CN114979464B - Industrial camera view angle accurate configuration method and system adaptive to target area - Google Patents
Industrial camera view angle accurate configuration method and system adaptive to target area Download PDFInfo
- Publication number
- CN114979464B CN114979464B CN202210404940.1A CN202210404940A CN114979464B CN 114979464 B CN114979464 B CN 114979464B CN 202210404940 A CN202210404940 A CN 202210404940A CN 114979464 B CN114979464 B CN 114979464B
- Authority
- CN
- China
- Prior art keywords
- industrial camera
- imaging
- field angle
- angle
- target area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/69—Control of means for changing angle of the field of view, e.g. optical zoom objectives or electronic zooming
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Abstract
The invention discloses an industrial camera view angle accurate configuration method and system adaptive to a target area, which are used for establishing an imaging area model of an industrial camera by carrying out quantitative description on an imaging scene of the industrial camera, providing a target function for acquiring a complete target image at a minimum view angle based on the imaging scene and the imaging area model which are quantitatively described, and designing a heuristic solving algorithm based on binary-particle swarm combination to carry out accurate configuration on the view angle of the industrial camera.
Description
Technical Field
The invention mainly relates to the technical field of optical imaging, in particular to a method and a system for accurately configuring the field angle of an industrial camera adaptive to a target area.
Background
With the development of optical imaging devices and the advancement of image processing technologies, machine vision technologies have been widely used in the industrial fields of metallurgy, petrochemistry, electric power, and the like. The target area image acquired by the industrial camera is a data source applied to the machine vision technology, and the improvement of the image quality plays an important role in improving the subsequent application effect.
The field angle of an industrial camera determines the size of an imaging area and is one of key parameters influencing the imaging quality of a target. The field angle is too large, the effective pixel proportion of the target in the image is small, a large number of pixels of the image sensor are wasted, the image processing work such as removing invalid areas is increased, and the spatial resolution of the target area in the image is reduced; the field angle is too small, the industrial camera can only acquire partial area images of the target, and comprehensive target information is difficult to provide for subsequent application. Therefore, the field angle of the industrial camera is accurately configured, the pixels of the image sensor are fully utilized while the complete image of the target area is acquired, the completeness of target information can be ensured, the image quality of the target can be improved, and the method has important significance for promoting further development and application of a machine vision technology in the industrial field.
However, due to the lack of a general method for quantitatively describing the imaging area of the industrial camera, the angle of view of the industrial camera is difficult to be precisely configured according to the target area. At present, most of configuration methods of the field angle of the industrial camera are manually estimated, certain randomness and blindness exist, the imaging area of the industrial camera is not matched with the target area, and a large number of pixels of an image sensor are wasted. Therefore, the invention provides an industrial camera view angle accurate configuration method adaptive to a target area, which can acquire a complete and high-quality target image with a minimum view angle and can provide effective guidance for selection of the industrial camera view angle when a machine vision technology is applied.
Patent publication No. CN 111491093A proposes a method for adjusting the angle of view of a camera, which is to set up a local detection frame for the area where the target is located and adjust the angle of view of the camera according to the proportion of the local detection frame in the whole image.
However, this patent does not consider the influence of the imaging direction of the camera on the imaging area, and it is difficult to precisely arrange the camera angle that best matches the target area, and the acquired image cannot be of optimal quality.
The patent publication No. CN 113542572B proposes a method for arranging a rifle bolt camera and selecting a lens type, which includes loading parameters of the rifle bolt camera into a Revit platform, and simulating and calculating monitoring ranges of the rifle bolt camera at different positions and different lens focal length models, so as to provide reference for the configuration of the lens focal length selection, i.e. the view angle.
However, the method for calculating the monitoring range of the camera in the patent is discrete, only the monitoring range of the camera at a fixed distance can be calculated, the quantitative relation between the parameters of the camera and the monitoring range is not clear, and the method is difficult to be applied to the industrial field with complex scenes.
Disclosure of Invention
The method and the system for accurately configuring the field angle of the industrial camera adaptive to the target area solve the technical problem that the field angle of the existing industrial camera is difficult to accurately configure according to the target area.
