CN112991453A - Calibration parameter calibration method and device for binocular camera and electronic equipment - Google Patents
Calibration parameter calibration method and device for binocular camera and electronic equipment Download PDFInfo
- Publication number
- CN112991453A CN112991453A CN201911303865.4A CN201911303865A CN112991453A CN 112991453 A CN112991453 A CN 112991453A CN 201911303865 A CN201911303865 A CN 201911303865A CN 112991453 A CN112991453 A CN 112991453A
- Authority
- CN
- China
- Prior art keywords
- target
- image data
- binocular camera
- mark
- preset
- 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 51
- 238000012795 verification Methods 0.000 claims abstract description 37
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 230000003287 optical effect Effects 0.000 abstract description 10
- 238000009434 installation Methods 0.000 abstract description 6
- 238000001514 detection method Methods 0.000 abstract description 2
- 239000003550 marker Substances 0.000 description 14
- 238000004891 communication Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 230000009471 action Effects 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000875 corresponding effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
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
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)
Abstract
The embodiment of the application provides a method and a device for calibrating parameters of a binocular camera and electronic equipment. The method is applied to the technical field of camera parameter detection, the image position of a preset mark target in first image data and the actual position of the preset mark target in a world coordinate system are utilized, the depth distance from the preset mark target to a first lens is calculated, the real depth distance is obtained, the real depth distance is compared with the target depth distance calculated according to calibration parameters of the binocular camera, whether the calibration parameters of the binocular camera pass verification or not is judged, the optical axis of the binocular camera does not need to be debugged to be perpendicular to a calibration plate, the requirement on the verification and installation accuracy is lowered, and the workload of verification personnel can be reduced.
Description
Technical Field
The application relates to the technical field of camera parameter detection, in particular to a calibration parameter calibration method and device for a binocular camera and electronic equipment.
Background
The binocular camera generally includes a left eye camera and a right eye camera, which are respectively used for simulating the left eye and the right eye of a human, thereby realizing the functions of positioning or depth distance output, etc. Before the binocular camera leaves the factory, parameters such as the base length of the binocular camera are calibrated, and the binocular camera calculates the depth distance of the designated pixel point in the image according to the calibrated parameters. In order to ensure the accuracy of the output depth distance, calibration parameters of the binocular camera need to be checked.
In the related art, a calibrated binocular camera needs to be installed on a calibration tool with a fixed distance, the fixed distance refers to the constant distance between a calibration plate and the optical centers of the binocular camera, and when the error between the depth distance of the calibration plate output by the binocular camera and the fixed distance is within a specified error range, calibration parameters of the binocular camera are verified to be passed.
However, by adopting the method, the optical axis of the binocular camera is required to be completely perpendicular to the calibration board, and the fixed distance can be used as a true value for checking the binocular depth distance, so that when the binocular camera is installed, in order to enable the optical axis of the binocular camera to be perpendicular to the calibration board as much as possible, the installation angle of the binocular camera needs to be debugged by a checker for many times, and the workload of the checker is greatly increased.
Disclosure of Invention
An object of the embodiments of the present application is to provide a method and an apparatus for calibrating parameters of a binocular camera, and an electronic device, so as to reduce requirements for calibration and installation accuracy and reduce workload of calibration personnel. The specific technical scheme is as follows:
in a first aspect, an embodiment of the present application provides a method for calibrating parameters of a binocular camera, where the method includes:
acquiring first image data and second image data obtained by acquiring a preset mark target through a first lens and a second lens of a binocular camera to be verified;
polar line calibration is carried out on the first image data and the second image data by using the calibration parameters of the binocular camera to obtain first target image data and second target image data;
calculating the depth distance between the preset mark target and the first lens according to the image position of the preset mark target in the first image data and the actual position of the preset mark target in a world coordinate system to obtain a real depth distance;
calculating a target depth distance of a preset mark target by using calibration parameters of the binocular camera according to the first target image data and the second target image data;
calculating a deviation value of the target depth distance and the real depth distance, and if the deviation value is smaller than a preset deviation threshold value, judging that calibration parameters of the binocular camera pass verification; otherwise, judging that the calibration parameters of the binocular camera are not verified.
In a possible implementation manner, the calculating a depth distance between the preset mark target and the first lens according to the image position of the preset mark target in the first image data and the actual position of the preset mark target in the world coordinate system to obtain a real depth distance includes:
determining the image positions of at least three mark points of the preset mark target in the first image data to obtain the image positions of all reference mark points;
acquiring the actual position of each mark point in a world coordinate system to obtain the actual position of each world mark point;
calculating the depth distance between each mark point and the first lens according to the image position of the reference mark point of each mark point and the actual position of the world mark point by a PnP (pseudo-random projection) algorithm to obtain the real depth distance of each mark point;
the calculating the target depth distance of the preset mark target by using the calibration parameters of the binocular camera according to the first target image data and the second target image data comprises the following steps:
and calculating the target depth distance of each mark point by using the calibration parameters of the binocular camera according to the first target image data and the second target image data.
In a possible implementation manner, the calculating a deviation value of the target depth distance and the real depth distance, and if the deviation value is smaller than a preset deviation threshold, determining that the calibration parameters of the binocular camera pass the verification; otherwise, judging that the calibration parameters of the binocular camera fail to pass the verification, including:
calculating a deviation value of the target depth distance of each mark point and the real depth distance of the mark point aiming at each mark point to respectively obtain the deviation value of each mark point;
respectively comparing the deviation value of each mark point with a preset deviation threshold value, and if the deviation value of each mark point is smaller than the preset deviation threshold value, judging that the calibration parameters of the binocular camera pass the verification; otherwise, judging that the calibration parameters of the binocular camera are not verified.
In a possible embodiment, when the binocular camera captures the first image data and the second image data, each marker point of the preset marker target is located in an edge area of the field of view of the binocular camera.
