CN111758120A - Calibration method and system of camera device, three-dimensional calibration device and storage medium - Google Patents
Calibration method and system of camera device, three-dimensional calibration device and storage medium Download PDFInfo
- Publication number
- CN111758120A CN111758120A CN201980012283.2A CN201980012283A CN111758120A CN 111758120 A CN111758120 A CN 111758120A CN 201980012283 A CN201980012283 A CN 201980012283A CN 111758120 A CN111758120 A CN 111758120A
- Authority
- CN
- China
- Prior art keywords
- calibration
- image
- feature points
- camera device
- dimensional
- 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 84
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 230000033001 locomotion Effects 0.000 claims abstract description 7
- 238000004590 computer program Methods 0.000 claims description 34
- 238000012216 screening Methods 0.000 claims description 27
- 230000005540 biological transmission Effects 0.000 claims description 9
- 239000007787 solid Substances 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 238000003384 imaging method Methods 0.000 abstract description 8
- 230000000007 visual effect Effects 0.000 description 18
- 238000004519 manufacturing process Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000010923 batch production Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 239000000919 ceramic Substances 0.000 description 3
- 239000011521 glass Substances 0.000 description 3
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 239000000758 substrate Substances 0.000 description 2
- 238000010998 test method Methods 0.000 description 2
- 239000002253 acid Substances 0.000 description 1
- 239000003513 alkali Substances 0.000 description 1
- 229910010293 ceramic material Inorganic materials 0.000 description 1
- 238000011109 contamination Methods 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000009827 uniform distribution Methods 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
A calibration method, a system, a three-dimensional calibration device and a storage medium of a camera device are provided, the method comprises the following steps: the camera device moves along a fixed path (S101); in the movement process, acquiring a calibration image acquired by a camera device by a three-dimensional calibration device, wherein the three-dimensional calibration device comprises a plurality of different calibration planes, each calibration plane is provided with a calibration pattern for calibration, and the calibration image comprises the calibration patterns on the plurality of different calibration planes of the three-dimensional calibration device (S102); the imaging device is calibrated by the calibration image (S103).
Description
Technical Field
The present disclosure relates to the field of camera calibration technologies, and in particular, to a camera calibration method, a camera calibration system, a stereo calibration apparatus, and a storage medium.
Background
The internal parameters (focal length, optical center and distortion coefficient) and external parameters of the camera device are important in the applications of three-dimensional imaging, visual positioning navigation and the like. In the process of calibrating the internal and external parameters of the camera device, the calibration plate needs to be shot from a plurality of different visual angles. In a non-factory environment, calibration is usually performed by using a handheld mobile camera device or a calibration board. Batch production's product under the mill environment adopts the mode of handheld mobile camera device or calibration board, and calibration efficiency is low, and each visual angle is shot the position and is difficult to guarantee, and the parameter result uniformity of demarcation is not good.
Disclosure of Invention
Based on this, the application provides a calibration method and system of a camera device, a three-dimensional calibration device and a storage medium.
In a first aspect, the present application provides a calibration method for an image capturing apparatus, including:
the camera device moves along a fixed path;
in the movement process, acquiring a calibration image acquired by a camera device by acquiring a three-dimensional calibration device, wherein the three-dimensional calibration device comprises a plurality of different calibration planes, each calibration plane is provided with a calibration pattern for calibration, and the calibration image comprises the calibration patterns on the plurality of different calibration planes of the three-dimensional calibration device;
and calibrating the camera device through the calibration image.
In a second aspect, the present application provides a three-dimensional calibration device, which includes a plurality of calibration plates, wherein the calibration plates have calibration planes thereon, and the calibration planes are disposed on the same side of the calibration plates; and different calibration patterns are arranged on the calibration planes of the adjacent calibration plates.
In a third aspect, the present application provides a calibration system for an image capturing apparatus, the system including: a memory and a processor;
the memory is used for storing a computer program;
the processor is configured to execute the computer program and, when executing the computer program, implement the steps of:
in the process that a camera device moves along a fixed path, acquiring a calibration image acquired by the camera device by acquiring a three-dimensional calibration device, wherein the three-dimensional calibration device comprises a plurality of different calibration planes, each calibration plane is provided with a calibration pattern for calibration, and the calibration image comprises the calibration patterns on the plurality of different calibration planes of the three-dimensional calibration device;
and calibrating the camera device through the calibration image.
In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to implement the calibration method of an imaging apparatus as described above.
The embodiment of the application provides a calibration method and a calibration system of a camera device, a three-dimensional calibration device and a storage medium, wherein in the process that the camera device moves along a fixed path, a calibration image acquired by the camera device through acquiring the three-dimensional calibration device is acquired; and calibrating the camera device through the calibration image. Compared with the prior calibration plate which only comprises one calibration plane and can only be matched with one plane at most once when being shot, the three-dimensional calibration device comprises a plurality of different calibration planes, each calibration plane is provided with a calibration pattern for calibration, and the calibration image comprises the calibration patterns on the plurality of different calibration planes of the three-dimensional calibration device, so that the calibration planes can be matched, the shooting from more visual angles is not needed, the number of pictures needed in the calibration process can be reduced, and the calibration efficiency is improved; compared with the mode that a handheld mobile camera device is needed in the existing calibration, the camera device moves along a fixed path and does not move randomly in a handheld mode, so that the shooting position of each visual angle can be guaranteed, and the consistency of the calibration result can be guaranteed. Especially when the method is applied to factory calibration, manual operation is eliminated, and the labor cost of factory calibration can be greatly reduced; the consistency of the calibration result can be improved, and the product performance is further improved; the time required by calibration can be shortened, and the production standardization degree of a factory is improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flowchart of an embodiment of a calibration method for an image capturing apparatus according to the present application;
fig. 2 is a schematic diagram of a position and a connection relationship of an embodiment of a three-dimensional calibration device, a transmission device and a camera device in the calibration method of the camera device according to the present application;
fig. 3 is a schematic structural diagram of an embodiment of a three-dimensional calibration device in the calibration method of the camera device according to the present application;
fig. 4 is a schematic flowchart of another embodiment of a calibration method of the imaging apparatus according to the present application;
fig. 5 is a schematic flowchart of a calibration method of the imaging apparatus according to another embodiment of the present application;
fig. 6 is a schematic flowchart of a calibration method of the imaging apparatus according to another embodiment of the present application;
fig. 7 is a schematic structural diagram of an embodiment of a calibration system of the imaging apparatus according to 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 some, but not all, embodiments of the present application. 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.
