CN114199141A - Device and method for detecting left-right height difference of automobile body based on stereoscopic vision - Google Patents
Device and method for detecting left-right height difference of automobile body based on stereoscopic vision Download PDFInfo
- Publication number
- CN114199141A CN114199141A CN202111482163.4A CN202111482163A CN114199141A CN 114199141 A CN114199141 A CN 114199141A CN 202111482163 A CN202111482163 A CN 202111482163A CN 114199141 A CN114199141 A CN 114199141A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- height difference
- camera
- image
- industrial control
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 14
- 238000001514 detection method Methods 0.000 claims abstract description 27
- 238000005516 engineering process Methods 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 7
- 239000000284 extract Substances 0.000 claims abstract description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 abstract description 4
- 238000009434 installation Methods 0.000 abstract description 3
- 238000011160 research Methods 0.000 abstract description 2
- 230000002146 bilateral effect Effects 0.000 description 6
- 229910000831 Steel Inorganic materials 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000004642 transportation engineering Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/06—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness for measuring thickness ; e.g. of sheet material
- G01B11/0608—Height gauges
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a device and a method for detecting left and right height difference of an automobile body based on stereoscopic vision, belonging to automobile safety performance detection equipment. The device includes: 2 cameras with the same model, 1 gantry support, 1 industrial control computer and the like. The device utilizes 1 group of cameras to collect the image of the tail part of the vehicle when the brake lamp at the tail part of the vehicle is lightened, adopts a computer image processing technology to segment and extract the outline of the brake lamp at the tail part of the vehicle, reconstructs two-dimensional coordinates of the outline of the brake lamp, and calculates the absolute value of the difference value of the longitudinal coordinates of the outline centroids of the brake lamps at the left side and the right side by extracting the outline centroids of the brake lamps so as to obtain the height difference of the left side and the right side of the vehicle body. The invention can obtain the left-right height difference of the automobile body under the non-contact condition. The method has the advantages of novel and unique design concept, good detection precision, simple device structure and convenient installation and operation. The research result has certain theoretical value and practical value and has good application and popularization prospect.
Description
Technical Field
The invention belongs to detection equipment of automobile safety performance, and particularly relates to a device and a method for detecting left and right height difference of an automobile body based on stereoscopic vision. The method comprises the steps of collecting a vehicle tail image when a vehicle tail brake lamp is turned on by using 2 cameras, segmenting and extracting the outline of the vehicle tail brake lamp by using a computer image processing technology, reconstructing two-dimensional coordinates of the outline of the tail brake lamp, calculating the outline centroid of the brake lamp, and calculating the absolute value of the difference value of the longitudinal coordinates of the outline centroids of the left brake lamp and the right brake lamp so as to obtain the left-right height difference of a vehicle body. The device has the characteristics of high detection precision and good system reliability, has high detection speed and strong repeatability, has a simple structure, is reasonable in design, and reduces the manufacturing cost of the detection device.
Background
After the automobile runs for a long time, jolts or collides, the height difference of the bilateral symmetry point of the automobile body is overlarge due to the deformation of the frame and the axle, the loosening of the riding bolt, the abrasion of the axle connection part, looseness and the like. The height difference of the bilateral symmetry point of the automobile body directly influences the smoothness of the automobile and influences various performances of the automobile such as safety, operation stability, trafficability, fuel economy and the like. For the requirement of the height difference of the bilateral symmetry point of the automobile body, the 5.1.10.2.2 th regulation in the national standard GB 18565-2016 (the comprehensive performance requirement and inspection method of road transport vehicles): the car body should be well-rounded, and the height difference of the left and right symmetrical parts of the outer edge of the car body should be less than or equal to 40 mm.
The research institute of automobile transportation engineering of Jilin university has developed the height difference measuring apparatu of automobile body bilateral symmetry point based on laser rangefinder principle. The device firstly finds a point on a vehicle body through a laser, and the laser is reset and cleared. And then, the holder is controlled to rotate horizontally until the laser finds the position close to the symmetric point on the other side of the vehicle body, at the moment, the laser finally finds the symmetric point by controlling the lifting of the holder, and the data at the moment is the height difference of the bilateral symmetric point of the vehicle body. However, the method is difficult to detect the red vehicle, and large errors are caused by manually controlling the cradle head to ascend and descend to search for the symmetrical point, so that the detection speed is low.
At present, there is no efficient device for detecting the left-right height difference of the automobile body, and with the development of the digital image processing technology, a device for detecting the left-right height difference of the automobile body based on the stereoscopic vision is researched to detect the left-right height difference of the automobile body.
Disclosure of Invention
The invention mainly aims to provide a device and a method for detecting the left-right height difference of an automobile body based on stereoscopic vision. The device has unique design concept, convenient installation and high detection precision.
The above object of the present invention can be achieved by the following technical solutions, which are described below with reference to the accompanying drawings:
the device comprises 1 group of camera devices and an industrial control computer, wherein the camera devices respectively comprise 2 cameras with the same type and 1 gantry support, and the gantry supports are arranged at the tail ends of a vehicle detection area. The cameras A1 and A2 are installed on a camera horizontal bracket of the gantry bracket and are horizontally installed perpendicular to a driving line. The distance between the camera and the vehicle detection area is the optimal wide-angle calibration distance (1500-2000 mm) of the camera, the height from the ground is 4500mm, and the base line distance between the two cameras is 1400-2500 mm.
The detection method of the left-right height difference of the automobile body by the detection device comprises the following steps.
Step one, performing wide-angle accurate calibration of the shooting direction on calibration templates for the camera respectively.
And step two, after the vehicle enters the detection area and stops, the industrial control computer prompts a driver to step on a service brake pedal, and after the tail brake light of the vehicle is lightened, the camera starts to acquire the tail image of the vehicle.
And step three, simultaneously, extracting the outline of the tail lamp and reconstructing a two-dimensional coordinate by a detection program in the industrial control computer according to the image acquired by the camera by adopting a computer image processing technology, calculating the outline centroid of the stop lamp, and calculating the absolute value of the difference value of the longitudinal coordinates of the outline centroids of the left tail lamp and the right tail lamp so as to obtain the left-right height difference of the vehicle body.
The method for detecting the centroid of the tail lamp of the vehicle by the industrial control computer comprises the following steps: after the camera collects the image of the tail of the vehicle and transmits the image to the industrial control computer, the computer extracts the tail lamp part of the vehicle by identifying the gray value of the image, and binarizes the tail lamp part and the background part, wherein the tail lamp part is set to be white, and the rest part is black. Binarization and threshold determination are as follows:
in the formula, 1 represents white, 0 represents black, target represents a tail stop lamp portion, and background represents a portion other than the stop lamp. x and y represent pixel coordinate values in the horizontal direction and the vertical direction of the acquired image, respectively. g (x, y) is a gray value gray expression of coordinates (x, y). Calculation expression of the tail lamp centroid coordinate value:
in the formula x0、y0And the coordinate values of the centroid in the horizontal direction and the vertical direction are respectively represented, and N is a total pixel point in the horizontal direction and the vertical direction. According to the formula, the left tail and the right tail can be calculated through the traversal of the pixelsCoordinates (x) of the center of the lampl,yl)_And (x)r,yr) And finally calculating ylAnd yrAnd the absolute value of the difference can obtain the left-right height difference of the vehicle body.
The innovation of the invention is as follows: (1) the left-right height difference of the vehicle body is detected by calculating the left-right symmetric points of the vehicle body by using a binocular vision and centroid detection technology. (2) A set of mode for automatically extracting the centroid of the tail lamp of the vehicle is designed to calculate the bilateral symmetry point of the vehicle body. (3) The height difference of the left and right sides of the vehicle body can be efficiently, conveniently and accurately detected.
Drawings
FIG. 1 is a schematic axial side projection view of a device for detecting a lateral height difference of an automobile body.
Figure 2 is a front view of the gantry support.
Fig. 3 is a schematic view of an image captured by a binocular camera.
FIG. 4 is a binary graphical illustration after processing by an industrial control computer.
Fig. 5 is a schematic view of a pixel coordinate system of the tail light extraction section.
Fig. 6 is a detection flowchart.
In the figure: 1. camera A, B for 2, gantry support for 3, industrial control computer for 4, camera vertical support for 5, and camera horizontal support for 6.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. The following examples are presented merely to further understand and practice the present invention and are not to be construed as further limiting the claims of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, where terms are involved, such as: the directional or positional relationships indicated by "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., are based on the directional or positional relationships shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the device or part (element) referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention.
In the description of the present invention, it should be noted that unless otherwise explicitly stated or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; the two elements can be directly connected or indirectly connected through an intermediate medium, and the two elements can be communicated with each other internally, and can be flexibly connected, rigidly connected or movably connected. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
The invention relates to a device for detecting the left-right height difference of an automobile body based on stereoscopic vision, which mainly comprises a gantry support 3, 2 cameras A1 and B2 with the same model and an industrial control computer 4. The model of the camera is DH-HV3150UC, a color digital image sensor is adopted, the resolution is 2048 x 1536, a USB interface is adopted, a variable focus lens can be matched, and the model of the industrial control computer 4 is Inulae IPC-810E.
Referring to fig. 2, the gantry support 3 is composed of a camera vertical support 5 and a camera horizontal support 6, and is composed of hollow square steel, the side length of the hollow square steel is 150mm, the height of the camera vertical support 5 is 4500mm, and the length of the camera horizontal support 6 is 5000 mm.
The invention relates to a method for detecting left and right height difference of an automobile body based on stereoscopic vision. Before the detection starts, the internal and external parameters of two cameras A1 and A2 are obtained according to a camera calibration method, after the vehicle enters a detection area and stops, the industrial control computer 4 prompts a driver to step on a service brake pedal, and after the tail brake light of the vehicle is lightened, the cameras start to acquire the tail images of the vehicle. The detection program in the industrial control computer 4 extracts the tail lamp part and reconstructs two-dimensional coordinates by adopting a computer image processing technology according to the image acquired by the camera, calculates the outline centroid of the stop lamp, and obtains the left-right height difference of the vehicle body by calculating the absolute value of the difference value of the longitudinal coordinates of the outline centroids of the left stop lamp and the right stop lamp.
Referring to fig. 3, a vehicle tail image is taken for a binocular camera.
Referring to fig. 4, the method for the industrial control computer 4 to detect the centroid of the tail light of the vehicle: after the camera collects the image of the tail of the vehicle and transmits the image to the industrial control computer 4, the industrial control computer 4 extracts the tail lamp part of the vehicle by identifying the gray value of the image, and binarizes the tail lamp part and the background part, wherein the tail lamp part is set to be white, and the background part is black. Binarization and threshold determination are as follows:
in the formula, 1 represents white, 0 represents black, target represents a tail stop lamp portion, and background represents a portion other than the stop lamp. x and y represent pixel coordinate values in the horizontal direction and the vertical direction of the acquired image, respectively. g (x, y) is a gray value gray expression of coordinates (x, y). Calculation expression of the tail lamp centroid coordinate value:
in the formula x0、y0And the coordinate values of the centroid in the horizontal direction and the vertical direction are respectively represented, and N is a total pixel point in the horizontal direction and the vertical direction. According to the formula, the coordinates (x) of the centroids of the left tail lamp and the right tail lamp can be calculated through the traversal of the pixelsl,yl)_And (x)r,yr) And finally calculating ylAnd yrAnd the absolute value of the difference can obtain the left-right height difference of the vehicle body.
Referring to fig. 5, the horizontal direction is an x-axis of the pixel coordinate system, and the vertical direction is a y-axis of the pixel coordinate system; the tail lamp part is a part (target) to be extracted, and g (x, y) of each pixel point of the part is 1; the portion other than the tail light is a background portion (background), and g (x, y) of each pixel point in the background portion is 0.
Referring to fig. 1, the overall arrangement of the detection system is as shown in fig. 1. The detection device has the advantages of novel and unique structural design concept, high verification precision, strong repeatability, simple structure and convenience in installation and operation.
The foregoing embodiments are merely illustrative of the technical spirit and features of the present invention, and are intended to enable those skilled in the art to understand the contents of the present invention and implement the present invention, and not to limit the scope of the present invention. All equivalent changes and modifications made according to the spirit of the present invention should be covered within the protection scope of the present invention.
While embodiments of the invention have been disclosed above, it is not intended to be limited to the uses set forth in the specification and examples. It can be applied to all kinds of fields suitable for the present invention. Additional modifications will readily occur to those skilled in the art. It is therefore intended that the invention not be limited to the exact details and illustrations described and illustrated herein, but fall within the scope of the appended claims and equivalents thereof.
Claims (3)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111482163.4A CN114199141A (en) | 2021-12-07 | 2021-12-07 | Device and method for detecting left-right height difference of automobile body based on stereoscopic vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111482163.4A CN114199141A (en) | 2021-12-07 | 2021-12-07 | Device and method for detecting left-right height difference of automobile body based on stereoscopic vision |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114199141A true CN114199141A (en) | 2022-03-18 |
Family
ID=80650824
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111482163.4A Pending CN114199141A (en) | 2021-12-07 | 2021-12-07 | Device and method for detecting left-right height difference of automobile body based on stereoscopic vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114199141A (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH06258044A (en) * | 1993-03-09 | 1994-09-16 | Hitachi Electron Eng Co Ltd | Orbit measuring device optical system water drop prevention device |
CN101025360A (en) * | 2007-02-02 | 2007-08-29 | 吉林大学 | Non-contact type hand-driven automobile body left-right symmetric point height difference detector |
CN101825447A (en) * | 2010-01-08 | 2010-09-08 | 浙江浙大鸣泉科技有限公司 | Motor vehicle parking deflection angle testing method and device |
CN103411565A (en) * | 2013-08-29 | 2013-11-27 | 临沂大学 | Automobile body inclination degree measurement method of small automobile |
CN103826096A (en) * | 2012-11-15 | 2014-05-28 | Og技术公司 | Method and apparatus for uniformly focused ring light |
CN106197374A (en) * | 2016-08-15 | 2016-12-07 | 临沂大学 | Car body angle excursion measuring method |
CN109781016A (en) * | 2019-03-13 | 2019-05-21 | 江西五十铃汽车有限公司 | A kind of method of the high performances such as real-time measurement automobile |
CN111895861A (en) * | 2020-07-27 | 2020-11-06 | 张劲 | Automatic target-reporting and trajectory measuring system of related double-sampling linear array sensor |
-
2021
- 2021-12-07 CN CN202111482163.4A patent/CN114199141A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH06258044A (en) * | 1993-03-09 | 1994-09-16 | Hitachi Electron Eng Co Ltd | Orbit measuring device optical system water drop prevention device |
CN101025360A (en) * | 2007-02-02 | 2007-08-29 | 吉林大学 | Non-contact type hand-driven automobile body left-right symmetric point height difference detector |
CN101825447A (en) * | 2010-01-08 | 2010-09-08 | 浙江浙大鸣泉科技有限公司 | Motor vehicle parking deflection angle testing method and device |
CN103826096A (en) * | 2012-11-15 | 2014-05-28 | Og技术公司 | Method and apparatus for uniformly focused ring light |
CN103411565A (en) * | 2013-08-29 | 2013-11-27 | 临沂大学 | Automobile body inclination degree measurement method of small automobile |
CN106197374A (en) * | 2016-08-15 | 2016-12-07 | 临沂大学 | Car body angle excursion measuring method |
CN109781016A (en) * | 2019-03-13 | 2019-05-21 | 江西五十铃汽车有限公司 | A kind of method of the high performances such as real-time measurement automobile |
CN111895861A (en) * | 2020-07-27 | 2020-11-06 | 张劲 | Automatic target-reporting and trajectory measuring system of related double-sampling linear array sensor |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107133985B (en) | An automatic calibration method of vehicle camera based on vanishing point of lane line | |
CN101549683B (en) | Vehicle intelligent method for automatically identifying road pit or obstruction | |
CN104916163B (en) | Parking space detection method | |
CN110008893B (en) | An automatic detection method of vehicle deviation based on vehicle image sensor | |
CN111967360B (en) | Target vehicle posture detection method based on wheels | |
CN106289159B (en) | Vehicle distance measurement method and device based on distance measurement compensation | |
CN109435942A (en) | A kind of parking stall line parking stall recognition methods and device based on information fusion | |
CN101131321A (en) | A method and device for real-time measurement of safe vehicle distance for vehicle collision avoidance warning | |
CN103661365B (en) | A kind of method improving vehicle meeting security | |
CN102288121A (en) | Method for measuring and pre-warning lane departure distance based on monocular vision | |
CN111272139B (en) | A vehicle length measurement method based on monocular vision | |
CN109827516B (en) | Method for measuring distance through wheel | |
CN104700414A (en) | Rapid distance-measuring method for pedestrian on road ahead on the basis of on-board binocular camera | |
US20200074212A1 (en) | Information processing device, imaging device, equipment control system, mobile object, information processing method, and computer-readable recording medium | |
CN103837139A (en) | Rough road surface driving assisted equipment and method for rough road driving assisting | |
CN106153000A (en) | A kind of front vehicles distance detection method | |
CN102706291B (en) | Method for automatically measuring road curvature radius | |
CN112529935B (en) | Target vehicle motion state identification method and device | |
CN105206109A (en) | Infrared CCD based foggy day identifying early-warning system and method for vehicle | |
CN103196418A (en) | Measuring method of vehicle distance at curves | |
CN106679633A (en) | Vehicle-mounted distance measuring system and vehicle-mounted distance measuring method | |
CN102538766A (en) | Obstacle test method for active intelligent vehicle | |
CN104792302A (en) | Modeling method for measuring car distance | |
CN103411565B (en) | Automobile body inclination degree measurement method of small automobile | |
JPWO2016208198A1 (en) | Three-dimensional object detection device, stereo camera device, vehicle, and three-dimensional object detection method |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20220318 |