In one possible embodiment, the method further comprises:
and judging whether the same mark point of the preset mark target is the same as the ordinate in the first target image data and the ordinate in the second target image data, and if not, judging that the calibration parameters of the binocular camera do not pass the verification.
In a possible implementation manner, the calculating a depth distance between the preset mark target and the first lens according to the image position of the preset mark target in the first image data and the actual position of the preset mark target in the world coordinate system to obtain a real depth distance includes:
if the vertical coordinate of the same mark point in the first target image data is the same as the vertical coordinate in the second target image data, calculating the depth distance between the preset mark target and the first lens according to the image position of the preset mark target in the first image data and the actual position of the preset mark target in a world coordinate system, and obtaining the real depth distance.
In a second aspect, an embodiment of the present application provides a calibration apparatus for calibrating parameters of a binocular camera, the apparatus includes:
the image acquisition module is used for acquiring first image data and second image data obtained by acquiring a preset mark target through a first lens and a second lens of a binocular camera to be verified;
the image calibration module is used for carrying out polar line calibration on the first image data and the second image data by using the calibration parameters of the binocular camera to obtain first target image data and second target image data;
a real depth calculation module, configured to calculate a depth distance between the preset mark target and the first lens according to an image position of the preset mark target in the first image data and an actual position of the preset mark target in a world coordinate system, so as to obtain a real depth distance;
the target depth acquisition module is used for calculating a target depth distance of a preset mark target by using calibration parameters of the binocular camera according to the first target image data and the second target image data;
the calibration parameter calibration module is used for calculating a deviation value of the target depth distance and the real depth distance, and if the deviation value is smaller than a preset deviation threshold value, the calibration parameter of the binocular camera is judged to pass calibration; otherwise, judging that the calibration parameters of the binocular camera are not verified.
In a possible implementation manner, the real depth calculation module is specifically configured to: determining the image position of each mark point of the preset mark target in the first image data to obtain the image position of each reference mark point; acquiring the actual positions of at least three mark points of the preset mark target in a world coordinate system to obtain the actual positions of all world mark points; calculating the depth distance between each mark point and the first lens according to the image position of the reference mark point of each mark point and the actual position of the world mark point by a PnP (pseudo-random projection) algorithm to obtain the real depth distance of each mark point;
the target depth acquisition module is specifically configured to: and calculating the target depth distance of each mark point by using the calibration parameters of the binocular camera according to the first target image data and the second target image data.
In a possible implementation manner, the calibration parameter verification module is specifically configured to: calculating a deviation value of the target depth distance of each mark point and the real depth distance of the mark point aiming at each mark point to respectively obtain the deviation value of each mark point; respectively comparing the deviation value of each mark point with a preset deviation threshold value, and if the deviation value of each mark point is smaller than the preset deviation threshold value, judging that the calibration parameters of the binocular camera pass the verification; otherwise, judging that the calibration parameters of the binocular camera are not verified.
In a possible embodiment, when the binocular camera captures the first image data and the second image data, each marker point of the preset marker target is located in an edge area of the field of view of the binocular camera.
In a possible embodiment, the apparatus further comprises: and the ordinate checking module is used for judging whether the ordinate in the first target image data is the same as the ordinate in the second target image data of the same mark point of the preset mark target, and if not, judging that the calibration parameters of the binocular camera do not pass the checking.
In a possible implementation manner, the real depth calculation module is specifically configured to: if the vertical coordinate of the same mark point in the first target image data is the same as the vertical coordinate in the second target image data, calculating the depth distance between the preset mark target and the first lens according to the image position of the preset mark target in the first image data and the actual position of the preset mark target in a world coordinate system, and obtaining the real depth distance.
In a third aspect, an embodiment of the present application provides an electronic device, including a processor and a memory;
the memory is used for storing a computer program;
the processor is used for realizing the calibration parameter calibration method of any binocular camera when executing the program stored in the memory.
In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the method for verifying calibration parameters of a binocular camera is implemented.
The embodiment of the application provides a method and a device for calibrating parameters of a binocular camera and electronic equipment. The method comprises the steps of calculating the depth distance between a preset mark target and a first lens by utilizing the image position of the preset mark target in first image data and the actual position of the preset mark target in a world coordinate system to obtain a real depth distance, and comparing the real depth distance with the target depth distance calculated according to calibration parameters of a binocular camera, so as to judge whether the calibration parameters of the binocular camera pass verification or not, and the optical axis of the binocular camera does not need to be debugged to be perpendicular to a calibration plate, so that the requirement on the verification and installation accuracy is reduced, and the workload of a verifier can be reduced. Of course, not all advantages described above need to be achieved at the same time in the practice of any one product or method of the present application.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a first schematic diagram of a calibration parameter calibration method for a binocular camera according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a pre-marked target according to an embodiment of the present application;
fig. 3a is a first schematic view of a position relationship between a calibration plate and a binocular camera according to an embodiment of the present application;
fig. 3b is a second schematic view of the position relationship between the calibration plate and the binocular camera according to the embodiment of the present application;
FIG. 3c is a graph of parallax depth in accordance with an embodiment of the present application;
FIG. 3d is a schematic view of a preset field of view according to an embodiment of the present application;
fig. 4 is a second schematic diagram of a calibration parameter calibration method for a binocular camera according to an embodiment of the present application;
fig. 5 is a third schematic diagram of a calibration parameter calibration method for a binocular camera according to an embodiment of the present application;
fig. 6 is a schematic diagram of a calibration parameter calibration device for a binocular camera according to an embodiment of the present application;
fig. 7 is a schematic diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. 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 application.
First, terms of art in the embodiments of the present application are explained:
calibrating a plate: a flat plate with a pattern array with fixed spacing is a common calibration plate with black and white checkerboards and dot arrays;
corner points: namely extreme points, points with particularly outstanding properties in some respect, which refer to points in the image where both gradient values and the rate of change of gradient direction are high;
world coordinate system: a three-dimensional coordinate system for describing the coordinate position of an object in the real world;
camera coordinate system: a coordinate system established on the camera for describing the coordinate position of the object from the perspective of the camera;
image pixel coordinate system: a rectangular coordinate system which is established by taking the upper left point of the image as an origin and takes the pixel as a unit;
calibrating a binocular camera: calibrating internal parameters and distortion coefficients of the two cameras and a relative relation between the two cameras;
internal reference of the camera: the camera determines the structural parameters inside the camera, and the structural parameters are not influenced by the external environment, such as the information of focal length, image center position and the like;
distortion parameters: the correction coefficient comprises a radial distortion coefficient and a tangential distortion coefficient of a camera, and is used for transforming the position of an actual imaging point to the position of an ideal imaging point;
parallax: deviation of imaging positions of the same point in a binocular two-phase machine image pixel coordinate system in the X-axis direction on a binocular image after polar line calibration;
depth map: an image containing information of distances from the viewpoint to the surface of the scene object, each pixel value representing an actual distance of the sensor from the object;
PnP (Passive-n-Point) algorithm: resolving the posture of the camera by using n pairs of matched space 3D points and image 2D points;
polar line calibration: the method is used for calibrating the two-camera image plane to the same plane, so that when the same point is projected to the two-camera image plane, the coordinates are positioned on the same line of the pixel coordinate systems of the two image planes.
In order to reduce the workload of the calibration personnel, an embodiment of the present application provides a calibration method for calibration parameters of a binocular camera, and referring to fig. 1, the method includes:
s101, acquiring first image data and second image data obtained by acquiring a preset mark target through a first lens and a second lens of a binocular camera to be checked.
The calibration parameter calibration method of the binocular camera is used for calibrating calibration parameters of the binocular camera, and therefore the calibration parameter calibration method can be achieved through the binocular camera, and certainly can also be achieved through electronic equipment with a computing function, such as a server.
The first lens can be a left eyepiece or a right eyepiece in the binocular camera and can be set by self definition. The second lens is the other lens except the first lens in the binocular camera. The image data captured by the first lens is referred to as first image data, and the image data captured by the second lens is referred to as second image data.
The first image data and the second image data are images collected by the binocular camera at the same position and comprise preset mark targets, the preset mark targets are targets different from the background, the preset mark targets can be patterns on a calibration board, and the preset mark targets can be polygonal patterns, designated characters, designated symbols and the like. During the process of acquiring the first image data and the second image data, the base line of the binocular camera should be parallel to the ground plane as much as possible, and the calibration plate should be perpendicular to the ground plane as much as possible. In one possible embodiment, referring to fig. 2, the preset mark targets a checkerboard pattern.
In one possible embodiment, in order to reduce errors caused by position changes during image acquisition, referring to fig. 3a, a binocular camera is mounted on a binocular fixed bracket with a height h1, and an image of a calibration plate is acquired by the binocular camera, wherein the distance between the upper end of the binocular fixed bracket and the calibration plate is a. In the process of one-time verification, the first image data and the second image data are images acquired by the binocular camera at the same position, and generally, the first image data and the second image data are images acquired at the same time in the process of the same-time verification. The distance a between the binocular fixing support and the calibration plate is adjustable, for example, the distance a can be adjusted from the calibration position 1 to the calibration position 2, and therefore calibration of calibration parameters under different distances is achieved. The top views of the binocular camera and the calibration board can be as shown in fig. 3b, and the binocular camera is arranged on the alignment base line, so that the base line of the binocular camera is parallel to the ground plane as much as possible.
And S102, performing polar line calibration on the first image data and the second image data by using the calibration parameters of the binocular camera to obtain first target image data and second target image data.
Polar line calibration is carried out on the first image data through calibration parameters of a binocular camera to obtain first target image data; and performing polar line calibration on the second image data through calibration parameters of the binocular camera to obtain second target image data. The polar line calibration method for the first image data and the second image data using the calibration parameters of the binocular camera may be a line calibration method in any related art, and details are not repeated here.
S103, calculating a depth distance between the preset mark target and the first lens according to the image position of the preset mark target in the first image data and the actual position of the preset mark target in the world coordinate system, so as to obtain a real depth distance.
By using a related calculation method, the depth distance between the preset mark target and the first lens can be calculated according to the actual position (coordinates) of the preset mark target in the world coordinate system and the image position of the preset mark target in the first image data, and the depth distance is used as the real depth distance between the preset mark target and the first lens. For example, when the center of the preset mark target is the intersection point of the optical axis of the first lens and the preset mark target, the depth distance between the preset mark target and the first lens may be the depth distance between the center point of the preset mark target and the first lens; the depth distance between the preset mark target and the first lens can be preset, and the depth distance between the corner point of the preset mark target and the first lens can also be preset.
And S104, calculating the target depth distance of the preset mark target by using the calibration parameters of the binocular camera according to the first target image data and the second target image data.
And calculating to obtain the depth distance between the binocular camera and the preset mark target, namely the target depth distance, according to the first target image data and the second target image data by using the calibration parameters of the binocular camera. In general, the target depth distance may be a depth distance with respect to the left eyepiece as a reference.
The binocular camera may calculate a depth distance of the designated target according to the first target image data and the second target image data using the calibration parameter. The depth distance calculation method adopted by the binocular camera can be any related depth distance calculation method. For example, the binocular camera may calculate the depth distance of a specified target using a depth calculation formula as shown below.
ZcI.e. the corresponding depth value, fxB is the focal length of the pixel in the calibration parameter, b is the base length (distance between the optical center points of the two-camera), d is the parallax value, wherein d is ul-urWherein u isl,urThe image data of the designated object is displayed in the first and second target image data, and the image data of the designated object is displayed in the second and third target image data. As can be seen from the above formula (1), the farther an object is from the camera, the smaller the parallax value is, and the closer the object is, the larger the parallax is.