In order to solve the technical problem, the method for accurately configuring the field angle of the industrial camera adaptive to the target area comprises the following steps:
quantitatively describing an imaging scene of the industrial camera, wherein the imaging scene at least comprises an installation position, an imaging direction and a target area of the industrial camera;
establishing an imaging area model of the industrial camera, wherein the imaging area model is used for quantitatively describing an imaging area of the industrial camera under a scene coordinate system;
and accurately configuring the field angle of the industrial camera based on the imaging scene and the imaging area model which are described quantitatively.
Further, the quantitative description of the imaging scene of the industrial camera comprises the following steps:
establishing a three-dimensional world coordinate system by taking the optical center of the industrial camera as an origin to obtain a scene coordinate system;
establishing a camera coordinate system by taking the optical center of the industrial camera as an original point, taking the optical axis as a Z axis and taking the directions respectively parallel to the length and the width of the industrial camera image sensor as a Y axis and an X axis;
carrying out quantitative description on the imaging direction according to the rotation angles of three axes in the scene coordinate system when the scene coordinate system is transformed to the camera coordinate system;
and carrying out quantitative description on the target area by adopting a discrete point set on the outline of the target area.
Further, modeling the imaging area of the industrial camera includes:
acquiring a camera imaging area of an industrial camera in a camera coordinate system, wherein a calculation formula of the camera imaging area is as follows:
wherein k is the length-width ratio of the industrial camera image sensor, omega is the angle of field, (X) C 、Y C 、Z C ) Coordinates representing points within the camera imaging area;
and according to the imaging direction of the industrial camera, carrying out coordinate transformation on the imaging area of the camera to obtain the imaging area of the industrial camera in a scene coordinate system, thereby obtaining an imaging area model of the industrial camera.
Further, the calculation formula of the imaging area model of the industrial camera is as follows:
wherein k is the length-width ratio of the industrial camera image sensor, omega is the angle of field, (X) W 、Y W 、Z W ) Coordinates representing points within the imaging area of the industrial camera in the scene coordinate system, a 1 、a 2 And a 3 The rotation angles of three axes in the scene coordinate system when the scene coordinate system is transformed to the camera coordinate system are respectively.
Further, the precisely configuring the field angle of the industrial camera based on the imaging scene and the imaging area model described by the quantification comprises:
determining an objective function of the precise configuration problem of the field angle, wherein the calculation formula of the objective function is as follows:
wherein, ω is an angle of view, α is a coverage rate, the coverage rate is used to characterize the completeness of the imaged target region, and a calculation formula of the coverage rate is as follows:
wherein Ω is a set of discrete points on the contour of the target region, Ω A For the imaging area of an industrial camera in the scene coordinate system, t i (x i y i z i ) The coordinates of the ith point on the outline of the target area are shown, and n is the number of points on the outline of the whole target area;
and according to the imaging region model, performing optimization solution on the objective function, thereby accurately configuring the field angle of the industrial camera.
Further, the solving of the optimization of the objective function according to the imaging region model comprises:
step1: setting initialization parameters including an aspect ratio k, a target area omega and an angle of view upper limit value omega of an industrial camera image sensor max Lower limit value of angle of view ω min And an initial value of the iteration number N, wherein the upper limit value of the field angle represents a critical value from the target area can be completely covered to the target area can not be completely covered;
step2: updating the current field angle omega by using a bisection method, wherein the updating rule specifically comprises the following steps:
step3: imaging direction a of an industrial camera 1 、a 2 And a 3 As an optimization adjustment variable, the value range is (-pi/2, pi/2), and the maximum coverage rate under the current field angle is calculated by utilizing a particle swarm optimization algorithm;
step4: updating the upper limit value and the lower limit value of the angle of view according to the maximum coverage rate calculated in the Step3, if the coverage rate is 1, updating the upper limit value of the angle of view to the current angle of view, keeping the lower limit value of the angle of view unchanged, recording the imaging direction when the coverage rate is 1, and if the coverage rate is less than 1, updating the lower limit value of the angle of view to the current angle of view, keeping the upper limit value of the angle of view unchanged;
step5: and repeating the steps Step2, step3 and Step4 until the iteration number N is reached, and outputting the upper limit value of the field angle and the corresponding imaging direction.
Further, setting the initialization parameter further includes setting configuration precision of the field angle, and the setting formula of the configuration precision is as follows:
wherein, delta ω For configuration accuracy, N is the number of iterations, ω max Is the upper limit value of the angle of view, omega min Is the lower limit of the angle of view.
The industrial camera view angle accurate configuration system adaptive to the target area comprises:
the device comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to realize the steps of the industrial camera view angle precise configuration method for adapting the target area provided by the invention.
Compared with the prior art, the invention has the advantages that:
the invention provides a method and a system for accurately configuring an industrial camera field angle adaptive to a target area, which are used for establishing an imaging area model of an industrial camera by quantitatively describing an imaging scene of the industrial camera, providing a target function for acquiring a complete target image at a minimum field angle based on the imaging scene and the imaging area model which are quantitatively described, and designing a heuristic solving algorithm based on binary-particle swarm combination to accurately configure the field angle of the industrial camera.
Drawings
FIG. 1 is a diagram of an imaging scene according to a second embodiment of the present invention;
fig. 2 is a schematic view of an imaging area of an industrial camera in a camera coordinate system according to a second embodiment of the present invention;
FIG. 3 is a flowchart of an algorithm for configuring an angle of view based on binary-particle swarm combination according to a second embodiment of the present invention;
FIG. 4 is a schematic diagram of a target area according to a second embodiment of the present invention;
FIG. 5 is a configuration result diagram according to a third embodiment of the present invention;
fig. 6 is a block diagram of a system for accurately configuring a field angle of an industrial camera according to an embodiment of the present invention.
Reference numerals are as follows:
10. a memory; 20. a processor.
Detailed Description
In order to facilitate an understanding of the invention, the invention will be described more fully and in detail below with reference to the accompanying drawings and preferred embodiments, but the scope of the invention is not limited to the specific embodiments below.
Embodiments of the invention will be described in detail below with reference to the drawings, but the invention can be implemented in many different ways as defined and covered by the claims.
Example one
The method for accurately configuring the field angle of the industrial camera adaptive to the target area, provided by the embodiment of the invention, comprises the following steps:
s101, quantitatively describing an imaging scene of the industrial camera, wherein the imaging scene at least comprises an installation position, an imaging direction and a target area of the industrial camera;
step S102, establishing an imaging area model of the industrial camera, wherein the imaging area model is used for quantitatively describing an imaging area of the industrial camera in a scene coordinate system;
and step S103, accurately configuring the field angle of the industrial camera based on the imaging scene and the imaging area model which are described quantitatively.
The method for accurately configuring the field angle of the industrial camera adaptive to the target area, provided by the embodiment of the invention, comprises the steps of carrying out quantitative description on an imaging scene of the industrial camera, establishing an imaging area model of the industrial camera, based on the imaging scene and the imaging area model which are quantitatively described, providing an objective function for obtaining a complete target image with a minimum field angle, and designing a heuristic solving algorithm based on binary-particle swarm combination to accurately configure the field angle of the industrial camera, so that the technical problem that the field angle of the existing industrial camera is difficult to be accurately configured according to the target area is solved, the direction of the industrial camera is continuously optimized and adjusted and the field angle is reduced according to the quantitative relation between the imaging area of the industrial camera, the field angle of the industrial camera and the imaging direction, so that the imaging area is adaptive to the target area, the complete high-quality image of the target is obtained, and reliable guidance is provided for related industry personnel to configure the field angle of the industrial camera when applying the machine vision technology.
Example two
The method for accurately configuring the field angle of the industrial camera adaptive to the target area comprises the following steps:
(1) Quantitatively describing an imaging scene;
(2) Establishing an imaging area model of an industrial camera;
(3) And designing a precise configuration algorithm of the field angle of the industrial camera.