The flow diagrams depicted in the figures are merely illustrative and do not necessarily include all of the elements and operations/steps, nor do they necessarily have to be performed in the order depicted. For example, some operations/steps may be decomposed, combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
In the process of calibrating the internal and external parameters of the camera device, the calibration plate needs to be shot from a plurality of different visual angles. In a non-factory environment, calibration is usually performed by using a handheld mobile camera device or a calibration board. Batch production's product under the mill environment adopts the mode of handheld mobile camera device or calibration board, and calibration efficiency is low, and each visual angle is shot the position and is difficult to guarantee, and the parameter result uniformity of demarcation is not good. In the embodiment of the application, a calibration image acquired by a camera device and acquired by a three-dimensional calibration device is acquired in the process that the camera device moves along a fixed path; and calibrating the camera device through the calibration image. Compared with the prior calibration plate which only comprises one calibration plane and can only be matched with one plane at most once when being shot, the three-dimensional calibration device comprises a plurality of different calibration planes, each calibration plane is provided with a calibration pattern for calibration, and the calibration image comprises the calibration patterns on the plurality of different calibration planes of the three-dimensional calibration device, so that the calibration planes can be matched, the shooting from more visual angles is not needed, the number of pictures needed in the calibration process can be reduced, and the calibration efficiency is improved; compared with the mode that a handheld mobile camera device is needed in the existing calibration, the camera device moves along a fixed path and does not move randomly in a handheld mode, so that the calibration efficiency can be improved, the shooting position of each visual angle can be guaranteed, and the consistency of the calibration result can be guaranteed. Especially when the method is applied to factory calibration, manual operation is eliminated, and the labor cost of factory calibration can be greatly reduced; the consistency of the calibration result can be improved, and the product performance is further improved; the time required by calibration can be shortened, and the production standardization degree of a factory is improved.
Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a schematic flowchart of an embodiment of a calibration method of an image capturing apparatus according to the present application, where the method includes:
step S101: the camera device moves along a fixed path.
The camera device moves along a fixed path, and can be conveniently realized in a non-manual mode, for example: mechanical arm conveying, conveying by a conveying belt, conveying by a movable platform and the like, as long as the camera device can be stably controlled to acquire images at a plurality of fixed positions.
In one application, the camera device moves along a fixed path under the transmission of the transmission device, and the mode can be simply and conveniently realized. Specifically, referring to fig. 2, the stereoscopic calibration device 1 is fixed, and the transmission device 2 (e.g., a conveyor belt) is used for transmitting the camera device 3, so that the beat of the acquired image can be controlled by a program, manual intervention is avoided, the consistency of the calibration result can be improved, and the method is suitable for batch production in a factory.
Because camera device follows fixed path motion, not handheld random movement can realize through non-manual, automatic mode, through this kind of mode, can improve and mark efficiency, can guarantee that each visual angle shoots the position, can guarantee to mark the result uniformity.
Step S102: in the movement process, a calibration image acquired by the camera device through collecting the three-dimensional calibration device is acquired, the three-dimensional calibration device comprises a plurality of different calibration planes, each calibration plane is provided with a calibration pattern used for calibration, and the calibration image comprises the calibration patterns on the plurality of different calibration planes of the three-dimensional calibration device.
Step S103: and calibrating the camera device through the calibration image.
In this embodiment, an existing calibration plate with a single calibration plane is not used, but a three-dimensional calibration device is used, the three-dimensional calibration device includes a plurality of different calibration planes, each calibration plane is provided with a calibration pattern for calibration, and in brief, one three-dimensional calibration device includes a plurality of existing calibration plates with a single calibration plane. The existing calibration plate with a single calibration plane can only obtain an image matched with one surface at one angle at most once, and in order to obtain an accurate calibration result, the calibration plate with the single calibration plane needs to be shot from more visual angles. In this embodiment, the shooting device shoots the three-dimensional calibration device once, the calibration image includes the calibration patterns on a plurality of different calibration planes of the three-dimensional calibration device, and a plurality of calibration planes at different angles can be matched simultaneously. Especially when the method is applied to factory calibration, manual operation is eliminated, and the labor cost of factory calibration can be greatly reduced; the consistency of the calibration result can be improved, and the product performance is further improved; the time required by calibration can be shortened, and the production standardization degree of a factory is improved.
In the embodiment of the application, a calibration image acquired by a camera device and acquired by a three-dimensional calibration device is acquired in the process that the camera device moves along a fixed path; and calibrating the camera device through the calibration image. Compared with the prior calibration plate which only comprises one calibration plane and can only be matched with one plane at most once when being shot, the three-dimensional calibration device comprises a plurality of different calibration planes, each calibration plane is provided with a calibration pattern for calibration, and the calibration image comprises the calibration patterns on the plurality of different calibration planes of the three-dimensional calibration device, so that the calibration planes can be matched, the shooting from more visual angles is not needed, the number of pictures needed in the calibration process can be reduced, and the calibration efficiency is improved; compared with the mode that a handheld mobile camera device is needed in the existing calibration, the camera device moves along a fixed path and does not move randomly in a handheld mode, so that the calibration efficiency can be improved, the shooting position of each visual angle can be guaranteed, and the consistency of the calibration result can be guaranteed. Especially when the method is applied to factory calibration, manual operation is eliminated, and the labor cost of factory calibration can be greatly reduced; the consistency of the calibration result can be improved, and the product performance is further improved; the time required by calibration can be shortened, and the production standardization degree of a factory is improved.
One key of the embodiments of the present application is a three-dimensional calibration device, which is described in detail below.
In one application, the three-dimensional calibration device can be a simple and convenient three-dimensional calibration plate. The three-dimensional calibration device is generally made of two materials: the first is glass, and the calibration plate of the glass substrate is widely applied to a transmission type vision measurement system and has the characteristics of small thermal expansion coefficient, high precision, larger hardness, good corrosion resistance and the like; the second one is ceramic material, the ceramic calibration plate adopts a standard plate with a ceramic substrate, and has the characteristics of small thermal expansion coefficient, high strength, high hardness, good wear resistance, low thermal conductivity, good acid and alkali resistance and the like; the ceramic calibration plate has good surface diffuse reflection processing capacity, and can better identify the pattern detail information of the calibration plate compared with the difficult problem of light reflection of a glass calibration plate under the condition of a front light source, so that higher calibration precision and measurement precision can be achieved.
As shown in fig. 3, the three-dimensional calibration device includes a plurality of calibration plates 11, 12, 13, 14, 15 (5 calibration plates are shown in the figure), calibration plates 11, 12, 13, 14, 15 have calibration planes 111, 121, 131, 141, 151, and the calibration planes 111, 121, 131, 141, 151 are disposed on the same side of the calibration plates 11, 12, 13, 14, 15; wherein, different calibration patterns are arranged on the calibration planes of the adjacent calibration plates. In fig. 3, the patterns on the calibration planes 111, 121, 131, 141, 151 on the 5 calibration plates 11, 12, 13, 14, 15 are illustrated as different squares, triangles, ellipses, cross stars, solid circles, respectively. It should be noted that the shapes on the calibration plates in fig. 3 are only schematic and do not necessarily represent the specific calibration patterns used in the embodiments.
In the embodiment, the plurality of calibration planes are arranged on the same side of the plurality of calibration plates, so that the plurality of calibration planes can be shot as far as possible when shooting is carried out once, and the shooting frequency is reduced as far as possible; different calibration patterns are arranged on the calibration planes on the adjacent calibration plates, so that the three-dimensional calibration device, the adjacent calibration planes on the calibration image and the calibration patterns on the calibration planes can be quickly distinguished and matched.
In one embodiment, the calibration pattern on the three-dimensional calibration device comprises one or more of a random solid circle array pattern, a checkerboard pattern, and an elliptical array pattern.
In order to further and rapidly match the calibration plane and the calibration pattern on the calibration plane on the three-dimensional calibration device 1 with the corresponding calibration plane and the calibration image on the calibration plane on the calibration image, the calibration patterns on each calibration plane on the three-dimensional calibration device are different in actual design.
In one application, in order to enable the calibration planes of the three-dimensional calibration device 1 to show different angles and not to be shielded from each other during shooting, a plurality of calibration plates of the three-dimensional calibration device 1 form a concave space, as shown in fig. 3, and 5 calibration plates 11, 12, 13, 14, and 15 form a concave space.
Further, in order to prevent the calibration pattern on the calibration plane from being excessively contacted by the outside, exposed outside and polluted, damaged, etc. by human or surrounding environment, the calibration pattern disposed on each calibration plane 111, 121, 131, 141, 151 is located on a side facing the recessed space. In this way, the calibration pattern on the calibration plane can be protected from human or ambient contamination, damage, and the like.
The three-dimensional calibration device 1 comprises 3 to 5 calibration plates, and the 3 to 5 calibration plates correspondingly comprise 3 to 5 calibration planes. The number of calibration planes is too small, so that the beneficial effects of reducing the number of images required in the calibration process and improving the calibration efficiency are not obvious; the number of the calibration planes is too many, so that the calibration planes are easy to shield during shooting, and the shielded part is difficult to achieve the effect of improving the calibration efficiency in practice; the three-dimensional calibration device 1 comprises 3 to 5 calibration plates, the number of the calibration planes is proper, and each calibration plane can exert the beneficial effect of improving the calibration efficiency.
In one embodiment, the plurality of calibration boards includes a main board 11 and a plurality of sub-boards 12, 13, 14, 15, each sub-board 12, 13, 14, 15 forming an obtuse angle with the main board 11. In this way, the plurality of different calibration planes 121, 131, 141, 151 represented by the main board 11 and the plurality of secondary boards 12, 13, 14, 15 can be distributed in a mutually balanced manner, and are not influenced or shielded as much as possible; an obtuse angle is formed between each secondary board 12, 13, 14, 15 and the main board 11, so that calibration patterns on a plurality of calibration boards can be further ensured to be simultaneously shot at the same position when the image shooting device shoots images.
The size of the main board 11 can be larger than the sizes of the secondary boards 12, 13, 14 and 15, so that the obtained calibration pattern on the main board is easier to calibrate; the size of the main board 11 may be smaller than the size of the sub-boards 12, 13, 14, 15, so that the size of the calibration patterns on each calibration board obtained by shooting is approximately the same.
The number of the main board 11 is one, the number of the secondary boards 12, 13, 14 and 15 is four, the four secondary boards 12, 13, 14 and 15 take the main board 11 as the center, and two adjacent secondary boards are connected with each other to form a concave space.
In one application, when the calibration pattern comprises an elliptical array pattern, the ratio of the major to minor axes of the ellipses on the secondary plate is inversely related to the obtuse angle formed. In this way, when the calibration pattern is designed, the ellipses in the ellipse array pattern can be approximated to a circle on the calibration image obtained by the image pickup device during shooting, so as to be easier to identify.
In the specific calibration process, due to limitation of computing capability, or due to limitation of whether the feature points on the captured calibration image are qualified or not, and the like, all the feature points on the calibration pattern of the calibration image are not usually used for calibration. The detailed process and details of step S103 will be described in detail below.
Referring to fig. 4, in an embodiment, step S103 may include: substep S1031, substep S1032, and substep S1033.
Substep S1031: and acquiring matching characteristic points matched with the entity characteristic points of the calibration patterns on a plurality of different calibration planes on the three-dimensional calibration device on the calibration image.
As in the existing calibration process, the characteristic points are selected for calibration, so that on one hand, the calculated amount can be reduced, and on the other hand, the pertinence is stronger when the image is matched with the entity calibration device. In this embodiment, first, matching feature points on the calibration image that match with the entity feature points of the calibration patterns on a plurality of different calibration planes on the stereo calibration device are selected.
The spatial positions of the entity characteristic points of the calibration patterns on the different calibration planes on the three-dimensional calibration device are known, the position information of each entity characteristic point in the calibration image can be obtained by obtaining the position information corresponding to the calibration image shot by the camera device through the motion information of the camera device, and the position information corresponding to the calibration image shot by the camera device through the spatial positions of the entity characteristic points, so that the matching characteristic points matched with the entity characteristic points of the calibration patterns on the different calibration planes on the three-dimensional calibration device on the calibration image can be obtained.
Sub-step S1032: and screening the matched characteristic points on the calibration image according to the preset requirement to obtain the calibration characteristic points.
Substep S1033: and calibrating the camera device through the calibration characteristic points.
The preset requirement refers to a specific requirement matched with software and hardware actually used for calibration, a calibration precision requirement, a calibration accuracy requirement and the like. For example: computing power, computing speed, memory size, calibration accuracy, and the like. The matched feature points are screened according to preset requirements to obtain calibration feature points, and then the camera device can be calibrated by using the existing calibration method (such as Zhangyingyou calibration method and the like) through the calibration feature points on the calibration image.
By the method, the speed of the calibration process can be matched with the actual configuration, and the calibration result can meet the actual requirement.
Referring to fig. 5, in a practical application, in order to further reduce the amount of calculation, the sub-step S1031 may further include: substep S1031a and substep S1031 b.
Sub-step S1031 a: and acquiring initial characteristic points on the calibration image.
Sub-step S1031 b: and matching the initial characteristic points of the calibration image with the entity characteristic points of the calibration patterns on a plurality of different calibration planes on the three-dimensional calibration device to obtain matched characteristic points.
When the camera device shoots, all calibration planes on the three-dimensional calibration device can not be shot into the calibration image, so that the number of the characteristic points on the calibration image is less than the number of the entity characteristic points on the three-dimensional calibration device and at most equal to the number of the entity characteristic points under normal conditions. The matching feature points matched on the calibration image are searched through the entity feature points, redundant calculation usually exists, and calculation resources and memory resources are wasted.
In order to reduce the calculation amount, the initial feature points on the calibration image can be obtained firstly, and the position information of the corresponding entity feature points on the stereo calibration device can be obtained through the position information of the initial feature points on the calibration image and the pose information corresponding to the calibration image shot by the camera device, so that the matching feature points which are successfully matched can be obtained.
For a process calibration process in a factory, it is usually beneficial to determine a calibrated shooting position, when a subsequent shooting device shoots, the shooting is basically carried out at a fixed position, so that the change of a shot calibration image is not large at the fixed position, a 2D-3D matching relation between an initial feature point on the calibration image and a corresponding entity feature point on a three-dimensional calibration device can be established, a matching feature point is obtained through the 2D-3D matching relation, repeated redundant calculation can be further reduced, and the calibration process is accelerated. That is, the sub-step S1031b may specifically include: and establishing a 2D-3D matching relation between the initial characteristic points on the calibration image and the corresponding entity characteristic points on the three-dimensional calibration device to obtain matching characteristic points.
Details of the screening in sub-step S1032 are described in detail below.
Although theoretically, through a proper shooting angle, only one calibration image containing calibration patterns on a plurality of different calibration planes of the three-dimensional calibration device is needed to obtain a calibration result, in the actual calibration, the calibration accuracy and the accuracy are required, a plurality of calibration images are actually collected (although the number of the calibration images is more, compared with a calibration plate with a single calibration plane, the number of the calibration images is far less than that of the images shot by the calibration plate with the single calibration plane), many matching feature points are overlapped on the calibration images, a small number of the matching feature points are overlapped, and the possible number of the matching feature points is only one or two.
In an application, in order to make the selected matching feature points as representative as possible and as evenly distributed as possible, sub-step S1032 may include: and screening the matched characteristic points on the calibration image through the image grid, so that the calibration characteristic points obtained after screening are uniformly distributed in the image grid.
In order to avoid detecting incomplete edge matching feature points, sub-step S1032 may be preceded by: and filtering the matching feature points of the upper edge of the calibration image, wherein the distance from the matching feature points of the edge to the edge of the calibration image is less than a distance threshold value. If the distance from the matching feature point to the edge of the calibration image is less than the distance threshold, the matching feature point is considered as the matching feature point of the edge and should be filtered.
In one embodiment, one way to measure the uniform distribution of calibration feature points in the image grid is the calibration feature point coverage, namely: and the ratio of the area of the convex hull surrounded by the calibration characteristic points obtained after screening to the area of the whole image grid is greater than or equal to an area threshold value. The coverage rate of the calibrated feature points can ensure that the 2D matching feature points can be uniformly covered in the whole image grid as much as possible. In one application, the coverage rate of the calibration feature points should be usually above 0.7.
Specifically, referring to fig. 6, in sub-step S1032, the screening the matching feature points on the calibration image through the image grid may include: sub-step S1032a, sub-step S1032b, and sub-step S1032 c.
Sub-step S1032 a: and dividing the screening image into grids.
The screening image is an image used for screening the matching feature points, and may be a reference image or one of the calibration images. The specific division of the grid may be determined according to computational power, pattern characteristics, and the like. Generally, the smaller the divided grid is, the easier it is to make the calibration feature points representative and uniformly distributed.
Sub-step S1032 b: and according to the positions of the matched feature points on the calibration image, putting the matched feature points into the grids at the corresponding positions one by one, and stopping adding other matched feature points into the grids when the number of the matched feature points put into the grids reaches a number threshold.
Sub-step S1032 c: and storing the matching feature points in the grid, and taking the matching feature points in the grid as calibration feature points.
In this embodiment, some matching feature points are almost on each calibration image, the overlapping probability is very high, all the matching feature points are not necessarily selected as the calibration feature points, and a certain number (i.e., a number threshold) of matching feature points can be selected as the calibration feature points. The number threshold is determined according to specific applications, computing capabilities, actual calibration requirements, and the like, and is not limited herein.
Specifically, if the addition of other matching feature points to the grid is stopped when the number of matching feature points reaches the number threshold according to the shooting sequence, the matching feature points in the later shot calibration image never have a chance to be selected as calibration feature points, and the number of possible shot and rare representative matching feature points in the later calibration image are easily missed. In order to avoid the above situation, in an application, before the sub-step S1032b, the method may further include: and randomly ordering the matched feature points. Through random sequencing, the sequence of the matching feature points can be disordered, so that the screened probability of the matching feature points in the calibration image shot successively is the same.
After the matched feature points are screened, the parameters of the camera device can be calibrated by using the calibration feature points through a Zhangyingyou calibration method and the like. Before calibration, the image resolution and the module focal length are known information, the prior parameter can be used as an initial optimization value, and the initial distortion coefficient value is usually set to be 0.
The calibrated parameter result needs to be checked, namely, the calibration result of the camera device is checked. At present, the checking method is used for checking the correctness of the parameters in the following ways.
The first inspection method: and (5) checking the calibration result of the camera device through the reprojection error. The reprojection error threshold needs to be determined according to the requirements of specific projects. For example: VGA (640 × 480), QVGA (320 × 240) images, the reprojection error threshold is usually below 0.3 pixels.
The second test method comprises the following steps: and checking the calibration result of the camera device through a preset distance, wherein the preset distance is the distance from the three-dimensional calibration device to the camera device. In the calibration process, besides internal reference of the camera device, the pose from each acquisition position of the camera device to each calibration plane of the three-dimensional calibration device can also be calculated. The distance from the three-dimensional calibration device to the camera device and the conveying device is preset, and whether the calibration result is correct or not can be checked according to the preset distance.
The third test method: carrying out distortion removal operation on the calibration image by using the calibration result of the camera device to obtain a distortion-removed calibration image; and checking the calibration result of the camera device through the undistorted calibration image. The embodiment mainly observes whether the image after distortion removal is normal or not, if so, the calibration result is credible, otherwise, the calibration result has problems and needs to be calibrated again.
Referring to fig. 3, the present application further provides a stereoscopic calibration device, which can be used for calibrating a camera device in the calibration method of the camera device, and for a detailed description of the stereoscopic calibration device, reference is made to the related content section above, which is not described herein in detail.
The three-dimensional calibration device 1 comprises: the calibration plates 11, 12, 13, 14, 15 are provided with calibration planes 111, 121, 131, 141, 151 on the calibration plates 11, 12, 13, 14, 15, and the calibration planes 111, 121, 131, 141, 151 are arranged on the same side of the calibration plates 11, 12, 13, 14, 15; wherein, different calibration patterns are arranged on the calibration planes of the adjacent calibration plates.
Compared with the prior calibration plate which only comprises one calibration plane and can only be matched with one plane at most once in shooting, the three-dimensional calibration device comprises a plurality of different calibration planes, each calibration plane is provided with the calibration pattern for calibration, the calibration image comprises the calibration patterns on the plurality of different calibration planes of the three-dimensional calibration device, the calibration planes can be matched, shooting from more visual angles is not needed, the number of the images required in the calibration process can be reduced, and the calibration efficiency is improved.
Wherein the calibration pattern comprises one or more of a random circular array pattern, a chessboard pattern and an elliptical array pattern.
The three-dimensional calibration device comprises a plurality of calibration plates, a plurality of positioning plates and a plurality of positioning plates.
The calibration pattern arranged on each calibration plane is positioned on one surface facing the concave space.
The three-dimensional calibration device comprises 3 to 5 calibration plates.
The calibration plates comprise a main plate and a plurality of secondary plates, and an obtuse angle is formed between each secondary plate and the main plate.
Wherein the size of the primary plate is larger than that of the secondary plate.
The number of the main board is one, the number of the secondary boards is four, the four secondary boards use the main board as the center, and two adjacent secondary boards are connected with each other to form a concave space.
Wherein, when the calibration pattern comprises an elliptical array pattern, the ratio of the major and minor axes of the ellipses on the secondary plate is inversely related to the obtuse angle formed.
Referring to fig. 7, fig. 7 is a schematic structural diagram of an embodiment of a calibration system of the image capturing apparatus of the present application, it should be noted that the calibration system of the image capturing apparatus of the present application can execute the steps in the calibration method of the image capturing apparatus described above, and please refer to the above method section for detailed description, which is not described herein.
The system 10 includes: a memory 11 and a processor 12; the memory 11 and the processor 12 are connected by a bus 13.
The processor 12 may be a micro-control unit, a central processing unit, a digital signal processor, or the like.
The memory 11 may be a Flash chip, a read-only memory, a magnetic disk, an optical disk, a usb disk, or a removable hard disk, among others.
The memory 11 is used for storing a computer program; the processor 12 is arranged to execute the computer program and when executing the computer program, to carry out the steps of:
in the process that the camera device moves along a fixed path, acquiring a calibration image acquired by the camera device by acquiring a three-dimensional calibration device, wherein the three-dimensional calibration device comprises a plurality of different calibration planes, each calibration plane is provided with a calibration pattern for calibration, and the calibration image comprises the calibration patterns on the plurality of different calibration planes of the three-dimensional calibration device; and calibrating the camera device through the calibration image.
In the embodiment of the application, a calibration image acquired by a camera device and acquired by a three-dimensional calibration device is acquired in the process that the camera device moves along a fixed path; and calibrating the camera device through the calibration image. Compared with the prior calibration plate which only comprises one calibration plane and can only be matched with one plane at most once when being shot, the three-dimensional calibration device comprises a plurality of different calibration planes, each calibration plane is provided with a calibration pattern for calibration, and the calibration image comprises the calibration patterns on the plurality of different calibration planes of the three-dimensional calibration device, so that the calibration planes can be matched, the shooting from more visual angles is not needed, the number of pictures needed in the calibration process can be reduced, and the calibration efficiency is improved; compared with the mode that a handheld mobile camera device is needed in the existing calibration, the camera device moves along a fixed path and does not move randomly in a handheld mode, so that the calibration efficiency can be improved, the shooting position of each visual angle can be guaranteed, and the consistency of the calibration result can be guaranteed. Especially when the method is applied to factory calibration, manual operation is eliminated, and the labor cost of factory calibration can be greatly reduced; the consistency of the calibration result can be improved, and the product performance is further improved; the time required by calibration can be shortened, and the production standardization degree of a factory is improved.
Wherein, when the processor executes the computer program, the following steps are realized: acquiring matching characteristic points matched with entity characteristic points of calibration patterns on a plurality of different calibration planes on a three-dimensional calibration device on a calibration image; screening matched feature points on the calibration image according to preset requirements to obtain calibration feature points; and calibrating the camera device through the calibration characteristic points.
Wherein, when the processor executes the computer program, the following steps are realized: acquiring initial characteristic points on a calibration image; and matching the initial characteristic points of the calibration image with the entity characteristic points of the calibration patterns on a plurality of different calibration planes on the three-dimensional calibration device to obtain matched characteristic points.
Wherein, when the processor executes the computer program, the following steps are realized: and establishing a 2D-3D matching relation between the initial characteristic points on the calibration image and the corresponding entity characteristic points on the three-dimensional calibration device to obtain matching characteristic points.
Wherein, when the processor executes the computer program, the following steps are realized: and screening the matched characteristic points on the calibration image through the image grid, so that the calibration characteristic points obtained after screening are uniformly distributed in the image grid.
Wherein, when the processor executes the computer program, the following steps are realized: dividing the screening image into grids;
according to the positions of the matched feature points on the calibration image, the matched feature points are placed into the grids at the corresponding positions one by one, and when the number of the matched feature points placed into the grids reaches a number threshold, the addition of other matched feature points into the grids is stopped; and storing the matching feature points in the grid, and taking the matching feature points in the grid as calibration feature points.
Wherein, when the processor executes the computer program, the following steps are realized: and randomly ordering the matched feature points.
Wherein, when the processor executes the computer program, the following steps are realized: and filtering the matching feature points of the upper edge of the calibration image, wherein the distance from the matching feature points of the edge to the edge of the calibration image is less than a distance threshold value.
And the ratio of the area of the convex hull surrounded by the calibration characteristic points obtained after screening to the area of the whole image grid is greater than or equal to an area threshold value.
Wherein, when the processor executes the computer program, the following steps are realized: and checking the calibration result of the camera device.
Wherein, when the processor executes the computer program, the following steps are realized: and (5) checking the calibration result of the camera device through the reprojection error.
Wherein, when the processor executes the computer program, the following steps are realized: and checking the calibration result of the camera device through a preset distance, wherein the preset distance is the distance from the three-dimensional calibration device to the camera device.
Wherein, when the processor executes the computer program, the following steps are realized: carrying out distortion removal operation on the calibration image by using the calibration result of the camera device to obtain a distortion-removed calibration image; and checking the calibration result of the camera device through the undistorted calibration image.
Wherein the calibration pattern comprises one or more of a random solid circle array pattern and a chessboard pattern.
Wherein, the calibration patterns arranged on each calibration plane are different.
Wherein the camera device moves along a fixed path under the transmission of the transmission device.
The present application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to implement the calibration method of the imaging apparatus as described in any one of the above. For a detailed description of relevant matters, reference is made to the above method section, which is not described in detail herein.
The computer-readable storage medium may be an internal storage unit of the calibration system of any of the above-mentioned image capturing apparatuses, for example, a hard disk or a memory of the calibration system of the image capturing apparatus. The computer readable storage medium may also be an external storage device of the calibration system of the camera device, such as a plug-in hard disk, a smart card, a secure digital card, a flash memory card, etc. provided on the calibration system of the camera device.
In the embodiment of the application, a calibration image acquired by a camera device and acquired by a three-dimensional calibration device is acquired in the process that the camera device moves along a fixed path; and calibrating the camera device through the calibration image. Compared with the prior calibration plate which only comprises one calibration plane and can only be matched with one plane at most once when being shot, the three-dimensional calibration device comprises a plurality of different calibration planes, each calibration plane is provided with a calibration pattern for calibration, and the calibration image comprises the calibration patterns on the plurality of different calibration planes of the three-dimensional calibration device, so that the calibration planes can be matched, the shooting from more visual angles is not needed, the number of pictures needed in the calibration process can be reduced, and the calibration efficiency is improved; compared with the mode that a handheld mobile camera device is needed in the existing calibration, the camera device moves along a fixed path and does not move randomly in a handheld mode, so that the calibration efficiency can be improved, the shooting position of each visual angle can be guaranteed, and the consistency of the calibration result can be guaranteed. Especially when the method is applied to factory calibration, manual operation is eliminated, and the labor cost of factory calibration can be greatly reduced; the consistency of the calibration result can be improved, and the product performance is further improved; the time required by calibration can be shortened, and the production standardization degree of a factory is improved.
It is to be understood that the terminology used in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.
It should also be understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
The above description is only for the specific embodiment of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present application, and these modifications or substitutions should be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (42)
1. A calibration method of an image pickup apparatus is characterized by comprising:
the camera device moves along a fixed path;
in the movement process, acquiring a calibration image acquired by a camera device by acquiring a three-dimensional calibration device, wherein the three-dimensional calibration device comprises a plurality of different calibration planes, each calibration plane is provided with a calibration pattern for calibration, and the calibration image comprises the calibration patterns on the plurality of different calibration planes of the three-dimensional calibration device;
and calibrating the camera device through the calibration image.
2. The method of claim 1, wherein said calibrating the camera with the calibration image comprises:
acquiring matching feature points on the calibration image, which are matched with entity feature points of calibration patterns on a plurality of different calibration planes on the three-dimensional calibration device;
screening matched feature points on the calibration image according to preset requirements to obtain calibration feature points;
and calibrating the camera device through the calibration characteristic point.
3. The method according to claim 2, wherein the obtaining matching feature points on the calibration image that match with the entity feature points of the calibration pattern on a plurality of different calibration planes on the stereoscopic calibration device comprises:
acquiring initial characteristic points on a calibration image;
and matching the initial characteristic points of the calibration image with the entity characteristic points of the calibration patterns on a plurality of different calibration planes on the three-dimensional calibration device to obtain matched characteristic points.
4. The method as claimed in claim 3, wherein the matching the initial feature points of the calibration image with the entity feature points of the calibration patterns on a plurality of different calibration planes on the stereo calibration device to obtain matching feature points comprises:
and establishing a 2D-3D matching relation between the initial characteristic points on the calibration image and the corresponding entity characteristic points on the three-dimensional calibration device to obtain matching characteristic points.
5. The method according to claim 2, wherein the screening the matching feature points on the calibration image according to a preset requirement to obtain calibration feature points comprises:
and screening the matched characteristic points on the calibration image through the image grid, so that the calibration characteristic points obtained after screening are uniformly distributed in the image grid.
6. The method of claim 5, wherein the screening of the matching feature points on the calibration image through the image grid comprises:
dividing the screening image into grids;
according to the positions of the matched feature points on the calibration image, the matched feature points are placed into the grids at the corresponding positions one by one, and when the number of the matched feature points placed into the grids reaches a number threshold, the addition of other matched feature points into the grids is stopped;
and storing the matching feature points in the grid, and taking the matching feature points in the grid as calibration feature points.
7. The method according to claim 6, wherein before placing the matched feature points one by one into the grid at the corresponding positions according to the positions of the matched feature points on the calibration image, the method comprises:
and randomly ordering the matched feature points.
8. The method of claim 5, wherein before the screening of the matching feature points on the calibration image through the image grid, the method comprises:
and filtering the matching feature points of the upper edge of the calibration image, wherein the distance from the matching feature points of the edge to the edge of the calibration image is less than a distance threshold value.
9. The method according to claim 5, wherein the ratio of the area of the convex hull surrounded by the calibrated feature points obtained after screening to the area of the whole image grid is greater than or equal to an area threshold.
10. The method according to any one of claims 1-9, further comprising:
and checking the calibration result of the camera device.
11. The method according to claim 10, wherein the verifying the calibration result of the camera device comprises:
and checking the calibration result of the camera device through the reprojection error.
12. The method according to claim 10, wherein the verifying the calibration result of the camera device comprises:
and checking the calibration result of the camera device through a preset distance, wherein the preset distance is the distance from the three-dimensional calibration device to the camera device.
13. The method according to claim 10, wherein the verifying the calibration result of the camera device comprises:
carrying out distortion removal operation on the calibration image by using the calibration result of the camera device to obtain a distortion-removed calibration image;
and checking the calibration result of the camera device through the undistorted calibration image.
14. The method of any of claims 1-13, wherein the calibration pattern comprises one or more of a random solid circle array pattern, a checkerboard pattern.
15. The method according to any of claims 1-14, wherein the calibration patterns provided on each calibration plane are different.
16. The method of any one of claims 1-15, wherein the camera device moves along a fixed path, comprising:
the camera device moves along a fixed path under the transmission of the transmission device.
17. A three-dimensional calibration device is characterized in that,
the three-dimensional calibration device comprises a plurality of calibration plates, wherein calibration planes are arranged on the calibration plates, and the calibration planes are arranged on the same side of the calibration plates;
and different calibration patterns are arranged on the calibration planes of the adjacent calibration plates.
18. The volumetric calibration device of claim 17, wherein the calibration pattern comprises one or more of a random circular array pattern, a checkerboard pattern, and an elliptical array pattern.
19. The three-dimensional calibration device according to claim 17, wherein a plurality of calibration plates of the three-dimensional calibration device form a concave space.
20. The apparatus according to claim 19, wherein the calibration pattern disposed on each calibration plane is located on a side facing the recessed space.
21. The stereoscopic marking apparatus according to claim 19, wherein the stereoscopic marking apparatus comprises 3 to 5 marking plates.
22. The apparatus according to claim 19, wherein the calibration plates comprise a main plate and a plurality of secondary plates, and each secondary plate forms an obtuse angle with the main plate.
23. The stereoscopic marking apparatus of claim 22, wherein the size of the primary plate is larger than the size of the secondary plate.
24. The apparatus according to claim 22, wherein the number of the main plate is one, the number of the secondary plates is four, four of the secondary plates are centered on the main plate, and two adjacent secondary plates are connected to each other to form the recessed space.
25. The volumetric calibration device of claim 22 wherein when the calibration pattern comprises an elliptical array pattern, the ratio of the major to minor axes of the ellipses on the secondary plate is inversely related to the obtuse angle formed.
26. A calibration system for an image capture device, the system comprising: a memory and a processor;
the memory is used for storing a computer program;
the processor is configured to execute the computer program and, when executing the computer program, implement the steps of:
in the process that a camera device moves along a fixed path, acquiring a calibration image acquired by the camera device by acquiring a three-dimensional calibration device, wherein the three-dimensional calibration device comprises a plurality of different calibration planes, each calibration plane is provided with a calibration pattern for calibration, and the calibration image comprises the calibration patterns on the plurality of different calibration planes of the three-dimensional calibration device;
and calibrating the camera device through the calibration image.
27. The system of claim 26, wherein the processor, when executing the computer program, performs the steps of:
acquiring matching feature points on the calibration image, which are matched with entity feature points of calibration patterns on a plurality of different calibration planes on the three-dimensional calibration device;
screening matched feature points on the calibration image according to preset requirements to obtain calibration feature points;
and calibrating the camera device through the calibration characteristic point.
28. The system of claim 27, wherein the processor, when executing the computer program, performs the steps of:
acquiring initial characteristic points on a calibration image;
and matching the initial characteristic points of the calibration image with the entity characteristic points of the calibration patterns on a plurality of different calibration planes on the three-dimensional calibration device to obtain matched characteristic points.
29. The system of claim 28, wherein the processor, when executing the computer program, performs the steps of:
and establishing a 2D-3D matching relation between the initial characteristic points on the calibration image and the corresponding entity characteristic points on the three-dimensional calibration device to obtain matching characteristic points.
30. The system of claim 27, wherein the processor, when executing the computer program, performs the steps of:
and screening the matched characteristic points on the calibration image through the image grid, so that the calibration characteristic points obtained after screening are uniformly distributed in the image grid.
31. The system of claim 30, wherein the processor, when executing the computer program, performs the steps of:
dividing the screening image into grids;
according to the positions of the matched feature points on the calibration image, the matched feature points are placed into the grids at the corresponding positions one by one, and when the number of the matched feature points placed into the grids reaches a number threshold, the addition of other matched feature points into the grids is stopped;
and storing the matching feature points in the grid, and taking the matching feature points in the grid as calibration feature points.
32. The system of claim 31, wherein the processor, when executing the computer program, performs the steps of:
and randomly ordering the matched feature points.
33. The system of claim 30, wherein the processor, when executing the computer program, performs the steps of:
and filtering the matching feature points of the upper edge of the calibration image, wherein the distance from the matching feature points of the edge to the edge of the calibration image is less than a distance threshold value.
34. The system of claim 30, wherein the ratio of the area of the convex hull surrounded by the calibrated feature points obtained after the screening to the area of the whole image grid is greater than or equal to an area threshold.
35. The system according to any of claims 26-34, wherein the processor, when executing the computer program, performs the steps of:
and checking the calibration result of the camera device.
36. The system of claim 35, wherein the processor, when executing the computer program, performs the steps of:
and checking the calibration result of the camera device through the reprojection error.
37. The system of claim 35, wherein the processor, when executing the computer program, performs the steps of:
and checking the calibration result of the camera device through a preset distance, wherein the preset distance is the distance from the three-dimensional calibration device to the camera device.
38. The system of claim 35, wherein the processor, when executing the computer program, performs the steps of:
carrying out distortion removal operation on the calibration image by using the calibration result of the camera device to obtain a distortion-removed calibration image;
and checking the calibration result of the camera device through the undistorted calibration image.
39. The system of any of claims 26-38, wherein the calibration pattern comprises one or more of a random solid circle array pattern, a checkerboard pattern.
40. The system of any one of claims 26 to 39, wherein the calibration patterns provided on each calibration plane are different.
41. A system according to any of claims 26 to 40, wherein the camera means is moved along a fixed path on transport by the transport means.
42. A computer-readable storage medium, characterized in that it stores a computer program which, when executed by a processor, causes the processor to carry out a calibration method of an image pickup apparatus according to any one of claims 1 to 16.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2019/112015 WO2021072767A1 (en) | 2019-10-18 | 2019-10-18 | Calibration method and system for camera device, and stereoscopic calibration device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111758120A true CN111758120A (en) | 2020-10-09 |
Family
ID=72673094
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201980012283.2A Pending CN111758120A (en) | 2019-10-18 | 2019-10-18 | Calibration method and system of camera device, three-dimensional calibration device and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111758120A (en) |
| WO (1) | WO2021072767A1 (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112669389A (en) * | 2020-12-08 | 2021-04-16 | 深圳先进技术研究院 | Automatic calibration system based on visual guidance |
| WO2022120567A1 (en) * | 2020-12-08 | 2022-06-16 | 深圳先进技术研究院 | Automatic calibration system based on visual guidance |
| CN117745833A (en) * | 2024-02-20 | 2024-03-22 | 中科慧远人工智能(烟台)有限公司 | Pose measurement method and device of camera array |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116672082B (en) * | 2023-07-24 | 2024-03-01 | 苏州铸正机器人有限公司 | Navigation registration method and device of operation navigation ruler |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008014940A (en) * | 2006-06-08 | 2008-01-24 | Fast:Kk | Camera calibration method for camera measurement of planar subject and measuring device applying same |
| CN108230397A (en) * | 2017-12-08 | 2018-06-29 | 深圳市商汤科技有限公司 | Multi-lens camera is demarcated and bearing calibration and device, equipment, program and medium |
| CN109416744A (en) * | 2016-06-28 | 2019-03-01 | 奇跃公司 | Improved camera calibration system, target and process |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003065714A (en) * | 2001-08-21 | 2003-03-05 | Sony Corp | Guiding device and guiding method for camera calibration, and camera calibration apparatus |
| CN105321174B (en) * | 2015-09-23 | 2019-03-26 | 浙江大学 | A kind of multiple plane mirror reflection tracking clouds terrace system scaling method |
| CN109176505B (en) * | 2018-08-10 | 2021-06-11 | 厦门大学 | Ball arm instrument-based six-axis joint industrial robot spatial error calibration method |
-
2019
- 2019-10-18 CN CN201980012283.2A patent/CN111758120A/en active Pending
- 2019-10-18 WO PCT/CN2019/112015 patent/WO2021072767A1/en active Application Filing
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008014940A (en) * | 2006-06-08 | 2008-01-24 | Fast:Kk | Camera calibration method for camera measurement of planar subject and measuring device applying same |
| CN109416744A (en) * | 2016-06-28 | 2019-03-01 | 奇跃公司 | Improved camera calibration system, target and process |
| CN108230397A (en) * | 2017-12-08 | 2018-06-29 | 深圳市商汤科技有限公司 | Multi-lens camera is demarcated and bearing calibration and device, equipment, program and medium |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112669389A (en) * | 2020-12-08 | 2021-04-16 | 深圳先进技术研究院 | Automatic calibration system based on visual guidance |
| WO2022120567A1 (en) * | 2020-12-08 | 2022-06-16 | 深圳先进技术研究院 | Automatic calibration system based on visual guidance |
| CN112669389B (en) * | 2020-12-08 | 2024-08-16 | 深圳先进技术研究院 | Automatic calibration system based on visual guidance |
| CN117745833A (en) * | 2024-02-20 | 2024-03-22 | 中科慧远人工智能(烟台)有限公司 | Pose measurement method and device of camera array |
| CN117745833B (en) * | 2024-02-20 | 2024-05-10 | 中科慧远人工智能(烟台)有限公司 | Pose measurement method and device of camera array |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021072767A1 (en) | 2021-04-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111758120A (en) | Calibration method and system of camera device, three-dimensional calibration device and storage medium | |
| US11503275B2 (en) | Camera calibration system, target, and process | |
| CN104613930B (en) | Method and device for measuring distance as well as mobile terminal | |
| CN103644865B (en) | Plane area measuring method based on digital image analysis | |
| CN108182708B (en) | Calibration method and calibration device of binocular camera and terminal equipment | |
| US20190108653A1 (en) | Capture Device Calibration Methods and Systems | |
| CN113124763B (en) | Optical axis calibration method, device, terminal, system and medium for optical axis detection system | |
| US20180278911A1 (en) | Apparatus and method for three-dimensional inspection | |
| CN111709999A (en) | Calibration plate, camera calibration method and device, electronic equipment and camera system | |
| CN103827626A (en) | Three-dimensional measurement device | |
| CN110260801A (en) | Method and apparatus for measuring volume of material | |
| CN116894786A (en) | Method for correcting distorted image and computer-readable storage medium | |
| EP3967969A1 (en) | Fisheye camera calibration system, method and apparatus, electronic device, and storage medium | |
| CN111311671A (en) | Workpiece measuring method and device, electronic equipment and storage medium | |
| CN112595262B (en) | Binocular structured light-based high-light-reflection surface workpiece depth image acquisition method | |
| CN104677911B (en) | Inspection apparatus and method for machine vision inspection | |
| CN111336938A (en) | Robot and object distance detection method and device thereof | |
| CN109040724B (en) | Light spot distortion detection method and device of structured light projector and readable storage medium | |
| CN116380918A (en) | Defect detection method, device and equipment | |
| CN115656988A (en) | Laser radar dynamic pitch angle detection method and device and electronic equipment | |
| WO2017116027A1 (en) | Visual inspecting method | |
| CN108204982A (en) | Multi-view image capturing device and multi-view image detecting equipment | |
| CN112991337A (en) | Method for correcting rock burst fragment kinetic energy test error | |
| CN109916341B (en) | Method and system for measuring horizontal inclination angle of product surface | |
| CN115937321B (en) | Gesture detection method and device of 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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20201009 |