S105, calculating a deviation value of the target depth distance and the real depth distance, and if the deviation value is smaller than a preset deviation threshold value, judging that the calibration parameters of the binocular camera pass verification; otherwise, judging that the calibration parameters of the binocular camera are not verified.
The preset deviation threshold may be preset, and as can be seen from the above calculation formula (1), the relationship between the depth information output by the binocular camera and the parallax is determined by the parameters of the camera, and thus the deviation thresholds set by different camera parameters are different. Under the condition that the camera parameters are determined, the preset deviation threshold value is positively correlated with the optical axis distance between the binocular camera and the calibration board, namely the real depth to a certain extent.
In a possible embodiment, the above-mentioned calculation formula (1) can obtain the relationship curve between the depth and the parallax as shown in fig. 3c, and the depth distance Z between the preset mark target0Corresponding parallax d0If the parallax error is + -1 pixel, it corresponds to d in FIG. 3c0+1 and d0-1, from the above relation curve Z can be calculatedmaxAnd ZminTaking Zmax，ZminMiddle and Z0With small deviation, e.g. when compared with Z0Value of less deviation is ZminThen calculate ZminAnd Z0Deviation Z betweenoffsetIs a reaction of ZoffsetDivided by Z0The maximum value of the deviation threshold value under the current condition can be obtained; when is in contact with Z0Value of less deviation is ZmaxMeanwhile, the calculation process is the same and is not described herein again.Because the precision of the corner sub-pixel refining process has deviation, the actually set deviation threshold value can be smaller than the obtained maximum value. In practical application, if the deviation is smaller than a set deviation threshold value, the calibration parameter is judged to pass the verification; otherwise, judging that the calibration parameters of the binocular camera fail to pass the verification.
In the embodiment of the application, the image position of the preset mark target in the first image data and the actual position of the preset mark target in the world coordinate system are utilized to calculate the depth distance between the preset mark target and the first lens to obtain the real depth distance, and the real depth distance is compared with the target depth distance calculated by the binocular camera according to the calibration parameters, so that whether the calibration parameters of the binocular camera pass the calibration or not is judged, the optical axis of the binocular camera does not need to be debugged to be perpendicular to the calibration plate, the requirement on the calibration installation precision is lowered, the workload of calibration personnel can be reduced, and the feasibility is high. And the deviation can be reduced to be within 1 pixel, and the verification precision is increased.
In a possible embodiment, the calculating the depth distance between the preset mark target and the first lens according to the image position of the preset mark target in the first image data and the actual position of the preset mark target in the world coordinate system to obtain the real depth distance may include:
the first step is to determine the image positions of at least three marker points of the preset marker target in the first image data to obtain the image positions of each reference marker point.
Optionally, the preset mark target may be a checkerboard pattern shown in fig. 2, and the number of the mark points may be four, specifically, may be four corner points at the outermost periphery of the checkerboard pattern.
And step two, acquiring the actual position of each mark point of the preset mark target in a world coordinate system to obtain the actual position of each world mark point.
And step three, calculating the depth distance between each mark point and the first lens through a PnP algorithm according to the image position of the reference mark point of each mark point and the actual position of the world mark point, and obtaining the real depth distance of each mark point.
The target depth distance calculated by using the calibration parameters of the binocular camera according to the first target image data and the second target image data comprises:
calculating the target depth distance of each mark point by using the calibration parameters of the binocular camera according to the first target image data and the second target image data;
calculating a deviation value of the target depth distance and the real depth distance, and if the deviation value is smaller than a preset deviation threshold value, judging that calibration parameters of the binocular camera pass verification; otherwise, judging that the calibration parameters of the binocular camera fail to pass the verification, including:
step A, calculating a deviation value of a target depth distance of each mark point and a real depth distance of the mark point aiming at each mark point, and respectively obtaining the deviation value of each mark point;
step B, respectively comparing the deviation value of each mark point with a preset deviation threshold value, and if the deviation value of each mark point is smaller than the preset deviation threshold value, judging that the calibration parameters of the binocular camera pass the verification; otherwise, judging that the calibration parameters of the binocular camera are not verified.
In the embodiment of the application, the characteristic that the PnP algorithm is high in short-distance measurement accuracy is utilized, the distance between each mark point and the PnP algorithm is used as a true value, calibration parameters of the binocular camera are checked, the characteristic that the attitude of the binocular camera can be ignored by the PnP algorithm is utilized, the optical axis of the binocular camera is not required to be completely perpendicular to the mark plate, the requirement on the installation accuracy of the checking device can be lowered, the scheme is suitable for the condition that the parallax error is +/-1 pixel, and the feasibility is high.
In one possible embodiment, when the binocular camera captures the first image data and the second image data, the marker points of the preset marker target are located in an edge region of the field of view of the binocular camera.
The edge area is an area within the field of view of the binocular camera and outside the preset field angle area. The preset field angle region may refer to a region within a preset field angle, and the preset field angle may be set according to actual conditions, for example, may be set to 80%, 90%, or 95% of the field angle of the binocular camera. Taking the horizontal angle of view as an example, the relationship between the horizontal angle of view a of the binocular camera and the horizontal angle of view B of the preset angle of view is shown in fig. 3 d.
Since the abnormal region where the parallax is deviated mainly appears at the edge of the image, the edge of the calibration plate should be as close as possible to the edge of the field of view of the binocular camera, as shown in fig. 3a below, the lower edge of the calibration plate is located at the edge of the field of view of the camera, and it is ensured that the preset mark object on the calibration plate appears completely within the field of view of the camera. Alternatively, the preset mark target may be a checkerboard pattern shown in fig. 2, and each mark point may be four corner points at the outermost periphery of the checkerboard pattern. Of course, the pattern on the calibration board can also be replaced by a pattern of a dot array or other mark patterns, so that the extracted feature points can be ensured to be accurate and easy to match.