The specific implementation scheme is as follows:
(1) Quantitatively describing an imaging scene
Industrial cameras are generally used to acquire an image of a certain object in order to monitor an operation state of the object or to extract other information of the object from the image, and an imaging area thereof is determined by a mounting position, an imaging direction and a field angle. In order to precisely arrange the angle of view of the industrial camera and to optimally match the imaging area with the target area, it is necessary to quantitatively describe elements of the imaging scene such as the installation position, the imaging direction, and the target area of the industrial camera. Therefore, the invention firstly establishes a three-dimensional space coordinate system to quantitatively describe the imaging scene.
As shown in FIG. 1, a scene coordinate system O is established with the optical center of the industrial camera as the origin W -X W Y W Z W The horizontal target direction and the vertical direction are Z W Axis and X W And a shaft. The imaging direction of the industrial camera can be taken around X W Angle of rotation of the shaft a 1 Winding Y W Angle of rotation of the shaft a 2 And around Z W Angle of rotation of the shaft a 3 And (4) showing.
In different application scenarios, the shape of the imaging target is not necessarily regular and different. Therefore, the embodiment of the present invention uses the discrete point set on the contour of the target region to represent the target region, as shown in formula (1)
Ω＝{t i (x i y i z i ),i＝1,2,3…n} (1)
Where Ω is a set of discrete points on the contour of the target region, t i (x i y i z i ) Is the coordinate of the ith point on the contour of the target area, and n is the number of points on the contour of the whole target area.
(2) Establishing an imaging region model of an industrial camera
Since the image sensor in the industrial camera is rectangular, the imaging area of the image sensor is a quadrangular pyramid which radiates outwards. Camera coordinate system O C -X C Y C Z C The imaging area of the industrial camera is shown in FIG. 2, and the invention proposes a mathematical description method of the imaging area, as shown in formula (2)
Where k is the aspect ratio of the industrial camera image sensor and ω is the angle of view of the industrial camera.
Optionally, the imaging direction of the industrial camera and the imaging area mathematical description method in the camera coordinate system are combined through space coordinate transformation to quantitatively describe the imaging area of the industrial camera in the scene coordinate system. The transformation relation between the camera coordinate system and the scene coordinate system is shown in formula (3)
In the formula, R X 、R Y And R Z Are respectively wound around X W Axis, Y W Axis and Z W The rotation matrix of the shaft is expressed as follows:
the joint type (2), the formula (3) and the formula (4) can obtain a mathematical model which can quantitatively describe the imaging area of the industrial camera in the imaging scene, as shown in the formula (5):
the imaging area model of the industrial camera reveals the quantitative relationship between the field angle, imaging direction and imaging area of the industrial camera. Knowing the field angle and the imaging direction of the industrial camera, the imaging area of the industrial camera in the scene coordinate system can be calculated by the formula (5).
(3) Precise configuration algorithm for designing field angle of industrial camera
The field angle and imaging direction of an industrial camera determine the size and position of the imaging area, respectively. Therefore, on the premise of ensuring that the target area can be imaged, the field angle can be accurately configured by optimizing and adjusting the imaging direction, and the optimal matching of the imaging area of the industrial camera and the target area is further realized. The embodiment of the invention adopts the coverage rate alpha to represent the imaged completeness of the target region, and the expression is as follows:
in the formula, omega A The method is an imaging area of an industrial camera under a scene coordinate system. When α is 1, it means that the entire target region is imaged.
Therefore, the objective function of the field angle precise configuration problem is:
in order to accurately configure the field angle of an industrial camera and realize the optimal matching of an imaging area and a target area, the embodiment of the invention designs a field angle configuration algorithm based on binary-particle swarm combination, and fig. 3 is a flowchart of the algorithm, which specifically comprises the following steps:
step1: setting an aspect ratio k, a target area omega and a view angle upper limit value omega of an industrial camera image sensor max Lower limit value of angle of view ω min And an initial value of the iteration number N. The upper viewing angle limit represents the critical value from full coverage to incomplete coverage.
Step2: updating the current angle of view omega by using a bisection method, wherein an updating rule is shown as a formula (8):
step3: imaging direction a of an industrial camera 1 、a 2 And a 3 As an optimization adjustment variable, the value range is (-pi/2, pi/2), and a particle swarm optimization algorithm is utilizedThe maximum coverage at the current field angle is calculated.
