WO2022143283A1

WO2022143283A1 - Camera calibration method and apparatus, and computer device and storage medium

Info

Publication number: WO2022143283A1
Application number: PCT/CN2021/139944
Authority: WO
Inventors: 杨勇; 吴泽晓; 曾浩宇
Original assignee: 深圳市杉川机器人有限公司
Priority date: 2020-12-30
Filing date: 2021-12-21
Publication date: 2022-07-07
Also published as: CN112581546A

Abstract

A camera calibration method and apparatus, and a computer device and a storage medium, which relate to the technical field of camera calibration. The method comprises: acquiring an initial image collected by a camera to be calibrated, wherein the initial image is obtained by means of said camera photographing a plurality of non-overlapping calibration plates, and a separation identifier is arranged between each two of the plurality of calibration plates; performing separation processing on the initial image according to the separation identifiers, so as to obtain a target image unit respectively corresponding to each calibration plate, wherein each target image unit includes all calibration information of the corresponding calibration plate; respectively detecting the calibration information in each target image unit, and screening, from the calibration information of the target image units and on the basis of detection results, target calibration information that meets a calibration condition; and calibrating said camera on the basis of the target calibration information.

Description

Camera calibration method, device, computer equipment and storage medium

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims the priority of the Chinese Patent Application No. 202011625915.3 and entitled "Camera Calibration Method, Apparatus, Computer Equipment and Storage Medium" filed on December 30, 2020, the entire contents of which are incorporated in this application by reference .

technical field

The present application relates to the technical field of camera calibration, and in particular, to a camera calibration method, device, computer equipment and storage medium.

Background technique

Whether in image measurement or machine vision applications, the calibration of camera parameters is a very critical link. The accuracy of the calibration results and the stability of the algorithm directly affect the accuracy of the results produced by the camera work. Therefore, doing a good job in camera calibration is the premise of the follow-up work, and improving the calibration accuracy is the focus of scientific research. Camera calibration is to use the images captured by the camera to restore objects in space. It may be assumed that there is a simple linear relationship between the image captured by the camera and the object in the three-dimensional space: [image]=M[object], where the matrix M can be regarded as the geometric model of camera imaging. The parameters in M are the camera parameters. Usually, these parameters are obtained through experiments and calculations. This process of solving parameters is called camera calibration.

The camera calibration method in the traditional technology needs to use the camera to be calibrated to take pictures of the calibration board at various angles. Each time you shoot, you need to manually adjust the placement and angle of the calibration board to ensure that the calibration board image captured by the camera can cover all direction.

However, because the current camera calibration method needs to frequently move the position of the calibration plate and constantly adjust the angle of the calibration plate when taking pictures, in order to ensure that the camera can capture the calibration plates in different directions, and the angle of the calibration plate needs to be adjusted continuously. Manual operation is cumbersome, and there is a problem of low calibration efficiency.

public content

The present application proposes a camera calibration method, device, computer equipment and storage medium to improve the camera calibration efficiency.

In a first aspect, the present application proposes a camera calibration method, the method includes: acquiring an initial image collected by a camera to be calibrated; the initial image shooting a plurality of non-overlapping calibration plates by the to-be-calibrated camera obtained, and a separation mark is set between the plurality of calibration plates; the initial image is separated according to the separation mark, and the target image unit corresponding to each of the calibration plates is obtained; the target image The unit contains all the calibration information in the corresponding calibration board; the calibration information in each of the target image units is detected respectively, and based on the detection results, the calibration information of each of the target image units is selected from the calibration information that meets the calibration conditions. target calibration information; the camera to be calibrated is calibrated based on the target calibration information in each of the target image units.

According to the camera calibration method of the embodiment of the present application, by restricting the positions, angles, etc. of the multiple calibration plates, the calibration plates in the initial image are presented at different angles and positions, and at the same time, in order to Multiple calibration plates are used to distinguish, and a separation mark is also set. By separating the logos, multiple calibration boards in the initial image can be distinguished, and correspondingly cropped into multiple individual target image units, thus avoiding the need to use the camera to be calibrated multiple times from different angles and different positions. The process of shooting. At the same time, for each individual target image unit, the calibration information detection is also carried out to ensure that each target image unit corresponds to the target calibration information contained in a complete calibration plate, and then based on each The target calibration information in the target image unit calibrates the camera to be calibrated. In this way, since the image acquisition of the multi-angle and different distance calibration plates can be completed through an initial image, errors caused by multiple manual changes of the calibration plates are avoided, and the efficiency and consistency of camera calibration are improved. In addition, the above scheme performs feature point detection on the picture of the calibration board before calibration, which reduces the wrong points introduced due to insufficient lighting or low resolution of the lens, and improves the accuracy of feature point detection on the calibration board.

In a second aspect, the present application proposes a camera calibration device, the device includes: acquiring an initial image collected by a camera to be calibrated; the initial image is captured by the camera to be calibrated on a plurality of non-overlapping calibration plates obtained, and a separation mark is set between the plurality of calibration plates; the initial image is separated according to the separation mark, and the target image unit corresponding to each of the calibration plates is obtained; the target image The unit contains all the calibration information in the corresponding calibration board; the calibration information in each of the target image units is detected respectively, and based on the detection results, the calibration information of each of the target image units is selected from the calibration information that meets the calibration conditions. target calibration information; the camera to be calibrated is calibrated based on the target calibration information in each of the target image units.

According to the camera calibration device of the embodiment of the present application, by restricting the positions, angles, etc. of the plurality of calibration plates, the calibration plates in the initial image are presented at different angles and positions. Multiple calibration plates are used to distinguish, and a separation mark is also set. By separating the logos, multiple calibration boards in the initial image can be distinguished, and correspondingly cropped into multiple individual target image units, thus avoiding the need to use the camera to be calibrated multiple times from different angles and different positions. The process of shooting. At the same time, for each individual target image unit, the calibration information detection is also carried out to ensure that each target image unit corresponds to the target calibration information contained in a complete calibration plate, and then based on each The target calibration information in the target image unit calibrates the camera to be calibrated. In this way, since the image acquisition of the multi-angle and different distance calibration plates can be completed through an initial image, errors caused by multiple manual changes of the calibration plates are avoided, and the efficiency and consistency of camera calibration are improved. Moreover, the above scheme first performs feature point detection on the picture of the calibration board before calibration, which reduces the error points introduced due to insufficient lighting or low resolution of the lens, and improves the accuracy of feature point detection on the calibration board.

In a third aspect, the present application proposes a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the processor implements the following steps: acquiring the initial data collected by the camera to be calibrated image; the initial image is obtained by shooting a plurality of non-overlapping calibration plates by the camera to be calibrated, and a separation mark is set between the plurality of calibration plates; the initial image is recorded according to the separation mark Perform separation processing to obtain target image units corresponding to each of the calibration plates; the target image units contain all the calibration information in the corresponding calibration plate; respectively, detect the calibration information in each of the target image units , and screen out target calibration information that satisfies the calibration conditions from the calibration information of each target image unit based on the detection result; calibrate the camera to be calibrated based on the target calibration information in each target image unit.

According to the computer device of the embodiment of the present application, by restricting the positions, angles, etc. of the plurality of calibration plates, the calibration plates in the initial image are presented at different angles and positions. Zhang calibration plate to distinguish, and also set the separation mark. By separating the logos, multiple calibration boards in the initial image can be distinguished, and correspondingly cropped into multiple individual target image units, thus avoiding the need to use the camera to be calibrated multiple times from different angles and different positions. The process of shooting. At the same time, for each individual target image unit, the calibration information detection is also carried out to ensure that each target image unit corresponds to the target calibration information contained in a complete calibration plate, and then based on each The target calibration information in the target image unit calibrates the camera to be calibrated. In this way, since the image acquisition of the multi-angle and different distance calibration plates can be completed through an initial image, errors caused by multiple manual changes of the calibration plates are avoided, and the efficiency and consistency of camera calibration are improved. In addition, the above scheme performs feature point detection on the picture of the calibration board before calibration, which reduces the wrong points introduced due to insufficient lighting or low resolution of the lens, and improves the accuracy of feature point detection on the calibration board.

In a fourth aspect, the present application proposes a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: acquiring an initial image collected by a camera to be calibrated; The image is obtained by photographing a plurality of non-overlapping calibration plates by the camera to be calibrated, and a separation mark is set between the plurality of calibration plates; the initial image is separated according to the separation mark, and the obtained A target image unit corresponding to each of the calibration plates; the target image unit contains all the calibration information in the corresponding calibration plate; the calibration information in each of the target image units is detected respectively, and based on the detection results The target calibration information that satisfies the calibration conditions is selected from the calibration information of each of the target image units; the camera to be calibrated is calibrated based on the target calibration information in each of the target image units.

According to the computer-readable storage medium of the embodiment of the present application, by restricting the positions, angles, etc. of the plurality of calibration plates, the calibration plates in the initial image are presented at different angles and positions. There are multiple calibration boards in the system to distinguish, and a separation mark is also set. By separating the logos, multiple calibration boards in the initial image can be distinguished, and correspondingly cropped into multiple individual target image units, thus avoiding the need to use the camera to be calibrated multiple times from different angles and different positions. The process of shooting. At the same time, for each individual target image unit, the calibration information detection is also carried out to ensure that each target image unit corresponds to the target calibration information contained in a complete calibration plate, and then based on each The target calibration information in the target image unit calibrates the camera to be calibrated. In this way, since the image acquisition of the multi-angle and different distance calibration plates can be completed through an initial image, errors caused by multiple manual changes of the calibration plates are avoided, and the efficiency and consistency of camera calibration are improved. In addition, the above scheme performs feature point detection on the picture of the calibration board before calibration, which reduces the wrong points introduced due to insufficient lighting or low resolution of the lens, and improves the accuracy of feature point detection on the calibration board.

Additional aspects and advantages of the present application will be set forth, in part, from the following description, and in part will become apparent from the following description, or may be learned by practice of the present application.

Description of drawings

The above and/or additional aspects and advantages of the present application will become apparent and readily understood from the following description of embodiments in conjunction with the accompanying drawings, wherein:

1 is an application environment diagram of a camera calibration method in one embodiment;

2 is a schematic flowchart of a camera calibration method in one embodiment;

Fig. 3 is a schematic diagram of setting the position and angle of the calibration plate photographed in one embodiment;

4 is a structural block diagram of a camera calibration device in one embodiment;

FIG. 5 is a diagram of the internal structure of a computer device in one embodiment.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application will be described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application.

The camera calibration method provided in this application can be applied to the application environment shown in FIG. 1 . Wherein, the terminal 102 and the camera 104 can communicate. After the camera 104 shoots the calibration plate array 106 , the initial image obtained by shooting is transmitted to the terminal 102 for processing. After the terminal 102 completes the processing and obtains the target calibration information, it is then used to calibrate the camera 104 . The terminal 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and may also be various hardware devices that need to be equipped with cameras for corresponding operations.

In order to better understand the present application, before describing the camera calibration method of the present application, it is introduced how the camera calibration in the traditional solution is completed. Generally speaking, in the traditional technical solution, the camera first needs to use the camera to take pictures of the calibration board at various angles, and the position and angle of the calibration board need to be manually adjusted for each shot to ensure that the calibration board pictures captured by the camera can cover all directions. . However, in this process, the camera calibration method of the traditional solution needs to frequently move the position of the calibration plate when taking pictures, so as to ensure that the camera can capture calibration plates in different orientations, and the angle of the calibration plate needs to be adjusted continuously. The feature point detection on the calibration board has not been processed. In the case of poor light or low resolution of the camera, it is easy to cause the phenomenon that the feature points of the calibration board cannot be detected. The position of artificially placing the calibration board and the direction of adjusting the calibration board cannot be guaranteed to be consistent, so there is no way to ensure the consistency of parameters when there are multiple cameras that need to be calibrated.

The present application is a solution obtained by improving some problems existing in the above scenarios. Before describing the camera calibration method in this application, some terms involved in the embodiments of this application are explained as follows:

Initial image: The original image obtained by the camera to be calibrated shooting the calibration plate.

Segmentation mark: a mark symbol used to distinguish different calibration boards and determine the division boundaries of different calibration boards.

Target image unit: a partial image separated from the initial image, including one and only one complete calibration plate image.

Calibration information: information contained in the target image unit that can be used to calibrate the camera to be calibrated, including at least one of position, color, and size.

Target calibration information: target calibration information that satisfies the calibration conditions obtained after the calibration information in the target image unit is screened.

In one embodiment, as shown in FIG. 2, a camera calibration method is provided, and the method is applied to the terminal 102 in FIG. 1 as an example for description, including the following steps:

Step S202, acquiring an initial image collected by the camera to be calibrated; the initial image is obtained by photographing a plurality of non-overlapping calibration plates by the camera to be calibrated, and a separation mark is set between the plurality of calibration plates.

That is to say, before the terminal acquires the initial image through the camera to be calibrated, the calibration board needs to be processed first. In order to reduce the problems caused by placing the calibration plate manually for many times, improve the calibration efficiency, and realize the rapid calibration of the camera to be calibrated, in this embodiment, multiple pieces of different angle information of the calibration plate need to be captured at one time. In order to ensure that the information in each calibration board can meet the requirements of camera calibration, multiple calibration boards are prevented from overlapping each other, so as to ensure that all the information on each calibration board is exposed within the field of view of the camera.

In one embodiment, the plurality of non-overlapping calibration plates include an initial calibration plate and a control calibration plate; before the initial image is captured by the camera to be calibrated, the plurality of non-overlapping calibration plates are set within the field of view of the camera to be calibrated , and the initial calibration plate among the multiple non-overlapping calibration plates is located at the center position, and the control calibration plates except the initial calibration plate among the multiple non-overlapping calibration plates are evenly distributed around the initial calibration plate.

In this embodiment, in order to better process multiple calibration plates, the above-mentioned calibration plates include an initial calibration plate and a comparison calibration plate, wherein the initial calibration plate is generally located at the center of the field of view for judging the camera to be calibrated, and the comparison calibration plate surrounds the The initial calibration plate is set to ensure the reasonable and uniform position of the calibration plate within the field of view, and further improve the image quality of the initial image obtained by the camera to be calibrated.

In one embodiment, the separation marks provided between the two calibration plates are located at the apex of the included angle between the adjacent comparison calibration plates, and/or, the planes where each comparison calibration plate is located are respectively different from those of the initial calibration plate. There is an included angle of 10 degrees to 30 degrees between the planes.

Since the initial image captured by the camera to be calibrated contains the information of multiple calibration plates, in order to ensure that the calibration plate information collected in the initial image is easy to be segmented and meets the specific calibration requirements, in the above embodiment, the separation marks are set on two The apex of the angle between two adjacent calibration plates, for example, in the boundary area of any adjacent two, three or more calibration plates at the edge of the calibration plate, is mainly used to separate different calibration plates. In addition, in order to further ensure that the image information of the calibration plate collected in each direction can meet the specific calibration requirements, the angle between the plane where the calibration plate is located and the plane where the initial calibration plate is located is 10 degrees to 30 degrees. .

In the above embodiment, except for the initial calibration plate in the middle, the angle of the calibration plate is generally greater than 10 degrees and less than 30 degrees, and the angle between the plane where the reference calibration plate is located and the plane where the initial calibration plate is located is generally greater than 10 degrees. The calibration plate has an angle, which is less than 30 degrees to ensure that the size of the feature points of the calibration plate is not very different on the same picture. If the angle is too large and close to 80 degrees, the feature points above the calibration board will be very small and the ones below will be very large, which will seriously affect the accuracy of the target calibration information.

For example, as shown in Figure 3, nine calibration plates are placed in the upper, lower, left, right, upper left, upper right, lower left, lower right and the center of the camera's field of view, except that the initial calibration plate in the center remains Horizontally, the reference calibration plates of other orientations are inclined downward or upward by 25 degrees (in this embodiment, it is not required that the reference calibration plates are all located on the same side of the plane where the initial calibration plate is located), and a piece of size is pasted between every two calibration plates. 5 cm black rectangles are used as dividers. Then use the camera to be calibrated to take a picture to ensure that all the dots on the calibration board in the picture can be taken without omission, which is the initial image.

Step S204: Perform separation processing on the initial image according to the separation identifier to obtain target image units corresponding to each calibration plate respectively; the target image unit contains all the calibration information in the corresponding calibration plate.

That is to say, since the initial image contains multiple calibration plates, when calibrating the camera to be calibrated, the information in a single calibration plate needs to be used as input to complete the calibration. After obtaining the initial image, the terminal also needs to process the initial image and divide it into a plurality of target image units corresponding to the information in the calibration board. The separation mark is mainly used to process the initial image to obtain multiple target image units. Since the separation marks are located in the boundary areas of different calibration boards when they are set, the terminal can cut the initial image through the separation marks, and obtain a target image unit containing all the calibration information in the corresponding calibration board.

In one embodiment, performing separation processing on the initial image according to the separation mark to obtain target image units corresponding to each calibration plate, including: detecting the initial image, identifying the separation mark in the initial image; determining the initial image by the separation mark A plurality of target cropping lines are provided, wherein each target cropping line has at least one separation mark; the initial image is cropped according to the plurality of target cropping lines to obtain target image units corresponding to each calibration plate respectively.

In this embodiment, in the process of cropping the initial image by using the separation mark, the terminal first needs to detect the initial image and identify the separation mark contained therein. Then, the target cropping lines are divided, each target cropping line passes through at least one separation mark, and then the initial image is segmented by the target cropping lines to obtain target image units corresponding to each calibration board respectively. In this way, it can be ensured that the target clipping line will pass through the boundary area of the calibration board where the separation mark is located, which reduces the difficulty of identifying specific calibration board information from the initial image and improves the calibration efficiency.

In this embodiment, there is no specific limitation on the number of separation marks, nor is there any specific limitation on the number of target cutting lines, but each target cutting line must pass at least one separation mark, and each cutting line can is a ray whose origin is inside the original image and extends outward.

In one embodiment, determining a plurality of target crop lines of the initial image by the separation mark includes: delimiting a plurality of initial crop lines of the initial image by the separation mark; and the plurality of initial crop lines divide the initial image into a plurality of calibration plates Multiple initial image units with an equal number; multiple initial image units are detected to determine whether each initial image unit contains all the calibration information in the corresponding calibration board; when there is a defective image unit in the initial image unit, change Initial cropping line, re-divide the initial image, and detect multiple initial image units obtained by re-dividing; the defective image unit is an image unit that does not include all the calibration information of a complete calibration plate; when the initial unit is When there is no defective image unit, the initial image unit is saved as the target image unit for calibrating the camera to be calibrated.

In this embodiment, the terminal can determine a plurality of cropping lines by separating the identifiers, but the initial image only needs to be divided into initial image units corresponding to the number of calibration boards. Therefore, when the cropping line is determined by using the separation mark, the number of initial image units obtained by division can be determined correspondingly. Since the setting form of the calibration board and the position of the separation mark are not completely fixed, and a complete calibration board information is required during the calibration process, after obtaining the initial image cropping scheme, the terminal also needs to detect it, Make sure that the cropped initial image unit corresponds to the complete image information of each calibration plate. In the process of detection, if it is found that there is a defective image unit in the obtained initial image unit, that is, the calibration plate information in the initial image unit is incomplete, or it is found that the initial image unit contains images that do not belong to the current corresponding calibration plate. If the calibration information is displayed, it means that the current image cropping scheme is not the optimal scheme. At this time, the initial cropping line will be re-determined according to the separation mark, until it is detected that there is no defective image unit in the initial image unit. At this time, the initial image unit corresponding to the current cropping scheme can be saved as the target image unit for calibrating the camera to be calibrated.

In the above embodiment, by detecting the initial image unit obtained by image cropping, it can be ensured that each target image unit is an image unit including all the calibration information of a complete calibration plate in the cropping stage, thereby improving the Efficiency and accuracy of the entire calibration process.

In step S206, the calibration information in each target image unit is detected respectively, and based on the detection result, the target calibration information that satisfies the calibration condition is selected from the calibration information of each target image unit.

That is, in order to apply the target image unit to a specific camera calibration, the terminal also needs to detect the calibration information in the target image unit according to the calibration information, and filter out the target calibration information that satisfies the calibration conditions.

In one embodiment, the calibration information in each target image unit is respectively detected, and the target calibration information that satisfies the calibration condition is selected from the calibration information of each target image unit based on the detection result, including: The calibration information in the unit is detected to extract the initial feature points in each image unit; for each image unit, based on the position, color, and size of the initial feature points in the corresponding image unit, the initial feature points are screened out. Set the number of target feature points; take the position information of the selected target feature points as the target calibration information of the corresponding image unit.

In this embodiment, in this process, for each target image unit, the terminal first obtains initial feature points that may be valid feature points in each target image unit. Since the feature points in the calibration board have corresponding calibration information, including one or more of parameters such as position, color, and size, through these calibration information, the terminal can screen out several qualified feature points from the initial feature points. A number of feature points screened by the terminal also need to be counted. Only when the number is the same as the preset number can they be determined as target feature points.

In the above-mentioned embodiment, the purpose of detecting and screening the feature points by the terminal is to further improve the accuracy of the calibration information, thereby improving the accuracy of the calibration result and reducing the error.

For example, in FIG. 3 , the feature points included in each calibration plate are arranged in a regular array, and the number of the feature points is fixed. After the above screening, the obtained calibration information can be used to calibrate the camera to be calibrated.

Step S208, the camera to be calibrated is calibrated based on the target calibration information in each target image unit.

That is to say, the purpose of the target calibration information obtained by the terminal based on the above process is to apply it to the calibration process of the to-be-calibrated camera, so as to complete the calibration of the to-be-calibrated camera.

In one embodiment, calibrating the camera to be calibrated based on the target calibration information in each image unit includes: converting the target calibration information into targets corresponding to the world coordinate system, the camera coordinate system, the image coordinate system and the pixel coordinate system respectively Coordinate information; based on the target coordinate information corresponding to the world coordinate system, camera coordinate system, image coordinate system and pixel coordinate system, calculate the external parameter matrix and internal parameter matrix of the camera to be calibrated; Camera calibration.

The process of camera calibration is the process of solving the camera parameter matrix to be calibrated. For the same specific object, after the terminal obtains the target calibration information, it has corresponding target coordinate information in the world coordinate system, camera coordinate system, image coordinate system and pixel coordinate system respectively, and these target coordinate information are associated with each other correspondingly. The matrix relationship constitutes the external parameter matrix and the internal parameter matrix of the camera to be calibrated. For the camera that has been calibrated, the external parameter matrix and the internal parameter matrix can be used to capture any item, and the corresponding matrix position of the item in other coordinate systems can be obtained.

The above camera calibration method limits the positions and angles of multiple calibration boards, so that the calibration boards in the initial image are presented at different angles and positions. Distinguish, and also set the separation flag. By separating the logos, multiple calibration boards in the initial image can be distinguished, and correspondingly cropped into multiple individual target image units, thus avoiding the need to use the camera to be calibrated multiple times from different angles and different positions. The process of shooting. At the same time, for each individual target image unit, the calibration information detection is also carried out to ensure that each target image unit corresponds to the target calibration information contained in a complete calibration plate, and then based on each The target calibration information in the target image unit calibrates the camera to be calibrated. In this way, since the image acquisition of the multi-angle and different distance calibration plates can be completed through an initial image, errors caused by multiple manual changes of the calibration plates are avoided, and the efficiency and consistency of camera calibration are improved. In addition, the above scheme performs feature point detection on the picture of the calibration board before calibration, which reduces the wrong points introduced due to insufficient lighting or low resolution of the lens, and improves the accuracy of feature point detection on the calibration board.

It should be understood that although the various steps in the flowchart of FIG. 2 are shown in sequence according to the arrows, these steps are not necessarily executed in the sequence shown by the arrows. Unless explicitly stated herein, the execution of these steps is not strictly limited to the order, and these steps may be performed in other orders. Moreover, at least a part of the steps in FIG. 2 may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but may be executed at different times, and the execution sequence of these steps or stages is also It does not have to be performed sequentially, but may be performed alternately or alternately with other steps or at least a portion of the steps or stages within the other steps.

In one embodiment, as shown in FIG. 4, a camera calibration device is provided, including: an image module 402, a separation module 404, a detection module 406, and a calibration module 408, wherein:

The image module 402 is used to obtain an initial image collected by a camera to be calibrated; the initial image is obtained by photographing a plurality of non-overlapping calibration plates by the camera to be calibrated, and a separation mark is set between the plurality of calibration plates;

The separation module 404 is used to perform separation processing on the initial image according to the separation identification, and obtain the target image unit corresponding to each calibration plate respectively; the target image unit contains all the calibration information in the corresponding calibration plate;

The detection module 406 is used to detect the calibration information in each target image unit respectively, and screen out the target calibration information that satisfies the calibration conditions from the calibration information of each target image unit based on the detection result;

The calibration module 408 is configured to calibrate the camera to be calibrated based on the target calibration information in each target image unit.

The above camera calibration device, by restricting the positions and angles of multiple calibration plates, allows the calibration plates in the initial image to be presented at different angles and positions. Distinguish, and also set the separation flag. By separating the logos, multiple calibration boards in the initial image can be distinguished, and correspondingly cropped into multiple individual target image units, thus avoiding the need to use the camera to be calibrated multiple times from different angles and different positions. The process of shooting. At the same time, for each individual target image unit, the calibration information detection is also carried out to ensure that each target image unit corresponds to the target calibration information contained in a complete calibration plate, and then based on each The target calibration information in the target image unit calibrates the camera to be calibrated. In this way, since the image acquisition of the multi-angle and different distance calibration plates can be completed through an initial image, errors caused by multiple manual changes of the calibration plates are avoided, and the efficiency and consistency of camera calibration are improved. In addition, the above-mentioned scheme first performs feature point detection on the picture of the calibration board before calibration, which reduces the wrong points introduced due to insufficient lighting or low resolution of the lens, and improves the accuracy of feature point detection on the calibration board.

In the above embodiment, in order to better process multiple calibration plates, the above-mentioned calibration plate includes an initial calibration plate and a comparison calibration plate, wherein the initial calibration plate is generally located in the center of the field of view for judging the camera to be calibrated, and the comparison calibration plate Set around the initial calibration plate to ensure the reasonable and uniform position of the calibration plate within the field of view, and further improve the image quality of the initial image obtained by the camera to be calibrated.

In the above-mentioned embodiment, since the initial image captured by the camera to be calibrated contains information of multiple calibration plates, the initial image can be guaranteed by setting the different angles of the calibration plate and using the separation mark located in the boundary area of the calibration plate. The information of the calibration plate collected in the data is easy to be segmented and meets the specific calibration requirements.

In one embodiment, the separation module is further configured to: detect the initial image, and identify the separation mark in the initial image; determine a plurality of target crop lines of the initial image by using the separation mark, Wherein, each target cropping line has at least one separation mark; the initial image is cropped according to the plurality of target cropping lines to obtain target image units corresponding to each of the calibration boards respectively.

In this embodiment, in the process of cropping the initial image by using the separation marks, the initial image is first detected, the separation marks contained therein are identified, and then the target cropping lines are divided, and each target cropping line passes at least one separation mark, Then, the initial image is segmented by the target crop line, and the target image units corresponding to each calibration plate are obtained.

In the above embodiment, it can be ensured that the target crop line will pass through the boundary area of the calibration plate where the separation mark is located, which reduces the difficulty of identifying specific calibration plate information from the initial image and improves the calibration efficiency.

In one embodiment, the separation module is further configured to: demarcate a plurality of initial crop lines of the initial image by using the separation identifier; and the plurality of initial crop lines divide the initial image into different parts from the plurality of initial crop lines A plurality of initial image units with the same number of calibration plates; the plurality of initial image units are detected to determine whether each of the initial image units contains all the calibration information in the corresponding calibration plate; when the initial image units are in When there is a defective image unit, the initial crop line is changed, the initial image is re-divided, and the plurality of initial image units obtained by re-dividing are detected; the defective image unit does not include a complete image unit. The image unit of all the calibration information of the calibration board; when the defective image unit does not exist in the initial unit, the initial image unit is saved as the target image unit for calibrating the camera to be calibrated.

In one embodiment, the detection module is further configured to: detect the calibration information in each of the image units respectively, so as to extract the initial feature points in each of the image units; for each image unit, based on the corresponding image The position, color, and size of the initial feature points in the unit, and a preset number of target feature points are screened from the initial feature points; the position information of the screened target feature points is used as the target calibration information of the corresponding image unit.

In the above embodiment, the purpose of detecting and screening feature points is to further improve the accuracy of calibration information, thereby improving the accuracy of calibration results and reducing errors.

In the above embodiment, the calibration module is further configured to: convert the target calibration information into target coordinate information corresponding to the world coordinate system, the camera coordinate system, the image coordinate system and the pixel coordinate system respectively; system, camera coordinate system, image coordinate system and pixel coordinate system respectively corresponding target coordinate information, calculate the external parameter matrix and internal parameter matrix of the camera to be calibrated; according to the external parameter matrix and the internal parameter matrix, realize the Calibration of the camera to be calibrated.

For the specific limitations of the above camera calibration device, reference may be made to the limitations on the camera calibration method above, which will not be repeated here. All or part of the modules in the above camera calibration device can be implemented by software, hardware and combinations thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

In one embodiment, a computer device is provided, and the computer device may be a terminal, and its internal structure diagram may be as shown in FIG. 5 . The computer equipment includes a processor, memory, a communication interface, a display screen, and an input device connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium, an internal memory. The nonvolatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the execution of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for wired or wireless communication with an external terminal, and the wireless communication can be realized by WIFI, operator network, NFC (Near Field Communication) or other technologies. The computer program implements a camera calibration method when executed by the processor. The display screen of the computer equipment may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment may be a touch layer covered on the display screen, or a button, a trackball or a touchpad set on the shell of the computer equipment , or an external keyboard, trackpad, or mouse.

Those skilled in the art can understand that the structure shown in FIG. 5 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. Include more or fewer components than shown in the figures, or combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is also provided, including a memory and a processor, where a computer program is stored in the memory, and the processor implements the steps in the foregoing method embodiments when the processor executes the computer program.

In one embodiment, a computer-readable storage medium is also provided, and a computer program is stored thereon, and when the computer program is executed by a processor, the steps in the foregoing method embodiments are implemented.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage In the medium, when the computer program is executed, it may include the processes of the above-mentioned method embodiments. Wherein, any reference to memory, storage, database or other media used in the various embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, or optical memory, and the like. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, the RAM may be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

The technical features of the above embodiments can be combined arbitrarily. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features It is considered to be the range described in this specification.

The above-mentioned embodiments only represent several embodiments of the present application, and the descriptions thereof are relatively specific and detailed, but should not be construed as a limitation on the scope of the patent application. It should be pointed out that for those skilled in the art, without departing from the concept of the present application, several modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the scope of protection of the patent of the present application shall be subject to the appended claims.

Claims

A camera calibration method, the method comprising:

acquiring an initial image collected by a camera to be calibrated; the initial image is obtained by shooting a plurality of non-overlapping calibration plates by the camera to be calibrated, and a separation mark is set between the plurality of calibration plates;

Perform separation processing on the initial image according to the separation identification to obtain target image units corresponding to each of the calibration plates; the target image units contain all the calibration information in the corresponding calibration plate;

Detecting the calibration information in each of the target image units respectively, and screening out target calibration information that satisfies the calibration conditions from the calibration information of each of the target image units based on the detection results;

The camera to be calibrated is calibrated based on the target calibration information in each of the target image units.
The method according to claim 1, wherein the plurality of non-overlapping calibration plates include an initial calibration plate and a control calibration plate; before collecting an initial image by the camera to be calibrated, the plurality of non-overlapping calibration plates The calibration plate is set in the field of view of the camera to be calibrated, and the initial calibration plate in the plurality of non-overlapping calibration plates is located at the center position, and the plurality of non-overlapping calibration plates except for the initial calibration plate. The control calibration plate is evenly distributed around the initial calibration plate.
The method according to claim 2, wherein the separation marks set between the two calibration plates are located at the apex of the included angle between the adjacent comparison calibration plates, and/or,

There is an included angle of 10 degrees to 30 degrees between the plane where each control calibration plate is located and the plane where the initial calibration plate is located.
The method according to any one of claims 1 to 3, wherein the performing separation processing on the initial image according to the separation identification to obtain target image units corresponding to each of the calibration plates, comprising:

Detecting the initial image, and identifying the separation mark in the initial image;

A plurality of target crop lines of the initial image are determined by the separation marks, wherein each target crop line has at least one separation mark;

The initial image is cropped according to the multiple target cropping lines to obtain target image units corresponding to each of the calibration boards respectively.
The method according to claim 4, wherein the determining a plurality of target crop lines of the initial image by the separation identification comprises:

A plurality of initial cropping lines of the initial image are delineated by the separation marks; the plurality of initial cropping lines divide the initial image into a plurality of initial image units equal to the number of the plurality of calibration plates;

Detecting the plurality of initial image units, and judging whether each of the initial image units contains all the calibration information in the corresponding calibration plate;

When there is a defective image unit in the initial image unit, the initial crop line is changed, the initial image is re-divided, and the plurality of initial image units obtained by re-dividing are detected; the defective image The unit is an image unit that does not include all the calibration information of a complete calibration plate;

When the defective image unit does not exist in the initial unit, the initial image unit is saved as a target image unit for calibrating the camera to be calibrated.
The method according to any one of claims 1 to 5, wherein the calibration information in each of the target image units is detected separately, and based on the detection result, the calibration information of each of the target image units is obtained from the calibration information. Filter out target calibration information that meets calibration conditions, including:

Detecting the calibration information in each of the image units respectively, to extract the initial feature points in each of the image units;

For each image unit, based on the position, color, and size of the initial feature points in the corresponding image unit, filter out a preset number of target feature points from the initial feature points;

The position information of the selected target feature points is used as the target calibration information of the corresponding image unit.
The method according to any one of claims 1 to 6, wherein the calibrating the camera to be calibrated based on the target calibration information in each of the image units comprises:

Converting the target calibration information into target coordinate information corresponding to the world coordinate system, the camera coordinate system, the image coordinate system and the pixel coordinate system respectively;

Calculate the external parameter matrix and the internal parameter matrix of the camera to be calibrated based on the target coordinate information corresponding to the world coordinate system, the camera coordinate system, the image coordinate system and the pixel coordinate system respectively;

The calibration of the camera to be calibrated is realized according to the external parameter matrix and the internal parameter matrix.
A camera calibration device, the device comprising:

The image module is used to obtain the initial image collected by the camera to be calibrated; the initial image is obtained by shooting a plurality of non-overlapping calibration plates by the camera to be calibrated, and the plurality of calibration plates are set between two There is a separation mark;

a separation module, configured to perform separation processing on the initial image according to the separation identification to obtain target image units corresponding to each of the calibration plates; the target image units contain all the calibration information in the corresponding calibration plate;

a detection module, configured to detect the calibration information in each of the target image units respectively, and screen out target calibration information that satisfies the calibration conditions from the calibration information of each of the target image units based on the detection result;

A calibration module, configured to calibrate the camera to be calibrated based on the target calibration information in each of the target image units.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the steps of the method of any one of claims 1 to 7 when the processor executes the computer program.
A computer-readable storage medium having stored thereon a computer program that, when executed by a processor, implements the steps of the method of any one of claims 1 to 7.