to the character region extracted by the character region recognition unit.
상기 번호판영역인식부는, 상기 이진영상이미지와 사전분석된 번호판의 특징점을 비교하는 방법, 및 상기 이진영상이미지에 모폴로지 연산과 BLOB 연산을 순차적으로 수행하여 얻은 연산이미지와 사전분석된 번호판의 가로세로비율을 비교하는 방법 중 어느 하나의 방법으로 번호판영역을 추출할 수 있다.The license plate area recognition unit compares the feature points of the binary image image with the pre-analyzed license plate, and the aspect ratio of the computed image and the pre-analyzed license plate obtained by sequentially performing a morphology operation and a BLOB operation on the binary image image. The license plate area may be extracted by any of the methods of comparing the two.
상기 ROI데이터 처리부는, 이전프레임과 현재프레임의 특징점을 이용하여 차량번호판정보에 대응되는 ROI데이터를 추적하는 차량번호트래킹부;를 더 구비할 수 있다.The ROI data processor may further include a vehicle number tracking unit that tracks ROI data corresponding to the license plate information by using feature points of a previous frame and a current frame.
상기 ROI데이터 처리부는, 문자식별이 어려운 다수개의 비압축이미지프레임에 슈퍼레졸루션기법을 적용하여 차량번호판정보를 포함하는 문자영역을 복원할 수 있는 문자영역복원부;를 더 구비할 수 있다.The ROI data processor may further include a character area restoration unit capable of restoring a character area including license plate information by applying a super resolution technique to a plurality of uncompressed image frames that are difficult to identify.
상기 제어부는, 상기 통신모듈을 통해 원격지에 위치한 관제센터에 상기 차량번호판정보 생성장치에서 생성된 차량번호판정보를 송신하거나 관제센터로부터 수신하는 범죄차량정보와 상기 차량번호판정보 생성장치에서 생성된 불특정차량의 차량번호판정보를 비교하여 실시간으로 범죄차량조회를 할 수 있다.The control unit transmits the license plate information generated by the vehicle license plate information generating apparatus to the control center located at a remote location through the communication module or the crime vehicle information received from the control center and the unspecified vehicle generated by the vehicle license plate information generating apparatus. By comparing the license plate information of the crime can lookup the vehicle in real time.
본 발명의 실시예에 따른 주행차량의 번호판 인식이 실시간으로 가능한 차량용 블랙박스는, 상기 엔코더부에서 생성된 주행동영상 디지털압축데이터를 저장하는 메모리와; GPS위성과 통신하여 상기 특정차량의 주행정보에 포함되는 위치정보, 시간정보, 및 경로정보를 획득하는 GPS모듈과; 상기 특정차량의 주행정보와 상기 메모리에 저장된 주행동영상 디지털압축데이터의 재생화면 및 뺑소니차량이나 긴급상황시 응급신호를 입력하기 위한 입력메뉴를 표시하는 터치패널부와; 사전설정된 기준값 이상의 충격을 감지하는 경우 상기 제어부에 충격감지신호를 전송하여 제어부로 하여금 실시간으로 상기 메모리에 일정시간동안의 주행정보와 상기 주행정보에 대응되는 주행동영상 디지털압축데이터를 저장하게 하는 충격감지부; 및 차량부착시 가속도센서를 이용하여 수평상태를 체크하고 조절하는 캘리브레이션부;를 더 포함할 수 있다.A vehicle black box capable of real-time license plate recognition of a driving vehicle according to an embodiment of the present invention includes a memory for storing driving video digital compression data generated by the encoder; A GPS module which communicates with a GPS satellite to obtain location information, time information, and route information included in driving information of the specific vehicle; A touch panel unit which displays a driving screen of the specific vehicle and a playback screen of the driving video digital compression data stored in the memory, and an input menu for inputting emergency signals in case of a hit-off vehicle or emergency; In the event of detecting a shock equal to or greater than a predetermined reference value, a shock detection signal is transmitted to the control unit so that the control unit stores driving information for a predetermined time and driving video digital compression data corresponding to the driving information in real time in the memory. part; And a calibration unit which checks and adjusts a horizontal state by using the acceleration sensor when the vehicle is attached.
이상에서 설명한 바와 같이, 본 발명은, 촬영시 생성되는 고해상도의 디지털동영상 비압축데이터를 이용하여 차량번호판정보를 추출하는 차량번호판정보 생성장치를 구비함으로써 촬영영상이 디지털동영상 파일 포맷으로 압축하는 경우에 손실되는 영상데이터의 정보량부족을 방지할 수 있어 주행중인 차량의 번호판 인식효율을 향상시켜 주행중인 상태의 촬영영상을 이용하여 차량번호정보를 용이하게 추출할 수 있는 차량용 블랙박스를 제공하는 효과가 있다.As described above, the present invention provides a license plate information generating apparatus for extracting license plate information by using high-resolution digital video uncompressed data generated at the time of shooting. It is possible to prevent the lack of information of the lost image data, thereby improving the license plate recognition efficiency of the driving vehicle, and it is effective to provide a vehicle black box that can easily extract the vehicle number information using the photographed image while driving. .
또한, 본 발명은, 촬영시 생성되는 고해상도의 디지털동영상 비압축데이터를 최적의 영상으로 보정하는 영상처리부를 구비하여 고속으로 주행중에 촬영한 영상에서 차량번호정보를 용이하게 추출하는 효과가 있다.In addition, the present invention has an effect of easily extracting the vehicle number information from the image taken while driving at high speed with an image processing unit for correcting the high-resolution digital video uncompressed data generated at the time of shooting to an optimal image.
또한, 본 발명은, 고해상도의 디지털동영상 비압축데이터를 구성하는 프레임영역 중 주행차량의 차량번호판을 인식하는데 불필요한 영역을 제외한 ROI데이터를 선별하는 ROI데이터 선택부를 차량번호생성장치 내부에 구비함으로써 차량번호판을 인식하는데 필요한 ROI데이터의 크기를 줄일 수 있기 때문에 차량번호판 인식에 소요되는 시간을 감소시켜 주행차량의 번호판 인식이 실시간으로 가능하게 하는 효과가 있다.In addition, the present invention provides a vehicle license plate by providing a ROI data selection unit inside the vehicle number generation device for selecting ROI data excluding the unnecessary area for recognizing the vehicle license plate of the driving vehicle among the frame areas constituting the high-resolution digital video uncompressed data Since it is possible to reduce the size of the ROI data required to recognize the license plate, it is possible to reduce the time required to recognize the license plate, thereby enabling the license plate recognition of the driving vehicle in real time.
또한, 본 발명은, 문자식별이 어려운 다수개의 프레임을 슈퍼레졸루션기법을 이용하여 결합함으로써 차량번호에 해당하는 문자를 복원할 수 있는 문자영역복원부를 차량번호생성장치를 구성하는 ROI데이터 처리부 내부에 구비하여 번호판 인식효율을 향상시키는 효과가 있다. In addition, the present invention, by combining a plurality of frames difficult to identify by using a super resolution technique, a character area restoring unit capable of restoring a character corresponding to the vehicle number is provided inside the ROI data processing unit constituting the vehicle number generation device. It is effective to improve the license plate recognition efficiency.
게다가, 본 발명은, 차량번호판정보 생성장치를 구성하는 ROI데이터 처리부에 차량번호판정보가 인식된 ROI데이터의 프레임좌표를 프레임이 바뀔때마다 추적하는 차량번호트래킹부를 구비하여 이미 인식된 차량번호판정보에 해당하는 특정영역을 ROI데이터 선택대상에서 삭제 할 수 있기 때문에 ROI데이터 선택부에서 선별되는 ROI데이터의 크기를 줄일 수 있어 주행차량의 번호판 인식속도를 향상시키는 효과가 있다.Furthermore, the present invention includes a vehicle number tracking unit that tracks the frame coordinates of the ROI data from which the license plate information is recognized, each time the frame changes, to the ROI data processing unit constituting the vehicle license plate information generating apparatus. Since the specific area can be deleted from the ROI data selection target, the size of the ROI data selected by the ROI data selection unit can be reduced, thereby improving the license plate recognition speed of the driving vehicle.
뿐만 아니라, 본 발명은, 이동통신네트워크에 접속이 가능한 통신모듈을 구비하여 범죄차량이 조회되거나 지근거리에서 뺑소니 사고가 발생하여 즉각적인 대응이 필요할 경우에 관제센터에 실시간으로 차량번호정보를 전송할 수 있는 효과가 있다.In addition, the present invention is equipped with a communication module that can be connected to the mobile communication network, when the crime vehicle is inquired or hit by a short-distance accident in the near-by, when the immediate response is necessary to transmit the vehicle number information in real time to the control center It works.
도 1은 본 발명의 실시예에 따른 주행차량의 번호판 인식이 실시간으로 가능한 차량용 블랙박스의 전체구성을 나타내기 위한 도면이다.1 is a view showing the overall configuration of a vehicle black box capable of real-time license plate recognition of the driving vehicle according to an embodiment of the present invention.
도 2는 도 1에 도시된 차량용 블랙박스를 구성하는 차량번호판정보 생성장치의 세부구성도이다.FIG. 2 is a detailed configuration diagram of a vehicle license plate information generating device constituting the vehicle black box shown in FIG. 1.
도 3은 도 2에 도시된 차량번호판정보 생성장치를 구성하는 ROI데이터 선택부에서 제거되는 ROI데이터를 설명하기 위한 도면이다. FIG. 3 is a view for explaining ROI data removed by the ROI data selecting unit constituting the vehicle license plate information generating apparatus shown in FIG. 2.
도 4는 도 2에 도시된 차량번호판정보 생성장치를 구성하는 ROI데이터 처리부의 문자영역인식부에서 히스토그램을 사용하여 문자영역을 분리하는 것을 나타내는 도면이다. FIG. 4 is a diagram illustrating separating a character area using a histogram in a character area recognition unit of the ROI data processor of the vehicle license plate information generating device shown in FIG. 2.
본 발명에 관한 설명은 구조적 내지 기능적 설명을 위한 실시예에 불과하므로, 본 발명의 권리범위는 본문에 설명된 실시예에 의하여 제한되는 것으로 해석되어서는 아니 된다. 즉, 실시예는 다양한 변경이 가능하고 여러 가지 형태를 가질 수 있으므로 본 발명의 권리범위는 기술적 사상을 실현할 수 있는 균등물들을 포함하는 것으로 이해되어야 한다.Description of the present invention is only an embodiment for structural or functional description, the scope of the present invention should not be construed as limited by the embodiments described in the text. That is, since the embodiments may be variously modified and may have various forms, the scope of the present invention should be understood to include equivalents capable of realizing the technical idea.