Optionally, after acquiring first image data acquired by a first lens in the binocular camera and target image data of the binocular camera, the method for calibrating parameters of the binocular camera according to the embodiment of the present application further includes:
and judging whether the same mark point of the preset mark target is the same as the ordinate in the first target image data and the ordinate in the second target image data, and if not, judging that the calibration parameters of the binocular camera do not pass the verification.
The base line of the binocular camera is parallel to the ground plane, so that the vertical coordinate of the same mark point in the first target image data and the vertical coordinate in the second target image data after calibration should be the same, and if the two are different, the calibration parameters are directly judged to be not verified.
Optionally, the calculating a depth distance between the preset mark target and the first lens according to the image position of the preset mark target in the first image data and the actual position of the preset mark target in the world coordinate system to obtain a real depth distance includes:
and if the vertical coordinate of the same mark point in the first target image data is the same as the vertical coordinate in the second target image data, calculating the depth distance between the preset mark target and the first lens according to the image position of the preset mark target in the first image data and the actual position of the preset mark target in the world coordinate system, and obtaining the real depth distance.
If the same mark point of the mark target is preset, the vertical coordinate in the first target image data is different from the vertical coordinate in the second target image data, the calibration parameters of the binocular camera are not verified, and the real depth distance is not calculated. And if the vertical coordinate of the same mark point in the first target image data is the same as the vertical coordinate in the second target image data, performing subsequent steps of calculating the real depth distance and the like.
As shown in fig. 4, the method for calibrating parameters of a binocular camera according to the embodiment of the present application may further include:
s101, acquiring first image data and second image data obtained by acquiring a preset checkerboard pattern through a first lens and a second lens of a binocular camera to be verified.
And S102, performing polar line calibration on the first image data and the second image data by using the calibration parameters of the binocular camera to obtain first target image data and second target image data.
And step S1031, determining image positions of four corner points at the outermost periphery of the predetermined checkerboard pattern in the first image data, and obtaining image positions of the reference mark points.
S1032, acquiring the actual positions of the corner points of the checkerboard pattern in a world coordinate system to obtain the actual positions of the world mark points.
And S1033, calculating the depth distance from each corner point to the first lens through a PnP algorithm according to the reference mark point image position and the world mark point actual position of each corner point, and obtaining the real depth distance of each corner point.
And S1041, obtaining the target depth distance of each corner point calculated by the binocular camera according to the first target image data and the second target image data by using the calibration parameters of the binocular camera.
S1051, aiming at each corner point, calculating a deviation value of the target depth distance of the corner point and the real depth distance of the corner point, and respectively obtaining the deviation value of each corner point.
S1052, respectively comparing the deviation value of each angular point with a preset deviation threshold, and if the deviation value of each angular point is smaller than the preset deviation threshold, judging that the calibration parameters of the binocular camera pass the verification; otherwise, judging that the calibration parameters of the binocular camera are not verified.
As shown in fig. 5, the method for calibrating parameters of a binocular camera according to the embodiment of the present application may further include:
s101, acquiring first image data and second image data obtained by acquiring a preset mark target through a first lens and a second lens of a binocular camera to be checked.
And S102, performing polar line calibration on the first image data and the second image data by using the calibration parameters of the binocular camera to obtain first target image data and second target image data.
And S501, judging whether the same mark point of the preset mark target is the same as the ordinate in the first target image data and the ordinate in the second target image data, and if not, judging that the calibration parameters of the binocular camera do not pass the verification.
S502, if the ordinate of the same mark point in the first target image data is the same as the ordinate of the same mark point in the second target image data, calculating the depth distance between the preset mark target and the first lens according to the image position of the preset mark target in the first image data and the actual position of the preset mark target in the world coordinate system, and obtaining the actual depth distance.
And S104, calculating the target depth distance of the preset mark target by using the calibration parameters of the binocular camera according to the first target image data and the second target image data.
S105, calculating a deviation value of the target depth distance and the real depth distance, and if the deviation value is smaller than a preset deviation threshold value, judging that the calibration parameters of the binocular camera pass verification; otherwise, judging that the calibration parameters of the binocular camera are not verified.
The embodiment of the present application further provides a calibration apparatus for calibrating parameters of a binocular camera, referring to fig. 6, where the apparatus includes:
the image acquisition module 601 is used for acquiring first image data and second image data obtained by acquiring a preset mark target by a first lens and a second lens of a binocular camera to be verified;
an image calibration module 602, configured to perform polar line calibration on the first image data and the second image data by using the calibration parameters of the binocular camera to obtain first target image data and second target image data;
a real depth calculating module 603, configured to calculate a depth distance between the preset mark target and the first lens according to an image position of the preset mark target in the first image data and an actual position of the preset mark target in a world coordinate system, so as to obtain a real depth distance;
a target depth obtaining module 604, configured to calculate, according to the first target image data and the second target image data, a target depth distance of a preset mark target by using the calibration parameters of the binocular camera;
a calibration parameter calibration module 605, configured to calculate a deviation value between the target depth distance and the real depth distance, and determine that the calibration parameter of the binocular camera passes calibration if the deviation value is smaller than a preset deviation threshold; otherwise, judging that the calibration parameters of the binocular camera are not verified.
Optionally, the real depth calculating module 603 is specifically configured to: determining image positions of at least three marker points of the preset marker target in the first image data to obtain image positions of each reference marker point; acquiring the actual position of each mark point of the preset mark target in a world coordinate system to obtain the actual position of each world mark point; calculating the depth distance between each mark point and the first lens through a PnP algorithm according to the reference mark point image position of each mark point and the actual position of the world mark point to obtain the real depth distance of each mark point;
the target depth obtaining module 604 is specifically configured to: and calculating the target depth distance of each mark point by using the calibration parameters of the binocular camera according to the first target image data and the second target image data.
