Three-dimensional high-speed vibration target clear image acquisition method, system and medium

Abstract

The application provides a three-dimensional high-speed vibration target clear image acquisition method, system and medium, the method comprising: collecting vibration target images based on a high-speed camera, preprocessing the vibration target images, and extracting target contours; analyzing target center points based on the target contours, measuring three-dimensional position information of the target center points at different time nodes based on a laser displacement meter; analyzing plane vibration information and depth vibration information of the target based on the three-dimensional position information of the target center points at different time nodes; fusing and processing the plane vibration information and the depth vibration information to generate three-dimensional vibration state information of the target; adjusting the viewing angle and focal length of the high-speed camera based on the three-dimensional vibration state information of the target to obtain a clear image of the target; and dynamically zooming and adjusting the angle of the high-speed camera to track high-speed vibration of a complex shape target at a high magnification and acquire a clear image.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of robot parameter calibration, in particular to a three-dimensional high-speed vibration target clear image acquisition method, system and medium. BACKGROUND

[0002] In the manufacturing industry, the automation of precision visual inspection is crucial. However, when observing small objects, the vibration effect of the object cannot be ignored, especially at high magnification, vibration will cause image blur and defocus. Existing visual inspection systems usually cannot handle complex shape targets at high magnification and high frequency vibration at the same time, resulting in low detection accuracy and efficiency. In addition, the existing high-speed visual system has the problems of image detail loss, insufficient contrast and the like when processing complex shape targets at high magnification. SUMMARY

[0003] The purpose of the embodiments of the present application is to provide a three-dimensional high-speed vibration target clear image acquisition method, system and medium, which can track high-speed vibration of complex shape targets at high magnification and acquire clear images through dynamic zoom and angle adjustment of a high-speed camera.

[0004] The embodiments of the present application also provide a three-dimensional high-speed vibration target clear image acquisition method, comprising:

[0005] Based on the high-speed camera, vibration target images are collected, the vibration target images are preprocessed, and target contours are extracted;

[0006] Based on the target contour, the target center point is analyzed, and the three-dimensional position information of the target center point at different time nodes is measured based on the laser displacement meter;

[0007] Based on the three-dimensional position information of the target center point at different time nodes, the planar vibration information and the depth vibration information of the target are analyzed;

[0008] The planar vibration information and the depth vibration information are fused and processed to generate three-dimensional vibration state information of the target;

[0009] Based on the three-dimensional vibration state information of the target, the viewing angle and focal length of the high-speed camera are adjusted to obtain a clear target image.

[0010] Optionally, in the three-dimensional high-speed vibration target clear image acquisition method described in the embodiments of the present application, based on the high-speed camera, vibration target images are collected, the vibration target images are preprocessed, and target contours are extracted, specifically comprising:

[0011] The vibration target image is obtained, the vibration target image is smoothed based on a Gaussian filter, image noise is removed, and a denoised image is obtained;

[0012] Set a binary threshold, and binarize the denoised image to obtain the contrast of the denoised image;

[0013] Determine the contrast and the set contrast threshold interval to obtain an analysis result, dynamically adjust the binary threshold based on the analysis result, and obtain a preprocessed image;

[0014] Search for the edge pixels of the target in the preprocessed image based on an edge detection algorithm;

[0015] Connect the edge pixels into a complete contour based on a contour tracking algorithm to obtain a target contour.

[0016] Optionally, in the three-dimensional high-speed vibration target clear image acquisition method described in the embodiments of the present application, the target center point is analyzed based on the target contour, and the three-dimensional position information of the target center point at different time nodes is measured based on the laser displacement meter, specifically including:

[0017] Obtain the target contour, and calculate the minimum circumscribed rectangle of the target contour;

[0018] Diagonal line processing is performed on the minimum circumscribed rectangle to obtain the intersection point of the diagonal lines;

[0019] Based on the intersection point of the diagonal lines, the center point of the minimum circumscribed rectangle is obtained, and the coordinates of the center point are calculated;

[0020] The coordinate values of the center point coordinates are analyzed based on the laser displacement meter to obtain the three-dimensional position information of the target center point.

[0021] Optionally, in the three-dimensional high-speed vibration target clear image acquisition method described in the embodiments of the present application, the planar vibration information and the depth vibration information of the target are analyzed based on the three-dimensional position information of the target center point at different time nodes, specifically including:

[0022] Obtain the three-dimensional position information of the target center point at different time nodes;

[0023] Based on the three-dimensional position information, planar coordinates under different planes are extracted to obtain corresponding planar coordinate points;

[0024] The planar coordinate points are plotted in a planar coordinate system to generate a motion trajectory graph of the target center point on the plane;

[0025] Based on the motion trajectory graph, the vibration amplitudes of the target center in the X-axis and Y-axis directions are analyzed;

[0026] Based on the Fourier transform method, the planar coordinate points are subjected to frequency spectrum analysis to obtain frequency distribution information;

[0027] Based on the vibration amplitudes in the X-axis and Y-axis directions, the planar vibration information of the target is obtained, and based on the frequency distribution information, the depth vibration information is obtained.

[0028] Optionally, in the three-dimensional high-speed vibration target clear image acquisition method, the planar vibration information and the depth vibration information are fused and processed to generate three-dimensional vibration state information of the target, and the method specifically comprises the following steps:

[0029] The planar vibration information is acquired, the vibration amplitude is analyzed, and the vibration amplitude feature is extracted;

[0030] The depth vibration information is acquired, the vibration frequency and phase are analyzed based on the depth vibration information, and the frequency feature is obtained;

[0031] The influence degree of the vibration state is analyzed based on the vibration amplitude feature and the frequency feature, and the weighting coefficient corresponding to the vibration amplitude and the vibration frequency is obtained;

[0032] Different weight values are matched based on the weighting coefficient, the vibration amplitude feature and the frequency feature are weighted and fused according to the weight values, and the three-dimensional vibration state information of the target is obtained.

[0033] Optionally, in the three-dimensional high-speed vibration target clear image acquisition method, the view angle and the focal length of the high-speed camera are adjusted based on the three-dimensional vibration state information of the target, and a clear target image is obtained, and the method specifically comprises the following steps:

[0034] The distance information between the target and the high-speed camera is measured based on the laser displacement meter;

[0035] The fluctuation state information of the distance information is analyzed based on the three-dimensional vibration state information of the target;

[0036] The view angle and the focal length of the high-speed camera are adjusted based on the fluctuation state information, and an adjusted image is acquired;

[0037] The image edge information is extracted based on the edge detection algorithm, and the definition of the image edge information is analyzed;

[0038] The view angle and the focal length are feedback adjusted based on the definition of the image edge information, and a clear target image is obtained.

[0039] In a second aspect, the embodiments of the present application provide a three-dimensional high-speed vibration target clear image acquisition system, which comprises a memory and a processor, the memory comprises a three-dimensional high-speed vibration target clear image acquisition method program, and the three-dimensional high-speed vibration target clear image acquisition method program is executed by the processor to realize the following steps:

[0040] The vibration target image is preprocessed based on the high-speed camera, and the target contour is extracted;

[0041] The target center point is analyzed based on the target contour, and the three-dimensional position information of the target center point at different time nodes is measured based on the laser displacement meter;

[0042] The three-dimensional position information of the target center point at different time nodes is analyzed to obtain the planar vibration information and the depth vibration information of the target;

[0043] The planar vibration information and the depth vibration information are fused to generate three-dimensional vibration state information of the target;

[0044] The three-dimensional vibration state information of the target is used to adjust the view angle and the focal length of the high-speed camera to obtain a clear image of the target.

[0045] Optionally, in the three-dimensional high-speed vibration target clear image acquisition system, the vibration target image is preprocessed based on the high-speed camera collecting the vibration target image, and the target contour is extracted, and the preprocessing specifically includes:

[0046] The vibration target image is obtained, and the vibration target image is smoothed based on a Gaussian filter to remove image noise and obtain a denoised image;

[0047] A binary threshold is set, the denoised image is binarized, and the contrast of the denoised image is obtained;

[0048] The contrast is compared with the set contrast threshold interval to obtain an analysis result, the binary threshold is dynamically adjusted based on the analysis result, and a preprocessed image is obtained;

[0049] Edge pixels of the target in the preprocessed image are searched based on an edge detection algorithm;

[0050] The edge pixels are connected into a complete contour based on a contour tracking algorithm to obtain the target contour.

[0051] Optionally, in the three-dimensional high-speed vibration target clear image acquisition system, the target center point is analyzed based on the target contour, and the three-dimensional position information of the target center point at different time nodes is measured based on a laser displacement meter, and the measurement specifically includes:

[0052] The target contour is obtained, and a minimum circumscribed rectangle of the target contour is calculated;

[0053] The minimum circumscribed rectangle is processed by diagonal lines to obtain a diagonal intersection point;

[0054] The center point of the minimum circumscribed rectangle is obtained based on the diagonal intersection point, and the center point coordinates are calculated;

[0055] The coordinate values of the center point coordinates are analyzed based on the laser displacement meter to obtain the three-dimensional position information of the target center point.

[0056] In a third aspect, the embodiments of the present application further provide a computer readable storage medium, which comprises a three-dimensional high-speed vibration target clear image acquisition method program. When the three-dimensional high-speed vibration target clear image acquisition method program is executed by a processor, the steps of the three-dimensional high-speed vibration target clear image acquisition method according to any one of the above embodiments are implemented.

[0057] As can be seen from the above, the three-dimensional high-speed vibration target clear image acquisition method, system and medium provided by the embodiments of the present application can collect vibration target images based on a high-speed camera, pre-process the vibration target images, and extract target contours; analyze target center points based on the target contours, measure three-dimensional position information of the target center points at different time nodes based on a laser displacement meter; analyze planar vibration information and depth vibration information of the target based on the three-dimensional position information of the target center points at different time nodes; fuse process the planar vibration information and the depth vibration information to generate three-dimensional vibration state information of the target; adjust the angle of view and the focal length of the high-speed camera based on the three-dimensional vibration state information of the target to obtain a target clear image; and through dynamic zooming and angle adjustment of the high-speed camera, high-speed vibration tracking of a complex shape target can be performed at a high magnification, and a clear image can be obtained. BRIEF DESCRIPTION OF DRAWINGS

[0058] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments of the present application. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0059] Figure 1 A flowchart of the three-dimensional high-speed vibration target clear image acquisition method provided by the embodiments of the present application;

[0060] Figure 2 A target contour extraction method flowchart of the three-dimensional high-speed vibration target clear image acquisition method provided by the embodiments of the present application;

[0061] Figure 3 A three-dimensional position information acquisition method flowchart of the three-dimensional high-speed vibration target clear image acquisition method provided by the embodiments of the present application;

[0062] Figure 4 A system composition schematic diagram of the three-dimensional high-speed vibration target clear image acquisition method provided by the embodiments of the present application;

[0063] Figure 5 A target tracking schematic diagram of the three-dimensional high-speed vibration target clear image acquisition method provided by the embodiments of the present application;

[0064] Figure 6 A clear image acquisition diagram of the three-dimensional high-speed vibration target clear image acquisition method provided by the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0065] The technical solutions in the embodiments of the present application will be clearly and completely described in connection with the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. The components of the embodiments of the present application described and shown in the accompanying drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0066] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. Meanwhile, in the description of the present application, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0067] Please refer to Figure 1 , Figure 1 is a flowchart of a three-dimensional high-speed vibration target clear image acquisition method in some embodiments of the present application. The three-dimensional high-speed vibration target clear image acquisition method is used in a terminal device. The three-dimensional high-speed vibration target clear image acquisition method comprises the following steps:

[0068] S101, based on a high-speed camera collecting a vibration target image, pre-processing the vibration target image, and extracting a target contour;

[0069] S102, analyzing a target center point based on the target contour, and measuring three-dimensional position information of the target center point at different time nodes based on a laser displacement meter;

[0070] S103, analyzing the planar vibration information and the depth vibration information of the target based on the three-dimensional position information of the target center point at different time nodes;

[0071] S104, fusing and processing the planar vibration information and the depth vibration information to generate three-dimensional vibration state information of the target;

[0072] S105, adjusting the viewing angle and focal length of the high-speed camera based on the three-dimensional vibration state information of the target to obtain a target clear image.

[0073] It should be noted that a high-speed camera is used in combination with a macro lens to collect images of the target. The high-speed camera can quickly capture the dynamic changes of the target, and the macro lens can achieve high magnification to clearly present the details of the target. During the collection process, the frame rate, exposure time and other parameters of the camera should be reasonably set according to the motion speed and size of the target. For example, for a fast-moving target, the frame rate should be increased to avoid motion blur; for a small target, the magnification advantage of the macro lens should be fully utilized, and the focal length and working distance should be adjusted to track the three-dimensional vibration of the target in real time and obtain clear images, and output clear images at high magnification for subsequent visual detection and analysis.

[0074] Please refer to Figure 2 , Figure 2 is a target contour extraction method flowchart of a three-dimensional high-speed vibration target clear image acquisition method in some embodiments of the present application. According to the embodiment of the present application, the vibration target image is collected based on a high-speed camera, the vibration target image is preprocessed, the target contour is extracted, and specifically includes:

[0075] S201, acquiring a vibration target image, performing smoothing processing on the vibration target image based on a Gaussian filter, eliminating image noise, and obtaining a denoising image;

[0076] S202, setting a binary threshold, performing binary processing on the denoising image, and obtaining a contrast of the denoising image;

[0077] S203, judging the contrast and the set contrast threshold interval to obtain an analysis result, dynamically adjusting the binary threshold based on the analysis result, and obtaining a preprocessed image;

[0078] S204, searching for edge pixels of the target in the preprocessed image based on an edge detection algorithm;

[0079] S205, connecting the edge pixels into a complete contour based on a contour tracking algorithm to obtain a target contour.

[0080] It should be noted that the collected image is preprocessed, including smoothing processing and binary processing, the smoothing processing is used to reduce noise, and the binary processing is used to extract the contour of the target.

[0081] Smoothing processing: a Gaussian filter is used to perform smoothing processing on the image, the smoothing kernel size is 10 pixels, and the smoothing processing formula is as follows:

[0082] ,

[0083] wherein, represents the value of the two-dimensional Gaussian function at point (x, y), i.e. the weight of the point;

[0084] x represents the horizontal coordinate offset relative to the center point of the Gaussian kernel, and y represents the vertical coordinate offset. For example, if the Gaussian kernel size is 5x5 and the center point is (0, 0), the edge points can be (-2, -2), (2, 2), etc.

[0085] is the standard deviation of the smoothing kernel;

[0086] Binary processing: dynamically adjust the binary threshold according to the contrast of the image, to ensure that the target contour under different contrast can be accurately extracted.

[0087] The binary processing formula is as follows:

[0088] ,

[0089] By dynamically adjusting T, the image under different light or vibration conditions can be adapted, ensuring accurate extraction of the target contour, especially when the image is blurred or the contrast changes due to high-speed vibration,

[0090] wherein, is the average gray value of the image, is the standard deviation of the gray value, and k is the adjustment coefficient.

[0091] Please refer to Figure 3 , Figure 3 is a three-dimensional position information acquisition method flow chart of a three-dimensional high-speed vibration target clear image acquisition method in some embodiments of the present application. According to the embodiment of the present application, the target center point is analyzed based on the target contour, and the three-dimensional position information of the target center point at different time nodes is measured based on the laser displacement meter, specifically including:

[0092] S301, acquiring the target contour, calculating the minimum circumscribed rectangle of the target contour;

[0093] S302, performing diagonal line processing on the minimum circumscribed rectangle to obtain the intersection point of the diagonal lines;

[0094] S303, obtaining the center point of the minimum circumscribed rectangle based on the intersection point of the diagonal lines, calculating the center point coordinates;

[0095] S304, analyzing the coordinate value of the center point coordinates based on the laser displacement meter, obtaining the three-dimensional position information of the target center point.

[0096] It should be noted that the collected vibration target image is preprocessed (gray scale conversion, smoothing, binary processing, etc.), and then the edge detection algorithm (such as Canny operator) and contour tracking algorithm are used to obtain the contour of the target.

[0097] According to the embodiment of the present application, the planar vibration information and the depth vibration information of the target are analyzed based on the three-dimensional position information of the target center point at different time nodes, specifically including:

[0098] acquiring the three-dimensional position information of the target center point at different time nodes;

[0099] extracting the planar coordinates under different planes based on the three-dimensional position information to obtain corresponding planar coordinate points;

[0100] drawing the planar coordinate points in a planar coordinate system to generate a motion trajectory graph of the target center point on the plane;

[0101] analyzing the vibration amplitudes of the target center in the X-axis and Y-axis directions based on the motion trajectory graph;

[0102] performing frequency spectrum analysis on the planar coordinate points based on the Fourier transform method to obtain frequency distribution information;

[0103] obtaining the planar vibration information of the target based on the vibration amplitudes in the X-axis and Y-axis directions, and obtaining the depth vibration information based on the frequency distribution information.

[0104] It should be noted that the galvanometer is arranged between the variable focal length lens and the high-brightness illumination, and through the cooperative work of the galvanometer and the variable focal length lens, the three-dimensional vibration of the target is tracked in real time. The galvanometer is used to adjust the angle of view of the camera to track the planar vibration of the target, and the variable focal length lens is used to adjust the focal length to track the depth vibration of the target.

[0105] planar vibration tracking: according to the planar vibration information of the target, the angle of the galvanometer is adjusted to ensure that the target is always located at the center of the field of view of the camera,

[0106] ,

[0107] represents the deflection angle of the galvanometer in the X-axis direction (horizontal direction);

[0108] According to the displacement of the target in the X-axis direction (such as Δx in the formula), the camera is dynamically adjusted to horizontally track the vibration of the target;

[0109] represents the deflection angle of the galvanometer in the Y-axis direction (vertical direction);

[0110] According to the displacement of the target in the Y-axis direction (such as Δy in the formula), the camera is dynamically adjusted to vertically track the vibration of the target;

[0111] wherein Δx and Δy are the displacements of the target in the planar direction, and f is the focal length of the camera.

[0112] Depth vibration tracking: according to the depth vibration information of the target, the focal length of the variable focal length lens is adjusted to ensure that the target is always in sharp focus,

[0113] ,

[0114] is the change amount of the camera lens focal length that needs to be dynamically adjusted, used to compensate for the vibration displacement of the target in the depth direction (Z axis) Δd, to ensure that the target is always in sharp focus;

[0115] wherein D is the initial distance of the target, is the depth displacement of the target.

[0116] According to the embodiment of the present application, the planar vibration information and the depth vibration information are fused and processed to generate the three-dimensional vibration state information of the target, specifically including:

[0117] Obtain the planar vibration information, analyze the vibration amplitude, and extract the vibration amplitude feature;

[0118] Obtain the depth vibration information, analyze the vibration frequency and phase based on the depth vibration information, and obtain the frequency feature;

[0119] Based on the vibration amplitude feature and the frequency feature, the influence degree of the vibration state is analyzed to obtain the weighted coefficient corresponding to the vibration amplitude and the vibration frequency;

[0120] Based on the weighted coefficient, different weight values are matched, and the vibration amplitude feature and the frequency feature are weighted and fused according to the weight values to obtain the three-dimensional vibration state information of the target.

[0121] It should be noted that the filtering method based on Gaussian distribution gives different weights to each pixel in the image according to its distance from the neighborhood pixels, and the closer the point to the center pixel, the higher the weight.

[0122] According to the embodiment of the present application, the field of view and the focal length of the high-speed camera are adjusted based on the three-dimensional vibration state information of the target to obtain a clear image of the target, specifically including:

[0123] Based on the distance information between the target and the high-speed camera measured by the laser displacement meter;

[0124] Based on the three-dimensional vibration state information of the target, the fluctuation state information of the distance information is analyzed;

[0125] Based on the fluctuation state information, the field of view and the focal length of the high-speed camera are adjusted, and the adjusted image is obtained;

[0126] Based on the edge detection algorithm, the image edge information is extracted, and the sharpness of the image edge information is analyzed;

[0127] Based on the image edge information, the definition feedback adjustment of the view angle and the focal length is obtained, and a clear target image is obtained.

[0128] It should be noted that, according to the predicted target distance, the best focal length value is calculated by using a suitable focal length adjustment algorithm. A mathematical model based on imaging principles can be used to calculate the focal length that meets the clear imaging requirements, combined with the parameters of the camera (such as sensor size, aperture size, etc.). At the same time, considering the accuracy and speed of focal length adjustment, a stepping motor or other high-precision focal length adjustment mechanism is used to realize accurate control of the focal length. According to the image definition evaluation result, a feedback optimization mechanism is established. If the image definition does not meet the requirements, the camera's view angle and focal length are automatically adjusted, and image acquisition and evaluation are performed again. Through continuous iterative optimization, the image definition is gradually improved until a satisfactory result is achieved.

[0129] As shown in Figures 4-6 the second aspect, the embodiments of the present application provide a three-dimensional high-speed vibration target clear image acquisition system, which comprises a memory and a processor. The memory comprises a three-dimensional high-speed vibration target clear image acquisition method program, and the three-dimensional high-speed vibration target clear image acquisition method program is executed by the processor to realize the following steps:

[0130] Based on the high-speed camera, the vibration target image is collected, the vibration target image is preprocessed, and the target contour is extracted;

[0131] Based on the target contour, the target center point is analyzed, and the three-dimensional position information of the target center point at different time nodes is measured based on the laser displacement meter;

[0132] Based on the three-dimensional position information of the target center point at different time nodes, the planar vibration information and the depth vibration information of the target are analyzed;

[0133] The planar vibration information and the depth vibration information are fused and processed to generate the three-dimensional vibration state information of the target;

[0134] Based on the three-dimensional vibration state information of the target, the view angle and the focal length of the high-speed camera are adjusted to obtain a clear target image.

[0135] It should be noted that a high-speed camera is used to collect images of the target. The high-speed camera can quickly capture the dynamic changes of the target, and the macro lens can realize high magnification to clearly present the details of the target. During the collection process, the frame rate, exposure time and other parameters of the camera should be reasonably set according to the motion speed and size of the target. For example, for a fast-moving target, the frame rate should be increased to avoid motion blur; for a small target, the magnification advantage of the macro lens should be fully utilized, and the focal length and working distance should be adjusted to track the three-dimensional vibration of the target in real time and obtain a clear image. The clear image at high magnification is output for subsequent visual detection and analysis.

[0136] Specifically, the system of the present application comprises the following components:

[0137] High-speed camera: used for capturing images of high-speed vibrating targets,

[0138] Macro lens: used for image acquisition at high magnification;

[0139] Variable focus lens: used for real-time adjustment of focal length to ensure clear images;

[0140] Laser displacement meter: used for measuring three-dimensional position information of the target;

[0141] Galvanometer: used for quickly adjusting the viewing angle of the camera and tracking the vibration of the target;

[0142] High-brightness illumination: used to provide sufficient illumination to ensure image brightness;

[0143] Control and data processing unit: used to control the camera, galvanometer and variable focus lens, and process image data.

[0144] Install the high-speed camera, macro lens, variable focus lens, laser displacement meter, galvanometer and high-brightness illumination on the experimental platform.

[0145] Start the system to collect image data and three-dimensional position information of the target.

[0146] Smooth and binarize the image to extract the target contour.

[0147] Real-time tracking of the three-dimensional vibration of the target through the cooperative work of the galvanometer and the variable focus lens.

[0148] Output clear images at high magnification for subsequent visual inspection and analysis. This method can track high-speed vibration of complex-shaped targets at high magnification and obtain clear images. By optimizing image processing algorithms and optical systems, it solves the problems of image blur and insufficient contrast in the prior art, and has high practicality and robustness.

[0149] According to the embodiment of the present application, the high-speed camera is used to collect the image of the vibrating target, and the vibrating target image is preprocessed to extract the target contour, specifically including:

[0150] Obtain the vibrating target image, smooth the vibrating target image based on the Gaussian filter, eliminate image noise, and obtain the denoised image;

[0151] Set the binarization threshold, binarize the denoised image, and obtain the contrast of the denoised image;

[0152] The contrast is judged with a set contrast threshold interval, an analysis result is obtained, the binary threshold is dynamically adjusted based on the analysis result, and a pretreatment image is obtained;

[0153] Edge pixels of the target in the pretreatment image are searched based on an edge detection algorithm;

[0154] The edge pixels are connected into a complete contour based on a contour tracking algorithm, and a target contour is obtained.

[0155] It should be noted that the collected image is pretreated, including smoothing processing and binary processing, the smoothing processing is used for reducing noise, and the binary processing is used for extracting the contour of the target.

[0156] The smoothing processing is performed on the image using a Gaussian filter, the smoothing kernel size is 10 pixels, and the smoothing processing formula is as follows:

[0157] ,

[0158] Wherein, is the standard deviation of the smoothing kernel;

[0159] The binary processing is dynamically adjusted according to the contrast of the image, and the target contour under different contrasts can be accurately extracted;

[0160] The binary processing formula is as follows:

[0161] ,

[0162] Wherein, is the average gray value of the image, is the standard deviation of the gray value, and k is an adjustment coefficient.

[0163] According to the embodiment of the application, the target center point is analyzed based on the target contour, and the three-dimensional position information of the target center point at different time nodes is measured based on the laser displacement meter, specifically including:

[0164] The target contour is obtained, and the minimum circumscribed rectangle of the target contour is calculated;

[0165] The minimum circumscribed rectangle is processed by diagonal line, and the intersection point of the diagonal line is obtained;

[0166] The center point of the minimum circumscribed rectangle is obtained based on the intersection point of the diagonal line, and the coordinates of the center point are calculated;

[0167] The coordinate value of the center point coordinates is analyzed based on the laser displacement meter, and the three-dimensional position information of the target center point is obtained.

[0168] It should be noted that the target image collected is preprocessed (gray scale conversion, smoothing, binarization, etc.), and then the edge detection algorithm (such as Canny operator) and the contour tracking algorithm are used to obtain the contour of the target.

[0169] According to the embodiment of the present application, the planar vibration information and the depth vibration information of the target are analyzed based on the three-dimensional position information of the target center point at different time nodes, specifically including:

[0170] The three-dimensional position information of the target center point at different time nodes is obtained;

[0171] Based on the three-dimensional position information, the planar coordinates under different planes are extracted to obtain corresponding planar coordinate points;

[0172] The planar coordinate points are plotted in the planar coordinate system to generate a motion trajectory graph of the target center point on the plane;

[0173] Based on the motion trajectory graph, the vibration amplitudes of the target center in the X-axis and Y-axis directions are analyzed, the X-axis is the length direction of the experimental platform, the Y-axis is the width direction of the experimental platform, and the X-axis and the Y-axis are perpendicular to each other;

[0174] Based on the Fourier transform method, the frequency spectrum analysis of the planar coordinate points is performed to obtain the frequency distribution information;

[0175] Based on the vibration amplitudes in the X-axis and Y-axis directions, the planar vibration information of the target is obtained, and based on the frequency distribution information, the depth vibration information is obtained.

[0176] It should be noted that through the cooperative work of the galvanometer and the variable focal length lens, the three-dimensional vibration of the target is tracked in real time. The galvanometer is used to adjust the angle of the camera to track the planar vibration of the target, and the variable focal length lens is used to adjust the focal length to track the depth vibration of the target.

[0177] Planar vibration tracking: according to the planar vibration information of the target, the angle of the galvanometer is adjusted to ensure that the target is always located at the center of the field of view of the camera,

[0178] ,

[0179] Where Δx and Δy are the displacements of the target in the planar direction, and f is the focal length of the camera.

[0180] Depth vibration tracking: according to the depth vibration information of the target, the focal length of the variable focal length lens is adjusted to ensure that the target is always in a clear focus state,

[0181] ,

[0182] Where D is the initial distance of the target, is the depth displacement of the target.

[0183] According to the embodiment of the present application, the planar vibration information and the depth vibration information are fused to generate the three-dimensional vibration state information of the target, and specifically includes:

[0184] The planar vibration information is acquired, the vibration amplitude is analyzed, and the vibration amplitude feature is extracted;

[0185] The depth vibration information is acquired, the vibration frequency and phase are analyzed based on the depth vibration information, and the frequency feature is obtained;

[0186] The influence degree of the vibration state is analyzed based on the vibration amplitude feature and the frequency feature, and the weighted coefficient corresponding to the vibration amplitude and the vibration frequency is obtained;

[0187] Different weight values are matched based on the weighted coefficient, the vibration amplitude feature and the frequency feature are weighted and fused according to the weight values, and the three-dimensional vibration state information of the target is obtained.

[0188] It should be noted that the filtering method based on Gaussian distribution gives different weights to each pixel point in the image according to the distance of the pixel point from the neighborhood pixels, and the closer the point is to the center pixel, the higher the weight.

[0189] According to the embodiment of the present application, the three-dimensional vibration state information of the target is used to adjust the viewing angle and focal length of the high-speed camera to obtain a clear image of the target, and specifically includes:

[0190] The distance information between the target and the high-speed camera measured by the laser displacement meter is obtained;

[0191] The fluctuation state information of the distance information is analyzed based on the three-dimensional vibration state information of the target;

[0192] The viewing angle and focal length of the high-speed camera are adjusted based on the fluctuation state information, and the adjusted image is obtained;

[0193] The image edge information is extracted based on the edge detection algorithm, and the definition of the image edge information is analyzed;

[0194] The viewing angle and focal length are feedback adjusted based on the definition of the image edge information, and a clear image of the target is obtained.

[0195] It should be noted that according to the predicted target distance, the best focal length value is calculated by using a suitable focal length adjustment algorithm, and a mathematical model based on imaging principles can be used to calculate the focal length that meets the clear imaging requirements in combination with the parameters of the camera (such as sensor size, aperture size, etc.). At the same time, considering the accuracy and speed of focal length adjustment, a stepping motor or other high-precision focal length adjustment mechanism is used to realize accurate control of the focal length. According to the image sharpness evaluation result, a feedback optimization mechanism is established. If the image sharpness does not meet the requirements, the camera's angle of view and focal length are automatically adjusted, and image acquisition and evaluation are performed again. Through continuous iterative optimization, the image sharpness is gradually improved until a satisfactory result is achieved.

[0196] The third aspect of the present application provides a computer-readable storage medium, and the readable storage medium includes a three-dimensional high-speed vibration target clear image acquisition method program. When the three-dimensional high-speed vibration target clear image acquisition method program is executed by a processor, the steps of the three-dimensional high-speed vibration target clear image acquisition method of any one of the above are realized.

[0197] The three-dimensional high-speed vibration target clear image acquisition method, system and medium disclosed by the present application can collect vibration target images based on a high-speed camera, preprocess the vibration target images, and extract target contours. The target center points are analyzed based on the target contours, and the three-dimensional position information of the target center points at different time nodes is measured based on a laser displacement meter. The planar vibration information and depth vibration information of the target are analyzed based on the three-dimensional position information of the target center points at different time nodes. The planar vibration information and depth vibration information are fused and processed to generate three-dimensional vibration state information of the target. The angle of view and focal length of the high-speed camera are adjusted based on the three-dimensional vibration state information of the target to obtain a clear target image. Through dynamic zooming and angle adjustment of the high-speed camera, high-speed vibration tracking of a complex shape target can be performed at a high magnification, and a clear image can be obtained.

[0198] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of units is only a logical function division, and actual implementation can have another division manner, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed components can be through some interface, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0199] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0200] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0201] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0202] Alternatively, if the integrated units of the present invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

Claims

1. A method for obtaining a clear image of a three-dimensional high-speed vibrating object, characterized in that, The method comprises the following steps: Based on the high-speed camera, the vibration target image is collected, and the vibration target image is smoothed based on the Gaussian filter to remove image noise and obtain a denoised image; A binary threshold is set, the denoised image is binarized, and the contrast of the denoised image is obtained; The contrast is compared with the set contrast threshold interval to obtain an analysis result, the binary threshold is dynamically adjusted based on the analysis result, and a preprocessed image is obtained; Based on the edge detection algorithm, the edge pixels of the target in the preprocessed image are searched; Based on the contour tracking algorithm, the edge pixels are connected into a complete contour to obtain a target contour; Based on the target contour, the center point of the target is analyzed, and the three-dimensional position information of the center point of the target at different time nodes is measured based on the laser displacement meter; Based on the three-dimensional position information of the center point of the target at different time nodes, the planar vibration information and the depth vibration information of the target are analyzed; The planar vibration information and the depth vibration information are fused to generate three-dimensional vibration state information of the target; The distance information between the target and the high-speed camera measured by the laser displacement meter is obtained; Based on the three-dimensional vibration state information of the target, the fluctuation state information of the distance information is analyzed; Based on the fluctuation state information, the viewing angle and focal length of the high-speed camera are adjusted, and an adjusted image is obtained; Based on the edge detection algorithm, the edge information of the image is extracted, and the definition of the image edge information is analyzed; Based on the definition of the image edge information, the viewing angle and focal length are feedback adjusted to obtain a target clear image.

2. The method of claim 1, wherein, Based on the target contour, the center point of the target is analyzed, and the three-dimensional position information of the center point of the target at different time nodes is measured based on the laser displacement meter, specifically including: The target contour is obtained, and the minimum circumscribed rectangle of the target contour is calculated; The minimum circumscribed rectangle is processed by diagonal line to obtain the intersection point of the diagonal line; Based on the intersection point of the diagonal line, the center point of the minimum circumscribed rectangle is obtained, and the center point coordinates are calculated; Based on the laser displacement meter, the coordinate values of the center point coordinates are analyzed to obtain the three-dimensional position information of the target center point.

3. The method of claim 2, wherein, Based on the three-dimensional position information of the center point of the target at different time nodes, the planar vibration information and the depth vibration information of the target are analyzed, specifically including: The three-dimensional position information of the center point of the target at different time nodes is obtained; Based on the three-dimensional position information, the planar coordinates under different planes are extracted to obtain corresponding planar coordinate points; The planar coordinate points are plotted in the planar coordinate system to generate a motion trajectory diagram of the target center point on the plane; Based on the motion trajectory diagram, the vibration amplitudes of the target center in the X-axis and Y-axis directions are analyzed; Based on the Fourier transform method, the frequency spectrum of the planar coordinate points is analyzed to obtain frequency distribution information; Based on the vibration amplitudes in the X-axis and Y-axis directions, the planar vibration information of the target is obtained, and based on the frequency distribution information, the depth vibration information is obtained.

4. The method of claim 3, wherein, The planar vibration information and the depth vibration information are fused to generate three-dimensional vibration state information of the target, specifically including: The planar vibration information is obtained, the vibration amplitude is analyzed, and the vibration amplitude feature is extracted; The depth vibration information is obtained, the vibration frequency and phase are analyzed based on the depth vibration information, and the frequency feature is obtained; Based on the vibration amplitude feature and the frequency feature, the influence degree of the vibration state is analyzed to obtain the weighted coefficients corresponding to the vibration amplitude and the vibration frequency; The different weight values are matched based on the weight coefficients, the vibration amplitude feature and the frequency feature are weighted and fused according to the weight values, and three-dimensional vibration state information of the target is obtained.

5. A system for obtaining a clear image of a three-dimensional high-speed vibrating object, characterized in that The system comprises a memory and a processor, the memory comprises a three-dimensional high-speed vibration target clear image acquisition method program, and the three-dimensional high-speed vibration target clear image acquisition method program is executed by the processor to realize the following steps: An image of the vibration target is collected based on a high-speed camera, the image of the vibration target is smoothed based on a Gaussian filter, image noise is removed, and a denoised image is obtained; A binary threshold is set, the denoised image is binarized, and the contrast of the denoised image is obtained; The contrast is compared with a set contrast threshold interval, an analysis result is obtained, the binary threshold is dynamically adjusted based on the analysis result, and a preprocessed image is obtained; Edge pixels of the target in the preprocessed image are searched based on an edge detection algorithm; The edge pixels are connected into a complete contour based on a contour tracking algorithm, and a target contour is obtained; The center point of the target is analyzed based on the target contour, three-dimensional position information of the center point of the target at different time nodes is measured based on a laser displacement meter; Planar vibration information and depth vibration information of the target are analyzed based on the three-dimensional position information of the center point of the target at different time nodes; The planar vibration information and the depth vibration information are fused, and three-dimensional vibration state information of the target is generated; Distance information between the target and the high-speed camera measured based on the laser displacement meter; Wave state information of the distance information is analyzed based on the three-dimensional vibration state information of the target; The viewing angle and the focal length of the high-speed camera are adjusted based on the wave state information, and an adjusted image is obtained; Image edge information is extracted based on the edge detection algorithm, and the definition of the image edge information is analyzed; The viewing angle and the focal length are feedback adjusted based on the definition of the image edge information, and a target clear image is obtained.

6. The three-dimensional high speed vibrating target sharp image acquisition system of claim 5, wherein, The center point of the target is analyzed based on the target contour, and three-dimensional position information of the center point of the target at different time nodes is measured based on the laser displacement meter, specifically comprising: The target contour is obtained, and a minimum circumscribed rectangle of the target contour is calculated; The minimum circumscribed rectangle is processed by diagonal lines, and a diagonal intersection point is obtained; The center point of the minimum circumscribed rectangle is obtained based on the diagonal intersection point, and the coordinates of the center point are calculated; The coordinate values of the center point coordinates are analyzed based on the laser displacement meter, and the three-dimensional position information of the center point of the target is obtained.

7. A computer readable storage medium characterized by, The computer readable storage medium comprises a three-dimensional high-speed vibration target clear image acquisition method program, and the three-dimensional high-speed vibration target clear image acquisition method program is executed by the processor to realize the steps of the three-dimensional high-speed vibration target clear image acquisition method according to any one of claims 1 to 4.

Images