한편, 본 발명에서 서술되는 용어의 의미는 다음과 같이 이해되어야 할 것이다.On the other hand, the meaning of the terms described in the present invention will be understood as follows.
"제1", "제2" 등의 용어는 하나의 구성요소를 다른 구성요소로부터 구별하기 위한 것으로, 이들 용어들에 의해 권리범위가 한정되어서는 아니 된다. 예를 들어, 제1 구성요소는 제2 구성요소로 명명될 수 있고, 유사하게 제2 구성요소도 제1 구성요소로 명명될 수 있다.Terms such as "first" and "second" are intended to distinguish one component from another component, and the scope of rights should not be limited by these terms. For example, the first component may be named a second component, and similarly, the second component may also be named a first component.
어떤 구성요소가 다른 구성요소에 "연결되어"있다고 언급된 때에는, 그 다른 구성요소에 직접적으로 연결될 수도 있지만, 중간에 다른 구성요소가 존재할 수도 있다고 이해되어야 할 것이다. 반면에, 어떤 구성요소가 다른 구성요소에 "직접 연결되어"있다고 언급된 때에는 중간에 다른 구성요소가 존재하지 않는 것으로 이해되어야 할 것이다. 한편, 구성요소들 간의 관계를 설명하는 다른 표현들, 즉 "~사이에"와 "바로 ~사이에" 또는 "~에 이웃하는"과 "~에 직접 이웃하는" 등도 마찬가지로 해석되어야 한다.When a component is referred to as being "connected" to another component, it should be understood that there may be other components in between, although it may be directly connected to the other component. On the other hand, when a component is referred to as being "directly connected" to another component, it should be understood that there is no other component in between. On the other hand, other expressions describing the relationship between the components, such as "between" and "immediately between" or "neighboring to" and "directly neighboring to", should be interpreted as well.
단수의 표현은 문맥상 명백하게 다르게 뜻하지 않는 한 복수의 표현을 포함하는 것으로 이해되어야 하고, "포함하다"또는 "가지다" 등의 용어는 설시된 특징, 숫자, 단계, 동작, 구성요소, 부분품 또는 이들을 조합한 것이 존재함을 지정하려는 것이며, 하나 또는 그 이상의 다른 특징이나 숫자, 단계, 동작, 구성요소, 부분품 또는 이들을 조합한 것들의 존재 또는 부가 가능성을 미리 배제하지 않는 것으로 이해되어야 한다.Singular expressions should be understood to include plural expressions unless the context clearly indicates otherwise, and terms such as "comprise" or "have" refer to features, numbers, steps, operations, components, parts, or parts thereof described. It is to be understood that the combination is intended to be present and does not exclude in advance the possibility of the presence or addition of one or more other features or numbers, steps, operations, components, parts or combinations thereof.
각 단계들에 있어 식별부호(예를 들어, a, b, c 등)는 설명의 편의를 위하여 사용되는 것으로 식별부호는 각 단계들의 순서를 설명하는 것이 아니며, 각 단계들은 문맥상 명백하게 특정 순서를 기재하지 않는 이상 명기된 순서와 다르게 일어날 수 있다. 즉, 각 단계들은 명기된 순서와 동일하게 일어날 수도 있고 실질적으로 동시에 수행될 수도 있으며 반대의 순서대로 수행될 수도 있다.In each step, an identification code (e.g., a, b, c, etc.) is used for convenience of description, and the identification code does not describe the order of the steps, and each step clearly indicates a specific order in context. Unless stated otherwise, they may occur out of the order noted. That is, each step may occur in the same order as specified, may be performed substantially simultaneously, or may be performed in the reverse order.
여기서 사용되는 모든 용어들은 다르게 정의되지 않는 한, 본 발명이 속하는 분야에서 통상의 지식을 가진 자에 의해 일반적으로 이해되는 것과 동일한 의미를 가진다. 일반적으로 사용되는 사전에 정의되어 있는 용어들은 관련 기술의 문맥상 가지는 의미와 일치하는 것으로 해석되어야 하며, 본 발명에서 명백하게 정의하지 않는 한 이상적이거나 과도하게 형식적인 의미를 지니는 것으로 해석될 수 없다.All terms used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. Generally, the terms defined in the dictionary used are to be interpreted as being consistent with the meanings in the context of the related art, and should not be interpreted as having ideal or excessively formal meanings unless clearly defined in the present invention.
본 발명에 따른 주행차량의 번호판 인식이 실시간으로 가능한 차량용 블랙박스는, 카메라렌즈를 구비한 채 특정차량에 부착되어 특정차량주변을 촬영하는 차량용 블랙박스에 관한 것으로서, 도로에서 주행하는 주행차량의 번호판 촬영시 실시간으로 생성되는 고해상도의 디지털동영상 비압축데이터를 이용하여 디지털동영상 파일 포맷으로 압축하기 전에 주행차량의 차량번호판정보를 추출함으로써 주행중인 차량의 번호판 인식효율을 향상시킬 수 있다.A vehicle black box capable of real-time license plate recognition of a driving vehicle according to the present invention relates to a vehicle black box attached to a specific vehicle with a camera lens and photographing the vicinity of the specific vehicle. The license plate recognition efficiency of the driving vehicle can be improved by extracting the license plate information of the driving vehicle before compressing it into a digital video file format by using the high resolution digital video uncompressed data generated in real time during shooting.
또한, 본 발명에 따른 주행차량의 번호판 인식이 실시간으로 가능한 차량용 블랙박는, 경찰서와 소방서 및 보안회사와 같은 관제센터와 차량번호판정보 및 범죄차량정보를 실시간으로 주고 받을 수 있기 때문에 범죄차량조회나 응급상황시 실시간으로 대응할 수 있다.In addition, the vehicle black foil capable of real-time license plate recognition of the driving vehicle according to the present invention, because it can send and receive vehicle license plate information and criminal vehicle information in real time with the control centers such as police station, fire department and security company in real-time crime vehicle inquiry or emergency Can respond in real time in situations.
한편, 본 발명에 따른 명세서에 기재된 관심영역은 영상처리에 필요한 영역을 가리키는 것으로 관심영역에 해당하는 영역의 데이터를 ROI데이터(관심영역데이터, Rigion of interest)라 한다.On the other hand, the region of interest described in the specification according to the present invention indicates a region necessary for image processing, and the data of the region corresponding to the region of interest is referred to as ROI data (region of interest).
관심영역은 영상전체에 영상처리를 적용하지 않고 필요한 부분의 특정영역에만 영상처리를 해도 원하는 결과를 얻을 수 있을 경우에 사용하며, 이와 같이 영상의 전체영역을 처리하는 대신 부분영역만 처리하는 경우에 영상처리에 걸리는 시간을 단축할 수 있다.The ROI is used when image processing is performed only on a specific area of the required part without applying image processing to the whole image, and a desired result can be obtained.In this case, only the partial area is processed instead of the whole area of the image. The time taken for image processing can be shortened.
본 발명에 따른 명세서에서, 관심영역은 주로 디지털동영상 비압축데이터를 구성하는 비압축이미지프레임에서 추출하는 영역으로 본 발명의 실시예에서는 XY좌표범위를 사용하여 구체적으로 직사각형 형태로 한정하여 사용한 것을 알 수 있으며 단순히 프레임의 좌표범위만을 가리키는 것이 아니라 필요에 따라 각종 정보를 추가로 추출하여 사용할 수 있다.In the specification according to the present invention, the ROI is mainly extracted from the uncompressed image frame constituting the digital video uncompressed data. In the embodiment of the present invention, it is understood that the region of interest is specifically limited to the rectangular shape using the XY coordinate range. In addition to simply indicating the coordinate range of the frame, various types of information may be additionally extracted and used as necessary.
이하, 첨부된 도면을 참조하여 본 발명의 실시예들을 설명하기로 한다.Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings.
도 1은 본 발명의 실시예에 따른 주행차량의 번호판 인식이 실시간으로 가능한 차량용 블랙박스의 전체구성을 나타내기 위한 도면이다.1 is a view showing the overall configuration of a vehicle black box capable of real-time license plate recognition of the driving vehicle according to an embodiment of the present invention.
도면에 도시된 바와 같이, 본 발명의 실시예에 따른 주행차량의 번호판 인식이 실시간으로 가능한 차량용 블랙박스는, 이미지센서(10), 영상처리부(20), 차량번호판정 생성장치(100), 제어부(30), 엔코더부(40),및 통신모듈(50)을 포함할 수 있다.As shown in the figure, the vehicle black box capable of real-time license plate recognition of the driving vehicle according to an embodiment of the present invention, the image sensor 10, the image processing unit 20, the vehicle number determination generating apparatus 100, the control unit 30, the encoder 40, and the communication module 50 may be included.
보다 상세하게는, 상기 이미지센서(10)는, 차량용 블랙박스의 카메라렌즈를 통하여 촬영한 차량주변의 영상정보를 전기적 신호로 변환하여 디지털영상신호를 생성할 수 있다.In more detail, the image sensor 10 may generate a digital image signal by converting image information around the vehicle photographed through a camera lens of a vehicle black box into an electrical signal.
본 발명의 실시예에 적용된 이미지센서(10)는, 주행중인 상태에서 차량주변을 고해상도의 영상으로 촬영하는 역할을 하는 것으로서 90만화소 이상 HD급 이상으로 초당 20프레임 이상을 촬영할 수 있다.The image sensor 10 applied to the embodiment of the present invention serves to photograph a high-resolution image of the surroundings of the vehicle while driving, and can capture 20 frames or more per second at a HD level of 900,000 pixels or more.
또한, 본 발명의 실시예에 사용된 이미지센서(10)는 CMOS 방식의 이미지센서가 사용될 수 있다.In addition, the image sensor 10 used in the embodiment of the present invention may be a CMOS image sensor.
일반적으로, CMOS방식의 이미지센서는, 광변환된 전기신호의 읽기에 의해서 전기 노이즈의 발생이 적어지는 특징이 있으며, CCD방식의 이미지센서에 비해 대량생산이 가능하기 때문에 고전압 아날로그 회로를 가지는 CCD 이미지 센서와 비교해서 제조 단가가 낮고 소자의 크기가 작아서 소비 전력이 적다는 장점이 있다.In general, the CMOS image sensor is characterized in that the generation of electrical noise is reduced by reading the light-converted electrical signal, and the CCD image having a high voltage analog circuit is possible because it can be mass-produced compared to the CCD image sensor. Compared to the sensor, the manufacturing cost is low and the device size is small, so the power consumption is low.
또한, 본 발명의 실시예에 적용된 CMOS방식의 이미지센서는, 논리 회로를 동일한 공정으로 제작해서 화상 처리 회로를 On-Chip화 할 수 있다.In addition, in the CMOS image sensor applied to the embodiment of the present invention, a logic circuit can be manufactured in the same process so that the image processing circuit can be turned on-chip.
한편, 본 발명의 실시예에서는 CMOS방식의 이미지센서가 사용되었으나, 사용목적에 따라 CMOS카메라, CCD(Charged Coupled Device)카메라, 또는 기타 영상 촬영 장치 등이 모두 사용될 수 있다.In the embodiment of the present invention, a CMOS image sensor is used, but a CMOS camera, a Charged Coupled Device (CCD) camera, or other imaging apparatus may be used depending on the purpose of use.
상기 영상처리부(20)는, 영상처리기법을 이용하여 고속주행상태에서 촬영된 영상을 보정하여 선명하게 처리하는 곳으로서, 상기 이미지센서(10)에서 생성된 디지털영상신호를 가공하여 주행중인 상태에 있는 특정차량주위의 영상정보에 대응되는 정보량을 가지며 압축된 상태에 비해 상대적으로 고해상도 상태의 디지털동영상 비압축데이터를 생성할 수 있다.The image processing unit 20 is a place for correcting and sharply processing an image captured in a high speed driving state by using an image processing technique, and processing a digital image signal generated by the image sensor 10 while driving. The digital video uncompressed data having a relatively high resolution compared to the compressed state having an information amount corresponding to the image information around the specific vehicle.
상기 영상처리부(20)는 주행중인 차량에서 고속으로 움직이는 물체를 촬영했을 때 상이 흔들리는 현상을 극복하기 위하여 다음과 같은 다양한 영상처리기법을 사용할 수 있다.The image processor 20 may use various image processing techniques as follows to overcome a phenomenon in which an image shakes when a moving object is photographed at a high speed in a driving vehicle.
본 발명의 일실시예에서, 상기 영상처리부(20)는 이미지센서(10)의 설정 및 조리개와 필터를 제어하는 카메라제어기능을 포함하고 자동노출을 제어하는 기능을 포함하여 광량에 따라 카메라 노출을 최적으로 제어할 수 있으며, 자동색상조절기능을 포함하여 광원에 따라 물체의 색상이 영향을 받더라도 광원에 상관없이 동일하게 보이도록 조절할 수 있다.In one embodiment of the present invention, the image processing unit 20 includes a camera control function for controlling the setting of the image sensor 10 and the aperture and the filter, and includes a function for controlling the automatic exposure to perform camera exposure according to the amount of light. It can be optimally controlled, and it can be adjusted to look the same regardless of the light source even if the color of the object is affected by the light source, including automatic color adjustment function.
일반적으로 차량번호판의 색상은 후술하는 번호판영역을 판단하는데 있어서 중요한 인자가 될 수 있기 때문에 자동색상조절기능을 구비하여 광원에 따라 색상이 변경되는 것을 방지하면 번호판 인식률을 향상시킬 수 있다.In general, since the color of the license plate can be an important factor in determining the license plate area to be described later, it is possible to improve the license plate recognition rate by preventing the color change according to the light source with the automatic color control function.
또한, 본 발명의 실시예에서, 상기 영상처리부(20)는 센서다이나믹레인지 증폭기능을 구비하여 촬영된 영상에서 상대적으로 어둡고 밝은 영역이 동시에 존재할 때 어두운 영역은 좀더 밝게하고 밝은 영역은 조금 어둡게 하여 모든 영역이 동시에 선명하게 보이도록 할 수 있으며, 이것은, 역광상황에서 전방에서 주행하는 차량의 번호판이 그늘이 져 인식률이 떨어질 수 있기 때문에 상대적으로 어두워진 번호판 부분을 밝게 보이도록 영상처리를 할 수 있다.In addition, in the exemplary embodiment of the present invention, the image processing unit 20 has a sensor dynamic range amplifier function, and when the relatively dark and bright areas exist simultaneously in the captured image, the dark areas are lighter and the bright areas are slightly darker. The area can be clearly seen at the same time, and this can be image processing to make the relatively dark portion of the license plate brighter because the license plate of the vehicle running in front of the backlight can be shaded and the recognition rate can be reduced.
또한, 본 발명의 실시예에서, 상기 영상처리부(20)는 노이즈억제기능을 구비할 수 있다. 일반적으로, 저조도환경에서 선명한 영상을 확보하기 위해서 이미지센서(10)의 아날로그 신호를 증폭하여 사용할 수 있는데, 이때, 원치않은 노이즈도 함께 증폭되기 때문에 획득한 영상의 퀄리티가 현저히 나빠질 수 있다. 이러한 현상을 방지하기 위하여 노이즈를 억제하는 디지털 신호처리기술을 이용할 수 있다.In addition, in the embodiment of the present invention, the image processing unit 20 may have a noise suppression function. In general, the analog signal of the image sensor 10 may be amplified and used in order to secure a clear image in a low light environment, and since the unwanted noise is also amplified together, the quality of the acquired image may be significantly degraded. In order to prevent such a phenomenon, a digital signal processing technology for suppressing noise may be used.
또한, 본 발명의 실시예에서, 상기 영상처리부(20)는, 촬영된 물체의 윤곽선을 강조할수 있도록 선명도개선기능을 구비할 수 있다. 일반적으로 노이즈억제를 위하여 노이즈를 제거하면 윤곽선도 함께 사라질 수 있는데 이를 보완하는 기능이다.In addition, in the embodiment of the present invention, the image processing unit 20 may include a sharpness improving function to emphasize the outline of the photographed object. In general, if the noise is removed for noise suppression, the contour may disappear together.
한편, 본 발명의 실시예에서와 같이 차량용 블랙박스에 사용되는 카메라렌즈는 화각이 100도 이상인 광각렌즈를 사용하는데, 광각렌즈를 사용하면 렌즈 중심부에서 멀어질 수록 기하학적 왜곡이 발생하여 영상인식을 어렵게 할 수 있다.On the other hand, the camera lens used in the vehicle black box as in the embodiment of the present invention uses a wide-angle lens having an angle of view of 100 degrees or more, when using a wide-angle lens, the geometric distortion occurs as the distance from the center of the lens becomes difficult to recognize the image. can do.
또한, 차량용 블랙박스에 사용되는 카메라렌즈와 같이 소형렌즈일 경우에 렌즈중앙부와 렌즈외곽의 경우에 빛이 통과하는 양이 달라 렌즈중앙에 비해 상대적으로 렌즈외곽이 어두어지는 현상이 일어날 수 있다.In addition, in the case of a small lens such as a camera lens used in a vehicle black box, the amount of light passing through the lens center portion and the lens outer portion may be darker than the lens center.
이와 같은 왜곡현상을 방지하기 위하여 본 발명의 실시예에 따른 영상처리부(20)는 렌즈왜곡을 보정하는 기능을 포함하고 있으며 렌즈중앙대비 렌즈외곽으로 갈수록 거리에 따른 밝기를 보정해줄 수 있다.In order to prevent such a distortion phenomenon, the image processor 20 according to an exemplary embodiment of the present invention includes a function of correcting lens distortion, and may correct brightness according to distance toward the outside of the lens from the center of the lens.
상술한 바와 같이, 본 발명의 실시예에 적용된 영상처리부(20)는, 역광,야간, 및 우천등의 환경을 자동인식하여 최적의 영상이 획득되도록 각종 파라매터를 설정하고 자동수행하는 기능을 구비하는 ISP(Image Signal Proceesor)로 형성될 수 있다.As described above, the image processing unit 20 applied to the embodiment of the present invention has a function of automatically setting various parameters to automatically obtain an optimal image by automatically recognizing an environment such as backlight, nighttime, and rainy weather, and performing the automatic operation. It may be formed of an ISP (Image Signal Proceesor).
이와 같이, 본 발명의 실시예에 따른 차량용 블랙박스는 촬영시 생성되는 고해상도의 디지털동영상 비압축데이터를 최적의 영상으로 보정하는 영상처리부를 구비하여 고속으로 주행중에 촬영한 영상에서 차량번호정보를 용이하게 추출할 수 있다.As such, the vehicle black box according to the embodiment of the present invention includes an image processing unit for correcting high-resolution digital video uncompressed data generated during shooting to an optimal image, thereby easily obtaining vehicle number information from an image taken while driving at high speed. Can be extracted.
한편, 본 발명의 실시예에서, 상기 차량번호판정보 생성장치(100)는, 상기 영상처리부(20)에서 생성된 디지털동영상 비압축데이터를 분석하여 특정차량주위에서 주행하거나 인접한 불특정차량의 차량번호판정보를 생성할 수 있다.Meanwhile, in the embodiment of the present invention, the vehicle license plate information generating apparatus 100 analyzes the digital video uncompressed data generated by the image processing unit 20 to drive around a specific vehicle or vehicle license plate information of an adjacent unspecified vehicle. Can be generated.
또한, 상기 차량번호판정보 생성장치(100)는, 상기 영상처리부(20)에서 생성된 디지털동영상 비압축데이터를 구성하는 특정 비압축이미지프레임을 이용하여 차량번호를 인식할 수 있으며, 이와 같은 방식은 종래의 압축이미지프레임을 구성하는 I프레임(Intraframe-coded picture;JPEG)을 기초로 영상분석을 하는 것에 비하여 상대적으로 해상도가 높고 영상정보의 정보량이 많기 때문에 차량번호를 손쉽게 인식할 수 있다. In addition, the vehicle license plate information generating apparatus 100 may recognize the vehicle number using a specific uncompressed image frame constituting the digital video uncompressed data generated by the image processor 20. Compared to image analysis based on I-frames (JPEG) constituting the compressed image frame, the vehicle number can be easily recognized because of the relatively high resolution and a large amount of information of the image information.
상기 제어부(30)는, 본 발명의 실시예에 따른 차량용 블랙박스의 전체동작을 제어하는 역할을 수행하는 곳으로서, 상기 영상처리부(20)에서 생성된 디지털동영상 비압축데이터에 상기 차량번호판정보 생성장치(100)에서 생성된 불특정차량의 차량번호판정보를 포함하는 특정차량의 주행정보를 결합하여 특정차량의 주행동영상 데이터를 생성할 수 있다.The control unit 30 serves to control the overall operation of the vehicle black box according to an embodiment of the present invention, and generates the license plate information in the digital video uncompressed data generated by the image processing unit 20. The driving video data of the specific vehicle may be generated by combining driving information of the specific vehicle including the license plate information of the unspecified vehicle generated by the apparatus 100.
또한, 상기 제어부(30)는, 통신모듈(50)을 통해 원격지에 위치한 관제센터에 상기 차량번호판정보 생성장치(100)에서 생성된 차량번호판정보를 송신하거나 관제센터로부터 수신하는 범죄차량정보와 상기 차량번호판정보 생성장치에서 생성된 불특정차량의 차량번호판정보를 비교하여 실시간으로 범죄차량조회를 할 수 있다. In addition, the control unit 30 transmits the license plate information generated by the vehicle license plate information generating apparatus 100 to the control center located at a remote location through the communication module 50 or the crime vehicle information received from the control center and the Criminal vehicle search can be performed in real time by comparing the license plate information of the unspecified vehicle generated by the license plate information generating device.
상기 엔코더부(40)는, 상기 제어부(30)에서 생성된 주행동영상 데이터를 디지털동영상 파일포맷으로 압축하여 주행동영상 디지털압축데이터를 생성할 수 있다.The encoder 40 may generate driving video digital compression data by compressing the driving video data generated by the control unit 30 into a digital video file format.
상기 통신모듈(50)은, 상기 제어부(30)의 제어에 따라 상기 엔코더부(40)에서 생성된 주행동영상 디지털압축데이터를 원격의 관제센터로 전송하거나 상기 원격의 관제센터로부터 범죄차량정보를 수신할 수 있다.The communication module 50 transmits the driving moving picture digital compression data generated by the encoder 40 to a remote control center or receives crime vehicle information from the remote control center under the control of the controller 30. can do.
본 발명의 실시예에서 상기 통신모듈(50)은, 저장영상이 차량번호판 정보를 원격의 관제센터에 전송할 수도 있고 원격의 관제센터로부터 다양한 제어신호정보도 추가하여 수신할 수 있으며, 유선통신모듈 및 무선통신모듈 중 하나 이상의 방식으로 관제센터와 통신하게 구현될 수 있다.In the embodiment of the present invention, the communication module 50, the stored image may transmit the license plate information to the remote control center, and can receive and receive various control signal information from the remote control center, wired communication module and One or more of the wireless communication modules can be implemented to communicate with the control center.
또한, 본 발명의 실시예에서는 상기 통신모듈(50)이 LTE 모뎀방식을 지원하거나 CDMA 방식을 지원하는 이동통신용 통신모듈로 구현될 수 있다.In addition, in the embodiment of the present invention, the communication module 50 may be implemented as a communication module for mobile communication supporting the LTE modem method or the CDMA method.
이와 같이, 본 발명의 실시예에 따른 차량용 블랙박스는, 이동통신네트워크에 접속이 가능한 통신모듈을 구비하여 범죄차량이 조회되거나 지근거리에서 뺑소니 사고가 발생하여 즉각적인 대응이 필요할 경우에 관제센터에 실시간으로 차량번호정보를 전송할 수 있다.As such, the black box for a vehicle according to an embodiment of the present invention includes a communication module that can be connected to a mobile communication network, and when a crime vehicle is inquired or a hit-and-shoot accident occurs in a short distance, an immediate response is required in a control center. Vehicle number information can be transmitted.
또한, 도면에 도시된 바와 같이, 본 발명의 실시예에 따른 주행차량의 번호판 인식이 실시간으로 가능한 차량용 블랙박스는, 메모리(60), GPS모듈(70), 터치패널부(80), 충격감지부(90), 및 캘리브레이션부(200)를 더 포함할 수 있다.In addition, as shown in the figure, the vehicle black box capable of real-time license plate recognition of the driving vehicle according to an embodiment of the present invention, the memory 60, GPS module 70, the touch panel unit 80, shock detection The unit 90 may further include a calibration unit 200.
보다 상세하게는, 상기 메모리(60)는, 상기 엔코더부(40)에서 생성된 주행동영상 디지털압축데이터를 저장할 수 있으며, 상기 GPS모듈(70)은 GPS위성과 통신하여 특정차량의 주행정보에 포함되는 위치정보, 시간정보, 및 경로정보를 획득할 수 있다.In more detail, the memory 60 may store driving video digital compression data generated by the encoder 40, and the GPS module 70 communicates with a GPS satellite to include in driving information of a specific vehicle. The location information, time information, and route information can be obtained.
여기서, 상기 메모리(60)는 주행동영상 뿐만 아니라 차량용 블랙박스를 제어하기 위한 제어프로그램, 각종 데이터를 저장하는 저장공간역할을 수행할 수 있다.Here, the memory 60 may serve as a storage space for storing various data and a control program for controlling the vehicle black box as well as a moving video.
또한, 상기 터치패널부(80)는, 특정차량의 주행정보와 상기 메모리에 저장된 주행동영상 디지털압축데이터의 재생화면 및 뺑소니차량이나 긴급상황시 응급신호를 입력하기 위한 입력메뉴를 표시힐 수 있다.In addition, the touch panel unit 80 may display a driving screen of a specific vehicle, a playback screen of the moving video digital compression data stored in the memory, and an input menu for inputting an emergency signal in case of an emergency vehicle or an emergency vehicle.
이때, 상기 터치패널부(80)는 제어부(30)의 제어에 따라 범죄차량으로 인식되는 차량번호를 표시할 수 있으며, 별도의 입력장치와 연동되는 LCD액정표시장치와 LED디스플레이 화면으로 구현될 수 있다.In this case, the touch panel unit 80 may display a vehicle number recognized as a crime vehicle under the control of the controller 30, and may be implemented as an LCD display device and an LED display screen interlocked with a separate input device. have.
상기 충격감지부(90)는, 충격감지센서를 구비하여 사전설정된 기준값 이상의 충격을 감지하는 경우 이벤트를 발생시키고 제어부(30)에 충격감지신호를 전송하여 제어부(30)로 하여금 실시간으로 메모리(60)에 일정시간동안의 주행정보와 상기 주행정보에 대응되는 주행동영상 디지털압축데이터를 저장하게 할 수 있다.The shock detection unit 90 includes an impact sensor to generate an event when it detects a shock greater than a predetermined reference value and transmits an impact detection signal to the control unit 30 to cause the control unit 30 to perform a memory 60 in real time. ) May store the driving information for a predetermined time and the driving video digital compression data corresponding to the driving information.
또한, 본 발명의 실시예에서, 상기 캘리브레이션부(200)는 차량부착시 가속도센서를 이용하여 수평상태를 체크할 수 있다.In addition, in the embodiment of the present invention, the calibration unit 200 may check the horizontal state by using the acceleration sensor when the vehicle is attached.
여기서, 상기 캘리브레이션부(200)는 카메라설치시 최적상태에서 번호판 인식이 이루어질 수 있도록 가속도센서를 이용하여 수평상태를 사용자에게 알려주는 역할을 수행할 수 있다.Here, the calibration unit 200 may serve to inform the user of a horizontal state by using an acceleration sensor so that license plate recognition can be performed at an optimal state when the camera is installed.
또한, 상기 캘리브레이션부(200)는 상기 메모리에 저장되는 주행동영상 디지털압축데이터의 차선간격이나 차량폭을 이용하여 카메라 내부 및 외부의 카메라 파라매터를 추출하여 터치패널부에 출력하고 블랙박스 설치시에 문자인식이 가능한 상태로 조정할 수 있다.In addition, the calibration unit 200 extracts camera parameters inside and outside the camera and outputs them to the touch panel by using lane intervals or vehicle widths of the driving video digital compression data stored in the memory. The character can be adjusted in a state where it can be recognized.
도 2는 도 1에 도시된 차량용 블랙박스를 구성하는 차량번호판정보 생성장치의 세부구성도이다.FIG. 2 is a detailed configuration diagram of a vehicle license plate information generating device constituting the vehicle black box shown in FIG. 1.
도면에 도시된 바와 같이, 본 발명의 실시예에 따른 주행차량의 번호판 인식이 실시간으로 가능한 차량용 블랙박스를 구성하는 차량번호판정보 생성장치(100)는, ROI데이터 선택부(110)와 ROI데이터 처리부(120)를 구비할 수 있다.As shown in the figure, the vehicle license plate information generating device 100 constituting a vehicle black box capable of real-time license plate recognition of the driving vehicle according to an embodiment of the present invention, ROI data selection unit 110 and ROI data processing unit 120 may be provided.
보다 상세하게는, 상기 ROI데이터 선택부(110)는, 영상처리부(20)에서 생성된 디지털동영상 비압축데이터를 구성하는 각각의 비압축이미지프레임에서 후술하는 도 3에 도시된 하나 이상의 ROI데이터를 선택할 수 있다.In more detail, the ROI data selector 110 may include one or more ROI data shown in FIG. 3 described below in each uncompressed image frame constituting the digital video uncompressed data generated by the image processor 20. You can choose.
여기서, 상기 ROI데이터는, 차량번호판정보를 추출하기 위한 관심영역을 가리키는 것으로서 컬러영상이미지와 이진영상이미지를 포함하며 각각의 비압축이미지프레임에서 추출할 수 있다.Here, the ROI data, which indicates a region of interest for extracting the license plate information, includes a color image image and a binary image image and may be extracted from each uncompressed image frame.
또한, 본 발명의 실시예에서 상기 RO데이터 선택부(110)는, 후술하는 ROI데이터 처리부(120)에서 연산량을 줄이고 번호판정보를 추출하여 인식하는데 정확성을 향상시키기 위한 다양한 동작을 수행할 수 있다.In addition, in the embodiment of the present invention, the RO data selection unit 110 may perform various operations for improving the accuracy in reducing the amount of calculation and extracting and recognizing license plate information in the ROI data processing unit 120 to be described later.
좀더 상세하게 설명하면, 상기 ROI데이터 선택부(110)는, 촬영된 영상의 크기를 변경할 수 있고, 필요에 따라 컬러영상을 GRAY영상으로 변경할 수 있으며, 영상이진화를 수행하고, 외곽선을 추출함으로써 동영상 비압축데이터에서 획득한 ROI데이터에 대해 전처리를 수행하는 역할을 할 수 있다. In more detail, the ROI data selection unit 110 may change the size of the captured image, change the color image into a GRAY image as necessary, perform image binarization, and extract the outline. It may serve to perform preprocessing on ROI data obtained from uncompressed data.
또한, 상기 ROI데이터 선택부(110)는, 동영상 비압축데이터에서 획득한 ROI데이터에서 추가적으로 차선을 추출하거나 이전영상에서 확인된 번호판정보를 추적할 수 있고, 소실점을 추출할 수 있으며, 영상을 구성하는 배경영역에서 비도로영역을 제거할 수 있다.In addition, the ROI data selector 110 may additionally extract lanes from the ROI data obtained from the uncompressed video data, track license plate information identified in a previous image, extract vanishing points, and configure an image. The non-road area can be removed from the background area.
또한, 상기 ROI데이터 선택부(110)는, 다양한 화각의 렌즈에 대응하여 설치위치를 보정하고 카메라 시각을 보장하기 위하여 영상에서의 좌표위치 및 크기를 산출하기 위해 카메라렌즈와 이미지센서에 필요한 광학적 요소를 추출하거나 계산할 수 있다.In addition, the ROI data selection unit 110, an optical element required for the camera lens and the image sensor to calculate the coordinate position and size in the image in order to correct the installation position corresponding to the lens of various angles of view and ensure the camera vision Can be extracted or calculated.
한편, 본 발명의 실시예에서는, 상기 ROI데이터 선택부(110)에서 차량번호판정보를 생성하는데 필요하지 않은 ROI데이터를 제거할 수 있으며 이에 대한 구체적인 설명은 도 3에서 후술하기로 한다.Meanwhile, in the embodiment of the present invention, the ROI data that is not necessary to generate the license plate information in the ROI data selection unit 110 may be removed, and a detailed description thereof will be described later with reference to FIG. 3.
또한, 상기 ROI데이터 처리부(120)는, 상기 ROI데이터 선택부(110)에서 선택된 하나 이상의 ROI데이터로부터 차량번호판정보에 대응되는 차량영역, 번호판영역, 및 문자영역을 순차적으로 추출할 수 있다.In addition, the ROI data processor 120 may sequentially extract a vehicle area, a license plate area, and a character area corresponding to the vehicle license plate information from one or more ROI data selected by the ROI data selector 110.
상기 ROI데이터 처리부(120)는 순차적으로 추출한 상기 문자영역에 문자인식알고리즘을 적용하여 차량번호판을 구성하는 문자를 인식할 수 있으며 최종적으로 텍스트데이터로 이루어진 차량번호판정보를 생성할 수 있다.The ROI data processor 120 may recognize a character constituting the license plate by applying a character recognition algorithm to the character region sequentially extracted, and may generate vehicle license plate information consisting of text data.
이때, 상기 ROI데이터 처리부(120)는, 도면에 도시된 바와 같이, 차량영역추출부(121), 번호판영역추출부(122), 문자영역인식부(123), 문자코드생성부(124), 차량번호트래킹부(125), 및 문자영역복원부(126)을 포함할 수 있다.At this time, the ROI data processing unit 120, as shown in the figure, vehicle area extraction unit 121, license plate area extraction unit 122, character area recognition unit 123, character code generation unit 124, The vehicle number tracking unit 125 and the character area restoration unit 126 may be included.
보다 상세하게는, 상기 차량영역추출부(121)는, 상기 ROI데이터 선택부(110)에서 선택된 ROI데이터를 구성하는 컬러영상이미지와 사전분석된 차량의 특징점을 비교하여 상기 디지털동영상 비압축데이터를 구성하는 각각의 비압축이미지프레임상에서 도 3의 도면참조부호 ROI-1에 해당하는 차량영역을 추출할 수 있다.In more detail, the vehicle region extraction unit 121 compares the color image image constituting the ROI data selected by the ROI data selection unit 110 with the feature points of the pre-analyzed vehicle and compares the digital video uncompressed data. A vehicle region corresponding to reference numeral ROI-1 of FIG. 3 may be extracted on each of the uncompressed image frames.
상기 차량영역추출부(121)는, 자동차여부만 판단하여 차량영역을 프레임의 XY좌표범위로 추출하고, 차량영역이 인접한 지점에 중복으로 추출되는 경우에 단일의 차량영역만 대표차량으로 추출할 수 있다. The vehicle region extracting unit 121 may extract only a vehicle region as an XY coordinate range of a frame by judging only whether a vehicle is present and extract only a single vehicle region as a representative vehicle when the vehicle region is repeatedly extracted at an adjacent point. have.
상기 번호판영역추출부(122)는, 상기 차량영역추출부(121)에 의해 추출된 차량영역 내에서 ROI데이터를 구성하는 이진영상이미지를 이용하여 도 3의 도면참조부호 ROI-2에 해당하는 번호판영역을 추출할 수 있다.The license plate area extraction unit 122 uses a binary image image constituting the ROI data in the vehicle area extracted by the vehicle area extraction unit 121 and corresponds to the reference plate ROI-2 of FIG. 3. The area can be extracted.
여기서, 상기 번호판영역인식부(122)는, 이진영상이미지와 사전분석된 번호판의 특징점을 비교하는 방법, 및 이진영상이미지에 모폴로지 연산과 BLOB 연산을 순차적으로 수행하여 얻은 연산이미지와 사전분석된 번호판의 가로세로비율을 비교하는 방법 중 어느 하나의 방법으로 번호판영역을 추출할 수 있다.Here, the license plate area recognition unit 122, a method for comparing the feature points of the binary image image and the pre-analyzed license plate, and the operation image and pre-analyzed license plate obtained by sequentially performing a morphology operation and a BLOB operation on the binary image image The license plate area may be extracted by any of the methods of comparing the aspect ratios of.
또한, 본 발명의 실시예에서 상기 번호판영역인식부(122)는 보행자인식(HOG), 얼굴인식(HAAR), 기울기를 이용하여 번호판여부를 추출하는 알고리즘을 사용할 수 있다.In addition, in the embodiment of the present invention, the license plate area recognition unit 122 may use an algorithm for extracting whether the license plate is recognized using a pedestrian recognition (HOG), a face recognition (HAAR), or a slope.
상기 문자영역인식부(123)는, 상기 번호판영역인식부(122)에 의해 추출된 번호판영역에서 히스토그램을 사용하여 문자영역을 분리할 수 있으며, 이에 대한 자세한 설명은 도 4에서 후술하기로 한다.The character area recognition unit 123 may separate the character area from the license plate area extracted by the license plate area recognition unit 122 using a histogram, which will be described in detail later with reference to FIG. 4.
또한, 상기 문자코드생성부(124)는, 상기 문자영역인식부(123)에 의해 추출된 문자영역에 문자인식알고리즘을 적용하여 차량번호판정보에 해당하는 텍스트데이터용 문자코드를 생성할 수 있다.In addition, the character code generation unit 124 may generate a character code for text data corresponding to the vehicle license plate information by applying a character recognition algorithm to the character area extracted by the character area recognition unit 123.
도면에 도시된 상기 차량번호트래킹부(125)는, 번호판 인식에 필요한 ROI데이터를 줄이기 위한 구성으로서, 비압축이미지프레임을 구성하는 이전프레임과 현재프레임의 기준점을 이용하고 CAM SHIFT 및 OPTICAL FLOWER 알고리즘을 사용하여 차량번호판정보에 대응되는 ROI데이터를 추적할 수 있다.The vehicle number tracking unit 125 shown in the drawing is configured to reduce ROI data required for license plate recognition, and uses CAM SHIFT and OPTICAL FLOWER algorithms using reference points of previous and current frames constituting an uncompressed image frame. Can be used to track the ROI data corresponding to the license plate information.
이때, 상기 차량번호트래킹부(125)는 이전프레임과 현재프레임에서 번호판영역의 이동정보량을 계산하여 ROI데이터를 추적하는 것으로서, 기준점의 이동영역을 검사한 다음 프레임을 구성하는 각 픽셀들의 이동량을 추적하고 계산할 수 있다.At this time, the vehicle number tracking unit 125 tracks the ROI data by calculating the amount of movement information of the license plate area in the previous frame and the current frame, and checks the movement amount of each pixel constituting the frame after inspecting the movement area of the reference point. Can be calculated.
또한, 상기 문자영역복원부(126)는, 문자식별이 어려운 다수개의 비압축이미지프레임에 슈퍼레졸루션기법을 적용하여 차량번호판정보를 포함하는 문자영역을 복원할 수 있다.In addition, the character area restoring unit 126 may restore a character area including license plate information by applying a super resolution technique to a plurality of uncompressed image frames that are difficult to identify.
이와 같이, 본 발명의 실시예에 따른 차량용 블랙박스는, 디지털동영상 비압축데이터를 이용하여 차량번호판정보를 추출하기 때문에 손실되는 영상데이터의 정보량부족을 방지하고 차량번호정보를 용이하게 추출할 수 있으며, 차량번호에 해당하는 문자를 복원할 수 있는 문자영역복원부를 차량번호생성장치를 구성하는 ROI데이터 처리부 내부에 구비하여 번호판 인식효율을 향상시킬 수 있다.As such, the vehicle black box according to the embodiment of the present invention can extract the license plate information by using the digital video uncompressed data, thereby preventing the lack of information of the missing image data and easily extracting the vehicle number information. In addition, a character area restoring unit capable of restoring a character corresponding to the vehicle number may be provided inside the ROI data processing unit constituting the vehicle number generation device to improve license plate recognition efficiency.
도 3 내지 도 4를 참조하여 도 2에 도시된 차량번호판정보 생성장치를 더욱 상세하게 설명하면 다음과 같다.The apparatus for generating license plate information shown in FIG. 2 will be described in more detail with reference to FIGS. 3 to 4 as follows.
도 3은 도 2에 도시된 차량번호판정보 생성장치를 구성하는 ROI데이터 선택부에서 제거되는 ROI데이터를 설명하기 위한 도면이다. FIG. 3 is a view for explaining ROI data removed by the ROI data selecting unit constituting the vehicle license plate information generating apparatus shown in FIG. 2.
도면에 도시된 바와 같이, 도 1의 영상처리부(20)에서 생성된 디지털동영상 비압축데이터를 구성하는 각각의 비압축이미지프레임에 차량번호판정보를 추출하기 위한 관심영역(ROI)이 다수개 존재할 수 있다.As shown in FIG. 1, a plurality of ROIs may be present in each of the uncompressed image frames constituting the digital video uncompressed data generated by the image processor 20 of FIG. 1. have.
이때, 상기 관심영역(ROI)은 광각의 카메라렌즈를 갖는 차량용 블랙박스의 특성상 특정범위안에 위치하는 경우에 한하여 번호판인식이 가능할 수 있다.In this case, the ROI may be recognized only if the ROI is located within a specific range due to the characteristics of the vehicle black box having the wide-angle camera lens.
즉, ROI데이터 선택부(110)에서 디지털동영상 비압축데이터를 구성하는 각각의 비압축이미지프레임에서 ROI데이터를 선택하는 경우에 차량번호판정보를 생성하는데 필요하지 않은 ROI데이터를 제거할 수 있다면 번호판 인식 속도를 증가시킬 수 있다.That is, when the ROI data selection unit 110 selects the ROI data from each uncompressed image frame constituting the digital video uncompressed data, if the ROI data that is not necessary to generate the license plate information can be removed, the license plate recognition is performed. You can increase the speed.
도면에 도시된 바와 같이, 차량번호판정보를 생성하는데 필요하지 않은 관심영역(ROI)은, 차선이 만나는 소실점의 수평선으로 이루어지는 지평선의 상측으로 배치되는 경우, 도 2의 차량번호트래킹부(125)에 의하여 이전 프레임에서 이미 인식된 관심영역으로 추적되는 경우, 및 번호판 확인이 가능한 한계선을 벗어난 곳에 위치하여 도 2의 문자코드생성부(124)에서 문자코드로 인식하기 어려운 15픽셀 미만의 크기를 갖는 경우이다.As shown in the figure, a region of interest ROI, which is not necessary for generating license plate information, is disposed in the vehicle number tracking unit 125 of FIG. By tracking to the region of interest already recognized in the previous frame, and located in a position outside the limit line that can be identified by the license plate has a size of less than 15 pixels difficult to recognize as a character code in the character code generation unit 124 of FIG. to be.
따라서, 본 발명의 실시예에서는, ROI데이터 선택부(110)에서 차량번호판정보를 생성하는데 필요하지 않은 ROI데이터는, 각각의 비압축이미지프레임상에서 차선이 만나는 소실점의 수평선으로 이루어지는 지평선의 상측으로 배치되는 ROI데이터와, 문자크기가 15픽셀 미만인 문자영역을 포함하는 ROI데이타, 및 이전프레임에서 생성된 차량번호판정보에 대응되는 문자영역을 포함하는 ROI데이터를 포함할 수 있다.Therefore, in the embodiment of the present invention, the ROI data, which is not necessary for generating the license plate information in the ROI data selection unit 110, is disposed above the horizon line consisting of horizontal lines of vanishing points where the lanes meet on each uncompressed image frame. The ROI data may include ROI data, a ROI data including a character area having a character size of less than 15 pixels, and ROI data including a character area corresponding to vehicle license plate information generated in a previous frame.
이와 같이, 본 발명의 실시예에 따른 주행차량의 번호판 인식이 실시간으로 가능한 차량용 블랙박스는, 고해상도의 디지털동영상 비압축데이터를 구성하는 프레임영역 중 불필요한 영역을 제외하여 차량번호판을 인식하는데 필요한 ROI데이터의 크기를 줄일 수 있고, 차량번호판정보가 인식된 ROI데이터의 프레임좌표를 프레임이 바뀔때마다 추적하여 ROI데이터 선택부에서 선별되는 ROI데이터의 크기를 줄일 수 있어 주행차량의 번호판 인식을 실시간으로 할 수 있다.As described above, the vehicle black box capable of real-time license plate recognition of the driving vehicle according to an embodiment of the present invention includes ROI data necessary for recognizing the license plate except for unnecessary areas among frame regions constituting high-resolution digital video uncompressed data. The size of the ROI data selected by the ROI data selection unit can be reduced by tracking the frame coordinates of the ROI data in which the license plate information is recognized, and changing the frame. Can be.
도 4는 도 2에 도시된 차량번호판정보 생성장치를 구성하는 ROI데이터 처리부의 문자영역인식부에서 히스토그램을 사용하여 문자영역을 분리하는 것을 나타내는 도면이다. FIG. 4 is a diagram illustrating separating a character area using a histogram in a character area recognition unit of the ROI data processor of the vehicle license plate information generating device shown in FIG. 2.
도면에 도시된 바와 같이, 도 2의 문자영역인식부(123)는, 번호판영역추출부(122)에 의해 추출된 도 3의 번호판영역(ROI-2)에서 히스토그램을 사용하여 문자영역을 분리할 수 있다.As illustrated in FIG. 2, the character area recognition unit 123 of FIG. 2 may separate a character area using a histogram from the license plate area ROI-2 of FIG. 3 extracted by the license plate area extraction unit 122. Can be.
즉, 도면참조부호 Yb에 의하여 번호판영역의 상측 및 하측 문자영역을 분리하고, 이후에 도면참조부호a ~m에 의하여 각 번호에 대한 개별문자영역을 분리할 수 있다.That is, the upper and lower character areas of the license plate area can be separated by the reference numeral Yb, and then the individual character areas for each number can be separated by the reference numerals a to m.
여기서, 도 2의 문자코드생성부(124)는 상기 문자영역인식부(123)에 의해 추출된 문자영역에 문자인식알고리즘을 적용하여 차량번호판정보에 해당하는 텍스트데이터용 문자코드를 생성할 수 있다.Here, the character code generation unit 124 of FIG. 2 may generate a character code for text data corresponding to the license plate information by applying a character recognition algorithm to the character area extracted by the character area recognition unit 123. .
이 때, 상기 문자코드생성부(124)는, 주차관제시스템에 사용되는 통상의 문자인식방법을 사용하여 자동차번호판정보에 해당하는 문자코드를 생성하거나, 분리된 문자영역을 신경망, SVM, HMM 등의 알고리즘을 이용하여 문자인식을 할 수 있으며, 인식된 문자가 번호판의 문자 규격에 맞는지 검사하는 기능을 구비할 수 있다.At this time, the character code generation unit 124 generates a character code corresponding to the license plate information by using a conventional character recognition method used in the parking control system, or the separated character area neural network, SVM, HMM, etc. Character recognition can be performed using the algorithm of, and can be provided with a function to check whether the recognized character meets the character standard of the license plate.
상기와 같이, 본 발명은, 촬영시 생성되는 고해상도의 디지털동영상 비압축데이터를 이용하여 차량번호판정보를 추출하는 차량번호판정보 생성장치를 구비함으로써 촬영영상이 디지털동영상 파일 포맷으로 압축하는 경우에 손실되는 영상데이터의 정보량부족을 방지할 수 있어 주행중인 차량의 번호판 인식효율을 향상시켜 주행중인 상태의 촬영영상을 이용하여 차량번호정보를 용이하게 추출할 수 있는 차량용 블랙박스를 제공하는 효과가 있다.As described above, the present invention is provided by a vehicle license plate information generating apparatus for extracting license plate information by using high-resolution digital video uncompressed data generated at the time of shooting, which is lost when the captured image is compressed into a digital movie file format. The lack of information amount of the image data can be prevented, thereby improving the license plate recognition efficiency of the driving vehicle, thereby providing a vehicle black box that can easily extract the vehicle number information using the photographed image of the driving state.
또한, 본 발명은, 촬영시 생성되는 고해상도의 디지털동영상 비압축데이터를 최적의 영상으로 보정하는 영상처리부를 구비하여 고속으로 주행중에 촬영한 영상에서 차량번호정보를 용이하게 추출하는 효과가 있다.In addition, the present invention has an effect of easily extracting the vehicle number information from the image taken while driving at high speed with an image processing unit for correcting the high-resolution digital video uncompressed data generated at the time of shooting to an optimal image.
또한, 본 발명은, 고해상도의 디지털동영상 비압축데이터를 구성하는 프레임영역 중 주행차량의 차량번호판을 인식하는데 불필요한 영역을 제외한 ROI데이터를 선별하는 ROI데이터 선택부를 차량번호생성장치 내부에 구비함으로써 차량번호판을 인식하는데 필요한 ROI데이터의 크기를 줄일 수 있기 때문에 차량번호판 인식에 소요되는 시간을 감소시켜 주행차량의 번호판 인식이 실시간으로 가능하게 하는 효과가 있다.In addition, the present invention provides a vehicle license plate by providing a ROI data selection unit inside the vehicle number generation device for selecting ROI data excluding the unnecessary area for recognizing the vehicle license plate of the driving vehicle among the frame areas constituting the high-resolution digital video uncompressed data Since it is possible to reduce the size of the ROI data required to recognize the license plate, it is possible to reduce the time required to recognize the license plate, thereby enabling the license plate recognition of the driving vehicle in real time.
또한, 본 발명은, 문자식별이 어려운 다수개의 프레임을 슈퍼레졸루션기법을 이용하여 결합함으로써 차량번호에 해당하는 문자를 복원할 수 있는 문자영역복원부를 차량번호생성장치를 구성하는 ROI데이터 처리부 내부에 구비하여 번호판 인식효율을 향상시키는 효과가 있다. In addition, the present invention, by combining a plurality of frames difficult to identify by using a super resolution technique, a character area restoring unit capable of restoring a character corresponding to the vehicle number is provided inside the ROI data processing unit constituting the vehicle number generation device. It is effective to improve the license plate recognition efficiency.
게다가, 본 발명은, 차량번호판정보 생성장치를 구성하는 ROI데이터 처리부에 차량번호판정보가 인식된 ROI데이터의 프레임좌표를 프레임이 바뀔때마다 추적하는 차량번호트래킹부를 구비하여 이미 인식된 차량번호판정보에 해당하는 특정영역을 ROI데이터 선택대상에서 삭제 할 수 있기 때문에 ROI데이터 선택부에서 선별되는 ROI데이터의 크기를 줄일 수 있어 주행차량의 번호판 인식속도를 향상시키는 효과가 있다.Furthermore, the present invention includes a vehicle number tracking unit that tracks the frame coordinates of the ROI data from which the license plate information is recognized, each time the frame changes, to the ROI data processing unit constituting the vehicle license plate information generating apparatus. Since the specific area can be deleted from the ROI data selection target, the size of the ROI data selected by the ROI data selection unit can be reduced, thereby improving the license plate recognition speed of the driving vehicle.
뿐만 아니라, 본 발명은, 이동통신네트워크에 접속이 가능한 통신모듈을 구비하여 범죄차량이 조회되거나 지근거리에서 뺑소니 사고가 발생하여 즉각적인 대응이 필요할 경우에 관제센터에 실시간으로 차량번호정보를 전송할 수 있는 효과가 있다.In addition, the present invention is equipped with a communication module that can be connected to the mobile communication network, when the crime vehicle is inquired or hit by a short-distance accident in the near-by, when the immediate response is necessary to transmit the vehicle number information in real time to the control center It works.
지금까지 본 발명에 대해서 상세히 설명하였으나, 그 과정에서 언급한 실시예는 예시적인 것일 뿐이며, 한정적인 것이 아님을 분명히 하고, 본 발명은 이하의 특허청구범위에 의해 제공되는 본 발명의 기술적 사상이나 분야를 벗어나지 않는 범위내에서, 균등하게 대처될 수 있는 정도의 구성요소 변경은 본 발명의 범위에 속한다 할 것이다.The present invention has been described in detail so far, but the embodiments mentioned in the process are only illustrative and are not intended to be limiting, and the present invention is provided by the following claims and the technical spirit and field of the present invention. Within the scope not departing from the scope of the present invention, changes in the components that can be coped evenly will fall within the scope of the present invention.
본 발명은 차량용 블랙박스의 제조분야에 이용될 수 있다.The present invention can be used in the field of manufacturing a vehicle black box.

Claims (10)

  1. 카메라렌즈를 구비한 채 특정차량에 부착되어 특정차량주변을 촬영하는 차량용 블랙박스에 있어서, In a black box for a vehicle that is attached to a specific vehicle with a camera lens to shoot around the specific vehicle,
    상기 카메라렌즈를 통하여 촬영한 영상정보를 전기적 신호로 변환하여 디지털영상신호를 생성하는 이미지센서와;An image sensor converting the image information photographed through the camera lens into an electrical signal to generate a digital image signal;
    상기 이미지센서에서 생성된 디지털영상신호를 가공하여 특정차량주위의 영상정보에 대응되는 정보량을 갖는 디지털동영상 비압축데이터를 생성하는 영상처리부와;An image processor which processes the digital image signal generated by the image sensor to generate digital video uncompressed data having an information amount corresponding to the image information around a specific vehicle;
    상기 영상처리부에서 생성된 디지털동영상 비압축데이터를 분석하여 특정차량주위에서 주행하거나 인접한 불특정차량의 차량번호판정보를 생성하는 차량번호판정보 생성장치와; A vehicle license plate information generating device for analyzing the digital video uncompressed data generated by the image processor to generate vehicle license plate information of a non-specified vehicle traveling around a specific vehicle;
    상기 영상처리부에서 생성된 디지털동영상 비압축데이터에 상기 차량번호판정보 생성장치에서 생성된 불특정차량의 차량번호판정보를 포함하는 특정차량의 주행정보를 결합하여 특정차량의 주행동영상 데이터를 생성하고, 차량용 블랙박스의 전체동작을 제어하는 제어부와;Combining driving information of a specific vehicle including vehicle license plate information of an unspecified vehicle generated by the vehicle license plate information generating device with the digital video uncompressed data generated by the image processor to generate driving video data of a specific vehicle, and the vehicle black A controller for controlling the overall operation of the box;
    상기 제어부에서 생성된 주행동영상 데이터를 디지털동영상 파일포맷으로 압축하여 주행동영상 디지털압축데이터를 생성하는 엔코더부; 및An encoder for compressing the driving video data generated by the controller into a digital video file format to generate driving video digital compression data; And
    상기 제어부의 제어에 따라 상기 엔코더부에서 생성된 주행동영상 디지털압축데이터를 원격의 관제센터로 전송하거나 상기 원격의 관제센터로부터 범죄차량정보를 수신하는 통신모듈;을 포함하는 것을 특징으로 하는 주행차량의 번호판 인식이 실시간으로 가능한 차량용 블랙박스And a communication module for transmitting the moving video digital compression data generated by the encoder to a remote control center or receiving crime vehicle information from the remote control center under the control of the controller. Car black box with license plate recognition in real time
  2. 제 1항에 있어서, 상기 차량번호판정보 생성장치는,According to claim 1, The license plate information generating apparatus,
    상기 영상처리부에서 생성된 디지털동영상 비압축데이터를 구성하는 각각의 비압축이미지프레임에서 차량번호판정보를 추출하기 위한 관심영역에 대응되며 컬러영상이미지와 이진영상이미지를 포함하는 하나 이상의 ROI데이터를 선택하는 ROI데이터 선택부; 및Selecting one or more ROI data corresponding to a region of interest for extracting license plate information from each uncompressed image frame constituting the digital video uncompressed data generated by the image processor and including a color image image and a binary image image. ROI data selection unit; And
    상기 ROI데이터 선택부에서 선택된 하나 이상의 ROI데이터로부터 차량번호판정보에 대응되는 차량영역, 번호판영역, 및 문자영역을 순차적으로 추출한 다음 상기 문자영역에 문자인식알고리즘을 적용하고 차량번호판을 구성하는 문자를 인식하여 텍스트데이터로 이루어진 차량번호판정보를 생성하는 ROI데이터 처리부;를 포함하는 것을 특징으로 하는 주행차량의 번호판 인식이 실시간으로 가능한 차량용 블랙박스The vehicle area, license plate area, and character area corresponding to the license plate information are sequentially extracted from the ROI data selected by the ROI data selection unit, and then a character recognition algorithm is applied to the character area to recognize the characters constituting the license plate. ROI data processing unit for generating vehicle license plate information consisting of the text data; the vehicle black box capable of real-time license plate recognition of a driving vehicle comprising a
  3. 제 2항에 있어서, 상기 ROI데이터 선택부는,The method of claim 2, wherein the ROI data selector,
    상기 디지털동영상 비압축데이터를 구성하는 각각의 비압축이미지프레임에서 하나 이상의 ROI데이터를 선택하는 경우에 차량번호판정보를 생성하는데 필요하지 않은 ROI데이터를 제거하여 번호판 인식 속도를 증가시키는 것을 특징으로 하는 주행차량의 번호판 인식이 실시간으로 가능한 차량용 블랙박스When selecting one or more ROI data from each uncompressed image frame constituting the digital video uncompressed data, ROI data that is not necessary to generate vehicle license plate information is removed to increase the license plate recognition speed. Vehicle black box for real-time license plate recognition
  4. 제 3항에 있어서, The method of claim 3, wherein
    상기 차량번호판정보를 생성하는데 필요하지 않은 ROI데이터는, ROI data that is not necessary to generate the license plate information,
    상기 각각의 비압축이미지프레임상에서 차선이 만나는 소실점의 수평선으로 이루어지는 지평선의 상측으로 배치되는 ROI데이터와;ROI data disposed above the horizon consisting of horizontal lines of vanishing points where lanes meet on each uncompressed image frame;
    문자크기가 15픽셀 미만인 문자영역을 포함하는 ROI데이타; 및ROI data including a text area having a text size of less than 15 pixels; And
    이전프레임에서 생성된 차량번호판정보에 대응되는 문자영역을 포함하는 ROI데이터;를 포함하는 것을 특징으로 하는 주행차량의 번호판 인식이 실시간으로 가능한 차량용 블랙박스ROI data including a character area corresponding to the license plate information generated in the previous frame; vehicle black box capable of real-time license plate recognition
  5. 제 2항에 있어서, 상기 ROI데이터 처리부는,The method of claim 2, wherein the ROI data processing unit,
    상기 ROI데이터 선택부에서 선택된 ROI데이터를 구성하는 컬러영상이미지와 사전분석된 차량의 특징점을 비교하여 상기 디지털동영상 비압축데이터를 구성하는 각각의 비압축이미지프레임상에서 차량영역을 추출하는 차량영역추출부와;A vehicle region extraction unit for extracting a vehicle region on each uncompressed image frame constituting the digital video uncompressed data by comparing the color image image constituting the ROI data selected by the ROI data selection unit with the feature points of the pre-analyzed vehicle. Wow;
    상기 차량영역추출부에 의해 추출된 차량영역 내에서 ROI데이터를 구성하는 이진영상이미지를 이용하여 번호판영역을 추출하는 번호판영역추출부와;A license plate area extraction unit for extracting a license plate area using a binary image image constituting ROI data in the vehicle area extracted by the vehicle area extraction unit;
    상기 번호판영역추출부에 의해 추출된 번호판영역에서 히스토그램을 사용하여 문자영역을 분리하는 문자영역인식부; 및A character area recognition unit for separating a character area using a histogram from the number plate area extracted by the license plate area extraction unit; And
    상기 문자영역인식부에 의해 추출된 문자영역에 문자인식알고리즘을 적용하여 차량번호판정보에 해당하는 텍스트데이터용 문자코드를 생성하는 문자코드생성부;를 포함하는 것을 특징으로 하는 주행차량의 번호판 인식이 실시간으로 가능한 차량용 블랙박스 A character code generation unit for generating a character code for text data corresponding to the vehicle license plate information by applying a character recognition algorithm to the character area extracted by the character area recognition unit; Car black box available in real time
  6. 제 5항에 있어서, 상기 번호판영역추출부는,According to claim 5, The license plate area extraction unit,
    상기 이진영상이미지와 사전분석된 번호판의 특징점을 비교하는 방법, 및 상기 이진영상이미지에 모폴로지 연산과 BLOB 연산을 순차적으로 수행하여 얻은 연산이미지와 사전분석된 번호판의 가로세로비율을 비교하는 방법 중 어느 하나의 방법으로 번호판영역을 추출하는 것을 특징으로 하는 주행차량의 번호판 인식이 실시간으로 가능한 차량용 블랙박스A method of comparing the feature points of the binary image image and the pre-analyzed license plate, and a method of comparing the aspect ratio of the calculated image and the pre-analyzed license plate by sequentially performing morphology and BLOB operations on the binary image image Vehicle black box capable of real-time license plate recognition, characterized by extracting the license plate area in one way
  7. 제 5항에 있어서, 상기 ROI데이터 처리부는,The method of claim 5, wherein the ROI data processing unit,
    이전프레임과 현재프레임의 특징점을 이용하여 차량번호판정보에 대응되는 ROI데이터를 추적하는 차량번호트래킹부;를 더 구비하는 것을 특징으로 하는 주행차량의 번호판 인식이 실시간으로 가능한 차량용 블랙박스A vehicle number tracking unit for tracking the ROI data corresponding to the vehicle license plate information by using the feature points of the previous frame and the current frame;
  8. 제 5항에 있어서, 상기 ROI데이터 처리부는,The method of claim 5, wherein the ROI data processing unit,
    문자식별이 어려운 다수개의 비압축이미지프레임에 슈퍼레졸루션기법을 적용하여 차량번호판정보를 포함하는 문자영역을 복원할 수 있는 문자영역복원부;를 더 구비하는 것을 특징으로 하는 주행차량의 번호판 인식이 실시간으로 가능한 차량용 블랙박스Character area restoring unit further comprises a character area restoring unit for restoring a character area including vehicle license plate information by applying a super resolution technique to a plurality of uncompressed image frames that are difficult to identify characters. Car black box
  9. 제 1항에 있어서, 상기 제어부는,The method of claim 1, wherein the control unit,
    상기 통신모듈을 통해 원격지에 위치한 관제센터에 상기 차량번호판정보 생성장치에서 생성된 차량번호판정보를 송신하거나 관제센터로부터 수신하는 범죄차량정보와 상기 차량번호판정보 생성장치에서 생성된 불특정차량의 차량번호판정보를 비교하여 실시간으로 범죄차량조회를 할 수 있는 것을 특징으로 하는 주행차량의 번호판 인식이 실시간으로 가능한 차량용 블랙박스Criminal vehicle information transmitted from the vehicle license plate information generating device or received from the control center through the communication module and vehicle license plate information of the unspecified vehicle generated by the vehicle license plate information generating device. Vehicle black box capable of real-time license plate recognition, characterized in that to compare the crime vehicle in real time
  10. 제 1항에 있어서, The method of claim 1,
    상기 엔코더부에서 생성된 주행동영상 디지털압축데이터를 저장하는 메모리와;A memory for storing the moving video digital compression data generated by the encoder;
    GPS위성과 통신하여 상기 특정차량의 주행정보에 포함되는 위치정보, 시간정보, 및 경로정보를 획득하는 GPS모듈과; A GPS module which communicates with a GPS satellite to obtain location information, time information, and route information included in driving information of the specific vehicle;
    상기 특정차량의 주행정보와 상기 메모리에 저장된 주행동영상 디지털압축데이터의 재생화면 및 뺑소니차량이나 긴급상황시 응급신호를 입력하기 위한 입력메뉴를 표시하는 터치패널부와; A touch panel unit which displays a driving screen of the specific vehicle and a playback screen of the driving video digital compression data stored in the memory, and an input menu for inputting emergency signals in case of a hit-off vehicle or emergency;
    사전설정된 기준값 이상의 충격을 감지하는 경우 상기 제어부에 충격감지신호를 전송하여 제어부로 하여금 실시간으로 상기 메모리에 일정시간동안의 주행정보와 상기 주행정보에 대응되는 주행동영상 디지털압축데이터를 저장하게 하는 충격감지부; 및In the event of detecting a shock equal to or greater than a predetermined reference value, a shock detection signal is transmitted to the control unit so that the control unit stores driving information for a predetermined time and driving video digital compression data corresponding to the driving information in real time in the memory. part; And
    차량부착시 가속도센서를 이용하여 수평상태를 체크하고 조절하는 캘리브레이션부;를 더 포함하는 것을 특징으로 하는 주행차량의 번호판 인식이 실시간으로 가능한 차량용 블랙박스Calibration unit that checks and adjusts the horizontal state using the acceleration sensor when the vehicle is attached to the vehicle black box capable of real-time license plate recognition, characterized in that it further comprises
PCT/KR2015/001760 2014-08-11 2015-02-24 Vehicle black box capable of real-time recognition of license plate of moving vehicle WO2016024680A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR10-2014-0103384 2014-08-11
KR1020140103384A KR101561626B1 (en) 2014-08-11 2014-08-11 The Vehicle Black Box Capable of Real-Time Recognizing a License Number Plate for Moving Vehicle

Publications (1)

Publication Number Publication Date
WO2016024680A1 true WO2016024680A1 (en) 2016-02-18

Family

ID=54431049

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2015/001760 WO2016024680A1 (en) 2014-08-11 2015-02-24 Vehicle black box capable of real-time recognition of license plate of moving vehicle

Country Status (2)

Country Link
KR (1) KR101561626B1 (en)
WO (1) WO2016024680A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111126397A (en) * 2019-12-27 2020-05-08 上海眼控科技股份有限公司 Dynamic inspection method, system, terminal and medium for vehicle chassis
CN112802355A (en) * 2020-12-29 2021-05-14 北京万集科技股份有限公司 Method, system and storage medium for acquiring real-scene road conditions in real time

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101836088B1 (en) * 2016-11-30 2018-03-08 충북보건과학대학교 산학협력단 Apparatus for processing image
KR101979654B1 (en) * 2018-01-15 2019-05-17 주식회사 비엔인더스트리 License plate recognition apparatus and the method thereof
KR102054061B1 (en) * 2018-01-19 2019-12-09 한국기술교육대학교 산학협력단 Recognition method of Vehicle Licence Plate
CN111191481B (en) * 2018-11-14 2023-08-25 杭州海康威视数字技术股份有限公司 Vehicle identification method and system
KR102189299B1 (en) * 2019-09-11 2020-12-11 한국도로공사 Apparatus and Method for detecting traffic path based on license plate recognition

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004536410A (en) * 2001-07-18 2004-12-02 ヒュンジャエ テック カンパニー リミテッド System and method for automatically recognizing a vehicle number of a monitored vehicle using a monitoring vehicle
KR20100134206A (en) * 2009-06-15 2010-12-23 (주) 알티솔루션 The automatic vehicle identification system of non-trigger type based on image processing and that of using identification method
KR20120077455A (en) * 2010-12-30 2012-07-10 (주)세미솔루션 Image recording apparatus for vehicle
KR101399309B1 (en) * 2013-03-14 2014-05-28 임경묵 Blackbox for vehicle and controlling method for the same

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004536410A (en) * 2001-07-18 2004-12-02 ヒュンジャエ テック カンパニー リミテッド System and method for automatically recognizing a vehicle number of a monitored vehicle using a monitoring vehicle
KR20100134206A (en) * 2009-06-15 2010-12-23 (주) 알티솔루션 The automatic vehicle identification system of non-trigger type based on image processing and that of using identification method
KR20120077455A (en) * 2010-12-30 2012-07-10 (주)세미솔루션 Image recording apparatus for vehicle
KR101399309B1 (en) * 2013-03-14 2014-05-28 임경묵 Blackbox for vehicle and controlling method for the same

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111126397A (en) * 2019-12-27 2020-05-08 上海眼控科技股份有限公司 Dynamic inspection method, system, terminal and medium for vehicle chassis
CN112802355A (en) * 2020-12-29 2021-05-14 北京万集科技股份有限公司 Method, system and storage medium for acquiring real-scene road conditions in real time
CN112802355B (en) * 2020-12-29 2022-09-09 北京万集科技股份有限公司 Method, system and storage medium for acquiring real-scene road conditions in real time

Also Published As

Publication number Publication date
KR101561626B1 (en) 2015-10-30

Similar Documents

Publication Publication Date Title
WO2016024680A1 (en) Vehicle black box capable of real-time recognition of license plate of moving vehicle
WO2017030259A1 (en) Unmanned aerial vehicle having automatic tracking function and control method thereof
US20210183041A1 (en) Monitoring Method and Apparatus
CN105788286A (en) Intelligent red light running identifying system and vehicle behavior detecting and capturing method
CN101344988A (en) Image acquisition and processing equipment and method, vehicle monitoring and recording system
US8208022B2 (en) Apparatus and method for removing blooming of camera image
KR101492473B1 (en) Context-aware cctv intergrated managment system with user-based
CN110580808B (en) Information processing method and device, electronic equipment and intelligent traffic system
WO2016072625A1 (en) Vehicle location checking system for a parking lot using imaging technique, and method of controlling same
JP2020014144A (en) Camera system and event record system
CN101388146A (en) Image acquisition and treatment apparatus and method, and vehicle monitoring and recording system
KR101621822B1 (en) Device for security and recognizing number of license plate based on hybrid image transmission, and method for recognizing and providing number of license plate using the same
WO2017195965A1 (en) Apparatus and method for image processing according to vehicle speed
KR100948382B1 (en) Security service method and system
KR101340897B1 (en) The anticrime system in a school zone
US8229170B2 (en) Method and system for detecting a signal structure from a moving video platform
CN1808516A (en) Vehicle monitoring method, specific character pattern recognition device, and vehicle monitoring system
WO2016072627A1 (en) System and method for managing multiplanar parking lot using one omnidirectional camera
KR101360244B1 (en) Monitoring system for moving things using cctv fluoroscopy
KR102338912B1 (en) Recognition method of vehicles license plate using super resolution
KR101911239B1 (en) The channel extension operation system for detecting illegally parked vehicles
KR102220643B1 (en) CCTV for recognizing car number based on deep learning
KR20140078088A (en) A auto recognition system of vehicle number using CCTV camera
US20200126240A1 (en) In-vehicle camera device, monitoring system and method for estimating moving speed of vehicle
JP3650267B2 (en) Fixed point monitoring system

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 15832408

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 28.07.17)

122 Ep: pct application non-entry in european phase

Ref document number: 15832408

Country of ref document: EP

Kind code of ref document: A1