Optionally, the calibration parameter verification module 605 is specifically configured to: calculating the deviation value of the target depth distance of each mark point and the real depth distance of the mark point aiming at each mark point, and respectively obtaining the deviation value of each mark point; respectively comparing the deviation value of each mark point with a preset deviation threshold value, and if the deviation value of each mark point is smaller than the preset deviation threshold value, judging that the calibration parameters of the binocular camera pass the verification; otherwise, judging that the calibration parameters of the binocular camera are not verified.
Optionally, when the binocular camera collects the first image data and the second image data, the marker points of the preset marker target are located in an edge area of the field of view of the binocular camera.
Optionally, the apparatus further comprises: and the ordinate checking module is used for judging whether the ordinate in the first target image data is the same as the ordinate in the second target image data of the same mark point of the preset mark target, and if not, judging that the calibration parameters of the binocular camera do not pass the checking.
Optionally, the real depth calculating module 603 is specifically configured to: and if the vertical coordinate of the same mark point in the first target image data is the same as the vertical coordinate in the second target image data, calculating the depth distance between the preset mark target and the first lens according to the image position of the preset mark target in the first image data and the actual position of the preset mark target in the world coordinate system, and obtaining the real depth distance.
An embodiment of the present application further provides an electronic device, including: a processor and a memory;
the memory is used for storing computer programs;
when the processor is used for executing the computer program stored in the memory, the following steps are realized:
acquiring first image data and second image data obtained by acquiring a preset mark target through a first lens and a second lens of a binocular camera to be verified;
polar line calibration is carried out on the first image data and the second image data by using the calibration parameters of the binocular camera to obtain first target image data and second target image data;
calculating the depth distance between the preset mark target and the first lens according to the image position of the preset mark target in the first image data and the actual position of the preset mark target in a world coordinate system to obtain a real depth distance;
calculating a target depth distance of a preset mark target by using the calibration parameters of the binocular camera according to the first target image data and the second target image data;
calculating a deviation value of the target depth distance and the real depth distance, and if the deviation value is smaller than a preset deviation threshold value, judging that the calibration parameters of the binocular camera pass verification; otherwise, judging that the calibration parameters of the binocular camera are not verified.
Optionally, referring to fig. 7, the electronic device according to the embodiment of the present application further includes a communication interface 702 and a communication bus 704, where the processor 701, the communication interface 702, and the memory 703 complete communication with each other through the communication bus 704.
Optionally, when the processor is used to execute the computer program stored in the memory, the method for verifying the calibration parameters of any binocular camera can be further implemented.
The communication bus mentioned in the electronic device may be a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the electronic equipment and other equipment.
The Memory may include a RAM (Random Access Memory) or an NVM (Non-Volatile Memory), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also a DSP (Digital Signal Processing), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component.
An embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements the following steps:
acquiring first image data and second image data obtained by acquiring a preset mark target through a first lens and a second lens of a binocular camera to be verified;
polar line calibration is carried out on the first image data and the second image data by using the calibration parameters of the binocular camera to obtain first target image data and second target image data;
calculating the depth distance between the preset mark target and the first lens according to the image position of the preset mark target in the first image data and the actual position of the preset mark target in a world coordinate system to obtain a real depth distance;
calculating a target depth distance of a preset mark target by using the calibration parameters of the binocular camera according to the first target image data and the second target image data;
calculating a deviation value of the target depth distance and the real depth distance, and if the deviation value is smaller than a preset deviation threshold value, judging that the calibration parameters of the binocular camera pass verification; otherwise, judging that the calibration parameters of the binocular camera are not verified.
Optionally, when being executed by the processor, the computer program can also implement the method for checking the calibration parameters of any binocular camera.
It should be noted that, in this document, the technical features in the various alternatives can be combined to form the scheme as long as the technical features are not contradictory, and the scheme is within the scope of the disclosure of the present application. Relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the embodiments of the apparatus, the electronic device, and the storage medium, since they are substantially similar to the method embodiments, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiments.
The above description is only for the preferred embodiment of the present application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application are included in the protection scope of the present application.
Claims (14)
1. A calibration parameter calibration method for a binocular camera is characterized by comprising the following steps:
acquiring first image data and second image data obtained by acquiring a preset mark target through a first lens and a second lens of a binocular camera to be verified;
polar line calibration is carried out on the first image data and the second image data by using the calibration parameters of the binocular camera to obtain first target image data and second target image data;
calculating the depth distance between the preset mark target and the first lens according to the image position of the preset mark target in the first image data and the actual position of the preset mark target in a world coordinate system to obtain a real depth distance;
calculating a target depth distance of a preset mark target by using calibration parameters of the binocular camera according to the first target image data and the second target image data;
calculating a deviation value of the target depth distance and the real depth distance, and if the deviation value is smaller than a preset deviation threshold value, judging that calibration parameters of the binocular camera pass verification; otherwise, judging that the calibration parameters of the binocular camera are not verified.
2. The method according to claim 1, wherein the calculating a depth distance of the preset mark target from the first lens according to the image position of the preset mark target in the first image data and the actual position of the preset mark target in a world coordinate system to obtain a real depth distance comprises:
determining the image positions of at least three mark points of the preset mark target in the first image data to obtain the image positions of all reference mark points;
acquiring the actual position of each mark point in a world coordinate system to obtain the actual position of each world mark point;
calculating the depth distance between each mark point and the first lens according to the image position of the reference mark point of each mark point and the actual position of the world mark point by a PnP (pseudo-random projection) algorithm to obtain the real depth distance of each mark point;
the calculating the target depth distance of the preset mark target by using the calibration parameters of the binocular camera according to the first target image data and the second target image data comprises the following steps:
and calculating the target depth distance of each mark point by using the calibration parameters of the binocular camera according to the first target image data and the second target image data.
3. The method according to claim 2, wherein a deviation value of the target depth distance and the real depth distance is calculated, and if the deviation value is smaller than a preset deviation threshold value, it is determined that calibration parameters of the binocular camera pass verification; otherwise, judging that the calibration parameters of the binocular camera fail to pass the verification, including:
calculating a deviation value of the target depth distance of each mark point and the real depth distance of the mark point aiming at each mark point to respectively obtain the deviation value of each mark point;
respectively comparing the deviation value of each mark point with a preset deviation threshold value, and if the deviation value of each mark point is smaller than the preset deviation threshold value, judging that the calibration parameters of the binocular camera pass the verification; otherwise, judging that the calibration parameters of the binocular camera are not verified.
4. The method of claim 2, wherein each landmark point of the preset landmark target is located at an edge region of the field of view of the binocular camera when the binocular camera is capturing the first image data and the second image data.
5. The method of claim 1, further comprising:
and judging whether the same mark point of the preset mark target is the same as the ordinate in the first target image data and the ordinate in the second target image data, and if not, judging that the calibration parameters of the binocular camera do not pass the verification.
6. The method according to claim 5, wherein the calculating a depth distance of the preset mark target from the first lens according to the image position of the preset mark target in the first image data and the actual position of the preset mark target in the world coordinate system to obtain a real depth distance comprises:
if the vertical coordinate of the same mark point in the first target image data is the same as the vertical coordinate in the second target image data, calculating the depth distance between the preset mark target and the first lens according to the image position of the preset mark target in the first image data and the actual position of the preset mark target in a world coordinate system, and obtaining the real depth distance.
7. The utility model provides a calibration parameter's of binocular camera calibration device which characterized in that, the device includes:
the image acquisition module is used for acquiring first image data and second image data obtained by acquiring a preset mark target through a first lens and a second lens of a binocular camera to be verified;
the image calibration module is used for carrying out polar line calibration on the first image data and the second image data by using the calibration parameters of the binocular camera to obtain first target image data and second target image data;
a real depth calculation module, configured to calculate a depth distance between the preset mark target and the first lens according to an image position of the preset mark target in the first image data and an actual position of the preset mark target in a world coordinate system, so as to obtain a real depth distance;
the target depth acquisition module is used for calculating a target depth distance of a preset mark target by using calibration parameters of the binocular camera according to the first target image data and the second target image data;
the calibration parameter calibration module is used for calculating a deviation value of the target depth distance and the real depth distance, and if the deviation value is smaller than a preset deviation threshold value, the calibration parameter of the binocular camera is judged to pass calibration; otherwise, judging that the calibration parameters of the binocular camera are not verified.
8. The apparatus of claim 7, wherein the true depth calculation module is specifically configured to: determining the image position of each mark point of the preset mark target in the first image data to obtain the image position of each reference mark point; acquiring the actual positions of at least three mark points of the preset mark target in a world coordinate system to obtain the actual positions of all world mark points; calculating the depth distance between each mark point and the first lens according to the image position of the reference mark point of each mark point and the actual position of the world mark point by a PnP (pseudo-random projection) algorithm to obtain the real depth distance of each mark point;
the target depth acquisition module is specifically configured to: and calculating the target depth distance of each mark point by using the calibration parameters of the binocular camera according to the first target image data and the second target image data.
9. The apparatus of claim 8, wherein the calibration parameter verification module is specifically configured to: calculating a deviation value of the target depth distance of each mark point and the real depth distance of the mark point aiming at each mark point to respectively obtain the deviation value of each mark point; respectively comparing the deviation value of each mark point with a preset deviation threshold value, and if the deviation value of each mark point is smaller than the preset deviation threshold value, judging that the calibration parameters of the binocular camera pass the verification; otherwise, judging that the calibration parameters of the binocular camera are not verified.
10. The apparatus of claim 8, wherein each landmark point of the preset landmark target is located at an edge region of the field of view of the binocular camera when the binocular camera is capturing the first image data and the second image data.
11. The apparatus of claim 7, further comprising:
and the ordinate checking module is used for judging whether the ordinate in the first target image data is the same as the ordinate in the second target image data of the same mark point of the preset mark target, and if not, judging that the calibration parameters of the binocular camera do not pass the checking.
12. The apparatus of claim 11, wherein the true depth calculation module is specifically configured to: if the vertical coordinate of the same mark point in the first target image data is the same as the vertical coordinate in the second target image data, calculating the depth distance between the preset mark target and the first lens according to the image position of the preset mark target in the first image data and the actual position of the preset mark target in a world coordinate system, and obtaining the real depth distance.
13. An electronic device comprising a processor and a memory;
the memory is used for storing a computer program;
the processor is used for implementing the binocular camera calibration parameter verification method of any one of claims 1 to 6 when executing the program stored in the memory.
14. A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when being executed by a processor, the computer program implements the method for calibrating the calibration parameters of the binocular camera according to any one of the claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911303865.4A CN112991453A (en) | 2019-12-17 | 2019-12-17 | Calibration parameter calibration method and device for binocular camera and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911303865.4A CN112991453A (en) | 2019-12-17 | 2019-12-17 | Calibration parameter calibration method and device for binocular camera and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112991453A true CN112991453A (en) | 2021-06-18 |
Family
ID=76342415
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911303865.4A Pending CN112991453A (en) | 2019-12-17 | 2019-12-17 | Calibration parameter calibration method and device for binocular camera and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112991453A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113706499A (en) * | 2021-08-25 | 2021-11-26 | 北京市商汤科技开发有限公司 | Error detection method and related product |
| CN113781575A (en) * | 2021-08-09 | 2021-12-10 | 上海奥视达智能科技有限公司 | Camera parameter calibration method, device, terminal and storage medium |
| CN113870348A (en) * | 2021-09-18 | 2021-12-31 | 优层智能科技(上海)有限公司 | Object positioning method and device and string arranging machine |
| CN114205483A (en) * | 2022-02-17 | 2022-03-18 | 杭州思看科技有限公司 | Scanner precision calibration method and device and computer equipment |
| CN114310940A (en) * | 2021-12-20 | 2022-04-12 | 三一建筑机器人(西安)研究院有限公司 | Workpiece positioning method, device, medium, and working machine |
| CN115393442A (en) * | 2022-03-02 | 2022-11-25 | 深圳市深视智能科技有限公司 | Calibration method, device and system of three-dimensional camera |
| CN116993830A (en) * | 2023-08-17 | 2023-11-03 | 广州赋安数字科技有限公司 | Automatic calibration method for dynamic camera coordinate mapping |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109118545A (en) * | 2018-07-26 | 2019-01-01 | 深圳市易尚展示股份有限公司 | 3-D imaging system scaling method and system based on rotary shaft and binocular camera |
| CN109166152A (en) * | 2018-07-27 | 2019-01-08 | 深圳六滴科技有限公司 | Bearing calibration, system, computer equipment and the storage medium of panorama camera calibration |
| CN110490938A (en) * | 2019-08-05 | 2019-11-22 | Oppo广东移动通信有限公司 | For verifying the method, apparatus and electronic equipment of camera calibration parameter |
-
2019
- 2019-12-17 CN CN201911303865.4A patent/CN112991453A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109118545A (en) * | 2018-07-26 | 2019-01-01 | 深圳市易尚展示股份有限公司 | 3-D imaging system scaling method and system based on rotary shaft and binocular camera |
| CN109166152A (en) * | 2018-07-27 | 2019-01-08 | 深圳六滴科技有限公司 | Bearing calibration, system, computer equipment and the storage medium of panorama camera calibration |
| CN110490938A (en) * | 2019-08-05 | 2019-11-22 | Oppo广东移动通信有限公司 | For verifying the method, apparatus and electronic equipment of camera calibration parameter |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113781575A (en) * | 2021-08-09 | 2021-12-10 | 上海奥视达智能科技有限公司 | Camera parameter calibration method, device, terminal and storage medium |
| CN113781575B (en) * | 2021-08-09 | 2024-01-12 | 上海奥视达智能科技有限公司 | Calibration method and device for camera parameters, terminal and storage medium |
| CN113706499A (en) * | 2021-08-25 | 2021-11-26 | 北京市商汤科技开发有限公司 | Error detection method and related product |
| CN113870348A (en) * | 2021-09-18 | 2021-12-31 | 优层智能科技(上海)有限公司 | Object positioning method and device and string arranging machine |
| CN114310940A (en) * | 2021-12-20 | 2022-04-12 | 三一建筑机器人(西安)研究院有限公司 | Workpiece positioning method, device, medium, and working machine |
| CN114310940B (en) * | 2021-12-20 | 2024-02-06 | 三一建筑机器人(西安)研究院有限公司 | Workpiece positioning method, device, medium and working machine |
| CN114205483A (en) * | 2022-02-17 | 2022-03-18 | 杭州思看科技有限公司 | Scanner precision calibration method and device and computer equipment |
| CN115393442A (en) * | 2022-03-02 | 2022-11-25 | 深圳市深视智能科技有限公司 | Calibration method, device and system of three-dimensional camera |
| CN116993830A (en) * | 2023-08-17 | 2023-11-03 | 广州赋安数字科技有限公司 | Automatic calibration method for dynamic camera coordinate mapping |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112991453A (en) | Calibration parameter calibration method and device for binocular camera and electronic equipment | |
| JP6967715B2 (en) | Camera calibration method, camera calibration program and camera calibration device | |
| CN108111828B (en) | Projection equipment correction method and device and projection equipment | |
| CN109345467B (en) | Imaging distortion correction method, imaging distortion correction device, computer equipment and storage medium | |
| US10499038B2 (en) | Method and system for recalibrating sensing devices without familiar targets | |
| CN111210468A (en) | Image depth information acquisition method and device | |
| KR20180105875A (en) | Camera calibration method using single image and apparatus therefor | |
| US11212511B1 (en) | Residual error mitigation in multiview calibration | |
| CN107525652B (en) | Lens distortion testing method, device and system | |
| CN108182708B (en) | Calibration method and calibration device of binocular camera and terminal equipment | |
| WO2023201578A1 (en) | Extrinsic parameter calibration method and device for monocular laser speckle projection system | |
| CN116045851B (en) | Line laser profiler calibration method and device, electronic equipment and storage medium | |
| Ding et al. | A robust detection method of control points for calibration and measurement with defocused images | |
| KR101597163B1 (en) | Method and camera apparatus for calibration of stereo camera | |
| CN112970249A (en) | Assembly for calibrating a camera and measurement of such an assembly | |
| JP3696336B2 (en) | How to calibrate the camera | |
| CN117197245A (en) | Pose restoration method and device | |
| CN114018212B (en) | Spherical camera monocular ranging-oriented pitch angle correction method and system | |
| CN111598956A (en) | Calibration method, device and system | |
| CN111145247A (en) | Vision-based position detection method, robot and computer storage medium | |
| CN116188960A (en) | Instrument intelligent reading method, device, equipment and medium based on key point identification | |
| CN115018922A (en) | Distortion parameter calibration method, electronic device and computer readable storage medium | |
| CN115375773A (en) | External parameter calibration method and related device for monocular laser speckle projection system | |
| CN113365045B (en) | Camera module detection method, device and system | |
| CN107741220B (en) | Image processing method and device and electronic equipment |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 310051 room 304, B / F, building 2, 399 Danfeng Road, Binjiang District, Hangzhou City, Zhejiang Province Applicant after: Hangzhou Hikvision Robot Co.,Ltd. Address before: 310051 room 304, B / F, building 2, 399 Danfeng Road, Binjiang District, Hangzhou City, Zhejiang Province Applicant before: HANGZHOU HIKROBOT TECHNOLOGY Co.,Ltd. |