CN115861443A - Multi-camera internal reference calibration method and device, electronic equipment and storage medium - Google Patents
Multi-camera internal reference calibration method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115861443A CN115861443A CN202211659012.6A CN202211659012A CN115861443A CN 115861443 A CN115861443 A CN 115861443A CN 202211659012 A CN202211659012 A CN 202211659012A CN 115861443 A CN115861443 A CN 115861443A
- Authority
- CN
- China
- Prior art keywords
- camera
- calibration
- internal reference
- preset
- calibration result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Studio Devices (AREA)
Abstract
The disclosure provides a multi-camera internal reference calibration method and device, electronic equipment and a storage medium, and relates to the field of artificial intelligence, in particular to the fields of automatic driving and camera calibration. The specific implementation scheme is as follows: acquiring images of a calibration board at different positions, which are acquired by a plurality of cameras simultaneously, and filtering the images with incomplete corner points to obtain a target image; the focal length and the model of each camera are the same, and the distance between any two cameras is smaller than a preset distance threshold; and determining internal parameters of each camera based on the target image acquired by each camera. By applying the embodiment of the disclosure, a plurality of cameras with the same type and the same focal length are fixed at close positions, and the simultaneous acquisition of images of the calibration plates required by the cameras can be realized by continuously changing the position and the posture of the calibration plates, so that the image acquisition efficiency of the cameras is improved, and further the internal reference calibration efficiency of the multi-camera is improved. In addition, the integrity of the chessboard pattern calibration corner points in the target image is improved by filtering the image, and the calibration success rate and accuracy are further improved.
Description
Technical Field
The present disclosure relates to the field of artificial intelligence technology, and more particularly, to the field of autopilot and camera calibration technology.
Background
The camera is an important sensor in environmental perception, and is widely applied to various high-precision scenes. In order to obtain the position information of the target contained in the image from the image acquired by the camera, before the camera is used, the camera is usually required to be calibrated by internal reference.
Disclosure of Invention
The disclosure provides a method and a device for calibrating internal reference of multiple cameras, electronic equipment and a storage medium, so as to improve the calibration efficiency of the internal reference of the multiple cameras.
According to an aspect of the present disclosure, there is provided a multi-camera internal reference calibration method, including:
acquiring candidate images of the checkerboard calibration board at different positions, which are acquired by a plurality of cameras simultaneously; the focal lengths and the models of the cameras are the same; the distance between the cameras is smaller than a preset distance threshold;
carrying out corner detection on each candidate image to obtain the number of corners contained in each candidate image;
filtering candidate images with incomplete corners according to the number of corners contained in each candidate image and the number of actual corners in the checkerboard calibration plate to obtain each target image;
and aiming at each camera, determining internal parameters of the camera based on the target image acquired by the camera to obtain a target internal parameter calibration result of the camera.
According to another aspect of the present disclosure, there is provided a multi-camera internal reference calibration apparatus, including:
the candidate image acquisition module is used for acquiring candidate images of the checkerboard calibration board which are acquired by the plurality of cameras at different positions; the focal lengths and the models of the cameras are the same; the distance between the cameras is smaller than a preset distance threshold;
the corner detection module is used for carrying out corner detection on each candidate image to obtain the number of corners contained in each candidate image;
a target image obtaining module, configured to filter candidate images with incomplete corner points according to the number of corner points included in each candidate image and the number of actual corner points in the checkerboard calibration plate, to obtain each target image;
and the internal reference calibration module is used for determining the internal reference of the camera based on the target image acquired by the camera aiming at each camera to obtain the target internal reference calibration result of the camera.
According to another aspect of the present disclosure, there is provided an electronic device including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform any of the multi-camera internal reference calibration methods described above.
According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to execute any one of the above-mentioned multi-camera internal reference calibration methods.
According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements any of the multi-camera internal reference calibration methods described above.
It should be understood that the statements in this section are not intended to identify key or critical features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a schematic diagram of a first embodiment of a multi-camera internal reference calibration method provided in accordance with the present disclosure;
FIG. 2 is a schematic view of a checkerboard calibration plate;
FIG. 3 is a schematic diagram of obtaining a target internal reference calibration result according to the present disclosure;
FIG. 4 is a schematic diagram of a second embodiment of a multi-camera internal reference calibration method provided in accordance with the present disclosure;
FIG. 5 is a schematic diagram of a first embodiment of a multi-camera internal reference calibration apparatus provided in accordance with the present disclosure;
fig. 6 is a block diagram of an electronic device for implementing a multi-camera internal reference calibration method according to an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
The camera can project an object in the real world on a camera two-dimensional imaging plane as an important part of environment perception, but it is difficult to acquire three-dimensional stereo information of a target such as a vehicle in a real environment by only relying on a two-dimensional image plane camera. Therefore, in practical applications, such as automatic driving environment sensing, three-dimensional stereo information of an object such as a vehicle in the real world is usually obtained based on a pixel position of the object such as the vehicle in an image based on a conversion relationship between an image coordinate system and a real world coordinate system. The camera reference calibration is to find the corresponding relationship between the image and the real world. In order to ensure the accuracy of the three-dimensional information of the determined target, it is important to perform internal reference calibration on the camera before the camera is used, particularly before the camera of an automatic driving vehicle is loaded. The camera parameters generally include the focal length f of the camera, principal point coordinates (cx, cy), and values of distortion, etc. Wherein, the camera principal point refers to the intersection point of the camera optical axis and the imaging plane in the camera.
At present, the more applied internal reference calibration method is to calibrate checkerboard pictures by a Zhang calibration method to obtain the internal reference of the camera. In the related art, in a multi-camera internal reference calibration scene, when checkerboard pictures are acquired, multiple times of image acquisition are usually performed for a single camera one by one, and the acquisition efficiency is low, so that the multi-camera internal reference calibration efficiency is low.
In order to improve the multi-camera internal reference calibration efficiency, the disclosure provides a multi-camera internal reference calibration method, a multi-camera internal reference calibration device, an electronic device and a storage medium. The multi-camera internal reference calibration method provided by the present disclosure is first exemplarily explained as follows:
the multi-camera internal reference calibration method provided by the disclosure can be applied to any electronic equipment with a multi-camera internal reference calibration function. The electronic device may be a computer, a server, a mobile terminal, and the like.
As shown in fig. 1, fig. 1 is a schematic diagram of a first embodiment of a multi-camera internal reference calibration method provided by the present disclosure, which may include the following steps:
s101, acquiring candidate images of a checkerboard calibration plate at different positions, which are acquired by a plurality of cameras simultaneously;
step S102, carrying out corner detection on each candidate image to obtain the number of corners contained in each candidate image;
step S103, filtering candidate images with incomplete corners according to the number of corners contained in each candidate image and the number of actual corners in the chessboard pattern calibration plate to obtain each target image;
and step S104, aiming at each camera, determining the internal reference of the camera based on the target image acquired by the camera to obtain the target internal reference calibration result of the camera.
The focal length imaging distances are different, the clear positions of the calibration plates are also different, and when cameras with the same model and the same focal length collect images of the calibration plates, the clear imaging distances between the calibration plates and the cameras are always the same. By applying the embodiment of the disclosure, a plurality of cameras with the same type and the same focal length are fixed at the close positions, and the position of the calibration plate is continuously changed, so that the images of the calibration plate required by each camera can be acquired simultaneously, the image acquisition efficiency of the camera is improved, and the internal reference calibration efficiency of the multi-camera is further improved. In addition, in the zhang's calibration method, it is usually necessary to extract the corner points in the collected checkerboard calibration board image for camera internal reference calibration. If the corner points of the checkerboard in the image are incomplete, the calibration accuracy is reduced, and even the calibration fails. The calibration efficiency is greatly reduced. By applying the embodiment of the disclosure, the corner detection is carried out on the checkerboard calibration board image collected by the camera, and the image with incomplete corners is filtered, so that the integrity of the checkerboard corners in the extracted image can be improved, and the calibration success rate and accuracy are improved.
The following exemplifies the above steps S101 to S104:
in step S101, a plurality of cameras with the same model and the same focal length may be used to capture images of the same calibration plate at different positions. The number of cameras can be determined according to actual needs, such as 8, 10, and the like. The cameras with the same type and the same focal length are fixed at the similar positions. For example, the cameras may be placed on the same horizontal line, and the distance between any two cameras does not exceed a preset distance threshold. The preset distance threshold can be set according to actual needs, and can be 80cm, 100cm and the like. It is of course also possible to define a camera placement range in advance on the ground and place each camera within the range. The camera placement range can be set according to actual needs, and can be a circular area with a radius of 1m, a square area with a side length of 1.5m, and the like.
After fixing above-mentioned a plurality of cameras, can remove the position of calibration board many times to after the position of moving the calibration board at every turn, use above-mentioned a plurality of cameras to gather the image of calibration board simultaneously, so that every camera gathers the image of calibration board in the different positions of camera finder frame.
The above-mentioned multiple cameras simultaneously acquiring the images of the calibration plate means: the multiple cameras collect images of the calibration plate at the same position, and may collect the images at the same time, or collect the images in a preset time window, such as 5s or 10 s.
The calibration plate can be a solid circle array calibration plate, a checkerboard calibration plate, or the like. Moving the calibration plate refers to changing the distance between the calibration plate and the camera, and the orientation of the calibration plate relative to the camera, so that the calibration plate appears in as many positions in the image as possible.
As an embodiment of the present disclosure, a checkerboard calibration board may be selected for calibration of the multi-camera internal reference. The chessboard pattern calibration board, namely the pattern in the calibration board, is the chessboard of the international chess. Fig. 2 is a schematic view of a checkerboard calibration board, as shown in fig. 2.
The plurality of cameras can collect a plurality of chessboard pattern calibration plate images for calibration. The checkerboard calibration plate image collected by each camera for calibration is referred to as a target image hereinafter. The number of the target images can be preset according to actual needs, such as 40, 60, and the like.
In an embodiment of the present disclosure, the checkerboard calibration board image collected by each camera may be screened to obtain the target image for calibration.
Specifically, in step S101, the candidate image refers to the image of the full calibration plate collected by the unscreened camera. The number of candidate images acquired by each camera can be determined according to actual needs. Such as may be 60, 80, etc.
The angular point is the intersection point of two sides of each chessboard grid in the chessboard grid calibration board. In step S102, a Harris algorithm, a fast corner detection algorithm, a surf corner detection algorithm, and the like may be used to detect corners in the candidate image. And determining whether the number of the detected angular points is consistent with the number of the real angular points in the chessboard pattern calibration board. If the detected angular point number is not consistent with the real angular point number in the checkerboard calibration board, it is indicated that the checkerboard image in the candidate image is not complete, and therefore the candidate image can be filtered.
In an embodiment of the present disclosure, the candidate images with corners at the edges of the image may also be filtered. The corner detection generally determines a pixel where a gray value in an image changes greatly as a corner. Non-corner regions with large gray value changes easily appear at the edge positions of the image, so that false detection is easily caused, namely the non-corner regions are detected as corners. Therefore, the candidate images of the detected corner points at the edge positions of the images can be filtered, so that the possibility of false detection is reduced, and the calibration accuracy is further improved.
In the calibration process of the camera internal reference, the checkerboard calibration plate is expected to appear at different positions in the image in different postures, so that the situation that the position of the checkerboard calibration plate in the acquired image is too single, the local optimization of the calibration is caused, and the overall accuracy of the calibration of the internal reference is reduced. Therefore, in an embodiment of the disclosure, the positions of the checkerboard calibration plates in each candidate image can be detected, and images with more concentrated positions of the checkerboard calibration plates in the candidate images are filtered out, so that the checkerboard calibration plates are ensured to appear at different positions in the images as much as possible, and the accuracy of internal reference calibration is improved.
As a specific implementation, the images with more concentrated positions where the checkerboard calibration plates appear in the candidate images may be filtered by the following steps:
step S111, determining the mass center of each checkerboard corner point in each candidate image;
and step S112, respectively determining candidate images with a preset number of centroid positions falling in a preset area as target images for each camera.
In step S111, the centroid of the checkerboard corner points is obtained according to the coordinates of each checkerboard corner point. For example, the average value of the coordinates of each checkerboard corner may be used as the coordinates of the centroid of the checkerboard corner in the candidate image. Of course, the center of mass of the corner points of the checkerboard can be obtained in other ways.
In step S112, the nine-square lattices may be divided for each candidate image, and the number of candidate images having the centroid position falling in each lattice may be determined. And aiming at each nine-square grid, selecting a preset number of candidate images with the mass center positions falling in the grid as candidate images. The preset number can be set for each nine-square grid respectively or uniformly. Such as may be 5, 6, etc. Of course, the regions may be divided by other methods for each candidate image, which is not specifically limited by the present disclosure.
In an embodiment, for each camera, the similarity of the checkerboard calibration plate positions between the candidate images collected by the camera is determined, and the candidate images with similar checkerboard calibration plate positions are filtered.
Specifically, the candidate images acquired by each camera may be arranged in chronological order for the camera. And calculating the pixel difference between any position in the chessboard pattern calibration plate in the candidate image and the position of the same chessboard pattern calibration plate in the previous candidate image aiming at each candidate image. If the pixel difference is less than a predetermined pixel difference threshold, the previous image or the image may be discarded. To further enable the checkerboard to appear in as many locations in the image as possible. The pixel difference threshold may be set according to actual needs, and may be, for example, 20 pixels, 30 pixels, or the like.
In the image acquisition process, the condition that the acquired image is fuzzy may occur under the influence of the movement of the camera or the calibration plate, so that the corner point error of the extracted chessboard pattern calibration plate is large, and the accuracy of the calibration result is reduced. Therefore, in an embodiment of the present disclosure, a relatively modular image in the candidate images may be filtered to improve the accuracy of corner extraction and improve the calibration accuracy.
As a specific embodiment, the definition of each candidate image may be obtained; and taking the candidate image with the definition greater than a preset definition threshold value as a target image.
When the definition of each candidate image is obtained, the gray value of each pixel of the image processed by the sobel operator can be obtained, and the larger the gray value is, the higher the definition of the corresponding pixel is. Then, the gray value statistic of each pixel can be selected to measure the image definition, for example, the gray value average, the median, etc. of the image can be selected to measure the image definition. And selecting the candidate image with the definition greater than a preset definition threshold value as a target image.
The preset definition threshold may be a preset gray value threshold. The gray threshold can be selected according to actual needs, and specifically, the gray threshold can be obtained based on statistics of a large number of calibration pictures.
Of course, after obtaining the gray level image of each candidate image, the sharpness of the candidate image may be obtained by the sharpness calculation formula. For example, the above definition calculation formula may be:
in the formula, D is the image definition, and f (x, y) represents the gray value of a pixel point (x, y) in the image. And then, taking the image with the definition greater than the preset definition threshold value as a target image. The definition threshold value can be set according to actual needs.
After the candidate images are screened, the number of the acquired target images may be smaller than a preset number threshold. Therefore, for the cameras with the number of target images not reaching the preset number threshold, the candidate images of the checkerboard calibration plate at different positions, which are acquired by the cameras, can be acquired again; and returning to the step of performing corner detection on each candidate image to obtain the number of corners contained in each candidate image, and performing screening on the obtained images until the obtained target image reaches the preset number threshold. Therefore, camera internal reference calibration is carried out based on enough target images, and stability and accuracy of internal reference calibration results can be guaranteed.
In the related art, most of the images for calibration are obtained by manual rough screening, and the operation in the mass production process not only affects the production efficiency, but also is difficult to ensure the quality of the obtained images. By applying the embodiment of the disclosure, the quality of the picture acquired by the camera is automatically checked and managed by using the electronic device, and only the checked picture is input into the subsequent calibration process, so that the problem of calibration failure or error caused by the picture quality can be effectively avoided, the calibration accuracy and success rate are improved, and the calibration efficiency is improved.
After the target images acquired by the cameras are obtained, internal reference calibration can be carried out on the cameras based on the target images.
