CN111627067B - Calibration method of binocular camera and vehicle-mounted equipment - Google Patents
Calibration method of binocular camera and vehicle-mounted equipment Download PDFInfo
- Publication number
- CN111627067B CN111627067B CN201910153147.7A CN201910153147A CN111627067B CN 111627067 B CN111627067 B CN 111627067B CN 201910153147 A CN201910153147 A CN 201910153147A CN 111627067 B CN111627067 B CN 111627067B
- Authority
- CN
- China
- Prior art keywords
- calibration table
- calibration
- matrix
- measured
- sparse
- 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.)
- Active
Links
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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Analysis (AREA)
Abstract
The application provides a calibration method of a binocular camera and vehicle-mounted equipment, wherein the method can be used for obtaining a preset first calibration table as a calibration table to be tested; calibrating checkerboard images shot by a binocular camera to obtain a corner error matrix of the calibration table to be tested, and judging whether the calibration table to be tested meets preset conditions or not through the corner error matrix; if yes, the calibration table to be measured is used for calibrating the binocular camera; if the calibration table does not meet the preset conditions, correcting the calibration table to be measured according to the angular point error matrix to obtain a second calibration table, and taking the second calibration table as the calibration table to be measured until the calibration table to be measured meeting the preset conditions is obtained for the calibration of the binocular camera. According to the application, when the to-be-measured calibration table does not meet the preset condition, the to-be-measured calibration table can be continuously corrected according to the angular point error matrix corresponding to the to-be-measured calibration table until the calibration table meets the preset condition, so that the calibration precision of the binocular camera can be improved.
Description
Technical Field
The application relates to the technical field of intelligent transportation and auxiliary driving, in particular to a calibration method of a binocular camera and vehicle-mounted equipment.
Background
With the development trend of automobile intellectualization, auxiliary driving, automatic driving and the like are becoming research hotspots in academia and industry, and numerous traditional automobile manufacturers, high-tech enterprises and the like at home and abroad are devoted to pushing out respective solutions. In recent years, schemes based on millimeter wave radars and laser radars have been widely used for high-end automobiles, and the main advantages of the millimeter wave radars are that the millimeter wave radars have strong capability of resisting environmental interference, can penetrate fog, smoke, dust and the like, have all-weather all-day-time working capability, and can directly detect the distance and speed of a vehicle in front. The main advantages of lidar are very accurate ranging capability and ultra-high resolution. However, whether it is a millimeter wave radar or a lidar, there are problems in that a vertical field angle is narrow, a longitudinal resolution is low, color and texture information cannot be provided, and these parameters are very important for many application scenes, such as pedestrian detection, vehicle recognition, traffic sign recognition, and the like.
The vehicle-mounted binocular system comprises the parts of image acquisition, camera calibration, image correction, stereo matching, ADAS (Advanced Driving Assistant System, advanced driving assistance system) functions and the like. The binocular camera needs to keep high synchronism of acquisition time, definition and consistency of left and right image quality when acquiring images; the binocular camera is calibrated to obtain left and right images which are free of distortion, parallel and the like and have the ranging accuracy meeting the requirements; after the left image and the right image are subjected to image correction, stereo matching is carried out, so that sparse/dense parallax images are obtained and are used for a subsequent algorithm to use corresponding distance information; the ADAS function mainly comprises functions of obstacle detection, lane line detection and the like and is used for realizing obstacle detection and lane line detection in front of a vehicle, so that danger early warning is realized.
The existing binocular ADAS system mainly depends on the ranging performance of a camera, and the ranging accuracy of the camera is easily influenced by factors such as the assembly accuracy of a photosensitive unit and various aberrations of a lens, and is easily influenced by factors of algorithms such as a double-target determining algorithm and a matching algorithm. The dual-target calibration algorithm usually performs calibration directly according to a preset calibration table, but when the error existing in the preset calibration table is larger, the calibration accuracy of the dual-target camera calibration algorithm is poor.
Disclosure of Invention
In view of the above, the present application provides a calibration method of a binocular camera and a vehicle-mounted device to solve the problem of poor calibration accuracy of the binocular camera in the prior art.