Step4: and updating the upper viewing angle limit value and the lower viewing angle limit value according to the maximum coverage rate calculated in the Step3, if the coverage rate is 1, updating the upper viewing angle limit value to the current viewing angle, keeping the lower viewing angle limit value unchanged, recording the imaging direction when the coverage rate is 1, and if the coverage rate is less than 1, updating the lower viewing angle limit value to the current viewing angle, keeping the upper viewing angle limit value unchanged.
Step5: and repeating the steps Step2, step3 and Step4 until the iteration number N is reached, and outputting the upper limit value of the field angle and the corresponding imaging direction. The number of iterations N determines the accuracy delta of the field angle configuration ω As shown in formula (9):
the embodiment of the invention provides a method for accurately configuring the field angle of an industrial camera, which is adaptive to a target area and aims to solve the problems that the field angle of the industrial camera is difficult to accurately configure by the existing method, an imaging area is not matched with a known target area, and pixels of an image sensor are wasted. The method mainly comprises the following steps:
(1) An imaging scene description system based on a scene coordinate system is provided, and the mounting position, the imaging direction and the target area of the industrial camera are quantitatively described by using point coordinates, a rotation angle and a point coordinate set;
(2) An industrial camera imaging area model based on space coordinate transformation is established, and quantitative relations among the field angle, the imaging direction and the imaging area of the industrial camera are disclosed;
(3) An industrial camera field angle configuration algorithm based on binary-particle swarm combination is designed, and an imaging area of an industrial camera is matched with a target area.
The method for accurately configuring the field angle of the industrial camera adaptive to the target area, provided by the embodiment of the invention, comprises the steps of carrying out quantitative description on an imaging scene of the industrial camera, establishing an imaging area model of the industrial camera, based on the imaging scene and the imaging area model which are quantitatively described, providing an objective function for obtaining a complete target image with a minimum field angle, and designing a heuristic solving algorithm based on binary-particle swarm combination to accurately configure the field angle of the industrial camera, so that the technical problem that the field angle of the existing industrial camera is difficult to be accurately configured according to the target area is solved, according to the quantitative relation between the imaging area of the industrial camera, the field angle and the imaging direction, the imaging direction of the industrial camera is continuously optimized and adjusted through the algorithm, the field angle is reduced, the imaging area is made to be adaptive to the target area, so that a complete high-quality image of the target is obtained, and reliable guidance is provided for related industry personnel to configure the field angle of the industrial camera when applying a machine vision technology.
Specifically, the imaging scene is described quantitatively, and influencing factors related to the configuration of the field angle are represented by parameters; then, an imaging area model of the industrial camera is established, and a quantitative function relation between the imaging area of the industrial camera and the angle and the imaging direction of the view is described; on this basis, it is proposed to acquire an objective function of a complete target image at a minimum field angle in order to fully utilize the pixels of the image sensor. However, the objective function cannot be directly solved, and only a heuristic algorithm can be adopted for traversal solution. According to the characteristics of a target function, a heuristic solving algorithm based on binary-particle swarm combination is designed; the dichotomy is efficient and convenient, and is used for quickly solving the minimum field angle of the objective function; the particle swarm optimization has the advantages of simple structure and reliable result, and is used for ensuring that the solving result meets the constraint of acquiring a complete target image. The imaging direction of the industrial camera is optimally adjusted by the algorithm, so that the imaging area is matched with the target area, the field angle of the industrial camera is accurately configured, and the quality of the acquired image is improved.
EXAMPLE III
The target area of the present embodiment is shown in fig. 4, and is a common quadrilateral shape, and the discrete points on the outline of the shape are set as
Ω＝{(4 2 10),(11 5 10),(6 9 10),(12 10 10)} (10)
The aspect ratio of the industrial camera image sensor is set to 4; the upper limit value and the lower limit value of the field angle are respectively set to be 180 degrees and 0 degree, the iteration number of the configuration algorithm is set to be 8, namely the field angle configuration precision reaches 0.7 degree, and the requirements of most application scenes are met. The setting parameters of the particle swarm optimization algorithm are as follows: the number of particles is set to 500, the number of iterations is set to 10, the inertia factor is set to 0.8, and the learning factor is set to 2.
And substituting the parameters into an industrial camera view angle precise configuration algorithm, calculating the coverage rate of different imaging directions under the current view angle according to the formula (5), and continuously adjusting the imaging directions according to a particle swarm optimization algorithm to obtain the maximum coverage rate. When the maximum coverage rate is 1, the current field angle can completely cover the target, and the field angle can be further reduced; when the maximum coverage rate is less than 1, the current field angle is too small, complete target information cannot be acquired, and the field angle needs to be increased. Increasing and decreasing the angle of view are carried out according to the formula (8) until the number of iterations is met, and the angle of view upper limit value omega obtained by the algorithm is output max And its corresponding imaging direction a 1 、a 2 And a 3 。
The configuration result of the present embodiment is as shown in fig. 5, and the angle of view of the configuration is 38.7 °, and the corresponding imaging directions are a1=25.8 °, a2= -32.7 °, and a3=85.9 °. After the embodiment of the invention is utilized to accurately configure the field angle, the imaging area of the industrial camera can completely cover the target area, and the invalid area outside the target is rarely imaged, so that the pixels of the image sensor are fully utilized, and the imaging quality of the target and the application effect of the machine vision technology are favorably improved.
Referring to fig. 6, an industrial camera view angle precise configuration system adapted to a target area according to an embodiment of the present invention includes:
the device comprises a memory 10, a processor 20 and a computer program stored on the memory 10 and executable on the processor 20, wherein the processor 20 implements the steps of the industrial camera view angle precise configuration method adapted to the target area proposed by the present embodiment when executing the computer program.
The specific working process and working principle of the industrial camera view angle accurate configuration system adapted to the target area in this embodiment may refer to the working process and working principle of the industrial camera view angle accurate configuration method adapted to the target area in this embodiment.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes will occur to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (6)
1. An industrial camera view angle precise configuration method adapting to a target area is characterized by comprising the following steps:
quantitatively describing an imaging scene of the industrial camera, wherein the imaging scene at least comprises an installation position, an imaging direction and a target area of the industrial camera, and the quantitatively describing the imaging scene of the industrial camera comprises the following steps:
establishing a three-dimensional world coordinate system by taking the optical center of the industrial camera as an origin to obtain a scene coordinate system;
establishing a camera coordinate system by taking the optical center of the industrial camera as an original point, taking the optical axis as a Z axis and taking the directions respectively parallel to the length and the width of the industrial camera image sensor as a Y axis and an X axis;
carrying out quantitative description on the imaging direction according to the rotation angles of three axes in the scene coordinate system when the scene coordinate system is transformed to the camera coordinate system;
carrying out quantitative description on the target area by adopting a discrete point set on the outline of the target area;
establishing an imaging area model of the industrial camera, wherein the imaging area model is used for quantitatively describing an imaging area of the industrial camera under a scene coordinate system, and the establishing of the imaging area model of the industrial camera comprises the following steps:
acquiring a camera imaging area of an industrial camera under a camera coordinate system, wherein a calculation formula of the camera imaging area is as follows:
wherein k is the length-width ratio of the industrial camera image sensor, omega is the angle of field, (X) C 、Y C 、Z C ) Coordinates representing points within the camera imaging area;
according to the imaging direction of the industrial camera, carrying out coordinate transformation on an imaging area of the camera to obtain an imaging area of the industrial camera under a scene coordinate system, so as to obtain an imaging area model of the industrial camera;
and accurately configuring the field angle of the industrial camera based on the imaging scene described quantitatively and the imaging area model.
2. The method for accurately configuring the field angle of the industrial camera in accordance with the target area of claim 1, wherein the calculation formula of the imaging area model of the industrial camera is as follows:
wherein k is the length-width ratio of the industrial camera image sensor, omega is the angle of field, (X) W 、Y W 、Z W ) Coordinates representing points within the imaging area of the industrial camera in the scene coordinate system, a 1 、a 2 And a 3 The rotation angles of three axes in the scene coordinate system when the scene coordinate system is transformed to the camera coordinate system are respectively.
3. The method for accurately configuring the field angle of the industrial camera adapted to the target area according to claim 1 or 2, wherein the accurately configuring the field angle of the industrial camera based on the imaging scene described by quantification and the imaging area model comprises:
determining an objective function of a precise field angle configuration problem, wherein a calculation formula of the objective function is as follows:
wherein, ω is an angle of view, α is a coverage rate, the coverage rate is used to characterize the completeness of the imaged target region, and the calculation formula of the coverage rate is:
wherein Ω is a set of discrete points on the contour of the target region, Ω A For the imaging area of an industrial camera in the scene coordinate system, t i (x i y i z i ) The coordinates of the ith point on the outline of the target area are shown, and n is the number of points on the outline of the whole target area;
and according to the imaging region model, carrying out optimization solution on the objective function, thereby accurately configuring the field angle of the industrial camera.
4. The method for accurately configuring the field angle of an industrial camera adapted to the target area according to claim 3, wherein the performing an optimization solution on the objective function according to the imaging area model comprises:
step1: setting initialization parameters comprising an aspect ratio k, a target area omega and a visual angle upper limit value omega of an industrial camera image sensor max Lower limit value of angle of view ω min And an initial value of the iteration number N, wherein the upper limit value of the field angle represents a critical value from the target area can be completely covered to the target area can not be completely covered;
step2: updating the current field angle omega by using a bisection method, wherein the updating rule specifically comprises the following steps:
step3: industrial cameraImaging direction a of 1 、a 2 And a 3 As an optimization adjustment variable, the value range is (-pi/2, pi/2), and the maximum coverage rate under the current field angle is calculated by utilizing a particle swarm optimization algorithm;
step4: updating the upper field angle limit value and the lower field angle limit value according to the maximum coverage rate calculated in the Step3, if the coverage rate is 1, updating the upper field angle limit value to the current field angle, keeping the lower field angle limit value unchanged, recording the imaging direction when the coverage rate is 1, and if the coverage rate is less than 1, updating the lower field angle limit value to the current field angle, keeping the upper field angle limit value unchanged;
step5: and repeating the steps Step2, step3 and Step4 until the iteration number N is reached, and outputting the upper limit value of the field angle and the corresponding imaging direction.
5. The method for accurately configuring the field angle of the industrial camera adapted to the target area according to claim 4, wherein setting the initialization parameters further comprises setting the configuration accuracy of the field angle, and the setting formula of the configuration accuracy is as follows:
wherein, delta ω For configuration accuracy, N is the number of iterations, ω max Is the upper limit value of the angle of view, omega min Is the lower limit of the field angle.
6. An industrial camera field of view angle precision configuration system that adapts to a target area, the system comprising:
memory (10), processor (20) and computer program stored on the memory (10) and executable on the processor (20), characterized in that the steps of the method according to any of the preceding claims 1 to 5 are implemented when the computer program is executed by the processor (20).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210404940.1A CN114979464B (en) | 2022-04-18 | 2022-04-18 | Industrial camera view angle accurate configuration method and system adaptive to target area |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210404940.1A CN114979464B (en) | 2022-04-18 | 2022-04-18 | Industrial camera view angle accurate configuration method and system adaptive to target area |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114979464A CN114979464A (en) | 2022-08-30 |
| CN114979464B true CN114979464B (en) | 2023-04-07 |
Family
ID=82978217
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210404940.1A Active CN114979464B (en) | 2022-04-18 | 2022-04-18 | Industrial camera view angle accurate configuration method and system adaptive to target area |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114979464B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115431174B (en) * | 2022-09-05 | 2023-11-21 | 昆山市恒达精密机械工业有限公司 | Method and system for controlling grinding of middle plate |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112351248A (en) * | 2020-10-20 | 2021-02-09 | 杭州海康威视数字技术股份有限公司 | Processing method for associating image data and sound data |
| CN113733078A (en) * | 2020-05-27 | 2021-12-03 | 中国人民解放军63920部队 | Method for interpreting fine control quantity of mechanical arm and computer-readable storage medium |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101860732B (en) * | 2010-06-04 | 2014-08-27 | 天津市亚安科技股份有限公司 | Method of controlling holder camera to automatically track target |
| CN104079882A (en) * | 2014-07-07 | 2014-10-01 | 山东神戎电子股份有限公司 | Laser night-vision device 3D positioning method based on list searching |
| JP6844307B2 (en) * | 2017-02-24 | 2021-03-17 | 株式会社Ihi | Angle of view adjustment method |
| CN108449545B (en) * | 2018-03-29 | 2020-10-30 | 北京环境特性研究所 | Monitoring system and application method thereof |
| WO2021184326A1 (en) * | 2020-03-20 | 2021-09-23 | 深圳市大疆创新科技有限公司 | Control method and apparatus for electronic apparatus, and device and system |
| JP2022038176A (en) * | 2020-08-26 | 2022-03-10 | キヤノン株式会社 | Control device, control method, and program |
| CN112561915A (en) * | 2020-11-30 | 2021-03-26 | 成都市喜爱科技有限公司 | Image processing method and device, image acquisition device and storage medium |
-
2022
- 2022-04-18 CN CN202210404940.1A patent/CN114979464B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113733078A (en) * | 2020-05-27 | 2021-12-03 | 中国人民解放军63920部队 | Method for interpreting fine control quantity of mechanical arm and computer-readable storage medium |
| CN112351248A (en) * | 2020-10-20 | 2021-02-09 | 杭州海康威视数字技术股份有限公司 | Processing method for associating image data and sound data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114979464A (en) | 2022-08-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109035204B (en) | Real-time detection method for weld joint target | |
| JP2022528659A (en) | Projector keystone correction methods, devices, systems and readable storage media | |
| CN111897349A (en) | Underwater robot autonomous obstacle avoidance method based on binocular vision | |
| CN109035170B (en) | Self-adaptive wide-angle image correction method and device based on single grid image segmentation mapping | |
| CN114979464B (en) | Industrial camera view angle accurate configuration method and system adaptive to target area | |
| KR101111503B1 (en) | Apparatus for controlling Pan/Tilt/Zoom camera in omnidirectional and method for the same | |
| JP2022085910A (en) | Camera calibration method, apparatus, electronic device, storage medium, program, and roadside apparatus | |
| WO2019232793A1 (en) | Two-camera calibration method, electronic device and computer-readable storage medium | |
| CN109447901A (en) | A kind of method for panoramic imaging and device | |
| CN115563732A (en) | Spraying track simulation optimization method and device based on virtual reality | |
| CN116193108A (en) | Online self-calibration method, device, equipment and medium for camera | |
| JP6410411B2 (en) | Pattern matching apparatus and pattern matching method | |
| CN112017246A (en) | Image acquisition method and device based on inverse perspective transformation | |
| CN114627166A (en) | Robot holder servo control method based on point cloud registration ICP algorithm | |
| CN114063046A (en) | Parameter calibration method and device, computer equipment and storage medium | |
| CN111696141A (en) | Three-dimensional panoramic scanning acquisition method and device and storage device | |
| CN107423766B (en) | Method for detecting tail end motion pose of series-parallel automobile electrophoretic coating conveying mechanism | |
| CN113592934B (en) | Target depth and height measuring method and device based on monocular camera | |
| CN112330726B (en) | Image processing method and device | |
| CN111353945A (en) | Fisheye image correction method, fisheye image correction device and storage medium | |
| US20230089195A1 (en) | Control device, control system, control method, and recording medium with control program recorded thereon | |
| CN116170569A (en) | Hyperspectral image forward shooting correction method and device and storage medium | |
| CN116721094B (en) | Visual pattern recognition method and system under complex background and laser cutting machine | |
| JP7415028B2 (en) | Imaging condition adjustment device and imaging condition adjustment method | |
| CN112348875B (en) | Zxfoom sign rod sign mark rod parameter representation determination method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |