CN112465921A - Device and method for measuring front visual field of vehicle driver - Google Patents

Device and method for measuring front visual field of vehicle driver Download PDF

Info

Publication number
CN112465921A
CN112465921A CN202011462684.9A CN202011462684A CN112465921A CN 112465921 A CN112465921 A CN 112465921A CN 202011462684 A CN202011462684 A CN 202011462684A CN 112465921 A CN112465921 A CN 112465921A
Authority
CN
China
Prior art keywords
driver
camera
measuring
visual field
image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202011462684.9A
Other languages
Chinese (zh)
Inventor
寇戈
王飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing University of Science and Technology
Original Assignee
Nanjing University of Science and Technology
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 Nanjing University of Science and Technology filed Critical Nanjing University of Science and Technology
Priority to CN202011462684.9A priority Critical patent/CN112465921A/en
Publication of CN112465921A publication Critical patent/CN112465921A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
    • G06T7/85—Stereo camera calibration
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/70—Denoising; Smoothing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/80—Geometric correction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/90—Dynamic range modification of images or parts thereof
    • G06T5/92—Dynamic range modification of images or parts thereof based on global image properties
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20024—Filtering details
    • G06T2207/20032—Median filtering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30248—Vehicle exterior or interior
    • G06T2207/30252—Vehicle exterior; Vicinity of vehicle

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Processing (AREA)

Abstract

The invention discloses a device and a method for measuring the front visual field of a vehicle driver, wherein the device comprises a chassis, two CMOS cameras which are embedded into the front end surface of the chassis and arranged in parallel, and the cameras acquire images of windscreen in front of the driver in real time through wide-angle lenses; the switch and the power panel are arranged in the case, the power panel is used for supplying power for other parts of the device, the switch is used for transmitting images collected by the CMOS camera to the upper computer, and the upper computer performs image processing to calculate the front view of a driver. The device for measuring the front visual field of the vehicle driver adopts the wide-angle lens aperture diaphragm to simulate the pupils of human eyes, increases the measurement range, and simultaneously adopts the Zhang-friend method to calibrate the camera and correct distortion, thereby improving the measurement precision. The invention can carry out human-computer interaction through the upper computer, carry out operations such as real-time checking, storage and the like on the measurement result, and carry out qualification judgment on the result, and has convenient operation and strong practicability.

Description

Device and method for measuring front visual field of vehicle driver
Technical Field
The invention belongs to the technical field of vehicle measurement, and particularly relates to a device and a method for measuring the front visual field of a vehicle driver.
Background
The field of view in front of the driver of the vehicle refers to the entire area within 180 ° in front of the driver that can be directly observed without the aid of any tools or equipment. The front view is required as follows: the transparent area of the windshield should comprise at least the area enclosed by 6 windshield reference point connecting lines, wherein the reference points comprise: 1) a reference point a with a V1 point horizontally and forwards deviated by 17 degrees, 2) a reference point b with a V2 point forwards deviated by 7 degrees along the vertical plane, 3) a reference point c with a V2 point forwards deviated by 5 degrees along the vertical plane, 4) 3 reference points a ', b ' and c ' symmetrical to the reference points are added on the other side of the longitudinal symmetrical plane of the automobile. The measurement of the front view of the vehicle driver is one of the measurement items required by the national standard GB11562-2014 'requirements and measurement methods for the front view of the vehicle driver' and is also an important reference index in the vehicle safety inspection process. The front view of the vehicle driver also relates to whether the driver can timely and accurately find and avoid the obstacles on the front road, and the method has important significance on the driving safety and the maneuverability of the vehicle.
At present, a complete set of automobile visual field detection equipment consisting of a three-coordinate measuring machine, a laser visual field tester and an eyepoint simulator for measuring the automobile visual field is mainly adopted for measuring the front visual field of a vehicle driver. The device uses a helium-neon laser to emit red light beams to simulate the sight of a driver, the red light beams can rotate around a vertical axis and a horizontal axis in two directions, numerical value display and printing of a pitching angle and a horizontal angle and program control are realized under the control of a computer, and the visual field range can be visually seen through a laser measuring machine. However, the measurement method needs three large-scale instruments for cooperation, is complex to operate and is greatly influenced by human factors.
How to reduce the influence of human and environmental factors, improve the measurement precision, simplify the measurement steps, and make the measurement method develop to automation and practicality is a problem to be solved urgently by those skilled in the art.
Disclosure of Invention
The invention aims to provide a device and a method for measuring the front visual field of a vehicle driver, aiming at the problems in the prior art.
The technical solution for realizing the purpose of the invention is as follows: a device for measuring the front visual field of a vehicle driver comprises a chassis, two CMOS cameras which are embedded in the front end face of the chassis and arranged in parallel, wherein the cameras acquire images of windshield glass in front of the driver in real time through a wide-angle lens; the switch and the power panel are arranged in the case, the power panel is used for supplying power to other parts of the device, the switch is used for transmitting images collected by the CMOS camera to the upper computer, and the upper computer performs image processing to calculate the front view of a driver.
Further, the upper computer can carry out camera calibration before carrying out image processing, and the specific process comprises:
collecting a checkerboard calibration graph;
detecting image characteristic points;
and calculating the internal parameters and the external parameters of the camera according to the characteristic points to finish the calibration and distortion correction of the camera.
Further, the upper computer performs image processing, and the specific process comprises:
step 1, converting a received original image into a gray image;
step 2, performing thresholding segmentation to segment the target and the background;
step 3, median filtering is carried out to filter out high-frequency noise in the image;
step 4, carrying out edge detection to obtain the outline of the windshield glass;
and 5, calculating the front visual field of the driver according to the measuring method of the machine binocular vision distance measurement, namely calculating the angle values of the horizontal direction and the vertical direction of the windshield glass.
Further, in step 5, the angle values of the horizontal and vertical directions of the windshield glass are calculated according to the following formula:
Figure BDA0002833037700000021
wherein the content of the first and second substances,
Figure BDA0002833037700000022
z is the distance from the target point to the imaging plane of the CMOS camera, the target point is the central point of the horizontal edge or the central point of the vertical edge of the windshield glass, then alpha respectively corresponds to the angle values of the horizontal and vertical directions of the windshield glass, T is the central distance of the double CMOS cameras, and f is the distance of the CMOS cameraFocal length, d is parallax, d ═ xr-xl，(xr,yr)、(xl,yl) The coordinates of the target point in the left eye camera and the right eye camera are respectively, and y is the vertical distance from the target point to the middle point of the connecting line of the binocular camera.
A method of forward vision measurement for a vehicle driver, the method comprising the steps of:
step 1, calibrating and correcting distortion of a binocular CMOS camera;
step 2, a binocular CMOS camera collects images of windshield glass in front of a driver and transmits the images to an upper computer through a switch;
and 3, calculating the front view of the driver by the upper computer according to the received image.
Compared with the prior art, the invention has the following remarkable advantages: 1) the device adopts a wide-angle lens aperture diaphragm to simulate the pupil of a human eye, and the imaging measurement of a CMOS camera is less influenced by human and environmental factors; 2) the device adopts a wide-angle lens for imaging, so that the measurement range is enlarged, and meanwhile, a Zhang-friend method is adopted for camera calibration and distortion correction, so that the measurement precision is improved; 3) man-machine interaction can be carried out through the upper computer, and operations such as real-time checking, storage and the like are carried out on the measurement result; 4) the automatic measurement of the front view of the vehicle driver can be realized after the correct installation device is started, the result is subjected to qualification judgment, and the device is convenient to operate and high in practicability.
The present invention is described in further detail below with reference to the attached drawing figures.
Drawings
FIG. 1 is a schematic structural diagram of a device for measuring a forward field of view of a driver of a vehicle according to an embodiment.
Fig. 2 is a schematic diagram of the ranging principle in one embodiment.
FIG. 3 is a flow diagram of image processing in one embodiment.
FIG. 4 is a schematic diagram of a host computer of the measurement system in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In one embodiment, in combination with fig. 1, a device for measuring the front visual field of a driver of a vehicle is provided, and the device comprises a case 3, two parallel CMOS cameras 2 embedded in the front end face of the case 3, and the cameras collect images of a windshield in front of the driver in real time through a wide-angle lens 1; the switch 4 and the power panel 5 are arranged in the case 3, the power panel 5 is used for supplying power to other parts of the device, the switch 4 is used for transmitting images collected by the CMOS camera 2 to the upper computer 6, and the upper computer 6 performs image processing to calculate the front view of a driver.
The wide-angle lens is connected with the CMOS camera through an interface, and the switch is connected with the upper computer through a network cable.
As shown in fig. 4, the upper computer system interface of the device for measuring the field of vision in front of the driver of the vehicle can check the detection target in real time through the video window, and the system automatically measures the detection target after clicking the detection button to obtain the detection result.
Further, in one embodiment, before the image processing, the upper computer 6 performs camera calibration, and the specific process includes:
collecting a checkerboard calibration graph;
detecting image characteristic points;
and calculating the internal parameters and the external parameters of the camera according to the characteristic points to finish the calibration and distortion correction of the camera.
Further, in one embodiment, with reference to fig. 3, the upper computer 6 performs image processing, and the specific process includes:
step 1, converting a received original image into a gray image, and compressing the data volume;
step 2, performing thresholding segmentation to segment the target and the background;
step 3, median filtering is carried out to filter out high-frequency noise in the image;
step 4, carrying out edge detection to obtain the outline of the windshield glass;
and 5, calculating the front visual field of the driver according to the measuring method of the machine binocular vision distance measurement, namely calculating the angle values of the horizontal direction and the vertical direction of the windshield glass.
Further, in one embodiment, in conjunction with FIG. 2, XlOlYl、XrOrYrImage coordinate systems of a left eye camera and a right eye camera respectively, and the angle values of the horizontal direction and the vertical direction of the windshield glass are calculated in the step 5, wherein the calculation formula is as follows:
Figure BDA0002833037700000041
wherein the content of the first and second substances,
Figure BDA0002833037700000042
z is the distance from a target point P to the imaging plane of the CMOS camera, the target point is the central point of the horizontal edge or the central point of the vertical edge of the windshield glass, alpha respectively corresponds to the angle value of the horizontal direction and the vertical direction of the windshield glass, T is the central distance of the double CMOS cameras, f is the focal length of the CMOS camera, d is the parallax (the difference of the horizontal coordinates of the imaging of the target point on the left view and the right view), and d is xr-xl，(xr,yr)、(xl,yl) The coordinate of the target point in the left eye camera and the coordinate of the target point in the right eye camera are respectively, y is the vertical distance from the target point to the midpoint of the line connecting the binocular cameras, and alpha is the included angle of the line connecting the target point and the midpoint of the line connecting the binocular cameras relative to the XOY plane.
In one embodiment, a method of forward vision measurement for a vehicle driver is provided, the method comprising the steps of:
step 1, calibrating and correcting distortion of a binocular CMOS camera;
step 2, a binocular CMOS camera collects images of windshield glass in front of a driver and transmits the images to an upper computer 6 through a switch 4;
and 3, calculating the front view of the driver by the upper computer 6 according to the received image.
Further, in one embodiment, the upper computer 6 in step 3 calculates the front view of the driver according to the received image, and the specific process includes:
step 3-1, converting the received original image into a gray image;
step 3-2, performing thresholding segmentation to segment the target and the background;
3-3, performing median filtering to filter high-frequency noise in the image;
step 3-4, carrying out edge detection to obtain the outline of the windshield glass;
and 3-5, calculating the front visual field of the driver according to a measuring method of the machine binocular vision ranging, namely calculating the angle values of the horizontal direction and the vertical direction of the windshield glass.
For specific limitations of the vehicle driver front vision field measurement method, reference may be made to the above limitations of the vehicle driver front vision field measurement system, which are not described in detail herein.
It is to be understood that the above embodiments are merely exemplary embodiments that have been employed to illustrate the principles of the present invention. It will be apparent to those skilled in the art that various modifications and improvements can be made without departing from the spirit and substance of the invention, and these modifications and improvements are also considered to be within the scope of the invention.

Claims (6)

1. The device for measuring the front visual field of the vehicle driver is characterized by comprising a case (3), two CMOS cameras (2) which are embedded into the front end face of the case (3) and arranged in parallel, wherein the cameras acquire images of windshield glass in front of the driver in real time through a wide-angle lens (1); set up switch (4) and power strip (5) in quick-witted case (3), power strip (5) are used for supplying power for other parts of device, switch (4) are used for transmitting the image that CMOS camera (2) gathered to host computer (6), and host computer (6) carry out image processing and calculate driver place ahead field of vision.
2. The device for measuring the forward visual field of the driver of the vehicle according to claim 1, wherein the upper computer (6) performs camera calibration before image processing, and the specific process comprises the following steps:
collecting a checkerboard calibration graph;
detecting image characteristic points;
and calculating the internal parameters and the external parameters of the camera according to the characteristic points to finish the calibration and distortion correction of the camera.
3. The device for measuring the field of vision ahead of the driver of the vehicle according to claim 2, characterized in that the upper computer (6) performs image processing, and the specific process comprises:
step 1, converting a received original image into a gray image;
step 2, performing thresholding segmentation to segment the target and the background;
step 3, median filtering is carried out to filter out high-frequency noise in the image;
step 4, carrying out edge detection to obtain the outline of the windshield glass;
and 5, calculating the front visual field of the driver according to the measuring method of the machine binocular vision distance measurement, namely calculating the angle values of the horizontal direction and the vertical direction of the windshield glass.
4. The device for measuring the forward visibility of a vehicle driver as claimed in claim 3, wherein the calculation of the angle values of the horizontal and vertical directions of the windshield in step 5 is represented by the following formula:
Figure FDA0002833037690000011
wherein the content of the first and second substances,
Figure FDA0002833037690000012
z is the distance from the target point to the imaging plane of the CMOS camera, the target point is the central point of the horizontal edge or the central point of the vertical edge of the windshield glass, alpha respectively corresponds to the angle value of the horizontal and vertical directions of the windshield glass, T is the central distance of the double CMOS cameras, f is the focal length of the CMOS camera, d is the parallax, d is xr-xl，(xr,yr)、(xl,yl) The coordinates of the target point in the left eye camera and the right eye camera are respectively, and y is the vertical distance from the target point to the middle point of the connecting line of the binocular camera.
5. Method for measuring the forward visibility of a driver of a vehicle, based on the device according to any one of claims 1 to 4, characterized in that it comprises the following steps:
step 1, calibrating and correcting distortion of a binocular CMOS camera;
step 2, a binocular CMOS camera collects images of windshield glass in front of a driver and transmits the images to an upper computer (6) through a switch (4);
and 3, calculating the front view of the driver by the upper computer (6) according to the received image.
6. The method for measuring the front visual field of the vehicle driver according to claim 5, wherein the upper computer (6) in the step 3 calculates the front visual field of the driver according to the received image, and the specific process comprises the following steps:
step 3-1, converting the received original image into a gray image;
step 3-2, performing thresholding segmentation to segment the target and the background;
3-3, performing median filtering to filter high-frequency noise in the image;
step 3-4, carrying out edge detection to obtain the outline of the windshield glass;
and 3-5, calculating the front visual field of the driver according to a measuring method of the machine binocular vision ranging, namely calculating the angle values of the horizontal direction and the vertical direction of the windshield glass.
CN202011462684.9A 2020-12-14 2020-12-14 Device and method for measuring front visual field of vehicle driver Pending CN112465921A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011462684.9A CN112465921A (en) 2020-12-14 2020-12-14 Device and method for measuring front visual field of vehicle driver

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011462684.9A CN112465921A (en) 2020-12-14 2020-12-14 Device and method for measuring front visual field of vehicle driver

Publications (1)

Publication Number Publication Date
CN112465921A true CN112465921A (en) 2021-03-09

Family

ID=74804048

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011462684.9A Pending CN112465921A (en) 2020-12-14 2020-12-14 Device and method for measuring front visual field of vehicle driver

Country Status (1)

Country Link
CN (1) CN112465921A (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108805910A (en) * 2018-06-01 2018-11-13 海信集团有限公司 More mesh Train-borne recorders, object detection method, intelligent driving system and automobile
CN110207650A (en) * 2019-05-31 2019-09-06 重庆迪星天科技有限公司 Automobile-used highway height-limiting frame height measurement method and device based on binocular vision
CN111739101A (en) * 2020-05-12 2020-10-02 太原科技大学 Device and method for eliminating vehicle A column blind area

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108805910A (en) * 2018-06-01 2018-11-13 海信集团有限公司 More mesh Train-borne recorders, object detection method, intelligent driving system and automobile
CN110207650A (en) * 2019-05-31 2019-09-06 重庆迪星天科技有限公司 Automobile-used highway height-limiting frame height measurement method and device based on binocular vision
CN111739101A (en) * 2020-05-12 2020-10-02 太原科技大学 Device and method for eliminating vehicle A column blind area

Similar Documents

Publication Publication Date Title
CN109297413B (en) Visual measurement method for large-scale cylinder structure
EP3792660B1 (en) Method, apparatus and system for measuring distance
WO2023071834A1 (en) Alignment method and alignment apparatus for display device, and vehicle-mounted display system
CN110873879A (en) Device and method for deep fusion of characteristics of multi-source heterogeneous sensor
CN109855845B (en) Binocular eye lens measurement vehicle-mounted HUD virtual image distance and correction method
CN110220500B (en) Binocular camera-based distance measurement method for unmanned driving
CN110966956A (en) Binocular vision-based three-dimensional detection device and method
CN108681337B (en) Unmanned aerial vehicle special for inspection of culverts or bridges and unmanned aerial vehicle inspection method
CN109831655B (en) Ship environment sensing and early warning system based on multi-camera data fusion
CN112037159A (en) Cross-camera road space fusion and vehicle target detection tracking method and system
CN106705862A (en) Position detection method of sleeper bolt for fast rail exchange operation
CN112819711A (en) Monocular vision-based vehicle reverse positioning method utilizing road lane line
CN109299696B (en) Face detection method and device based on double cameras
CN108734729B (en) Method for detecting binocular parallax in head-up display system
CN107145828A (en) Vehicle panoramic image processing method and device
CN110197104B (en) Distance measurement method and device based on vehicle
CN108256487B (en) Driving state detection device and method based on reverse dual-purpose
WO2024046390A1 (en) Marine equipment underwater damage three-dimensional reconstruction method based on combination of vision and imus
CN113267128A (en) Binocular vision automatic side slope displacement monitoring method
CN112465921A (en) Device and method for measuring front visual field of vehicle driver
CN110276276A (en) The determination method and system of examinee's face direction of visual lines in a kind of Driving Test
CN111435075A (en) Computer vision measurement system
CN107886472B (en) Image splicing calibration method and image splicing calibration device of panoramic parking system
CN108454553A (en) One kind realizing obstacle detection technology based on human eye vision identification technology
CN114155300A (en) Projection effect detection method and device for vehicle-mounted HUD system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20210309

RJ01 Rejection of invention patent application after publication