Specifically, the application is realized by the following technical scheme:
the application provides a calibration method of a binocular camera, which comprises the following steps:
acquiring a preset first calibration table as a calibration table to be measured;
calibrating checkerboard images shot by a binocular camera to obtain a corner error matrix of the calibration table to be tested, and judging whether the calibration table to be tested meets preset conditions or not through the corner error matrix;
if yes, the calibration table to be measured is used for calibrating the binocular camera;
if the calibration table does not meet the preset conditions, correcting the calibration table to be measured according to the angular point error matrix to obtain a second calibration table, and taking the second calibration table as the calibration table to be measured until the calibration table to be measured meeting the preset conditions is obtained for the calibration of the binocular camera.
As one embodiment, the angular point error matrix of the calibration table to be measured is obtained by calibrating the checkerboard image shot by the binocular camera, which comprises
Acquiring left and right checkerboard images in a preset calibration area, and respectively acquiring a left corner coordinate matrix corresponding to the left checkerboard image and a right corner coordinate matrix corresponding to the right checkerboard image based on a calibration table to be tested;
and calculating a corner error matrix corresponding to the calibration table to be measured through the left corner coordinate matrix and the right corner coordinate matrix.
As an embodiment, calculating, by using the left corner coordinate matrix and the right corner coordinate matrix, a corner error matrix corresponding to the calibration table to be measured includes:
the angular point error matrix corresponding to the calibration table to be detected comprises a parallel equipotential error matrix and a parallax matrix, wherein the parallel equipotential error matrix is obtained by calculating the difference value of the ordinate of the left angular point in the left angular point coordinate matrix minus the ordinate of the right angular point in the corresponding right angular point coordinate matrix; and obtaining the parallax matrix by calculating the difference value of the abscissa of the left corner in the left corner coordinate matrix and the abscissa of the right corner in the corresponding right corner coordinate matrix.
As an embodiment, determining, by the angular point error matrix, whether the calibration table to be measured meets a preset condition includes:
calculating to obtain a maximum value, a minimum error value and an average value based on elements in the parallel equipotential error matrix;
calculating to obtain a gradient based on elements in the parallax matrix;
if the maximum value, the minimum value and the mean value are respectively smaller than the corresponding threshold values and the gradient has monotonicity, determining that the calibration table to be tested meets preset conditions; otherwise, determining that the calibration table to be tested does not meet the preset condition.
As an embodiment, correcting the calibration table to be measured according to the angular point error matrix to obtain a second calibration table includes:
correcting the calibration table to be measured based on the angular point error values in the angular point error matrix to obtain a corrected sparse calibration table;
filling the corrected sparse calibration table to obtain a second calibration table.
As an embodiment, correcting the calibration table to be measured based on the corner error value in the corner error matrix to obtain a corrected sparse calibration table includes:
acquiring a left sparse calibration table corresponding to the corner coordinates in the left corner coordinate matrix and a left to-be-measured calibration table in the to-be-measured calibration tables;
acquiring a right sparse calibration table corresponding to the right to-be-measured calibration table in the to-be-measured calibration tables and the corner coordinates in the right corner coordinate matrix;
subtracting half of the angular point error values from the horizontal coordinates and the vertical coordinates of the angular points in the left sparse calibration table to obtain a corrected left sparse calibration table;
and respectively adding half of the angular point error values to the horizontal coordinate and the vertical coordinate of the angular points in the right sparse calibration table to obtain a corrected right sparse calibration table.
As an embodiment, filling the corrected sparse calibration table to obtain a second calibration table includes:
and obtaining a second calibration table by interpolating and filling the corrected sparse calibration table.
Based on the same conception, the application also provides vehicle-mounted equipment, which comprises a memory, a processor, a communication interface and a communication bus;
the memory, the processor and the communication interface communicate with each other through the communication bus;
the memory is used for storing a computer program;
the processor is configured to execute a computer program stored in the memory, where the processor implements any step of the calibration method of the binocular camera when executing the computer program.
Based on the same conception, the present application also provides a computer readable storage medium having stored therein a computer program which, when executed by a processor, implements any step of the calibration method of the binocular camera.
Therefore, the method can be used for obtaining the preset first calibration table as the calibration table to be measured; calibrating checkerboard images shot by a binocular camera to obtain a corner error matrix of the calibration table to be tested, and judging whether the calibration table to be tested meets preset conditions or not through the corner error matrix; if yes, the calibration table to be measured is used for calibrating the binocular camera; if the calibration table does not meet the preset conditions, correcting the calibration table to be measured according to the angular point error matrix to obtain a second calibration table, and taking the second calibration table as the calibration table to be measured until the calibration table to be measured meeting the preset conditions is obtained for the calibration of the binocular camera. According to the application, when the to-be-measured calibration table does not meet the preset condition, the to-be-measured calibration table can be continuously corrected according to the angular point error matrix corresponding to the to-be-measured calibration table until the calibration table meets the preset condition, so that the calibration precision of the binocular camera can be improved.
Drawings
FIG. 1 is a process flow diagram of a method for calibrating a binocular camera in an exemplary embodiment of the present application;
FIG. 2 is a schematic diagram of a checkerboard image in an exemplary embodiment of the present application;
FIG. 3 is a schematic illustration of interpolation in an exemplary embodiment of the application;
FIG. 4 is a process flow diagram of another method of calibrating a binocular camera in an exemplary embodiment of the present application;
fig. 5 is a logical structural diagram of an in-vehicle apparatus in an exemplary embodiment of the present application.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the application. Rather, they are merely examples of apparatus and methods consistent with aspects of the application as detailed in the accompanying claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used herein to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the application. The word "if" as used herein may be interpreted as "at … …" or "at … …" or "responsive to a determination", depending on the context.
In order to solve the problems in the prior art, the application provides a calibration method of a binocular camera and vehicle-mounted equipment, wherein a preset first calibration table can be obtained as a calibration table to be tested; calibrating checkerboard images shot by a binocular camera to obtain a corner error matrix of the calibration table to be tested, and judging whether the calibration table to be tested meets preset conditions or not through the corner error matrix; if yes, the calibration table to be measured is used for calibrating the binocular camera; if the calibration table does not meet the preset conditions, correcting the calibration table to be measured according to the angular point error matrix to obtain a second calibration table, and taking the second calibration table as the calibration table to be measured until the calibration table to be measured meeting the preset conditions is obtained for the calibration of the binocular camera. According to the application, when the to-be-measured calibration table does not meet the preset condition, the to-be-measured calibration table can be continuously corrected according to the angular point error matrix corresponding to the to-be-measured calibration table until the calibration table meets the preset condition, so that the calibration precision of the binocular camera can be improved.
Referring to fig. 1, a process flow diagram of a calibration method of a binocular camera according to an exemplary embodiment of the present application is shown, the method includes:
step 101, acquiring a preset first calibration table as a calibration table to be measured;
in this embodiment, a first calibration table set before the delivery of the binocular camera may be obtained as the calibration table to be measured. The first calibration table comprises a left calibration table and a right calibration table, and the left calibration table and the right calibration table are respectively used for carrying out coordinate calibration on pixel points on a left image and a right image shot by the binocular camera.
102, calibrating a checkerboard image shot by a binocular camera to obtain a corner error matrix of the calibration table to be tested, and judging whether the calibration table to be tested meets preset conditions or not through the corner error matrix;
in this embodiment, the angular point error matrix of the calibration table to be measured may be obtained by calibrating the checkerboard image shot by the binocular camera, so as to determine whether the calibration table to be measured meets a preset condition according to the angular point error matrix. The specific method comprises the following steps:
first, the binocular camera can acquire left and right checkered images by shooting a checkered template, wherein the checkered template is a calibration plate formed by black and white square intervals, and is used as a calibration object for calibrating the camera, such as the checkered template shown in fig. 2, and the area marked by a black thin solid line frame is a preset calibration area. After shooting by a binocular camera, left and right checkerboard images in a preset calibration area can be obtained, and then a left corner coordinate matrix corresponding to the left checkerboard image and a right corner coordinate matrix corresponding to the right checkerboard image are obtained based on a calibration table to be tested. Specifically, the left calibration table and the right calibration table are included in the calibration table to be tested, so that the obtained left checkerboard image and right checkerboard image can be respectively corresponding to each other, coordinates corresponding to corner points of the checkerboard are searched for based on the calibration table to be tested corresponding to the checkerboard image, and the searched corner point coordinates form a matrix, so that a left corner point coordinate matrix and a right corner point coordinate matrix can be respectively obtained. The corner points refer to the intersection points of two adjacent black grids in the checkerboard image, as shown by a point A in fig. 2.
And secondly, calculating a corner error matrix corresponding to the calibration table to be measured through the left corner coordinate matrix and the right corner coordinate matrix. Specifically, a difference value obtained by subtracting the right corner coordinate in the corresponding right corner coordinate matrix from the left corner coordinate in the left corner coordinate matrix is used as a corner error matrix corresponding to the calibration table to be measured, wherein the corner error matrix comprises a parallel equipotential error matrix and a parallax matrix, and the parallel equipotential error matrix can be obtained by calculating a difference value obtained by subtracting the ordinate of the right corner in the corresponding right corner coordinate matrix from the ordinate of the left corner in the left corner coordinate matrix; and obtaining the parallax matrix by calculating the difference value of the abscissa of the left corner in the left corner coordinate matrix and the abscissa of the right corner in the corresponding right corner coordinate matrix.
And judging whether the calibration table to be tested meets preset conditions or not through the angular point error matrix. In particular, for a binocular camera, on the one hand, it is desirable that the smaller the parallel allele error Yerror is, the better, thereby facilitating matching to more effective and correct parallax; on the other hand, it is desirable that the variation of the parallax Disp of the plane at the fixed depth is smooth and monotonous, and theoretically, the plane at the fixed depth is perfectly parallel to the CMOS plane, the parallaxes of the planes should be equal everywhere, but it is difficult to ensure that the two planes are perfectly parallel in practical operation. If the requirements are met at the same time, the accuracy of the calibration table of the binocular camera can be considered to be higher. Therefore, in order to meet the above requirement, in this embodiment, the maximum value, the minimum error value and the average value of the parallel equipotential error values are calculated based on the elements in the parallel equipotential error matrix; and calculating a gradient of the parallax value based on the elements in the parallax matrix; judging that if the maximum value, the minimum value and the mean value of the parallel equipotential errors are respectively smaller than a preset threshold value and the parallax value gradient has monotonicity, determining that the calibration table to be tested meets a preset condition; otherwise, determining that the calibration table to be tested does not meet the preset condition. By considering the calibration table to be measured from multiple aspects, the error judgment standard can be improved, so that the calibration precision of the binocular camera is improved.
Step 103, if yes, the calibration table to be tested is used for calibrating the binocular camera;
in this embodiment, when the calibration table to be measured meets the preset condition, the calibration table to be measured, that is, the first calibration table, may be used for calibration of the binocular camera, and the current flow is ended.
And 104, if not, correcting the to-be-measured calibration table according to the angular point error matrix to obtain a second calibration table, and taking the second calibration table as the to-be-measured calibration table until the to-be-measured calibration table meeting the preset condition is obtained for the calibration of the binocular camera.
In this embodiment, when the calibration table to be measured does not meet the preset condition, the calibration table to be measured may be further corrected according to the angular point error matrix to obtain a second calibration table.
As an embodiment, the present application may first correct the calibration table to be measured based on the corner error values in the corner error matrix to obtain a corrected sparse calibration table. Specifically, a left sparse calibration table corresponding to the corner coordinates in the left corner coordinate matrix of the left to-be-measured calibration table and a right sparse calibration table corresponding to the corner coordinates in the right corner coordinate matrix of the right to-be-measured calibration table in the to-be-measured calibration table are obtained first; subtracting half of the angular point error values from the horizontal and vertical coordinates of the angular points in the left sparse calibration table to obtain a corrected left sparse calibration table; and then, respectively adding half of the angular point error values to the horizontal coordinate and the vertical coordinate of the angular points in the right sparse calibration table to obtain a corrected right sparse calibration table.
For example, the error value of the parallel equipotential error Yerror is divided equally to the ordinate of the left and right sparse calibration tables, and the correction amount at each corner point (x, y) is Yerror (x, y)/2. The coordinates of the corrected left and right sparse calibration tables are:
wherein, the liquid crystal display device comprises a liquid crystal display device,and->The vertical coordinates of the left calibration table and the right calibration table of the first calibration table are respectively +.>And->And the vertical coordinates in the corrected left sparse calibration table and the corrected right sparse calibration table are respectively.
Dividing the error value of parallax Disp into left and right sparse calibration table, and correcting the correction value at each corner point (x, y) to obtain (Disp) truth (x, y) -Disp (x, y))/2. The coordinates of the corrected left and right sparse calibration tables are:
wherein, the liquid crystal display device comprises a liquid crystal display device,and->The left and right horizontal coordinates of the first calibration table are respectively>Andand the abscissa in the corrected left and right sparse calibration tables.
So far, by combining the correction results of the horizontal coordinates and the vertical coordinates in the left sparse calibration table and the right sparse calibration table, the left sparse calibration table and the right sparse calibration table after correction at all corner points can be obtained.
After the corrected sparse calibration table is obtained, the corrected left and right sparse calibration tables can be further filled to obtain a second calibration table. The second calibration table can be obtained by interpolation filling of the corrected sparse calibration table.
The interpolation method is shown in fig. 3, wherein the bilinear interpolation core idea is to perform linear interpolation once in two directions respectively. As shown in fig. 3, the coordinates of the four known vertexes Q11, Q12, Q21, Q22 are first linearly interpolated in the abscissa direction, i.e. the abscissa of the insertion point R2 in the points Q12 and Q22 is half the sum of the abscissas of the points Q12 and Q22, and the ordinate of R2 is the same as the abscissas of the points Q12 and Q22; then inserting a point R1 in the points Q11 and Q21, namely inserting the point R1 in the points Q11 and Q21, wherein the abscissa of the point R1 is half of the sum of the abscissas of the points Q11 and Q21, and the ordinate of the point R1 is identical to the ordinate of the points Q11 and Q21; then, linear interpolation is performed in the ordinate direction, and the point P is inserted through the points R1 and R2 calculated in the above process, that is, the point P is inserted in the points R1 and R2, the ordinate of P is half of the sum of the ordinates of R1 and R2, and the abscissa of P is the same as the abscissa of R1 and R2. The interpolation method is used circularly, and the corrected left and right sparse calibration tables can be amplified into a dense second calibration table.
In this embodiment, the second calibration table obtained by the correction may be used as a new calibration table to be measured, and the determining process in the step 102 may be performed until the calibration table to be measured meeting the preset condition is obtained, where the calibration table to be measured meeting the preset condition is used for calibrating the binocular camera.
In order to further explain the technical scheme of the present application, the calibration method of the binocular camera of the present application is described in detail below with reference to fig. 4.
Referring to fig. 4, a process flow chart of the calibration method of the binocular camera of the present application includes the following steps:
step 401, acquiring a preset first calibration table as a calibration table to be measured;
step 402, calculating an angular point error matrix corresponding to the calibration table to be measured through the left angular point coordinate matrix and the right angular point coordinate matrix;
step 403, judging whether the calibration table to be tested meets a preset condition or not through an error value in the angular point error matrix; if yes, go to step 404; if not, go to step 405;
step 404, using the calibration table to be tested for the calibration of the binocular camera, and ending;
step 405, correcting the calibration table to be measured based on the error value in the angular point error matrix to obtain a corrected sparse calibration table;
406, filling the corrected sparse calibration table through interpolation to obtain a second calibration table;
step 407, taking the second calibration table as a calibration table to be tested, and turning to step 402.
Compared with the prior art that the calibration of the binocular camera is carried out by directly using the calibration table preset in factory, the method and the device can continuously correct the calibration table according to the error value of the angular point error matrix when the preset calibration table does not meet the preset condition until the calibration table meets the preset condition, so that the calibration precision of the binocular camera can be improved.
Based on the same conception, the present application also provides an in-vehicle apparatus including a memory 51, a processor 52, a communication interface 53, and a communication bus 54, as shown in fig. 5;
wherein the memory 51, the processor 52, and the communication interface 53 communicate with each other through the communication bus 54;
the memory 51 is used for storing a computer program;
the processor 52 is configured to execute a computer program stored in the memory 51, where any step of the calibration method of the binocular camera provided by the embodiment of the present application is implemented when the processor 52 executes the computer program.
The application also provides a computer readable storage medium, wherein a computer program is stored in the computer readable storage medium, and when the computer program is executed by a processor, any step of the calibration method of the binocular camera provided by the embodiment of the application is realized.
In this specification, each embodiment is described in a related manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for embodiments of the in-vehicle apparatus and the computer-readable storage medium, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the partial description of the method embodiments for relevant points.
In summary, the method can be used for obtaining the preset first calibration table as the calibration table to be measured; calibrating checkerboard images shot by a binocular camera to obtain a corner error matrix of the calibration table to be tested, and judging whether the calibration table to be tested meets preset conditions or not through the corner error matrix; if yes, the calibration table to be measured is used for calibrating the binocular camera; if the calibration table does not meet the preset conditions, correcting the calibration table to be measured according to the angular point error matrix to obtain a second calibration table, and taking the second calibration table as the calibration table to be measured until the calibration table to be measured meeting the preset conditions is obtained for the calibration of the binocular camera. According to the application, when the to-be-measured calibration table does not meet the preset condition, the to-be-measured calibration table can be continuously corrected according to the angular point error matrix corresponding to the to-be-measured calibration table until the calibration table meets the preset condition, so that the calibration precision of the binocular camera can be improved.
The foregoing description of the preferred embodiments of the application is not intended to be limiting, but rather to enable any modification, equivalent replacement, improvement or the like to be made within the spirit and principles of the application.
Claims (4)
1. A method for calibrating a binocular camera, the method comprising:
acquiring a preset first calibration table as a calibration table to be measured; the first calibration table is a calibration table set before the binocular camera leaves the factory;
calibrating checkerboard images shot by a binocular camera to obtain left and right checkerboard images in a preset calibration area, and respectively obtaining a left corner coordinate matrix corresponding to the left checkerboard image and a right corner coordinate matrix corresponding to the right checkerboard image based on a calibration table to be tested; judging whether the calibration table to be tested meets preset conditions or not through a parallel equipotential error matrix and a parallax matrix; the parallel equipotential error matrix is obtained by subtracting a difference value of the ordinate of the right corner in the corresponding right corner coordinate matrix from the ordinate of the left corner in the left corner coordinate matrix; the parallax matrix is obtained by calculating the difference value of the abscissa of the left corner in the left corner coordinate matrix minus the corresponding abscissa of the right corner in the right corner coordinate matrix;
judging whether the calibration table to be tested meets a preset condition or not through the parallel equipotential error matrix and the parallax matrix comprises the following steps: calculating to obtain a maximum value, a minimum error value and an average value based on elements in the parallel equipotential error matrix; calculating to obtain a gradient based on elements in the parallax matrix; if the maximum value, the minimum error value and the average value are respectively smaller than the corresponding threshold values and the gradient has monotonicity, determining that the calibration table to be tested meets a preset condition; otherwise, determining that the calibration table to be tested does not meet a preset condition;
if yes, the calibration table to be measured is used for calibrating the binocular camera;
if the parallel equipotential error matrix and the parallax matrix do not meet the preset conditions, correcting the to-be-measured calibration table according to the parallel equipotential error matrix and the parallax matrix to obtain a second calibration table, and taking the second calibration table as the to-be-measured calibration table until the to-be-measured calibration table meeting the preset conditions is obtained for the calibration of the binocular camera;
the correcting the calibration table to be measured according to the parallel equipotential error matrix and the parallax matrix to obtain a second calibration table includes: acquiring a left sparse calibration table corresponding to the corner coordinates in the left corner coordinate matrix and a left to-be-measured calibration table in the to-be-measured calibration tables; acquiring a right sparse calibration table corresponding to the right to-be-measured calibration table in the to-be-measured calibration tables and the corner coordinates in the right corner coordinate matrix; subtracting half of the parallel equipotential error values of the corner points from the ordinate of the corner points in the left sparse calibration table to obtain the ordinate of the corrected left sparse calibration table; adding half of parallel equipotential error values of the corner points to the ordinate of the corner points in the right sparse calibration table to obtain the ordinate of the corrected right sparse calibration table; subtracting half of parallax error values of the angular points from the abscissa of the angular points in the left sparse calibration table, wherein the abscissa of the left sparse calibration table is corrected; adding half of parallax error values of the angular points to the abscissa of the angular points in the right sparse calibration table, wherein the abscissa of the right sparse calibration table is corrected; determining a corrected left sparse calibration table according to the abscissa and the ordinate of the corrected left sparse calibration table; determining a corrected right sparse calibration table according to the abscissa and the ordinate of the corrected right sparse calibration table; filling the corrected left sparse calibration table and the corrected right sparse calibration table to obtain a second calibration table.
2. The method of claim 1, wherein filling the corrected left sparse calibration table and the corrected right sparse calibration table to obtain a second calibration table comprises:
and obtaining a second calibration table by interpolating and filling the corrected left sparse calibration table and the corrected right sparse calibration table.
3. An in-vehicle apparatus, wherein the in-vehicle apparatus includes a memory, a processor, a communication interface, and a communication bus;
the memory, the processor and the communication interface communicate with each other through the communication bus;
the memory is used for storing a computer program;
the processor being configured to execute a computer program stored on the memory, the processor implementing the method according to claim 1 or 2 when the processor executes the computer program.
4. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored therein a computer program which, when executed by a processor, implements the method according to claim 1 or 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910153147.7A CN111627067B (en) | 2019-02-28 | 2019-02-28 | Calibration method of binocular camera and vehicle-mounted equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910153147.7A CN111627067B (en) | 2019-02-28 | 2019-02-28 | Calibration method of binocular camera and vehicle-mounted equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111627067A CN111627067A (en) | 2020-09-04 |
| CN111627067B true CN111627067B (en) | 2023-08-22 |
Family
ID=72258780
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910153147.7A Active CN111627067B (en) | 2019-02-28 | 2019-02-28 | Calibration method of binocular camera and vehicle-mounted equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111627067B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112785653B (en) * | 2020-12-30 | 2024-06-21 | 中山联合汽车技术有限公司 | Vehicle-mounted camera attitude angle calibration method |
| CN112929535B (en) * | 2021-01-25 | 2022-09-20 | 北京中科慧眼科技有限公司 | Binocular camera-based lens attitude correction method and system and intelligent terminal |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101976455A (en) * | 2010-10-08 | 2011-02-16 | 东南大学 | Color image three-dimensional reconstruction method based on three-dimensional matching |
| WO2013182080A1 (en) * | 2012-06-08 | 2013-12-12 | 华为技术有限公司 | Parameter calibration method and device |
| CN103868460A (en) * | 2014-03-13 | 2014-06-18 | 桂林电子科技大学 | Parallax optimization algorithm-based binocular stereo vision automatic measurement method |
| CN105303574A (en) * | 2015-07-30 | 2016-02-03 | 四川大学 | Integrated imaging camera array calibration method based on homography transformation |
| CN106803273A (en) * | 2017-01-17 | 2017-06-06 | 湖南优象科技有限公司 | A kind of panoramic camera scaling method |
| JP2017116321A (en) * | 2015-12-22 | 2017-06-29 | トヨタ自動車株式会社 | Calibration device for onboard stereo camera |
| CN107194974A (en) * | 2017-05-23 | 2017-09-22 | 哈尔滨工业大学 | A kind of raising method of many mesh Camera extrinsic stated accuracies based on multiple identification scaling board image |
| CN108053450A (en) * | 2018-01-22 | 2018-05-18 | 浙江大学 | A kind of high-precision binocular camera scaling method based on multiple constraint |
| CN108122259A (en) * | 2017-12-20 | 2018-06-05 | 厦门美图之家科技有限公司 | Binocular camera scaling method, device, electronic equipment and readable storage medium storing program for executing |
| CN108376384A (en) * | 2018-03-12 | 2018-08-07 | 海信集团有限公司 | Antidote, device and the storage medium of disparity map |
| CN108520536A (en) * | 2018-03-27 | 2018-09-11 | 海信集团有限公司 | A kind of generation method of disparity map, device and terminal |
| CN108573215A (en) * | 2018-03-16 | 2018-09-25 | 海信集团有限公司 | Reflective road method for detecting area, device and terminal |
| CN108629810A (en) * | 2017-03-23 | 2018-10-09 | 展讯通信（上海）有限公司 | Scaling method, device and the terminal of binocular camera |
| CN109003311A (en) * | 2018-08-22 | 2018-12-14 | 上海庄生晓梦信息科技有限公司 | A kind of fish-eye scaling method |
| CN109242908A (en) * | 2018-07-12 | 2019-01-18 | 中国科学院自动化研究所 | Scaling method for underwater two CCD camera measure system |
| CN109285192A (en) * | 2017-07-19 | 2019-01-29 | 上海盟云移软网络科技股份有限公司 | The binocular camera shooting scaling method of holophotal system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9965870B2 (en) * | 2016-03-29 | 2018-05-08 | Institut National D'optique | Camera calibration method using a calibration target |
-
2019
- 2019-02-28 CN CN201910153147.7A patent/CN111627067B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101976455A (en) * | 2010-10-08 | 2011-02-16 | 东南大学 | Color image three-dimensional reconstruction method based on three-dimensional matching |
| WO2013182080A1 (en) * | 2012-06-08 | 2013-12-12 | 华为技术有限公司 | Parameter calibration method and device |
| CN103868460A (en) * | 2014-03-13 | 2014-06-18 | 桂林电子科技大学 | Parallax optimization algorithm-based binocular stereo vision automatic measurement method |
| CN105303574A (en) * | 2015-07-30 | 2016-02-03 | 四川大学 | Integrated imaging camera array calibration method based on homography transformation |
| JP2017116321A (en) * | 2015-12-22 | 2017-06-29 | トヨタ自動車株式会社 | Calibration device for onboard stereo camera |
| CN106803273A (en) * | 2017-01-17 | 2017-06-06 | 湖南优象科技有限公司 | A kind of panoramic camera scaling method |
| CN108629810A (en) * | 2017-03-23 | 2018-10-09 | 展讯通信（上海）有限公司 | Scaling method, device and the terminal of binocular camera |
| CN107194974A (en) * | 2017-05-23 | 2017-09-22 | 哈尔滨工业大学 | A kind of raising method of many mesh Camera extrinsic stated accuracies based on multiple identification scaling board image |
| CN109285192A (en) * | 2017-07-19 | 2019-01-29 | 上海盟云移软网络科技股份有限公司 | The binocular camera shooting scaling method of holophotal system |
| CN108122259A (en) * | 2017-12-20 | 2018-06-05 | 厦门美图之家科技有限公司 | Binocular camera scaling method, device, electronic equipment and readable storage medium storing program for executing |
| CN108053450A (en) * | 2018-01-22 | 2018-05-18 | 浙江大学 | A kind of high-precision binocular camera scaling method based on multiple constraint |
| CN108376384A (en) * | 2018-03-12 | 2018-08-07 | 海信集团有限公司 | Antidote, device and the storage medium of disparity map |
| CN108573215A (en) * | 2018-03-16 | 2018-09-25 | 海信集团有限公司 | Reflective road method for detecting area, device and terminal |
| CN108520536A (en) * | 2018-03-27 | 2018-09-11 | 海信集团有限公司 | A kind of generation method of disparity map, device and terminal |
| CN109242908A (en) * | 2018-07-12 | 2019-01-18 | 中国科学院自动化研究所 | Scaling method for underwater two CCD camera measure system |
| CN109003311A (en) * | 2018-08-22 | 2018-12-14 | 上海庄生晓梦信息科技有限公司 | A kind of fish-eye scaling method |
Non-Patent Citations (1)
| Title |
|---|
| A binocular machine vision system for three-dimensional surface measurement of small objects;Dimitris Gorpas, Kostas Politopoulos , Dido Yova;Computerized Medical Imaging and Graphics;第31卷(第8期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111627067A (en) | 2020-09-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109712194B (en) | Vehicle-mounted all-round looking system, three-dimensional calibration method thereof and computer readable storage medium | |
| CN111583663B (en) | Monocular perception correction method and device based on sparse point cloud and storage medium | |
| CN111383279B (en) | External parameter calibration method and device and electronic equipment | |
| CN109961468B (en) | Volume measurement method and device based on binocular vision and storage medium | |
| CN112270713B (en) | Calibration method and device, storage medium and electronic device | |
| CN111382591B (en) | Binocular camera ranging correction method and vehicle-mounted equipment | |
| CN109410264B (en) | Front vehicle distance measuring method based on laser point cloud and image fusion | |
| US10223802B2 (en) | Method for determining depth maps from stereo images with improved depth resolution in a range | |
| CN112902874B (en) | Image acquisition device and method, image processing method and device and image processing system | |
| CN111123242B (en) | Combined calibration method based on laser radar and camera and computer readable storage medium | |
| CN109801333A (en) | Volume measuring method, device, system and calculating equipment | |
| US20220277470A1 (en) | Method and system for detecting long-distance target through binocular camera, and intelligent terminal | |
| CN110969666B (en) | Binocular camera depth calibration method, device, system and storage medium | |
| CN105551020A (en) | Method and device for detecting dimensions of target object | |
| CN111627067B (en) | Calibration method of binocular camera and vehicle-mounted equipment | |
| CN110926408A (en) | Short-distance measuring method, device and system based on characteristic object and storage medium | |
| CN113205604A (en) | Feasible region detection method based on camera and laser radar | |
| CN113989766A (en) | Road edge detection method and road edge detection equipment applied to vehicle | |
| CN113965742B (en) | Dense disparity map extraction method and system based on multi-sensor fusion and intelligent terminal | |
| CN113140002B (en) | Road condition detection method and system based on binocular stereo camera and intelligent terminal | |
| CN111986248B (en) | Multi-vision sensing method and device and automatic driving automobile | |
| CN115100621A (en) | Ground scene detection method and system based on deep learning network | |
| CN110766740B (en) | Real-time high-precision binocular range finding system and method based on pedestrian tracking | |
| CN112785647A (en) | Three-eye stereo image detection method and system | |
| CN110542895A (en) | monocular-based freespace distance measurement 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |