CN114708326A - Full-automatic camera calibration system and method for adaptively adjusting brightness and ambiguity - Google Patents
Full-automatic camera calibration system and method for adaptively adjusting brightness and ambiguity Download PDFInfo
- Publication number
- CN114708326A CN114708326A CN202111527480.3A CN202111527480A CN114708326A CN 114708326 A CN114708326 A CN 114708326A CN 202111527480 A CN202111527480 A CN 202111527480A CN 114708326 A CN114708326 A CN 114708326A
- Authority
- CN
- China
- Prior art keywords
- calibration
- camera
- image
- platform
- rotary moving
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000005540 biological transmission Effects 0.000 claims abstract description 21
- 238000011156 evaluation Methods 0.000 claims description 34
- 230000003044 adaptive effect Effects 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 8
- 238000005096 rolling process Methods 0.000 claims description 7
- 239000003550 marker Substances 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 230000006872 improvement Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 239000003086 colorant Substances 0.000 claims description 3
- 238000002474 experimental method Methods 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 claims description 3
- 230000036544 posture Effects 0.000 claims description 3
- 238000011161 development Methods 0.000 claims description 2
- 238000012795 verification Methods 0.000 claims description 2
- 241000234427 Asparagus Species 0.000 description 1
- 235000005340 Asparagus officinalis Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910010293 ceramic material Inorganic materials 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 201000009482 yaws Diseases 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G06T5/90—
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/67—Focus control based on electronic image sensor signals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/70—Circuitry for compensating brightness variation in the scene
- H04N23/743—Bracketing, i.e. taking a series of images with varying exposure conditions
Abstract
The invention relates to the technical field of computer vision, in particular to a full-automatic camera calibration system and a full-automatic camera calibration method for adaptively adjusting brightness and ambiguity, wherein the system comprises a monocular camera, a rotary mobile platform, a platform motion controller, a circle center calibration plate, wireless transmission equipment, a processor, display equipment and automatic high-precision calibration software; the method comprises the steps of converting the proportion of the number of pixels with black and white gray values in a specific region of an image into 1:2 according to a compensation coefficient, and adaptively adjusting an exposure value according to the average gray value of the region; the method comprises the steps of extracting edge points in four directions of an image specific characteristic circle, fitting a curve with a gray value of the edge points, calculating an average slope of the edge points, feeding a numerical value of the average slope representing the current fuzzy condition of the image back to a platform controller to realize self-adaptive adjustment of the fuzzy degree, controlling a rotary moving platform to be adjusted to a preset optimal pose according to a preset instruction to automatically shoot the image, and realizing automatic high-precision calibration of a camera through a high-precision camera calibration strategy.
Description
Technical Field
The invention relates to the technical field of computer vision, in particular to a full-automatic camera calibration system and a full-automatic camera calibration method for adaptively adjusting brightness and ambiguity.
Background
In modern highly-developed automation systems, machine vision positioning systems are widely used in various fields, such as robot vision guidance, three-dimensional online dimension measurement, and the like. At present, the demand of the automation field on a high-precision machine vision positioning system is vigorous, and the precision of the industrial camera calibration is improved on the premise of improving the positioning precision of machine vision. However, the conventional industrial camera calibration techniques mainly include a self-calibration method, an active calibration method, and a conventional calibration method, wherein the conventional calibration method is widely used in the industry due to the characteristics of simple principle, high calibration accuracy, and the like, and the method mainly includes a zhangzhengyou calibration method and a two-step method, wherein the zhangzhengyou calibration method requires only one calibration plate to achieve camera calibration, and is most commonly used. At present, great progress is made on a camera calibration algorithm, and K.Sirisantessamd and the like calculate a lens distortion coefficient and a distance between a principal point and a camera by using an iterative linear method so as to determine parameters of the camera; wangkun and the like extract characteristic circular edges by utilizing a sub-pixel edge detection algorithm, and provide a Zhang camera calibration method based on a circular array calibration plate by carrying out condition limitation on edge sealing characteristics; penlonga, Guojun and the like propose a high-precision camera calibration method based on plane transformation in consideration of perspective deviation; huang 29740Ting and the like utilize MATLAB to carry out image preprocessing, and the accuracy of corner detection is improved by means of harris corner detection, sub-pixel accuracy and the like, so that high-precision camera calibration is achieved. The method mainly uses manual placement of the mark plate to carry out calibration calculation, the calibration process is complicated, the time consumption is long, the azimuth angle of the calibration plate is difficult to judge, the calibration angles are not uniform, the brightness and the definition of the mark plate cannot be judged, the calibration precision is easily influenced by human factors, and the like. Therefore, the automatic moving of the marker is at the optimal working distance, and the efficient and high-precision calibration of the camera is completed by using the optimal calibration angle and acquiring high-quality images, which is very important for the realization of the visual high-precision positioning system.
The existing full-automatic calibration system conveniently and efficiently completes camera internal reference calculation, and can overcome the problem of insufficient calculation precision caused by manual operation. The Wang Jianfeng of Changan university drives the marker through the conveyor belt, and the monocular camera continuously shoots images so as to realize automatic camera calibration; the design mechanical arms such as the Shang-Yin province and the like control the mark plate to move, and the acquisition equipment is fixed on the mechanical arms and shoots the calibration plate to realize camera calibration; an Asparagus three-degree-of-freedom motion platform with the university at Zhejiang supports checkerboard target paper, expected pitching attitude, yawing attitude and rolling attitude are input through a PC upper computer, and a camera collects calibration board images with different attitudes to realize automatic camera calibration; the existing full-automatic calibration system and method do not judge and self-adaptively adjust the image fuzziness and brightness, and depend on manual operation or random shooting on the pose of a marker, so that the calibration precision of a camera is greatly influenced, and the robustness is not high.
Disclosure of Invention
The invention aims to solve the defects of the prior art, and provides a full-automatic camera calibration system and a full-automatic camera calibration method capable of adaptively adjusting brightness and ambiguity.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
a full-automatic camera calibration system for adaptively adjusting brightness and ambiguity mainly comprises a monocular camera, a rotary moving platform, a platform motion controller, a circle center calibration plate, wireless transmission equipment, a processor, display equipment and automatic high-precision calibration software; the calibration system comprises: the monocular camera is fixed at a certain position, a rotary moving platform is arranged below the corresponding camera, the distance between the rotary moving platform and the camera is used for calculating an initial value through a working distance, the platform motion controller drives a calibration plate supported by the rotary moving platform to pitch, yaw and roll and adjusts the distance between the calibration plate and the camera, and the monocular camera shoots images of the circle center calibration plate at different poses to finish camera calibration;
a rotary moving platform and a platform motion controller are arranged below the monocular camera, the rotary moving platform supports a circle center calibration plate, the distance between the rotary moving platform and the camera calculates an initial value through a working distance, the monocular camera collects the image of the current circle center calibration plate and transmits the image back to automatic high-precision calibration software, the current image is displayed on a display device, the parameters such as the gain, the acquisition mode and the like of the camera are adjusted on line through the automatic high-precision calibration software to improve the image quality, a rectangular area of the adjusted image is extracted, the size ratio of the area with the black color and the white color is converted into 1:2, an exposure value is adjusted in a self-adaptive mode through the average gray level of the rectangular area, the image with proper brightness is subjected to circle detection through an EDcircle algorithm, edge gray points in four directions of a characteristic circle are extracted, a gray point fitting curve is fitted, and the average slope of the gray points is calculated to represent the fuzzy condition of the image, and the feedback is sent to a platform controller to control the rotary moving platform to adjust the distance in the Z direction so as to realize the self-adaptive adjustment of the ambiguity;
the platform motion controller controls the rotary moving platform to adjust to a preset optimal pose group through a preset instruction, the achieved poses comprise a pitching pose, a yawing pose, a rolling pose and an adjusting distance camera distance, and the rotary moving platform supports the calibration plate to move so as to achieve high-precision calibration of the camera;
the technical scheme of the invention is further improved as follows: the monocular camera consists of a camera and a lens and is used for acquiring images of the calibration plate switched by the rotary moving platform, and the initial position of the camera is ensured to be right above the rotary moving platform;
the rotary moving platform is a mechanical structure with four degrees of freedom, the angle of each degree of freedom is adjusted by a motor, the motors are uniformly controlled by a platform motion controller, the angle switching and the distance adjustment between the camera and the camera can be realized, and the rotary moving platform is mainly used for adjusting the pose of a circle center calibration plate;
the platform motion controller takes a stm32 development board as a core, is connected with a motor on a rotary moving platform through a connecting wire, is connected with a receiving end of a wireless transmission module at the other end stm32 and is mainly used for controlling the rotary moving platform to switch the pose, an operator sends a calibration starting command through high-precision camera calibration software by presetting the position of the best calibration board pose, the platform motion controller controls the rotary moving platform to rotate to the preset position one by one, and a camera automatically identifies the pose through the switching condition of the rotary moving platform and stores an image for calibration calculation;
the circle center calibration plate is used for calibrating the calculated image by the camera, and extracting the three-dimensional coordinates of the world coordinate system of the calibration plate and the two-dimensional coordinates of the image coordinate system through different positions and postures of the circle center calibration plate to realize camera calibration;
the wireless transmission equipment is used for sending a command of the motion controller of the control platform and sending a corresponding command to the motion controller through the wireless transmission equipment according to the operating condition of the high-precision camera calibration software;
the processor is used for realizing data acquisition, storage and internal reference calibration methods and providing a carrier for internal reference calibration software;
the display equipment is used for operating the high-precision camera calibration software by an operator and displaying image information acquired by the camera in real time;
the automatic calibration software comprises a function setting area, a function view area, a display view area and a high-precision calibration algorithm; the function setting area provides two functions required by camera calibration, namely camera parameter setting and camera calibration, and an operator can select the functions according to actual conditions; the function view area displays the selected calibration function in a specific way; and the display view area is used for displaying the image acquired by the camera.
The full-automatic camera calibration method for adaptively adjusting brightness and ambiguity comprises the following steps:
step 1, calculating an initial position of a rotary moving platform, knowing that a camera has a working distance in a certain range according to an aperture imaging model, and estimating a focal length f to solve the initial position WD of the rotary moving platform through a distance formula because the focal length of the current camera cannot be known;
step 2, setting camera parameters, switching to a camera parameter interface through a function setting area, acquiring the model and the current image of the camera, setting the working state of the camera, setting a camera acquisition mode and automatic white balance, and manually and coarsely adjusting an exposure value and a camera gain according to the field environment, so that the quality of the acquired image is improved;
step 3, adjusting exposure in a self-adaptive manner, wherein the colors of the circle center calibration plate are composed of black and white, the calibration plate is positioned right below the lens, and the number ratio R of the black and white pixels in the rectangular region with the fixed size at the center of the image is countednRatio R of number of black and white pixels according to the moderate luminanceoFor the current statistical fixed-area proportion RnConverting the quantity ratio of black and white pixels, solving the average gray value of the current region, and adaptively adjusting the exposure according to the average gray value;
step 4, adaptively adjusting the ambiguity, sequencing the feature circles on the circle center calibration plate, acquiring the gray values of the four azimuth edges of a plurality of specific feature circles, respectively performing curve fitting, solving the average slope of the gray values in each direction, comparing the average value of the slopes in the same direction in the plurality of circles and removing the maximum value; calculating the average slope of edge points of a plurality of circles in a plurality of directions as an evaluation factor of the image blurring degree, and realizing self-adaptive adjustment of the blurring degree according to the evaluation factor;
step 5, obtaining an optimal calibration angle, presetting a group of optimal calibration angles on a rotary moving platform and recording the optimal calibration angles on a platform motion controller, sending a calibration starting command to the platform motion controller by high-precision camera calibration software through wireless transmission equipment, rotating the preset poses by the rotary moving platform one by one, and acquiring stable and clear calibration images at different pose distances by a camera to count 18 calibration images;
and 6, calibrating the camera, respectively acquiring the circle centers of the characteristic circles of the 18 calibrated images, calculating the internal reference and distortion coefficient of the camera according to a Zhang Zhengyou calibration method, generating a calibration log according to a data result, and storing the calibration log in a database, so that an operator can conveniently check and use the calibration log.
The technical scheme of the invention is further improved in that in the step 3, the self-adaptive exposure adjustment realizes the functions through the following steps:
step 3.1, calculating the average gray value in the rectangular area: selecting a rectangular area with a certain area in the circle center calibration plate area, and setting the quantity ratio of standard black to white as RoCalculating the ratio R of the current black and white numbersnAnd based on RoCalculating black and white compensation parameters B of current areacAnd WcConverting the quantity ratio of the current black and white into the value consistent with the set standard value through the compensation parameter, thereby obtaining the average gray value after the compensation parameter is added; wherein the compensation parameter BcAnd WcThe expression of (a) is:
wherein, b and bnRepresenting the number of pixels whose values are the standard ratio and black in the nth-order specific region, w and wnExpressing the number of pixels whose values are the standard ratio and white in the nth-time specific area;
mean gray value GavecThe expression formula is:
wherein A isbWeight coefficient representing black area, AwThe weight coefficient A of the black area is increased because the gray value of the black area is much smaller than that of the white areabThe average gray value has more obvious change when the brightness changes;
step 3.2, adaptive adaptationThe whole exposure degree: collecting a series of luminance images from underexposure to overexposure and respectively solving an average gray value GavecThe brightness distribution of the average gray value based on compensation and weight distribution is established, the average gray value of the current selected area is calculated, and a brightness adjustment strategy is deduced based on the brightness distribution, so that the self-adaptive adjustment of the exposure is realized; wherein the brightness adjustment strategy is:
wherein E represents the modified exposure value, L represents the brightness case, KLRepresenting the exposure adjustment coefficient, the current acquired area average gray value Gavec,GupAnd GunderRepresenting the average gray value representing the appropriate upper and lower limits of luminance in the rectangular region; by correcting the value E, the brightness is adjusted in a self-adaptive mode, and a clear calibration image is obtained.
The technical scheme of the invention is further improved as follows: in the step 4, the self-adaptive fuzzy degree adjustment method realizes the functions through the following steps:
step 4.1, sorting the characteristic circles: detecting a feature circle of the image, removing an interference feature circle and an approximate circle, sequencing the feature circles, and selecting a plurality of specific feature circles as processing objects;
step 4.2, evaluating indexes of the edge points: counting edge points of the selected multiple feature circles in four directions, deducing edge point evaluation indexes according to different gray value change characteristics of the edge points and internal pixel points and external pixel points of the feature circles, and screening out edge pixel points based on the edge point evaluation indexes; the expression of the edge point evaluation index is as follows:
wherein M isnIndicates whether n points are edge point evaluation indexes, GnA grayscale value representing the nth point, d represents a step size;
step 4.3, calculating ambiguity evaluation indexes, performing polynomial fitting curve according to edge point pixel values of the multiple feature circles in four directions, calculating the slope of each edge point pixel value, and screening out the average slope with a larger difference value with the average slope of the edge point pixel values of other feature circles in the same direction, so as to calculate the average slope of the edge point pixel values of the multiple circles in multiple directions as the evaluation index of the image ambiguity; the expression of the ambiguity evaluation index is:
wherein m is the number of edge points, Y is an expression of edge point pixel values subjected to polynomial fitting, z represents the direction of the edge points, and i represents the number of acquired characteristic circle circles;
step 4.4, adaptively adjusting the ambiguity, judging the current image quality according to the ambiguity evaluation factor, and adjusting the distance between the camera and the circle center calibration plate by adaptively adjusting the ambiguity strategy of the image to realize the improvement of the image quality; the adaptive ambiguity adjustment expression is as follows:
wherein D isnIndicates the direction of the moving distance of the camera, AkAnd KoRepresenting fixed coefficients and image sharpness threshold, tnExpressing directional weight, adaptive ambiguity adjusting distance between camera and marker, tnEvaluation of the change in the ambiguity after the current move, tnDetermined according to the following relationship:
tn＝Kn-Kn-1
wherein, KnRepresenting the blur degree evaluation factor of the nth image.
The technical scheme of the invention is further improved in that the step 5 comprises the following steps:
step 5.1, presetting an optimal calibration angle: distortion of characteristic circle caused by overlarge inclination angle of pitching yawing rolling of calibration plateAnd repeatedly verifying through experiments to obtain an optimal calibration angle and recording the preset optimal calibration angle to the platform motion controller, wherein the number of the optimal calibration angles is set to be 18, the optimal calibration angles are collected in three groups, and each group has six fixed poses: pitching 5 degrees of rolling-5 degrees, pitching 5 degrees of rolling-10 degrees, pitching-5 degrees of rolling-15 degrees, pitching 5 degrees of rolling-20 degrees, pitching 10 degrees of rolling-15 degrees, pitching 10 degrees of rolling-20 degrees; the three sets of calibration images are divided into: the distance between the first group of cameras and the pose rotating platform is WD + DnThe distance between the second group of cameras and the pose rotating platform is WD + Dn+WD1The distance between the third group of cameras and the pose rotating platform is WD + Dn+WD1And the pose rotating platform drifts by 5 degrees, wherein DnIndicating the distance moved by the adaptive adjustment of the ambiguity, WD1Represents one fifth of the distance of the current lens depth of field;
step 5.2, calibrating image acquisition: the automatic high-precision calibration software sends a calibration starting command to the platform controller through the wireless transmission equipment and controls the rotary moving platform to rotate by a preset angle in sequence, and the automatic high-precision calibration software automatically identifies the state of the rotary moving platform and stores a stable and clear calibration image; the high-precision camera calibration system can adaptively adjust exposure and blur, improve the quality of acquired images, sequentially move to a preset optimal calibration angle through the rotary moving platform, calculate data such as camera internal parameters and distortion coefficients according to the acquired calibration images and realize an automatic camera calibration process.
Compared with the prior art, the full-automatic camera calibration system and the method thereof for adaptively adjusting the brightness and the ambiguity have the following beneficial effects:
1. the invention provides a full-automatic camera calibration system and a full-automatic camera calibration method for adaptively adjusting brightness and ambiguity, which can simplify the camera calibration process, enable the calibration positions to rotate in sequence, save interference caused by human factors, and save a large amount of labor and cost.
2. The invention provides a full-automatic camera calibration system and a method for adaptively adjusting brightness and ambiguity.
3. The invention provides a full-automatic camera calibration system and a full-automatic camera calibration method capable of adaptively adjusting brightness and ambiguity.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without any creative effort.
Fig. 1 is a flowchart of a full-automatic camera calibration method for adaptively adjusting brightness and blur degree according to the present invention.
Fig. 2 is a flow chart of the fully automatic camera calibration system for adaptively adjusting brightness and ambiguity according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the following examples:
as shown in figures 1 and 2, a full-automatic camera calibration system for adaptively adjusting brightness and ambiguity comprises fixing a monocular camera at a certain position, arranging a rotary moving platform and a platform motion controller below the corresponding monocular camera, supporting a circle center calibration plate by the rotary moving platform, calculating an initial position by the distance of the rotary moving platform through the working distance of the camera, acquiring the current circle center calibration plate image by the monocular camera and transmitting the image back to an automatic high-precision calibration software, displaying the acquired current image on a display device, improving the image quality by adjusting parameters such as camera gain and acquisition mode on line by the automatic high-precision calibration software, extracting a rectangular area from the adjusted image acquisition calibration plate area and converting the size ratio of the area with black and white color into 1:2, adaptively adjusting an exposure value by the average gray level of the rectangular area, and performing circle detection on the image with proper brightness by an EDcircle algorithm, edge gray points in four directions of the characteristic circle are extracted, a gray point fitting curve is fitted, the average slope of the gray points is calculated to represent the current fuzzy condition of the image, the average slope is fed back to the platform controller to control the rotary moving platform to adjust the distance in the Z direction so as to realize self-adaptive adjustment of the fuzzy degree, then the platform motion controller controls the rotary moving platform to move to a preset optimal pose group through a preset instruction, the achievable poses comprise a pitching pose, a yawing pose, a rolling pose and an adjustment distance camera distance (distance in the Z direction), and the rotary moving platform supports the calibration plate to finish high-precision calibration of the camera;
the calibration system comprises a monocular camera, a rotary moving platform, a platform motion controller, a circle center calibration plate, wireless transmission equipment, a processor, display equipment and automatic high-precision calibration software;
the monocular camera is mainly used for collecting images of the calibration plate switched by the rotary moving platform, and the initial position of the camera is ensured to be right above the rotary moving platform. In the embodiment, the camera is a large constant MER-503-20GM-P camera, the resolution is 2448(H) 2048(V), the frame rate is 20fps, and the data interface is Gige;
the rotary moving platform is mainly used for adjusting the pose of the circle center calibration plate, in the embodiment, the motor is an R140 square motor, and the no-load current is 600 mA;
the platform motion controller is mainly used for controlling the rotary moving platform to switch the pose, sending a calibration starting command through high-precision camera calibration software by an operator through presetting the position of the best calibration plate pose, controlling the rotary moving platform to rotate to the preset position one by one through the platform motion controller, and automatically identifying the pose and storing an image through the switching condition of the rotary moving platform by the camera for calibration calculation. STM32 chooses for use STM32F103ZET6 in this embodiment, and the wireless transmission module receiving end is 433 wireless receiving module and TTL changes RS485 module.
And the circle center calibration plate is used for calibrating the calculated image by the camera, and extracting the three-dimensional coordinates of the world coordinate system of the calibration plate and the two-dimensional coordinates of the image coordinate system through different positions and postures of the circle center calibration plate to realize camera calibration. In this embodiment, the circle center calibration plate is made of ceramic material;
and the wireless transmission equipment is used for sending a command for controlling the platform motion controller and sending a corresponding command to the motion controller through the wireless transmission equipment according to the operating condition of the high-precision camera calibration software. The wireless transmission device used in this embodiment is a 433 wireless transmission module;
the processor is mainly used for realizing data acquisition, storage and internal reference calibration methods and providing a carrier for internal reference calibration software; in the embodiment, the processor is a personal computer;
the display equipment is mainly used for operating the high-precision camera calibration software by an operator and displaying image information acquired by the camera in real time; in the embodiment, the display device is a 21-inch liquid crystal display screen;
the automatic calibration software comprises a function setting area, a function view area, a display view area and a self-adaptive fuzzy degree judgment algorithm; the function setting area is mainly divided into two functions of camera parameter setting and camera calibration, the camera parameter part is mainly used for setting basic parameters of the camera, the camera parameters are set under the condition sensed by human eyes, and the main function is to obtain the model of the currently used camera and display the model in an interface; setting a camera exposure value, wherein the range of the exposure value is 20-1000000; setting gain, and the gain range is not limited; and setting an automatic white balance function, automatically identifying the white balance function according to the camera type, and automatically closing a white balance option by the black and white camera. The camera calibration part is mainly used for calibrating the camera, providing the function of turning on/off the camera and controlling the running state of the camera; providing a pose adjusting function, controlling the rotary platform to carry out fine adjustment on the pose, and setting the rotary speed of the rotary platform, 1-6 preset positions and a guarding position; providing a text and image guidance function, and helping an operator to know and skillfully master the calibration step as soon as possible according to the text and image display step operation; providing an automatic image acquisition function, automatically identifying the rotation-to-position condition of the preset position of the rotary platform according to the state of the rotary platform and acquiring a current stable clear image; providing an automatic calibration function, performing calibration calculation according to the currently stored calibration image to obtain data such as camera internal parameters and distortion coefficients, and storing the data in a document;
the function view area is mainly used for displaying all functions of the switching part of the function setting area, the function setting is automatically stored in the database, the last stored content is automatically read when the function setting area is opened next time, and the function view area has the function of setting automatic storage;
and the display view area is mainly used for displaying the image acquired by the current camera, and the effect changed through the function setting area is presented in the display view.
The full-automatic camera calibration method for adaptively adjusting brightness and ambiguity comprises the following steps:
step 1, calculating an initial position of a rotary moving platform, knowing that a camera has a working distance in a certain range according to an aperture imaging model, and estimating a focal length f to solve the initial position WD of the rotary moving platform through a distance formula because the focal length of the current camera cannot be known;
step 2, setting camera parameters, switching to a camera parameter interface through a function setting area, acquiring the model and the current image of the camera, setting the working state of the camera, setting a camera acquisition mode and automatic white balance, and manually and coarsely adjusting an exposure value and a camera gain according to the field environment, so that the quality of the acquired image is improved; in the embodiment, the model of the camera is MER-503-20GM-P, the working state of the camera is set to be the acquisition starting mode, the acquisition mode of the camera is set to be the continuous acquisition mode, automatic white balance is forbidden, the rough adjustment exposure value is 45000, and the gain of the camera is set to be 1;
step 3, adjusting exposure in a self-adaptive manner, wherein the colors of the circle center calibration plate are composed of black and white, the calibration plate is positioned right below the lens, and the number ratio R of the black and white pixels in the rectangular region with the fixed size at the center of the image is countednRatio R according to the number of black and white pixels having moderate luminanceoFor the current statistical fixed-area proportion RnConverting the number ratio of black and white pixels, and calculating the average gray value G of the current regionavecAdjusting the exposure E in a self-adaptive manner according to the average gray value;
step 3, self-adaptive exposure adjustment, wherein the function is realized through the following steps:
step 3.1, calculating the rectangular areaInner average gray value: selecting a rectangular area R with a certain area in the circle center calibration plate area, and setting the number ratio of standard black and white pixels as RoCalculating the ratio R of the current black and white numbersnAnd based on RoCalculating black and white compensation parameters B of current areacAnd WcAnd converting the current quantity ratio of black and white into the value consistent with the set standard value through the compensation parameters, thereby obtaining the average gray value after the compensation parameters are added. The pixel number ratio R of standard black and white is defined in this embodimento1:2, the black and white numbers R of the current area are selectednThe ratio is 3:4, thus compensating for the parameter BcAnd Wc7/9 and 7/6, wherein the compensation parameter BcAnd WcThe expression of (a) is:
mean gray value GavecThe expression formula is:
step 3.2, self-adaptive adjustment of exposure: collecting a series of luminance images from underexposure to overexposure and respectively solving the average gray value GavecAnd constructing the brightness distribution of the average gray value based on compensation and weight distribution, calculating the average gray value of the current selected area, deducing a brightness adjustment strategy based on the brightness distribution, and realizing self-adaptive adjustment of the exposure. Wherein the brightness adjustment strategy is:
step 4, adaptively adjusting the ambiguity, sequencing the feature circles on the circle center calibration plate, acquiring the gray values of the four azimuth edges of a plurality of specific feature circles, respectively performing curve fitting, solving the average slope of the gray values in each direction, comparing the average values of the slopes in the same direction in the plurality of circles, and removing the maximum value; calculating the average slope of edge points of a plurality of circles in a plurality of directions as an evaluation factor of the image blurring degree, and realizing self-adaptive adjustment of the blurring degree according to the evaluation factor;
step 4, self-adaptive fuzzy degree adjustment, wherein the function is realized through the following steps:
step 4.1, sorting the characteristic circles: detecting the characteristic circle of the image, removing the interference characteristic circle and the approximate circle, sorting the characteristic circles, and selecting a plurality of specific characteristic circles c1,c2,c3K is the processing object. In this embodiment, 3 feature circles are selected as processing objects;
step 4.2, evaluating indexes of the edge points: and counting edge points of the selected plurality of feature circles in four directions, deducing an edge point evaluation index according to the characteristic that the gray value gradient of continuous pixel points of the edge points is large and the gray value gradient change of internal pixel points and external pixel points of the feature circles is small, and screening the edge pixel points based on the edge point evaluation index. The expression of the edge point evaluation index is as follows:
step 4.3, calculating ambiguity evaluation indexes, performing polynomial fitting curve according to edge point pixel values of the multiple feature circles in four directions, calculating the slope of each edge point pixel value, and screening out the average slope with a larger difference value with the average slope of the edge point pixel values of other feature circles in the same direction, so as to calculate the average slope of the edge point pixel values of the multiple circles in multiple directions as the evaluation index of the image ambiguity; the expression of the ambiguity evaluation index is:
step 4.4, adaptively adjusting the ambiguity, judging the current image quality according to the ambiguity evaluation factor, and adjusting the distance between the camera and the circle center calibration plate by adaptively adjusting the ambiguity strategy of the image to realize the improvement of the image quality; the adaptive ambiguity adjustment expression is as follows:
adjusting distance between camera and marker by adaptive ambiguitynEvaluation of the change in the current after-movement ambiguity, tnDetermined according to the following relationship:
tn＝Kn-Kn-1
step 5, acquiring an optimal calibration angle, presetting a group of optimal calibration angles on a rotary moving platform and recording the optimal calibration angles in a platform motion controller, sending a calibration starting command to the platform motion controller by high-precision camera calibration software through wireless transmission equipment, rotating the preset poses one by the rotary moving platform, and acquiring stable and clear calibration images at different pose distances through a camera to obtain 18 calibration images in total;
step 5, obtaining the optimal calibration angle, and realizing the function through the following steps:
step 5.1, presetting an optimal calibration angle: and the distortion of the characteristic circle is caused by the overlarge inclination angle of the pitching and yawing rolling of the calibration plate, the optimal calibration angle is obtained through repeated verification of experiments, and the preset optimal calibration angle is recorded to the platform motion controller. In this embodiment, the number of the optimal calibration angles is set to 18, and the optimal calibration angles are collected in three groups, where each group includes six fixed poses: pitching 5 degrees of rolling-5 degrees, pitching 5 degrees of rolling-10 degrees, pitching-5 degrees of rolling-15 degrees, pitching 5 degrees of rolling-20 degrees, pitching 10 degrees of rolling-15 degrees, pitching 10 degrees of rolling-20 degrees; the three sets of calibration images are divided into: the distance between the first group of cameras and the pose rotating platform is 26.5cm, the distance between the second group of cameras and the pose rotating platform is 27cm, the distance between the third group of cameras and the pose rotating platform is 27cm, and the pose rotating platform yaws by 5 degrees;
step 5.2, calibrating image acquisition: the automatic high-precision calibration software sends a calibration starting command to the platform controller through the wireless transmission equipment and controls the rotary moving platform to rotate by a preset angle in sequence, and the automatic high-precision calibration software automatically identifies the state of the rotary moving platform and stores a stable and clear calibration image;
step 6, calibrating the camera, respectively acquiring the circle centers of the characteristic circles of the 18 calibrated images, calculating the internal reference and distortion coefficient of the camera according to a Zhang Zhengyou calibration method, generating a calibration log according to a data result, and storing the calibration log in a database, so that an operator can conveniently check and use the calibration log; in this embodiment, the distance between the centers of the circle center calibration plates is 4mm, and the camera internal reference matrix obtained by calculation through the camera Zhang Yongyou calibration method is:
[3.5357001241414760e+03,0,1.2380236993640738e+03,0,3.53570012414147 60e+03,1.0383782746050902e+03,0,0,1]
distortion coefficient of camera:
[-5.2923747789825483e-02,-8.5220782269244866e-01,-2.311892613131 5680e-06,6.5681051237872253e-04,3.6634495847923979e+01]
the reprojection error of the camera is 0.015, the calibration precision of the camera is high;
the high-precision camera calibration system can adaptively adjust exposure and ambiguity, improve the quality of acquired images, sequentially move to a preset optimal calibration angle through the rotary moving platform, calculate data such as camera internal parameters and distortion coefficients according to the acquired calibration images, and realize an automatic camera calibration process.
The above-mentioned embodiments are merely illustrative of the preferred embodiments of the present invention, and do not limit the scope of the present invention, and various modifications and improvements of the technical solution of the present invention by those skilled in the art without departing from the spirit of the present invention should fall within the protection scope defined by the appended claims.
Claims (6)
1. The full-automatic camera calibration system for adaptively adjusting brightness and ambiguity is characterized in that: the system mainly comprises a monocular camera, a rotary moving platform, a platform motion controller, a circle center calibration plate, wireless transmission equipment, a processor, display equipment and automatic high-precision calibration software; the calibration system comprises: the monocular camera is fixed at a certain position, a rotary moving platform is arranged below the corresponding camera, the distance between the rotary moving platform and the camera calculates an initial value through a working distance, the platform motion controller drives a calibration plate supported by the rotary moving platform to pitch, yaw and roll and adjusts the distance between the calibration plate and the camera, and the monocular camera shoots images of the circle center calibration plate at different poses to finish camera calibration;
a rotary moving platform and a platform motion controller are arranged below the monocular camera, the rotary moving platform supports a circle center calibration plate, the distance between the rotary moving platform and the camera calculates an initial value through a working distance, the monocular camera collects the image of the current circle center calibration plate and transmits the image back to automatic high-precision calibration software, the current image is displayed on a display device, parameters such as camera gain, collection mode and the like are adjusted on line through the automatic high-precision calibration software to improve the image quality, a rectangular area of the adjusted image is extracted, the size ratio of a black area and a white area is converted into 1:2, an exposure value is adjusted in a self-adaptive mode through the average gray level of the rectangular area, the image with proper brightness is subjected to circle detection through an EDcircle algorithm, edge gray level points in four directions of a characteristic circle are extracted, a gray level point fitting curve is fitted, and the average slope of the gray level points is calculated to represent the fuzzy condition of the image, and the feedback is sent to a platform controller to control the rotary moving platform to adjust the distance in the Z direction so as to realize the self-adaptive adjustment of the ambiguity;
the platform motion controller controls the rotary moving platform to adjust to a preset optimal pose group through a preset instruction, the achieved poses comprise a pitching pose, a yawing pose, a rolling pose and an adjusting distance from the camera, and the rotary moving platform supports the calibration plate to move so as to achieve high-precision calibration of the camera.
2. The full-automatic camera calibration system for adaptively adjusting brightness and blur degree according to claim 1, wherein: the monocular camera consists of a camera and a lens and is used for acquiring images of the calibration plate switched by the rotary moving platform, and the initial position of the camera is ensured to be right above the rotary moving platform;
the rotary moving platform is a mechanical structure with four degrees of freedom, each degree of freedom is adjusted by a motor, the motors are uniformly controlled by a platform motion controller, the angle switching and the distance adjustment between the pitch attitude, the yaw attitude and the roll attitude can be realized, and the rotary moving platform is mainly used for adjusting the pose of a circle center calibration plate;
the platform motion controller takes a stm32 development board as a core, is connected with a motor on a rotary moving platform through a connecting wire, is connected with a receiving end of a wireless transmission module at the other end stm32 and is mainly used for controlling the rotary moving platform to switch the pose, an operator sends a calibration starting command through high-precision camera calibration software by presetting the position of the best calibration board pose, the platform motion controller controls the rotary moving platform to rotate to the preset position one by one, and the camera automatically identifies the pose through the switching condition of the rotary moving platform and stores an image for calibration calculation;
the circle center calibration plate is used for calibrating the calculated image by the camera, and extracting the three-dimensional coordinates of the world coordinate system of the calibration plate and the two-dimensional coordinates of the image coordinate system through different positions and postures of the circle center calibration plate to realize camera calibration;
the wireless transmission equipment is used for sending a command of the motion controller of the control platform and sending a corresponding command to the motion controller through the wireless transmission equipment according to the operating condition of the high-precision camera calibration software;
the processor is used for realizing data acquisition, storage and internal reference calibration methods and providing a carrier for internal reference calibration software;
the display equipment is used for operating the high-precision camera calibration software by an operator and displaying image information acquired by the camera in real time;
the automatic calibration software comprises a function setting area, a function view area, a display view area and a high-precision calibration algorithm; the function setting area provides two functions required by camera calibration, namely camera parameter setting and camera calibration, and an operator can select the functions according to actual conditions; the function view area displays the selected calibration function in a specific way; and the display view area is used for displaying the image acquired by the camera.
3. The full-automatic camera calibration method for adaptively adjusting brightness and ambiguity comprises the following steps:
step 1, calculating an initial position of a rotary moving platform, knowing that a camera has a working distance in a certain range according to a pinhole imaging model, and estimating a focal length f to solve the initial position WD of the rotary moving platform through a distance formula because the focal length of the current camera cannot be known;
step 2, setting camera parameters, switching to a camera parameter interface through a function setting area, acquiring the model and the current image of the camera, setting the working state of the camera, setting a camera acquisition mode and automatic white balance, and manually and coarsely adjusting an exposure value and a camera gain according to the field environment, so that the quality of the acquired image is improved;
step 3, adjusting exposure in a self-adaptive manner, wherein the colors of the circle center calibration plate are composed of black and white, the calibration plate is positioned right below the lens, and the number ratio R of the black and white pixels in the rectangular region with the fixed size at the center of the image is countednRatio R according to the number of black and white pixels having moderate luminanceoFor the current statistical fixed region internal ratio RnConverting the quantity ratio of black pixels to white pixels, solving the average gray value of the current area, and adaptively adjusting the exposure according to the average gray value;
step 4, adaptively adjusting the ambiguity, sequencing the feature circles on the circle center calibration plate, acquiring the gray values of the four azimuth edges of a plurality of specific feature circles, respectively performing curve fitting, solving the average slope of the gray values in each direction, comparing the average value of the slopes in the same direction in the plurality of circles and removing the maximum value; calculating the average slope of edge points of a plurality of circles in a plurality of directions as an evaluation factor of the image blurring degree, and realizing self-adaptive adjustment of the blurring degree according to the evaluation factor;
step 5, acquiring an optimal calibration angle, presetting a group of optimal calibration angles on a rotary moving platform and recording the optimal calibration angles in a platform motion controller, sending a calibration starting command to the platform motion controller by high-precision camera calibration software through wireless transmission equipment, rotating the preset poses one by the rotary moving platform, and acquiring stable and clear calibration images at different pose distances by a camera to count 18 calibration images;
and 6, calibrating the camera, respectively acquiring the circle centers of the characteristic circles of the 18 calibrated images, calculating the internal reference and distortion coefficient of the camera according to a Zhang Zhengyou calibration method, generating a calibration log according to a data result, and storing the calibration log in a database, so that an operator can conveniently check and use the calibration log.
4. The full-automatic camera calibration method for adaptively adjusting brightness and blur degree according to claim 3, wherein in step 3, the exposure degree is adaptively adjusted by the following steps:
step 3.1, calculating the average gray value in the rectangular area: selecting a rectangular area with a certain area in the circle center calibration plate area, and setting the quantity ratio of standard black to white as RoCalculating the current black and white quantity ratio RnAnd based on RoCalculating black and white compensation parameters B of current areacAnd WcConverting the quantity ratio of the current black and white into the value consistent with the set standard value through the compensation parameter, thereby obtaining the average gray value after the compensation parameter is added; wherein the compensation parameter BcAnd WcThe expression of (a) is:
wherein, b and bnRepresenting the number of pixels whose values are the standard ratio and black in the nth-order specific region, w and wnExpressing the number of pixels whose values are the standard ratio and white in the nth-time specific area;
mean gray value GavecThe expression formula is:
wherein A isbWeight coefficient representing black area, AwThe weight coefficient A of the black area is increased because the gray value of the black area is much smaller than that of the white areabThe average gray value has more obvious change when the brightness changes;
step 3.2, self-adaptive adjustment of exposure: collecting a series of luminance images from underexposure to overexposure and respectively solving the average gray value GavecThe brightness distribution of the average gray value based on compensation and weight distribution is established, the average gray value of the current selected area is calculated, and a brightness adjustment strategy is deduced based on the brightness distribution, so that the self-adaptive adjustment of the exposure is realized; the brightness adjustment strategy is as follows:
wherein E represents the modified exposure value, L represents the brightness case, KLRepresenting the exposure adjustment coefficient, the average gray value G of the current acquisition regionavec,GupAnd GunderRepresenting the average gray value representing the appropriate upper and lower limits of luminance in the rectangular region; by correcting the value E, the brightness is adjusted in a self-adaptive mode, and a clear calibration image is obtained.
5. The full-automatic camera calibration method for adaptively adjusting brightness and blur degree according to claim 3, wherein in the step 4, the adaptive blur degree is adjusted by the following steps:
step 4.1, sorting the characteristic circles: detecting a feature circle of the image, removing an interference feature circle and an approximate circle, sequencing the feature circles, and selecting a plurality of specific feature circles as processing objects;
step 4.2, evaluating indexes of the edge points: counting edge points of the selected multiple feature circles in four directions, deriving edge point evaluation indexes according to different gray value change characteristics of the edge points and internal pixel points and external pixel points of the feature circles, and screening out edge pixel points based on the edge point evaluation indexes; the expression of the edge point evaluation index is as follows:
wherein M isnIndicates whether n points are edge point evaluation indexes, GnA grayscale value representing the nth point, d represents a step size;
step 4.3, calculating ambiguity evaluation indexes, namely performing polynomial fitting curve according to edge point pixel values of a plurality of feature circles in four directions, calculating the slope of each edge point pixel value, and screening out the average slope with a larger difference value with the average slope of the edge point pixel values of other feature circles in the same direction, so that the average slope of the edge point pixel values of the plurality of circles in the plurality of directions is calculated and used as the evaluation index of the image ambiguity; the expression of the ambiguity evaluation index is:
wherein m is the number of edge points, Y is an expression of edge point pixel values subjected to polynomial fitting, z represents the direction of the edge points, and i represents the number of acquired characteristic circle circles;
step 4.4, adaptively adjusting the ambiguity, judging the current image quality according to the ambiguity evaluation factor, and adjusting the distance between the camera and the circle center calibration plate by adaptively adjusting the ambiguity strategy of the image to realize the improvement of the image quality; the adaptive ambiguity adjustment expression is as follows:
wherein D isnIndicates the direction of the moving distance of the camera, AkAnd KoRepresenting fixed coefficients and imagesClear threshold, tnExpressing directional weight, adaptive ambiguity adjusting distance between camera and marker, tnEvaluation of the change in the current after-movement ambiguity, tnDetermined according to the following relationship:
tn＝Kn-Kn-1
wherein, KnRepresenting the blur degree evaluation factor of the nth image.
6. The full-automatic camera calibration method for adaptively adjusting brightness and blur degree according to claim 3, wherein the step 5 comprises the following steps:
step 5.1, presetting an optimal calibration angle: the characteristic circle is distorted due to the fact that the inclination angle of the calibration plate in pitching yawing rolling is too large, the optimal calibration angle is obtained through repeated verification through experiments, the preset optimal calibration angle is recorded to the platform motion controller, the number of the optimal calibration angles is set to be 18, the optimal calibration angles are collected in three groups, and each group is six fixed poses: pitching 5 degrees of rolling-5 degrees, pitching 5 degrees of rolling-10 degrees, pitching-5 degrees of rolling-15 degrees, pitching 5 degrees of rolling-20 degrees, pitching 10 degrees of rolling-15 degrees, pitching 10 degrees of rolling-20 degrees; the three sets of calibration images are divided into: the distance between the first group of cameras and the pose rotating platform is WD + DnThe distance between the second group of cameras and the pose rotating platform is WD + Dn+WD1The distance between the third group of cameras and the pose rotating platform is WD + Dn+WD1And the pose rotating platform drifts by 5 degrees, wherein DnIndicating the distance moved by the adaptive adjustment of the ambiguity, WD1Represents one fifth of the distance of the current lens depth of field;
step 5.2, calibrating image acquisition: the automatic high-precision calibration software sends a calibration starting command to the platform controller through the wireless transmission equipment and controls the rotary moving platform to rotate by a preset angle in sequence, and the automatic high-precision calibration software automatically identifies the state of the rotary moving platform and stores a stable and clear calibration image; the high-precision camera calibration system can adaptively adjust exposure and blur, improve the quality of acquired images, sequentially move to a preset optimal calibration angle through the rotary moving platform, calculate data such as camera internal parameters and distortion coefficients according to the acquired calibration images, and realize an automatic camera calibration process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111527480.3A CN114708326A (en) | 2021-12-14 | 2021-12-14 | Full-automatic camera calibration system and method for adaptively adjusting brightness and ambiguity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111527480.3A CN114708326A (en) | 2021-12-14 | 2021-12-14 | Full-automatic camera calibration system and method for adaptively adjusting brightness and ambiguity |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114708326A true CN114708326A (en) | 2022-07-05 |
Family
ID=82167701
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111527480.3A Pending CN114708326A (en) | 2021-12-14 | 2021-12-14 | Full-automatic camera calibration system and method for adaptively adjusting brightness and ambiguity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114708326A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115604572A (en) * | 2022-09-02 | 2023-01-13 | 荣耀终端有限公司（Cn） | Image acquisition method and device |
| CN116229037A (en) * | 2023-04-24 | 2023-06-06 | 深圳锐盟半导体有限公司 | Image recognition method, system, device and storage medium |
| CN116338707A (en) * | 2023-05-31 | 2023-06-27 | 深圳玩智商科技有限公司 | Exposure adjustment method, device, apparatus, and computer-readable storage medium |
-
2021
- 2021-12-14 CN CN202111527480.3A patent/CN114708326A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115604572A (en) * | 2022-09-02 | 2023-01-13 | 荣耀终端有限公司（Cn） | Image acquisition method and device |
| CN115604572B (en) * | 2022-09-02 | 2023-12-01 | 荣耀终端有限公司 | Image acquisition method, electronic device and computer readable storage medium |
| CN116229037A (en) * | 2023-04-24 | 2023-06-06 | 深圳锐盟半导体有限公司 | Image recognition method, system, device and storage medium |
| CN116338707A (en) * | 2023-05-31 | 2023-06-27 | 深圳玩智商科技有限公司 | Exposure adjustment method, device, apparatus, and computer-readable storage medium |
| CN116338707B (en) * | 2023-05-31 | 2023-08-11 | 深圳玩智商科技有限公司 | Exposure adjustment method, device, apparatus, and computer-readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114708326A (en) | Full-automatic camera calibration system and method for adaptively adjusting brightness and ambiguity | |
| CN108436909A (en) | A kind of hand and eye calibrating method of camera and robot based on ROS | |
| CN110660107A (en) | Plane calibration plate, calibration data acquisition method and system | |
| CN110889829B (en) | Monocular distance measurement method based on fish eye lens | |
| CN107869954B (en) | Binocular vision volume weight measurement system and implementation method thereof | |
| CN106570938A (en) | OPENGL based panoramic monitoring method and system | |
| CN104760812B (en) | Product real-time positioning system and method on conveyer belt based on monocular vision | |
| CN110281240B (en) | Method and system for positioning and picking up glass of liquid crystal display screen and vision processing system | |
| CN109079788B (en) | Chess playing method based on humanoid robot and humanoid robot | |
| CN109191520B (en) | Plant leaf area measuring method and system based on color calibration | |
| US20190162508A1 (en) | Automatic deviation correction method | |
| CN111127561A (en) | Multi-view image calibration device and method | |
| CN113793270A (en) | Aerial image geometric correction method based on unmanned aerial vehicle attitude information | |
| CN109409290A (en) | A kind of thermometer calibrating reading automatic recognition system and method | |
| CN111693969A (en) | Combined calibration device and method for laser radar and camera | |
| CN208254424U (en) | A kind of laser blind hole depth detection system | |
| CN114820817A (en) | Calibration method and three-dimensional reconstruction method based on high-precision line laser 3D camera | |
| CN113298886A (en) | Calibration method of projector | |
| CN114371472A (en) | Automatic combined calibration device and method for laser radar and camera | |
| CN112911270A (en) | Image correction method for 100% offset three-dimensional sliced projection imaging system | |
| WO2021134219A1 (en) | Parameter calibration method and apapratus | |
| CN116125489A (en) | Indoor object three-dimensional detection method, computer equipment and storage medium | |
| CN112361989B (en) | Method for calibrating parameters of measurement system through point cloud uniformity consideration | |
| CN115767253A (en) | Method and device for adaptively adjusting camera exposure parameters and marker identification threshold | |
| CN114581506A (en) | Parallel algorithm for accurately calculating height by combining two-dimensional information and three-dimensional information |
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 |