Specifically, the camera internal reference calibration is performed by using a zhang's calibration method in the present disclosure. The zhang's scaling method is to detect feature points in a target image collected by a camera in the middle of each camera, and the feature points are usually corner points of a checkerboard scaling board. The angular point is the intersection point of two sides of each chessboard grid in the chessboard grid calibration board. And then obtaining the mapping relation from the world coordinate system to the image coordinate system based on the space coordinates of the characteristic points and the pixel coordinates of the characteristic points in the target image. And obtaining a homography matrix from the world coordinate system to the image coordinate system based on the mapping relation. A homography matrix is a transformation matrix from a pixel in one image to a pixel in another image. An internal reference matrix may then be derived based on the homography matrix. And performing joint solution on the internal reference matrix obtained based on the multiple target images to obtain an internal reference calibration result. The internal reference calibration result includes a focal length calibration result of the camera, a principal point calibration result, and the like. After the internal reference calibration result is obtained, the internal reference calibration result can be written into camera firmware, so that three-dimensional information of targets such as vehicles in images acquired by the camera can be acquired based on the internal reference calibration result in the subsequent use process of the camera.
The camera usually records the focal length reference f of the camera when the camera leaves the factory 0 And a principal point reference value cx 0 ,cy 0 And the calibration result is near the reference value, the calibration is considered to be successful, and if the difference between the calibration result and the reference value is larger, the calibration is considered to be failed. Due to the influences of factors such as lens errors, installation errors, checkerboard image quality, angle and position of a calibration plate and the like of the camera, calibration failure is easy to occur, and the quality of the camera which fails to be calibrated is often judged to have problems, so that the camera is difficult to apply to an automatic driving vehicle.
In order to accurately determine the specific reason of the failure of the internal reference calibration, i.e., to determine whether the camera device has a problem, the camera device is usually subjected to comprehensive analysis by acquiring images for multiple times and calibrating the images for multiple times. In the related art, the single calibration result is mainly judged manually and whether to perform the next calibration is determined, however, the method needs a large amount of labor cost and is extremely low in efficiency, the calibration result is greatly influenced by human factors, and the result reliability is low.
In the embodiment of the present disclosure, the electronic device may automatically determine the internal reference calibration result of the camera determined based on the target image according to a preset rule and the rule, so as to determine the target internal reference calibration result of the camera. The internal reference calibration result determined based on the target image of the camera is referred to as a current internal reference calibration result hereinafter.
Specifically, as shown in fig. 3, the target internal reference calibration result of each camera may be obtained based on the current internal reference calibration result of each camera through the following steps.
And S301, determining the calibration times of the internal reference calibration of each camera. If the calibration times are less than the preset lower limit time threshold, executing step S302; if the calibration times are greater than the preset upper limit time threshold, executing step S307; if the calibration number is between the preset lower limit threshold and the preset upper limit threshold, step S310 is executed.
Step S302, determining whether the current internal reference calibration result meets a first preset parameter range; if yes, step S303 is executed, and if no, step S304 is executed.
And step S303, determining the current internal reference calibration result as a target internal reference calibration result of the camera.
Step S304, determining whether the current internal reference calibration result meets a second preset parameter range; if yes, go to step S305; if not, go to step S306.
And S305, marking that the current internal reference calibration result is undetermined, and outputting re-calibration prompt information.
And step S306, determining that the camera fails calibration.
Step S307, judging whether the difference value between the current internal reference calibration result and each historical internal reference calibration result is smaller than a preset difference value threshold value or not; if the ratio is smaller than the predetermined value, step S308 is executed, and if the ratio is not smaller than the predetermined value, step S309 is executed.
And S308, taking the current internal reference calibration result and the statistic value of each historical internal reference calibration result as a target internal reference calibration result of the camera.
And step S309, determining that the camera fails to pass calibration.
And step S310, outputting the recalibration prompt information.
The following is an exemplary description of the above steps S301 to S310:
in a possible embodiment, after the current internal reference calibration result of each camera is obtained each time, the camera identifier, the current internal reference calibration result and the current time information can be correspondingly stored, and each internal reference calibration result can be uniquely identified through the camera identifier and the time information, so that the target internal reference calibration result of the camera can be conveniently obtained based on the multiple calibration results of the camera. The camera identification is specifically an SN code (sequence code) of the camera. The internal reference calibration result recorded before the present calibration of the camera is referred to as a historical internal reference calibration result hereinafter.
Therefore, in step S301, historical reference calibration results of the camera may be obtained from the recorded calibration results based on the camera identification. And the number of times of calibration of the camera is judged based on the number of calibration results. For example, if there is no historical internal reference calibration result of the camera, the calibration number of the camera is 1. If the historical internal reference calibration results of the camera have two, the calibration frequency of the camera is 3.
Of course, in a possible embodiment, a calibration time recording table may also be maintained, and the corresponding relationship between the camera identifier and the camera calibration time is stored. And after the current internal reference calibration result is obtained after each calibration is finished, adding 1 to the calibration times of the corresponding camera. Therefore, the calibration count of the camera may be directly acquired from the calibration count recording table based on the camera identification in step S301.
If the calibration number of the camera is smaller than the preset lower limit number threshold, the above steps S302-S306 may be executed. The lower limit time threshold can be set according to actual needs. As may be 2, 3, etc.
As described above, the internal reference calibration result of the camera includes the focal length f calibration result of the camera and the principal point coordinate calibration result of the camera. The camera records the focal length reference value f of the camera when leaving the factory 0 Andprincipal point reference value cx 0 ,cy 0 If the calibration result is near the reference value, the calibration is considered to be successful, and if the difference from the reference value is large, the camera problem or the influence of the position of the calibration plate and other factors needs to be considered. Therefore, in step S302, the first preset parameter range may be determined based on the focal length of the camera and the principal point coordinate reference value. Specifically, the first preset parameter range may be:
wherein epsilon is a focus floating range threshold value, and gamma is a main point floating range threshold value. The focus floating range threshold value and the principal point floating threshold value can be set according to actual needs.
And if the current internal reference calibration result of the camera meets the first preset parameter range, determining that the camera passes the calibration and determining the current internal reference calibration result as the target internal reference calibration result of the camera. And if the current internal reference calibration result of the camera does not meet the first preset parameter range, determining whether the camera needs to be calibrated again.
The inaccurate focal length calibration result of the camera is generally caused by lens errors, installation errors and other factors of the camera. Therefore, as a specific implementation manner, if the focal length calibration result in the current internal reference calibration result does not satisfy the focal length range in the first preset parameter range, it may be determined that the camera calibration fails and the camera is unavailable.
If the focus calibration result meets the focus range in the first preset parameter range, whether the principal point calibration result meets the principal point range in the first preset parameter range or not can be judged, if the principal point meets the principal point range, the current internal reference calibration result of the camera can be judged to meet the first preset parameter range, and if the principal point does not meet the principal point range, the current internal reference calibration result can be judged to not meet the first preset parameter range.
In step S304, the second predetermined parameter range includes the first predetermined parameter range. That is, if the current internal reference calibration result meets the first preset parameter range, the current internal reference calibration result also meets the second preset parameter range.
As a specific embodiment, the second preset parameter range may be:
of course, the coefficients before epsilon and gamma may be other values, and may be specifically set according to actual needs. The camera principal point calibration result does not satisfy the first preset parameter range, but satisfies the second preset parameter range, possibly due to the influence of factors such as the position of the calibration board and the quality of the checkerboard image. Therefore, if the current internal reference calibration result meets the second preset parameter range, the current internal reference calibration result can be recorded, and the recalibration prompt information is output. For example, the "recalibration" information may be displayed in the electronic device to recalibrate the camera, excluding the effects of factors such as the position of the calibration board, the image quality, etc. Specifically, the process of calibrating the camera again includes acquiring a target image of the calibration plate acquired by the camera at different positions again, and performing internal reference calibration on the camera based on the acquired target image.
If the camera principal point does not satisfy the second preset parameter range, the camera can be judged to have problems and is unavailable.
Therefore, the current internal reference calibration result of the camera is judged by setting the first preset parameter range and the second preset parameter range, the possible reason that the current calibration result has problems is determined, whether the next calibration needs to be carried out is judged manually based on self experience, and the camera calibration efficiency is improved.
In step S301, if the calibration number of the camera is greater than the preset upper limit number threshold, the steps S307 to S309 may be executed. The preset upper limit time threshold may be the same as or different from the preset lower limit threshold. Illustratively, the upper threshold number of times may be 3, 4, etc.
In step S307, differences may be obtained for the current internal reference calibration result and the focus calibration result and the principal point coordinate calibration result in each historical calibration result, respectively, so as to obtain a plurality of focus differences and a plurality of principal point coordinate differences. And judging whether the focus difference values are all smaller than a focus difference value threshold value or not, and whether the principal point coordinate difference values are all smaller than a preset principal point coordinate difference value threshold value or not. If the values are less than the preset values, the multiple calibration results are stable, otherwise, the multiple calibration results are unstable. Of course, it is also possible to obtain an average value of the difference values of the focal lengths and an average value of the difference values of the principal point coordinates, and respectively determine whether the average values of the two difference values are smaller than the corresponding preset difference threshold. If the values are less than the preset values, the multiple calibration results are stable. Otherwise, it is unstable. The difference threshold values can be set according to actual needs.
If the multiple calibration results are stable, the statistics of the current internal reference calibration result and the historical internal reference calibration result can be used as the target internal reference calibration result. The above statistical values may be mean values, median values, and the like. For example, the average value of the focal length calibration results in each calibration result may be used as the target focal length, and the average value of the principal point coordinate calibration results in each calibration result may be used as the target principal point coordinate. Of course, the calibration result corresponding to the median of the focus calibration results in the internal reference calibration results may also be selected as the target internal reference calibration result, which is not specifically limited in this disclosure.
If the multiple calibration results are unstable, the camera can be judged to have problems and be unusable.
In the related technology, there is no dependency relationship between multiple calibrations, and only the parameter results of each calibration can be compared manually, so that it is difficult to quantitatively determine the difference and stability of the result of each calibration, and it is difficult to determine whether the calibration is repeated for multiple times due to the defects of the camera, which results in the great reduction of the working efficiency of the calibration personnel and the sharp increase of the labor cost of the calibration. By applying the embodiment of the disclosure, the camera internal reference calibration result is recorded, and the current internal reference calibration result and the historical internal reference calibration result of the camera are comprehensively analyzed, so that the reason of the camera abnormality, such as the camera self reason or the calibration plate position, can be determined more quickly, and the camera calibration efficiency is improved.
For a camera with the calibration times between the preset lower limit time threshold and the preset upper limit time threshold, the calibration result is considered to be too small, and the reliability of the calibration result is low. Therefore, for the cameras, the current internal reference calibration result of the cameras can be recorded, and the prompt information of calibration again can be output, so that the reliability of the calibration result is improved. For example, if the preset upper limit time threshold and the preset lower limit time threshold are both 2, the recalibration prompt information may be directly output for a camera with a calibration time of 2. If the preset upper limit time threshold is 5 and the preset lower limit time threshold is 2, the camera with the calibration times of [2,5] can directly output the recalibration prompt information.
Therefore, by applying the embodiment of the disclosure, the multiple calibration results of the multiple cameras are managed in a mode of combining the SN number and the timestamp, and the final conclusion is obtained by automatically and comprehensively analyzing the calibration results according to the preset judgment rule, so that the calibration efficiency and the accuracy are improved, and the reliability of the result is improved.
As shown in fig. 4, fig. 4 is a schematic diagram of a specific example of the multi-camera internal reference calibration method provided in the embodiment of the present disclosure, which may specifically include the following three parts:
and (3) drawing management: the method comprises the steps that a plurality of cameras with the same model and the same focal length simultaneously acquire pictures, and judge acquired images, wherein the judgment is carried out on whether corner points are complete, whether the images are clear, whether the checkerboard positions are proper and whether the number of target pictures is enough until the target pictures needed by calibration are obtained for each camera.
Acquiring and calibrating an SN number of a camera: the method comprises the steps of calibrating internal parameters, acquiring an SN number of a camera, acquiring a system time stamp and storing a calibration result. Specifically, the calibration result is stored in a unique path formed by the SN number and the system timestamp.
And (3) calibration parameter management: and analyzing the calibration result and giving a corresponding conclusion, so as to realize the management of the internal reference results of multiple cameras and multiple calibration. Specifically, first, the calibration number N is checked for each camera, and if the calibration number is 1, the calibration number is determinedAnd determining whether the focal length f in the internal reference calibration result meets a first preset parameter range (a first range in fig. 4), if so, determining whether the principal point coordinates (cx, cy) meet the first preset parameter range, and if not, determining that the camera calibration fails and the camera has a problem. If the principal point meets the first preset parameter range, determining that the camera calibration is successful, and writing the current internal reference calibration result into the camera firmware; if the principal point does not meet the first preset parameter range, determining whether the principal point meets a second preset parameter range ((the second range in fig. 4)), if not, determining that the calibration fails and the camera has a problem, if so, calibrating that the current calibration result is undetermined, and outputting recalibration prompt information. The first preset parameter range is as follows:
wherein epsilon and gamma are preset constants. The second preset parameter range is as follows:
By applying the embodiment of the disclosure, the data are simultaneously acquired by using the plurality of cameras in the multi-camera internal reference calibration scene, the image acquisition efficiency is improved, and the calibration efficiency is further improved. Secondly, by screening the collected pictures, the calibration failure caused by the problems of incomplete picture quality, incomplete angular points, single chessboard grid position and the like is reduced, and the calibration success rate and accuracy are improved. Moreover, by using the mode of combining the SN number and the timestamp, a plurality of cameras and a plurality of calibration results are managed, the final conclusion is obtained through automatic comprehensive analysis, the calibration efficiency and the accuracy are improved, and the reliability of the results is improved.
According to an embodiment of the present disclosure, there is also provided a multi-camera internal reference calibration apparatus, as shown in fig. 5, the apparatus may include:
a candidate image obtaining module 501, configured to obtain candidate images of the checkerboard calibration board at different positions, where the candidate images are simultaneously collected by multiple cameras; the focal lengths and the models of the cameras are the same; the distance between the cameras is smaller than a preset distance threshold;
a corner detection module 502, configured to perform corner detection on each candidate image to obtain the number of corners included in each candidate image;
a target image obtaining module 503, configured to filter candidate images with incomplete corner points according to the number of corner points included in each candidate image and the number of actual corner points in the checkerboard calibration board, to obtain each target image;
an internal reference calibration module 504, configured to determine, for each camera, an internal reference of the camera based on a target image acquired by the camera, so as to obtain a target internal reference calibration result of the camera.
In a possible embodiment, the target image obtaining module is further configured to:
determining the mass center of each checkerboard corner point in each candidate image;
and respectively determining candidate images with a preset number of centroid positions falling in a preset area as target images for each camera.
In a possible embodiment, the target image obtaining module is further configured to:
acquiring the definition of each candidate image;
and taking the candidate image with the definition larger than a preset definition threshold value as a target image.
In a possible embodiment, the target image obtaining module is further configured to:
for the cameras with the target image quantity not reaching the preset quantity threshold value, acquiring candidate images of the checkerboard calibration board collected by the cameras at different positions again; and returning to the step of detecting the corner points of each candidate image to obtain the number of the corner points contained in each candidate image.
In a possible embodiment, the determining, for each camera, the internal reference of the camera based on the target image acquired by the camera to obtain the target internal reference calibration result of the camera includes:
for each camera, determining internal parameters of the camera based on a target image acquired by the camera to obtain a current internal parameter calibration result of the camera;
determining the number of times of calibrating the internal reference of each camera;
determining a first camera with the calibration times smaller than a preset lower limit time threshold;
determining that the current internal reference calibration result of the first camera is the target internal reference calibration result of the first camera aiming at the first camera with the current internal reference calibration result within a first preset parameter range;
recording the current internal reference calibration result of the first camera aiming at the first camera with the current internal reference calibration result in a second preset parameter range, and returning to the step of acquiring target images of the calibration plate at different positions, which are acquired by a plurality of cameras simultaneously; the second preset range comprises the first preset range;
and determining that the first camera fails to pass calibration aiming at the first camera with the current internal reference calibration result not in the second preset parameter range.
In a possible embodiment, the internal reference calibration module is further configured to:
determining a second camera with the calibration times larger than a preset upper limit time threshold;
for the second camera, obtaining a difference value between a current internal reference calibration result and a historical calibration result of the second camera;
and if the difference values are smaller than a preset difference value threshold value, taking the statistics of the current internal reference calibration result and the historical calibration results as the target internal reference calibration result of the second camera.
In a possible embodiment, the internal reference calibration module is further configured to:
and recording the current internal reference calibration result of the third camera aiming at the third camera with the calibration times between a preset lower limit time threshold and a preset upper limit time threshold, and outputting re-calibration prompt information.
In the technical scheme of the disclosure, the collection, storage, use, processing, transmission, provision, disclosure and other processing of the personal information of the related user are all in accordance with the regulations of related laws and regulations and do not violate the good customs of the public order.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
FIG. 6 illustrates a schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 6, the device 600 comprises a computing unit 601, which may perform various suitable actions and processes according to a computer program stored in a Read Only Memory (ROM) 602 or loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the device 600 can also be stored. The calculation unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
A number of components in the device 600 are connected to the I/O interface 605, including: an input unit 606 such as a keyboard, a mouse, or the like; an output unit 607 such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, optical disk, or the like; and a communication unit 609 such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 601 performs the various methods and processes described above, such as a multi-camera internal reference calibration method. For example, in some embodiments, the multi-camera internal reference calibration method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 600 via the ROM 602 and/or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the calculation unit 601, one or more steps of the multi-camera referencing method described above may be performed. Alternatively, in other embodiments, the calculation unit 601 may be configured to perform the multi-camera intra-reference calibration method by any other suitable means (e.g. by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel or sequentially or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.
Claims (17)
1. A multi-camera internal reference calibration method comprises the following steps:
acquiring candidate images of the checkerboard calibration board at different positions, which are acquired by a plurality of cameras simultaneously; the focal lengths and the models of the cameras are the same; the distance between the cameras is smaller than a preset distance threshold;
performing corner detection on each candidate image to obtain the number of corners contained in each candidate image;
filtering the candidate images with incomplete corners according to the number of corners contained in each candidate image and the number of actual corners in the chessboard pattern calibration plate to obtain each target image;
and aiming at each camera, determining internal parameters of the camera based on the target image acquired by the camera to obtain a target internal parameter calibration result of the camera.
2. The method of claim 1, further comprising:
determining the centroid of each corner point in the candidate image aiming at each candidate image;
and respectively determining candidate images with a preset number of centroid positions falling in a preset area as target images for each camera.
3. The method of claim 2, further comprising:
acquiring the definition of each candidate image;
and taking the candidate image with the definition larger than a preset definition threshold value as a target image.
4. The method of claim 3, further comprising:
for the cameras with the target image quantity not reaching the preset quantity threshold value, acquiring candidate images of the checkerboard calibration board collected by the cameras at different positions again; and returning to the step of detecting the corner points of each candidate image to obtain the number of the corner points contained in each candidate image.
5. The method according to claim 1, wherein for each camera, determining an internal reference of the camera based on a target image acquired by the camera to obtain a target internal reference calibration result of the camera comprises:
for each camera, determining internal parameters of the camera based on a target image acquired by the camera to obtain a current internal parameter calibration result of the camera;
determining the number of times of calibrating the internal reference of each camera;
determining a first camera with the calibration times smaller than a preset lower limit time threshold;
determining that the current internal reference calibration result of the first camera is the target internal reference calibration result of the first camera aiming at the first camera with the current internal reference calibration result within a first preset parameter range;
recording the current internal reference calibration result of the first camera aiming at the first camera with the current internal reference calibration result in a second preset parameter range, and returning to the step of acquiring target images of the calibration plate acquired by the plurality of cameras at different positions; the second preset range comprises the first preset range;
and determining that the first camera fails to pass calibration aiming at the first camera with the current internal reference calibration result not in the second preset parameter range.
6. The method of claim 5, further comprising:
determining a second camera with the calibration times larger than a preset upper limit time threshold;
aiming at the second camera, obtaining a difference value between a current internal reference calibration result and a historical calibration result of the second camera;
and if the difference values are smaller than a preset difference value threshold value, taking the statistics of the current internal reference calibration result and the historical calibration results as the target internal reference calibration result of the second camera.
7. The method of claim 6, further comprising:
and recording the current internal reference calibration result of the third camera aiming at the third camera with the calibration times between a preset lower limit time threshold and a preset upper limit time threshold, and outputting re-calibration prompt information.
8. A multi-camera internal reference calibration device, comprising:
the candidate image acquisition module is used for acquiring candidate images of the checkerboard calibration plate acquired by the plurality of cameras at different positions; the focal lengths and the models of the cameras are the same; the distance between the cameras is smaller than a preset distance threshold;
the corner detection module is used for carrying out corner detection on each candidate image to obtain the number of corners contained in each candidate image;
a target image obtaining module, configured to filter candidate images with incomplete corner points according to the number of corner points included in each candidate image and the number of actual corner points in the checkerboard calibration plate, to obtain each target image;
and the internal reference calibration module is used for determining the internal reference of the camera based on the target image acquired by the camera aiming at each camera to obtain the target internal reference calibration result of the camera.
9. The apparatus of claim 8, further comprising:
determining the mass center of each checkerboard corner point in each candidate image;
and respectively determining candidate images with a preset number of centroid positions falling in a preset area as target images for each camera.
10. The apparatus of claim 9, further comprising:
acquiring the definition of each candidate image;
and taking the candidate image with the definition larger than a preset definition threshold value as a target image.
11. The apparatus of claim 10, further comprising:
for the cameras with the target image quantity not reaching the preset quantity threshold value, acquiring candidate images of the checkerboard calibration board collected by the cameras at different positions again; and returning to the step of detecting the corner points of each candidate image to obtain the number of the corner points contained in each candidate image.
12. The apparatus of claim 8, wherein the determining, for each camera, an internal reference of the camera based on the target image acquired by the camera to obtain a target internal reference calibration result of the camera comprises:
for each camera, determining internal parameters of the camera based on a target image acquired by the camera to obtain a current internal parameter calibration result of the camera;
determining the times of calibrating the internal reference of each camera;
determining a first camera with the calibration times smaller than a preset lower limit time threshold;
aiming at a first camera with the current internal reference calibration result within a first preset parameter range, determining the current internal reference calibration result of the first camera as a target internal reference calibration result of the first camera;
recording the current internal reference calibration result of the first camera aiming at the first camera with the current internal reference calibration result in a second preset parameter range, and returning to the step of acquiring target images of the calibration plate acquired by the plurality of cameras at different positions; the second preset range comprises the first preset range;
and determining that the first camera fails to pass calibration aiming at the first camera with the current internal reference calibration result out of the second preset parameter range.
13. The apparatus of claim 12, further comprising:
determining a second camera with the calibration times larger than a preset upper limit time threshold;
for the second camera, obtaining a difference value between a current internal reference calibration result and a historical calibration result of the second camera;
and if the difference values are smaller than a preset difference value threshold value, taking the statistics of the current internal reference calibration result and the historical calibration results as the target internal reference calibration result of the second camera.
14. The apparatus of claim 13, further comprising:
and recording the current internal reference calibration result of the third camera aiming at the third camera with the calibration times between a preset lower limit time threshold and a preset upper limit time threshold, and outputting re-calibration prompt information.
15. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.
16. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-7.
17. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211659012.6A CN115861443A (en) | 2022-12-22 | 2022-12-22 | Multi-camera internal reference calibration method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211659012.6A CN115861443A (en) | 2022-12-22 | 2022-12-22 | Multi-camera internal reference calibration method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115861443A true CN115861443A (en) | 2023-03-28 |
Family
ID=85654008
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211659012.6A Pending CN115861443A (en) | 2022-12-22 | 2022-12-22 | Multi-camera internal reference calibration method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115861443A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117073988A (en) * | 2023-08-18 | 2023-11-17 | 交通运输部公路科学研究所 | System and method for measuring distance of head-up display virtual image and electronic equipment |
-
2022
- 2022-12-22 CN CN202211659012.6A patent/CN115861443A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117073988A (en) * | 2023-08-18 | 2023-11-17 | 交通运输部公路科学研究所 | System and method for measuring distance of head-up display virtual image and electronic equipment |
| CN117073988B (en) * | 2023-08-18 | 2024-06-04 | 交通运输部公路科学研究所 | System and method for measuring distance of head-up display virtual image and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111308448A (en) | Image acquisition equipment and radar external parameter determination method and device | |
| CN111412842B (en) | Method, device and system for measuring cross-sectional dimension of wall surface | |
| CN111710000B (en) | Camera line deviation self-checking method and system | |
| CN110634137A (en) | Bridge deformation monitoring method, device and equipment based on visual perception | |
| CN108596032B (en) | Detection method, device, equipment and medium for fighting behavior in video | |
| CN115861443A (en) | Multi-camera internal reference calibration method and device, electronic equipment and storage medium | |
| US20150029230A1 (en) | System and method for estimating target size | |
| CN116758006B (en) | Scaffold quality detection method and device | |
| CN111260735B (en) | External parameter calibration method for single-shot LIDAR and panoramic camera | |
| CN117434568A (en) | Intelligent positioning system based on remote sensing satellite | |
| CN111985266B (en) | Scale map determining method, device, equipment and storage medium | |
| CN112419402A (en) | Positioning method and system based on multispectral image and laser point cloud | |
| CN111311671A (en) | Workpiece measuring method and device, electronic equipment and storage medium | |
| CN113450335B (en) | Road edge detection method, road edge detection device and road surface construction vehicle | |
| CN113470103B (en) | Method and device for determining camera acting distance in vehicle-road cooperation and road side equipment | |
| CN113112551B (en) | Camera parameter determining method and device, road side equipment and cloud control platform | |
| CN112507838B (en) | Pointer meter identification method and device and electric power inspection robot | |
| CN110930344B (en) | Target quality determination method, device and system and electronic equipment | |
| CN107741220B (en) | Image processing method and device and electronic equipment | |
| CN112146834A (en) | Method and device for measuring structural vibration displacement | |
| CN111833370A (en) | Flight pixel filtering method and system | |
| CN113139454B (en) | Road width extraction method and device based on single image | |
| CN111815552A (en) | Workpiece detection method and device, readable storage medium and terminal equipment | |
| CN111586299B (en) | Image processing method and related equipment | |
| CN117392127B (en) | Method and device for detecting display panel frame and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |