Machine vision-based kraniofacial processing system and method
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- BEIJING INFORMATION SCI & TECH UNIV
- Filing Date
- 2026-06-25
- Publication Date
- 2026-08-07
AI Technical Summary
[0004]现有的克拉尼图形的检测与生成方式中，需操作人员手动调节振动激励参数，通过肉眼观测图形变化，主观性强、误差大，难以精准复现目标图形，人工依赖度高，自动化程度低，另外，需反复试错，生成目标图形的效率极低，且易受光照或背景噪声干扰，图像处理精度低
上述的基于机器视觉的克拉尼图形处理系统，包括振动板、振动激励模块、视觉采集模块和主控模块，振动板设置有振动颗粒；振动激励模块用于根据当前振动参数，驱动振动板产生振动，以使振动板产生当前振动图形；视觉采集模块用于采集当前振动图形；主控模块连接振动激励模块和视觉采集模块；主控模块被配置为：向振动激励模块传输当前振动参数，并获取视觉采集模块传输的当前振动图形；对当前振动图形进行特征提取，得到当前图形特征信息；在当前图形特征信息满足预设目标特征条件时，将当前振动图形确认为目标振动图形，实现对克拉尼图形观测与目标图形的准确生成。
Smart Images
Figure CN122530338A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of machine vision graphics processing technology, and in particular to a machine vision-based Kroni graphics processing system and method. Background Technology
[0002] The Clani pattern is a regular geometric pattern formed by the distribution of particles (such as sand or powder) on the surface of a rigid thin plate under mechanical vibration excitation at different frequencies / amplitudes due to the vibration nodes or antinodes.
[0003] Cranny diagrams can intuitively reflect the modal characteristics of a vibrating plate and are a core tool for studying the vibration characteristics of media in the fields of acoustics and vibration engineering.
[0004] The existing methods for detecting and generating Krani images require operators to manually adjust vibration excitation parameters and observe changes in the image with the naked eye. This method is highly subjective, prone to errors, and difficult to accurately reproduce the target image. It is highly dependent on manual labor, has a low degree of automation, requires repeated trial and error, has extremely low efficiency in generating the target image, and is easily affected by lighting or background noise, resulting in low image processing accuracy. Summary of the Invention
[0005] Based on this, and addressing the technical problems existing in the above-mentioned methods for detecting and generating Krani images, a machine vision-based Krani image processing system and method are provided, which can improve the accuracy, efficiency and automation of Krani image observation and generation.
[0006] In a first aspect, this application provides a machine vision-based Kroni graphics processing system, comprising: Vibrating plate, the vibrating plate is equipped with vibrating particles; The vibration excitation module is used to drive the vibrating plate to vibrate according to the current vibration parameters, so that the vibrating plate produces the current vibration pattern. The visual acquisition module is used to acquire the current vibration pattern; The main control module connects the vibration excitation module and the vision acquisition module. The main control module is configured to: transmit the current vibration parameters to the vibration excitation module and acquire the current vibration pattern transmitted by the vision acquisition module; extract features from the current vibration pattern to obtain the current pattern feature information; and confirm the current vibration pattern as the target vibration pattern when the current pattern feature information meets the preset target feature conditions.
[0007] In one embodiment, the main control module is further configured as follows: When the current graphic feature information does not meet the preset target feature conditions, the vibration parameters of the vibration excitation module are adjusted to obtain the next vibration parameters, and the next vibration parameters are transmitted to the vibration excitation module so that the vibrating plate generates the next vibration pattern, until the next graphic feature information of the corresponding next vibration pattern meets the preset target feature conditions, and the corresponding next vibration pattern is confirmed as the target vibration pattern.
[0008] In one embodiment, the vibration excitation module includes a signal generator, a power amplifier, and a vibration execution unit; The signal generator is connected to the main control module and the power amplifier. The power amplifier is connected to the vibration actuator, and the vibration actuator is equipped with a vibration plate. The main control module is configured to transmit the current vibration parameters to the signal generator, so that the signal generator sends the current excitation signal to the power amplifier based on the current vibration parameters. The power amplifier amplifies the current excitation signal and transmits the amplified signal to the vibration execution unit to drive the vibration execution unit to drive the vibrating plate to vibrate.
[0009] In one embodiment, the visual acquisition module includes a camera module and a lighting component; The camera module and the lighting component are respectively connected to the main control module. The lighting component is used to provide a light source for the vibrating plate, and the camera module is used to collect the vibration pattern of the vibrating plate to obtain the current vibration pattern.
[0010] In one embodiment, the main control module is further configured as follows: The current vibration pattern is preprocessed to obtain a preprocessed pattern; the preprocessed pattern is then contour extracted to obtain the current pattern contour; and the current pattern contour is then feature extracted to obtain the current pattern feature information.
[0011] In one embodiment, the main control module is further configured as follows: Based on the Hu moment analysis algorithm, feature extraction is performed on the current graphic contour to obtain the current graphic feature information.
[0012] In one embodiment, the main control module is further configured as follows: The feature values of the current graphic feature information are compared with the preset target feature values to obtain the feature deviation value; When the characteristic deviation value is lower than the preset threshold, the current vibration pattern is identified as the target vibration pattern.
[0013] In one embodiment, the main control module is further configured as follows: When the current graphic feature information does not meet the preset target feature conditions, a control command is generated based on the preset PID algorithm or reinforcement learning algorithm, and the control command is transmitted to the vibration excitation module so that the vibrating plate generates the next vibration pattern; the control command includes the next vibration parameters.
[0014] In one embodiment, the main control module is further configured as follows: The current graphic feature information is processed by Fast Fourier Transform to obtain the modal parameters corresponding to the current vibration graphic, and the modal parameters are stored.
[0015] Secondly, this application also provides a machine vision-based Krani image processing method, applied to any of the machine vision-based Krani image processing systems described above, the method comprising: Transmit the current vibration parameters to the vibration excitation module and acquire the current vibration image transmitted by the vision acquisition module; Feature extraction is performed on the current vibration pattern to obtain the feature information of the current pattern; When the current graphic feature information meets the preset target feature conditions, the current vibration graphic is identified as the target vibration graphic.
[0016] One of the above technical solutions has the following advantages and beneficial effects: The aforementioned machine vision-based Krani graphic processing system includes a vibrating plate, a vibration excitation module, a vision acquisition module, and a main control module. The vibrating plate is equipped with vibrating particles. The vibration excitation module drives the vibrating plate to vibrate according to the current vibration parameters, thereby generating a current vibration graphic. The vision acquisition module acquires the current vibration graphic. The main control module connects the vibration excitation module and the vision acquisition module. The main control module is configured to: transmit the current vibration parameters to the vibration excitation module and acquire the current vibration graphic transmitted by the vision acquisition module; extract features from the current vibration graphic to obtain current graphic feature information; and when the current graphic feature information meets preset target feature conditions, confirm the current vibration graphic as the target vibration graphic, thereby achieving accurate observation of Krani graphics and generation of target graphics.
[0017] This application uses a vibration excitation module to drive a vibrating plate to generate vibration, a vision acquisition module to acquire the current vibration pattern, a main control module to extract features from the current vibration pattern, and a preset target feature condition judgment on the current pattern feature information. When the preset target feature condition is met, the target vibration pattern is obtained, realizing real-time high-precision acquisition of the Krani pattern and automated generation of the target Krani pattern, improving the accuracy and efficiency of Krani pattern observation and generation, and increasing the degree of automation of target pattern generation. Attached Figure Description
[0018] Figure 1This is a first structural schematic diagram of the machine vision-based Klani graphics processing system in an embodiment of this application; Figure 2 This is a schematic diagram of the second structure of the machine vision-based Klani graphics processing system in an embodiment of this application; Figure 3 This is a flowchart illustrating the machine vision-based Kroni graphics processing method in this application embodiment. Detailed Implementation
[0019] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments.
[0020] Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.
[0021] It should be noted that the terms "first," "second," etc., in the specification, claims, and drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.
[0022] It should be understood that the data used in this way can be interchanged where appropriate, so as to the embodiments of this application described herein.
[0023] Furthermore, the terms “comprising” and “having”, and any variations thereof, are intended to cover non-exclusive inclusion, such that a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such process, method, product, or apparatus.
[0024] In addition, the term "multiple" should mean two or more.
[0025] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other.
[0026] The present application will now be described in detail with reference to the accompanying drawings and embodiments.
[0027] In one embodiment, such as Figure 1As shown, a machine vision-based Kroni graphics processing system is also provided, including a vibrating plate 10, a vibration excitation module 20, a vision acquisition module 30, and a main control module 40. The vibrating plate 10 is provided with vibrating particles. The vibration excitation module 20 is used to drive the vibrating plate 10 to vibrate according to the current vibration parameters, so that the vibrating plate 10 generates the current vibration pattern. The vision acquisition module 30 is used to acquire the current vibration pattern. The main control module 40 is connected to the vibration excitation module 20 and the vision acquisition module 30. The main control module 40 is configured to: transmit the current vibration parameters to the vibration excitation module 20 and acquire the current vibration pattern transmitted by the vision acquisition module 30; extract features from the current vibration pattern to obtain the current pattern feature information; and confirm the current vibration pattern as the target vibration pattern when the current pattern feature information meets the preset target feature conditions.
[0028] The vibrating plate 10 is used to generate the Clani pattern, and the vibrating plate 10 is also called the Clani plate.
[0029] For example, the vibrating plate 10 can be a thin metal plate, such as copper, aluminum or steel; or it can be a non-metallic thin plate, such as glass, acrylic or wood.
[0030] Vibrating particles refer to lightweight, fine solid particles, such as fine sand or salt grains.
[0031] The vibration excitation module 20 is used to control the vibrating plate 10 to generate controllable mechanical vibration.
[0032] For example, the vibration excitation module 20 is connected to the main control module 40, and the vibration plate 10 is attached to the vibration output end of the vibration excitation module 20. The main control module 40 transmits the current vibration parameters to the vibration excitation module 20, and then the vibration excitation module 20 drives the vibration plate 10 to vibrate according to the current vibration parameters, so that the vibrating particles on the vibration plate 10 produce the current vibration pattern.
[0033] It should be noted that the current vibration pattern refers to the current Clani pattern generated by the vibration excitation module 20 driving the vibration plate 10 based on the current vibration parameters.
[0034] Current vibration parameters may include vibration frequency and amplitude parameters, etc.
[0035] The visual acquisition module 30 is connected to the main control module 40. The visual acquisition module 30 acquires the current vibration pattern generated by the vibrating plate 10 and transmits the acquired current vibration pattern to the main control module 40.
[0036] For example, the visual acquisition module 30 and the vibration excitation module 20 can be synchronously triggered by hardware triggering or industrial communication protocol control to achieve real-time acquisition of Krani graphics without ghosting.
[0037] The main control module 40 can be an industrial computer or an embedded computing platform.
[0038] For example, the main control module 40 integrates a data acquisition card and a multi-protocol communication interface, which is responsible for controlling the collaborative work of each module and receiving the current vibration pattern acquired by the vision acquisition module 30. The main control module 40 is also used to process the current vibration pattern, and to judge the current pattern feature information obtained by processing it against the preset target feature conditions. Based on the processing result, it outputs the corresponding vibration parameter instructions to the vibration excitation module 20 to control the vibration excitation module 20 to drive the vibration plate 10 to generate vibration.
[0039] For example, after the system is powered on and initialized, the main control module 40 sends initial vibration parameters to the vibration excitation module 20 to drive the vibration plate 10 to generate initial vibration, so that the vibration plate 10 forms an initial Clani pattern.
[0040] The visual acquisition module 30 acquires the initial Kranny image and transmits it to the main control module 40.
[0041] The main control module 40 extracts features from the acquired initial Krani pattern to obtain initial pattern feature information. When the initial pattern feature information meets the preset target feature conditions, the main control module 40 confirms the initial Krani pattern as the target vibration pattern. If the initial pattern feature information does not meet the preset target feature conditions, the main control module 40 adjusts the vibration parameters of the vibration excitation module 20 to obtain the current vibration parameters, and then transmits the current vibration parameters to the vibration excitation module 20, and acquires the current vibration pattern transmitted by the vision acquisition module 30. Features are extracted from the current vibration pattern to obtain current pattern feature information. When the current pattern feature information meets the preset target feature conditions, the current vibration pattern is confirmed as the target vibration pattern, thereby achieving accurate detection of Krani pattern observation and automatic generation of the target Krani pattern.
[0042] The aforementioned machine vision-based Krani graphic processing system includes a vibrating plate 10, a vibration excitation module 20, a vision acquisition module 30, and a main control module 40. The vibrating plate 10 is equipped with vibrating particles. The vibration excitation module 20 drives the vibrating plate 10 to vibrate according to the current vibration parameters, so that the vibrating plate 10 generates the current vibration graphic. The vision acquisition module 30 is used to acquire the current vibration graphic. The main control module 40 is connected to the vibration excitation module 20 and the vision acquisition module 30. The main control module 40 is configured to: transmit the current vibration parameters to the vibration excitation module 20 and acquire the current vibration graphic transmitted by the vision acquisition module 30; extract features from the current vibration graphic to obtain the current graphic feature information; and when the current graphic feature information meets the preset target feature conditions, confirm the current vibration graphic as the target vibration graphic, thereby realizing the accurate observation of Krani graphics and the generation of target graphics.
[0043] This application uses a vibration excitation module 20 to drive a vibrating plate 10 to generate vibration, a vision acquisition module 30 to acquire the current vibration pattern, a main control module 40 to extract features from the current vibration pattern, and a preset target feature condition judgment on the current pattern feature information. When the preset target feature condition is met, the target vibration pattern is obtained, realizing real-time high-precision acquisition of the Krani pattern and automated generation of the target Krani pattern, improving the accuracy and efficiency of Krani pattern observation and generation, and increasing the degree of automation of target pattern generation.
[0044] In one embodiment, the main control module is further configured to: when the current graphic feature information does not meet the preset target feature conditions, adjust the vibration parameters of the vibration excitation module to obtain the next vibration parameters, and transmit the next vibration parameters to the vibration excitation module so that the vibrating plate generates the next vibration pattern until the next graphic feature information of the corresponding next vibration pattern meets the preset target feature conditions, and confirm the corresponding next vibration pattern as the target vibration pattern.
[0045] For example, the main control module compares the current graphic feature information with the preset target feature conditions. If the current graphic feature information does not meet the preset target feature conditions, it determines that there is a deviation between the current vibration graphic and the target vibration graphic. Then, it adjusts the vibration parameters of the vibration excitation module to obtain the next vibration parameters and transmits the next vibration parameters to the vibration excitation module. The vibration excitation module drives the vibrating plate to vibrate again according to the next vibration parameters, so that the vibrating plate generates the next vibration graphic. It extracts features from the next vibration graphic to obtain the next graphic feature information and determines whether the next graphic feature information of the corresponding next vibration graphic meets the preset target feature conditions. If the next graphic feature information meets the preset target feature conditions, the corresponding next vibration graphic is confirmed as the target vibration graphic. This realizes real-time high-precision acquisition of the Krani graphic and automated generation of the target Krani graphic, improving the accuracy and efficiency of Krani graphic observation and generation, and increasing the degree of automation of target graphic generation.
[0046] In one embodiment, such as Figure 2As shown, the vibration excitation module includes a signal generator 210, a power amplifier 220, and a vibration execution unit 230. The signal generator 210 is connected to the main control module 40 and the power amplifier 220. The power amplifier 220 is connected to the vibration execution unit 230, and the vibration execution unit 230 is equipped with a vibration plate 10. The main control module 40 is configured to transmit the current vibration parameters to the signal generator 210, so that the signal generator 210 sends the current excitation signal to the power amplifier 220 according to the current vibration parameters. The power amplifier 220 amplifies the current excitation signal and transmits the amplified signal to the vibration execution unit 230 to drive the vibration execution unit 230 to drive the vibration plate 10 to vibrate.
[0047] The signal generator 210 can be a direct digital synthesis (DDS) signal generator 210, which can be used to output an excitation signal with an adjustable frequency and amplitude of 0~20kHz.
[0048] The power amplifier 220 can be used to amplify the excitation signal transmitted by the signal generator 210 and transmit the amplified signal to the vibration actuator 230 to drive the vibration actuator 230 to work.
[0049] The vibration actuator 230 can be a piezoelectric ceramic transducer or an electromagnetic vibration table.
[0050] For example, the vibrating plate 10 is attached to the output end of the vibration execution unit 230, and the vibration execution unit 230 drives the vibrating plate 10 to generate controllable mechanical vibration based on the amplified signal.
[0051] For example, the main control module 40 transmits the current vibration parameters to the signal generator 210. The signal generator 210 sends the current excitation signal to the power amplifier 220 based on the current vibration parameters. The power amplifier 220 amplifies the current excitation signal and transmits the amplified signal to the vibration execution unit 230 to drive the vibration execution unit 230 to drive the vibration plate 10 to vibrate, so that the vibration plate 10 forms the current vibration pattern.
[0052] The visual acquisition module acquires the current vibration pattern and transmits it to the main control module 40.
[0053] The main control module 40 extracts features from the acquired current vibration pattern to obtain current pattern feature information. When the current pattern feature information meets the preset target feature conditions, the main control module 40 confirms the current vibration pattern as the target vibration pattern. If the current pattern feature information does not meet the preset target feature conditions, the main control module 40 adjusts the vibration parameters of the vibration excitation module to obtain the next vibration parameters and transmits the next vibration parameters to the vibration excitation module. The vibration excitation module drives the vibration plate 10 to vibrate again according to the next vibration parameters, so that the vibration plate 10 generates the next vibration pattern, and judges whether the next pattern feature information of the corresponding next vibration pattern meets the preset target feature conditions. When the next pattern feature information meets the preset target feature conditions, the corresponding next vibration pattern is confirmed as the target vibration pattern, realizing real-time high-precision acquisition of the Krani pattern and automated generation of the target Krani pattern, improving the accuracy and efficiency of Krani pattern observation and generation, and improving the automation level of target pattern generation.
[0054] In one embodiment, such as Figure 2 As shown, the visual acquisition module includes a camera module 310 and an illumination component 320; the camera module 310 and the illumination component 320 are respectively connected to the main control module 40. The illumination component 320 is used to provide a light source for the vibrating plate 10, and the camera module 310 is used to acquire the vibration pattern of the vibrating plate 10 to obtain the current vibration pattern.
[0055] Among them, the camera module 310 can be a global shutter industrial camera, such as a frame rate of 120fps or higher and a resolution of 1920×1080.
[0056] The camera module 310 can be synchronously executed with the vibration excitation module through hardware or software triggering to achieve real-time acquisition of Krani graphics without ghosting.
[0057] The lighting component 320 can be a ring-shaped low-noise LED lighting component 320, which provides a light source to the vibrating plate 10, thereby ensuring image contrast and uniformity.
[0058] In one example, the vision acquisition module also includes an optical calibration plate, which is a precision tool for calibrating and standardizing the camera module 310. The optical calibration plate can be used to provide a known, stable, and traceable reference benchmark for the camera module 310, thereby ensuring the accuracy of imaging, measurement, or sensing results.
[0059] For example, the main control module 40 controls the vibration excitation module to drive the vibration plate 10 to vibrate, while controlling the lighting component 320 to provide a light source to the vibration plate 10, and controlling the camera module 310 to acquire the current vibration pattern of the vibration plate 10, and extracting features from the current vibration pattern, and determining whether the extracted current pattern feature information meets the preset target feature conditions. When the preset target feature conditions are met, the current vibration pattern is confirmed as the target vibration pattern, thereby realizing the real-time high-precision acquisition of the Clani pattern and the automatic generation of the target Clani pattern.
[0060] In one example, the camera module 310 is calibrated with camera intrinsic and / or extrinsic parameters to calibrate the spatiotemporal synchronization between the vibration excitation module and the camera module 310, thereby eliminating image distortion and time delay.
[0061] It should be noted that the camera module 310 can capture images of the current vibration pattern of the vibrating plate 10 at a preset frame rate. For example, the captured current vibration pattern can be transmitted to the main control module 40 via a high-speed transmission protocol (USB3.0 or GigE protocol) to realize real-time acquisition of the current vibration pattern.
[0062] In one embodiment, the main control module is further configured to: perform graphic preprocessing on the current vibration graphic to obtain a preprocessed graphic; extract the contour of the preprocessed graphic to obtain the current graphic contour; and extract features from the current graphic contour to obtain the current graphic feature information.
[0063] For example, Gaussian filtering is applied to the current vibration pattern to remove background noise and obtain a filtered pattern; adaptive threshold segmentation is then applied to the filtered pattern to remove particle overlap interference and obtain a preprocessed pattern.
[0064] Based on morphological operations, contour extraction is performed on the preprocessed image to extract the effective contour of the image, thereby obtaining the current image contour and eliminating false contours. By performing feature detection on the current image contour and extracting the corresponding geometric features of the image, the corresponding current image feature information is obtained, so as to determine whether the extracted current image feature information meets the preset target feature conditions.
[0065] In one embodiment, the main control module is further configured to: extract features from the current graphic contour based on the Hu moment analysis algorithm to obtain the current graphic feature information.
[0066] Among them, the Hu moment analysis algorithm is a shape-invariant feature extraction method based on image geometric moments.
[0067] Based on the Hu moment analysis algorithm, geometric feature information such as node distribution, contour area, and symmetry information of the current graphic contour is extracted to obtain the current graphic feature information. Then, by judging whether the current graphic feature information meets the preset target feature conditions, the target vibration graphic is obtained when the preset target feature conditions are met, realizing real-time high-precision acquisition of the Krani graphic and automatic generation of the target Krani graphic.
[0068] In one embodiment, the main control module is further configured to: perform difference processing on the feature value of the current graphic feature information and the preset target feature value to obtain a feature deviation value; when the feature deviation value is lower than a preset threshold, the current vibration graphic is confirmed as the target vibration graphic.
[0069] For example, if the feature value of the current graphic feature information is the contour area value, the difference between the contour area value of the current graphic feature information and the preset target feature value is processed to obtain the feature deviation value of the corresponding contour area value. The feature deviation value is compared with a preset threshold, and based on the comparison result, if the feature deviation value is lower than the preset threshold, the current vibration graphic is confirmed as the target vibration graphic. This realizes real-time high-precision acquisition of the Krani graphic and automated generation of the target Krani graphic, improving the accuracy and efficiency of Krani graphic observation and generation, and increasing the degree of automation of target graphic generation.
[0070] In one embodiment, the main control module is further configured to: when the current graphic feature information does not meet the preset target feature conditions, generate a control command based on a preset PID algorithm or reinforcement learning algorithm, and transmit the control command to the vibration excitation module so that the vibrating plate generates the next vibration pattern; the control command includes the next vibration parameters.
[0071] Among them, reinforcement learning algorithm is a type of machine learning algorithm.
[0072] The next vibration parameters may include the corresponding vibration frequency and amplitude parameters.
[0073] For example, by determining whether the current graphic feature information meets the preset target feature conditions, when the current graphic feature information does not meet the preset target feature conditions, i.e., when the corresponding feature deviation value is higher than the preset threshold, a control command is generated based on a preset PID algorithm or reinforcement learning algorithm, and the control command is transmitted to the vibration excitation module to adjust the corresponding vibration parameters of the vibration excitation module. This allows the vibration excitation module to drive the vibrating plate to generate the next vibration pattern according to the corresponding next vibration parameters. Then, by determining whether the next graphic feature information of the corresponding next vibration pattern meets the preset target feature conditions, when the next graphic feature information meets the preset target feature conditions, the corresponding next vibration pattern is identified as the target vibration pattern, thus realizing real-time high-precision acquisition of the Clani pattern and automatic generation of the target Clani pattern.
[0074] In one embodiment, the main control module is further configured to: process the current graphic feature information based on the fast Fourier transform to obtain the modal parameters corresponding to the current vibration graphic, and store the modal parameters.
[0075] The current graphic feature information is processed based on Fast Fourier Transform (FFT) to analyze the frequency response of the vibrating plate, quantify and output the modal parameters corresponding to the current vibration graphic, and store the modal parameters for subsequent source tracing analysis.
[0076] It should be noted that it can also store vibration graphs, vibration parameters, and characteristic data for the entire process.
[0077] In one embodiment, such as Figure 3 As shown, a machine vision-based Kroni graphics processing method is also provided, applied to any of the machine vision-based Kroni graphics processing systems described above, the method comprising: Step S310: Transmit the current vibration parameters to the vibration excitation module and acquire the current vibration graphic transmitted by the vision acquisition module.
[0078] For example, the main control module sends the current vibration parameters to the vibration excitation module, drives the vibrating plate to vibrate, and forms the current vibration pattern; the vision acquisition module acquires the current vibration pattern and transmits it to the main control module, so that the main control module can obtain the corresponding current vibration pattern.
[0079] Step S320: Extract features from the current vibration pattern to obtain the feature information of the current pattern.
[0080] The main control module extracts features from the current vibration pattern to obtain the feature information of the current pattern.
[0081] Step S330: When the current graphic feature information meets the preset target feature conditions, the current vibration graphic is confirmed as the target vibration graphic.
[0082] When the main control module determines whether the current graphic feature information meets the preset target feature conditions, if the current graphic feature information meets the preset target feature conditions, the current vibration graphic is confirmed as the target vibration graphic, thereby achieving accurate detection of the Krani graphic observation and automatic generation of the target Krani graphic.
[0083] In the above embodiments, by controlling the vibration excitation module to drive the vibrating plate to generate vibration, the current vibration pattern is feature extracted, and the current pattern feature information is judged according to the preset target feature conditions. When the preset target feature conditions are met, the target vibration pattern is obtained, realizing real-time high-precision acquisition of the Krani pattern and automatic generation of the target Krani pattern, improving the accuracy and efficiency of Krani pattern observation and generation, and improving the degree of automation of target pattern generation.
[0084] In one example, the vibration excitation module uses a SIGLENT SDG2042X DDS signal generator (0~20kHz adjustable frequency) and a Krohn-Hite 7602M power amplifier, paired with a PZT-5H piezoelectric ceramic plate to drive a 300×300mm acrylic vibration plate; the vision acquisition module uses a Basler acA1920-150um global shutter camera (150fps, 1920×1080), paired with a 5000K ring LED lighting assembly; the main control module uses the NVIDIA Jetson Xavier NX embedded platform, integrating a GigE acquisition card and a USB serial communication module.
[0085] The machine vision-based Kranny image processing method is developed using Python 3.8 and its core dependencies are OpenCV 4.5, NumPy, and SciPy.
[0086] It should be noted that the machine vision-based Klani graphics processing system is also equipped with a display screen with an interactive interface that supports target graphic import, real-time graphic display, parametric curve plotting, and data export.
[0087] In a laboratory setting, this system can generate target krani graphics (such as regular hexagons and circular node distributions) within 10 seconds, with graphic feature deviation ≤3%. Compared with traditional manual adjustment methods, efficiency is improved by ≥80% and accuracy by ≥25%.
[0088] It should be understood that, although Figure 3 The steps in the flowchart are shown sequentially according to the arrows, but these steps are not necessarily executed in the order indicated by the arrows.
[0089] Unless otherwise specified in this document, there is no strict order in which these steps are performed, and they may be performed in any other order.
[0090] and, Figure 3At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.
[0091] In one embodiment, a computer storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the steps of any of the above-described animation image processing methods.
[0092] For example, when a computer program is executed by a processor, it performs the following steps: The current vibration parameters are transmitted to the vibration excitation module, and the current vibration pattern transmitted by the vision acquisition module is acquired; the current vibration pattern is feature extracted to obtain the current pattern feature information; when the current pattern feature information meets the preset target feature conditions, the current vibration pattern is identified as the target vibration pattern.
[0093] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the division operation methods described above.
[0094] Any references to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory.
[0095] Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory.
[0096] Volatile memory may include random access memory (RAM) or external cache memory.
[0097] By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), direct memory bus RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
[0098] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0099] The above-described embodiments are merely examples of several implementation methods of this application. They are described in a relatively specific and detailed manner, but should not be construed as limiting the scope of the patent application.
[0100] It should be noted that, for those skilled in the art, several modifications and improvements can be made without departing from the concept of this application, and these all fall within the scope of protection of this application.
[0101] Therefore, the scope of protection of this patent application shall be determined by the appended claims.
Claims
1. A machine vision-based Kroni graphics processing system, characterized in that, include: A vibrating plate, wherein the vibrating plate is provided with vibrating particles; A vibration excitation module is used to drive the vibrating plate to vibrate according to the current vibration parameters, so that the vibrating plate generates the current vibration pattern. A visual acquisition module, used to acquire the current vibration pattern; The main control module is connected to the vibration excitation module and the vision acquisition module; The main control module is configured to: transmit the current vibration parameters to the vibration excitation module and acquire the current vibration pattern transmitted by the vision acquisition module; extract features from the current vibration pattern to obtain current pattern feature information; and confirm the current vibration pattern as the target vibration pattern when the current pattern feature information meets the preset target feature conditions.
2. The machine vision-based Kroni graphics processing system according to claim 1, characterized in that, The main control module is also configured to: When the current graphic feature information does not meet the preset target feature conditions, the vibration parameters of the vibration excitation module are adjusted to obtain the next vibration parameters, and the next vibration parameters are transmitted to the vibration excitation module so that the vibration plate generates the next vibration pattern, until the next graphic feature information corresponding to the next vibration pattern meets the preset target feature conditions, and the corresponding next vibration pattern is confirmed as the target vibration pattern.
3. The machine vision-based Kroni graphics processing system according to claim 1, characterized in that, The vibration excitation module includes a signal generator, a power amplifier, and a vibration execution unit; The signal generator is connected to the main control module and the power amplifier, the power amplifier is connected to the vibration execution unit, and the vibration execution unit is equipped with the vibration plate; The main control module is configured to transmit current vibration parameters to the signal generator, so that the signal generator sends a current excitation signal to the power amplifier based on the current vibration parameters. The power amplifier amplifies the current excitation signal and transmits the amplified signal to the vibration execution unit to drive the vibration execution unit to generate vibration of the vibration plate.
4. The machine vision-based Kroni graphics processing system according to claim 1, characterized in that, The visual acquisition module includes a camera module and a lighting component; The camera module and the lighting component are respectively connected to the main control module. The lighting component is used to provide a light source for the vibrating plate, and the camera module is used to acquire the vibration pattern of the vibrating plate to obtain the current vibration pattern.
5. The machine vision-based Kroni graphics processing system according to any one of claims 1 to 4, characterized in that, The main control module is also configured to: The current vibration pattern is preprocessed to obtain a preprocessed pattern; the preprocessed pattern is then contour extracted to obtain the current pattern contour; and the current pattern contour is then feature extracted to obtain the current pattern feature information.
6. The machine vision-based Kroni graphics processing system according to claim 5, characterized in that, The main control module is also configured to: Based on the Hu moment analysis algorithm, feature extraction is performed on the current graphic contour to obtain the current graphic feature information.
7. The machine vision-based Kroni graphics processing system according to claim 5, characterized in that, The main control module is also configured to: The feature values of the current graphic feature information are compared with the preset target feature values to obtain the feature deviation value; When the characteristic deviation value is lower than a preset threshold, the current vibration pattern is identified as the target vibration pattern.
8. The machine vision-based Kroni graphics processing system according to claim 2, characterized in that, The main control module is also configured to: When the current graphic feature information does not meet the preset target feature conditions, a control command is generated based on a preset PID algorithm or reinforcement learning algorithm, and the control command is transmitted to the vibration excitation module so that the vibration plate generates the next vibration pattern; the control command includes the next vibration parameters.
9. The machine vision-based Kroni graphics processing system according to claim 5, characterized in that, The main control module is also configured to: The current graphic feature information is processed based on the Fast Fourier Transform to obtain the modal parameters corresponding to the current vibration graphic, and the modal parameters are stored.
10. A machine vision-based Kroni image processing method, characterized in that, The method, applied to the machine vision-based Kroni graphics processing system as described in any one of claims 1 to 9, comprises: Transmit the current vibration parameters to the vibration excitation module and acquire the current vibration image transmitted by the vision acquisition module; Feature extraction is performed on the current vibration pattern to obtain the current pattern feature information; When the current graphic feature information meets the preset target feature conditions, the current vibration graphic is confirmed as the target vibration graphic.