Zoom imaging and stray light suppression-based multi-target high signal-to-noise synchronous detection method, system and equipment and medium

Abstract

The invention provides a multi-target high-signal-to-noise synchronous detection method, system and device based on zoom imaging and stray light suppression and a medium, and belongs to the technical field of visual monitoring, the method comprises the following steps: adjusting the diameter of a parallel beam and the type of a resolution plate for simulating a target module to be detected, and generating a simulation target corresponding to a field angle and an angular resolution; adjusting the simulation light source module, and generating a parallel surface light beam which is normally incident to a simulation target; the position of the zoom lens group and the focal length of imaging are adjusted according to the size and the distance of the to-be-measured target; the detector module collects an optical image of a target to be detected, converts the optical image into a digital image signal and outputs the digital image signal, and the edge calculation module performs low illumination enhancement, high illumination suppression, image segmentation and target feature extraction on the digital image signal and performs defect identification, size measurement and state monitoring; and fusing step-by-step detection results of different to-be-detected targets, and synchronously displaying multi-target detection data. According to the invention, multi-target high-signal-noise synchronous detection of industrial equipment and parts is realized, and the detection efficiency is high.

Description

Technical Field

[0001] The present application belongs to the field of visual monitoring technology, and specifically relates to a multi-target high signal-to-noise synchronous detection method, system, equipment and medium based on zoom imaging and stray light suppression. Background Art

[0002] In industrial production, equipment status monitoring and part quality inspection are key to ensuring efficient and safe production. Traditional inspection methods, which rely primarily on manual labor, have numerous limitations, including low efficiency, strong subjectivity, and difficulty in quantifying data. In high-precision manufacturing, manual inspection accuracy and consistency are particularly difficult to guarantee, and in hazardous working environments, manual inspection poses significant safety risks.

[0003] As a new means of industrial production inspection and monitoring, visual inspection can break through the limitations of traditional manual inspection and achieve comprehensive monitoring of equipment operating status and industrial parts parameters through non-contact, high-precision, multi-dimensional optical perception methods. However, existing visual inspection systems still have many limitations in their use in industrial scenarios. First, a single focal length is difficult to take into account the detection needs of targets of different distances and sizes. The relevant patent uses a double-layer visual inspection device to adjust the detection distance, but the field of view is limited and cannot detect multiple targets simultaneously. Secondly, the complex lighting in the industrial environment leads to a decrease in image quality. The relevant patent uses a zoom optical system and lacks an effective stray light suppression design, which affects the extraction of target details. Thirdly, the relevant patent relies on mechanical flipping or fixed field of view, which makes it difficult to simultaneously detect differentiated targets and is prone to damage to precision components.

[0004] In summary, there is an urgent need for a visual inspection method that can adapt to the detection needs of targets of different distances and sizes, effectively suppress stray light under complex lighting conditions, and improve image quality, so as to achieve multi-target high signal-to-noise synchronous detection of industrial equipment and parts. Summary of the Invention

[0005] In a first aspect, an embodiment of the present application provides a multi-target high signal-to-noise synchronous detection method based on zoom imaging and stray light suppression, comprising the following steps: S1. Adjust the parallel beam diameter and resolution plate type of the simulated target module according to the size and distance of the target to be measured, and generate a simulated target with the corresponding field of view angle and angular resolution; S2. Adjust the simulated light source module so that the light beam generated by the xenon lamp is reflected by the parabolic reflector to form a parallel beam incident on the simulated target; S3. Adjust the position of the zoom lens assembly and the focal length of the image according to the size and distance of the target to be measured, and gradually block stray light through the layered circular apertures of the objective lens diaphragm; S4. The detector module collects the optical image of the target to be measured and converts it into a digital image signal and outputs it to the edge computing module; S5. The edge computing module performs low-light enhancement, high-light suppression, image segmentation, and target feature extraction on the digital image signal. It then performs defect identification, dimensional measurement, and condition monitoring on the extracted target features. S6. Fuse the step-by-step detection results of different targets to be detected and synchronously display the multi-target detection data.

[0006] Furthermore, the specific steps of step S1 are as follows: S11. Determine the size of the target to be measured based on the application scenario and adjust the diameter of the variable aperture to match the size of the target to be measured; S12. Determine the angular resolution requirements of the target to be measured according to the application scenario and select the resolution board type; S13. Adjust the variable aperture diaphragm to the selected diameter and install the selected resolution plate to generate a simulated target with corresponding field of view angle and angular resolution.

[0007] Furthermore, the specific steps of step S2 are as follows: S21. Start the xenon lamp and preheat it until the output state change amplitude is less than the set threshold; S22. Adjust the position and angle of the parabolic reflector so that the beam generated by the xenon lamp is reflected by the parabolic reflector to form a parallel beam; S23. Calibrate the direction of the parallel beam so that the parallel beam is incident on the simulated target.

[0008] Furthermore, the specific steps of step S3 are as follows: S31. According to the distance and size of the target to be measured, the electric adjustment zoom lens group moves along the guide rail until the target position, thereby adjusting the focal length of the imaging system; S32. Use a three-layer objective lens aperture to gradually attenuate stray light; S33. The aberration caused by the movement of the zoom lens group is compensated in real time by the focusing lens group.

[0009] Furthermore, the specific steps of step S4 are as follows: S41. Select a CMOS industrial camera that meets the pixel requirements for the detector module. S42. The detector module is set at the focal plane of the imaging system; S43. The detector module collects the optical image of the analog target, converts it into a digital signal image, and transmits it to the edge computing module through the interface.

[0010] Furthermore, the specific steps of step S5 are as follows: S51. The edge computing module first uses the Retinex algorithm to enhance low-light areas and the U-Net algorithm to suppress high-light areas on the digital signal image to complete preprocessing. S52. Use the deep learning convolutional neural network (RCNN) algorithm to extract target features from the preprocessed digital signal image and identify the target area and feature information; S53. Classify and identify the extracted target features according to the application scenario, and use the pre-configured defect recognition model, dimension measurement algorithm, and condition monitoring model to perform defect recognition, dimension measurement, and condition monitoring, respectively, to obtain detailed detection data for each target to be measured.

[0011] Furthermore, the specific steps of step S6 are as follows: S61. Determine whether all targets to be tested have completed detection; If yes, go to step S63; If not, proceed to step S62; S62. The detection results of different targets to be tested are cached in chronological order, and the same target type is associated by timestamp, the detection of the next target to be tested is started, and the process returns to step S1; S63. After the detection results of each target are integrated, they are output on the display interface of the edge module according to a preset refresh frequency.

[0012] In a second aspect, an embodiment of the present application further provides a multi-target high signal-to-noise synchronous detection system based on zoom imaging and stray light suppression, comprising: The target simulation module includes a variable aperture diaphragm and a resolution plate; the variable aperture diaphragm is used to adjust the beam diameter to simulate targets with different field angles, and the resolution plate is used to provide different line pairs to simulate angular resolution; The simulated light source module includes a xenon lamp and a parabolic reflector to generate a parallel light beam for the target to be measured; Zoom imaging and stray light suppression module, including: The objective lens aperture includes several layers of proportional reduction apertures, which are used to gradually attenuate stray light; The objective lens group is used to receive the light beam from the target to be measured and form a primary image. The focal length is fixed and it cooperates with the zoom lens group to achieve continuous zooming; A zoom lens group, used to adjust the focal length by moving the electric position device; Focusing lens group, used for aberration compensation; The detector module uses a CMOS industrial camera and is set at the focal plane of the imaging system; The edge computing module performs low-light enhancement, high-light suppression, image segmentation, and target feature extraction on images, and then performs defect recognition, dimension measurement, and status monitoring on the extracted target features.

[0013] In a third aspect, an embodiment of the present application further provides an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of the multi-target high signal-to-noise synchronous detection method based on zoom imaging and stray light suppression as described in the first aspect are implemented.

[0014] In a fourth aspect, an embodiment of the present application further provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the multi-target high signal-to-noise synchronous detection method based on zoom imaging and stray light suppression as described in the first aspect are implemented.

[0015] It can be seen from the above technical solutions that this application has the following advantages: The multi-target high signal-to-noise synchronous detection method, system, equipment and medium based on zoom imaging and stray light suppression provided in this application realize high-precision, high signal-to-noise ratio detection of targets of different distances and sizes in industrial production, which can improve the efficiency, accuracy and adaptability of industrial detection, reduce the risks and costs of manual detection, and provide guarantees for the stable operation of industrial equipment and the high-quality production of parts. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solution of the present application, the following is a brief introduction to the drawings required for the description. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0017] Figure 1 It is a flow chart of the multi-target high signal-to-noise synchronous detection method based on zoom imaging and stray light suppression of the present invention.

[0018] Figure 2 Schematic diagram of a multi-target high signal-to-noise synchronous detection system based on zoom imaging and stray light suppression according to the present invention.

[0019] Figure 3 This is a structural diagram of a multi-target high signal-to-noise synchronous detection system based on zoom imaging and stray light suppression according to the present invention.

[0020] Among them, 1-xenon lamp; 2-parabolic reflector; 3-variable aperture; 4-resolution plate; 5-collimating mirror; 6-objective aperture; 7-objective lens group; 8-magnification lens group; 9-electric displacement device; 10-field aperture; 11-focusing lens group; 12-detector module; 13-edge computing module. DETAILED DESCRIPTION

[0021] The various embodiments of the present disclosure will be described in more detail below in the specific steps of the multi-target high signal-to-noise synchronous detection method based on zoom imaging and stray light suppression. The present disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of the present disclosure to the specific embodiments disclosed herein, but rather that the present disclosure should be understood to cover all adjustments, equivalents, and / or alternatives that fall within the spirit and scope of the various embodiments of the present disclosure.

[0022] For example, in industrial production, equipment status monitoring and part quality inspection are key to ensuring efficient and safe production. Traditional inspection methods rely primarily on manual labor, which has numerous limitations, such as low time efficiency, strong subjectivity, and difficulty in quantifying data. In high-precision manufacturing, manual inspection accuracy and consistency are particularly difficult to guarantee, and in hazardous working environments, manual inspection poses significant safety risks.

[0023] As a new means of industrial production inspection and monitoring, problem-solving detection can break through the limitations of traditional manual inspection and achieve comprehensive monitoring of equipment operating status and industrial parts parameters through non-contact, high-precision, multi-dimensional optical perception methods. However, existing visual inspection systems still have many limitations in their use in industrial scenarios. First, a single focal length is difficult to take into account the detection needs of targets of different distances and sizes. The relevant patents use a double-layer visual inspection device to adjust the detection distance, but the field of view is limited and cannot detect multiple targets simultaneously. Secondly, the complex lighting in the industrial environment leads to a decline in image quality. The relevant patents use a zoom optical system and lack an effective stray light suppression design, which affects the extraction of target details. Thirdly, the relevant patents rely on mechanical flipping or fixed fields of view, which makes it difficult to synchronously detect differentiated targets and is prone to damage to precision components.

[0024] Currently, there is an urgent need for a visual inspection method that can adapt to the detection needs of targets of different distances and sizes, effectively suppress stray light under complex lighting conditions, and improve image quality, so as to achieve multi-target high signal-to-noise synchronous detection of industrial equipment and parts.

[0025] To address the above issues, this embodiment provides a multi-target high signal-to-noise synchronous detection method based on zoom imaging and stray light suppression, which can achieve high-precision detection of targets of different sizes and distances, while effectively suppressing the interference of stray light, improving image quality, and thus achieving high signal-to-noise synchronous detection of multiple targets.

[0026] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0027] See also Figure 1 FIG. 1 is a flow chart of a multi-target high signal-to-noise synchronous detection method based on zoom imaging and stray light suppression in a specific embodiment. The method includes the following steps: S1. Adjust the parallel beam diameter and resolution plate type of the simulated target module according to the size and distance of the target to be measured, and generate a simulated target with the corresponding field of view angle and angular resolution; It should be noted that by adjusting the parallel beam diameter and resolution plate type of the simulated target module according to the size and distance of the target to be measured, a simulated target that closely matches the actual detection requirements can be generated. This not only improves the accuracy and realism of the simulation, but also provides a precise object for subsequent imaging and detection processes, allowing the entire detection system to better adapt to the detection needs of targets of different sizes and distances. S2. Adjust the simulated light source module so that the light beam generated by the xenon lamp is reflected by the parabolic reflector to form a parallel beam incident on the simulated target; It should be noted that adjusting the simulated light source module so that the light beam generated by the xenon lamp forms a parallel beam and is incident on the simulated target can ensure that the simulated target is evenly and stably illuminated, thereby improving the imaging quality. This is because uniform illumination can reduce image errors caused by uneven illumination, thereby improving the accuracy of subsequent image processing and target recognition. S3. Adjust the position of the zoom lens assembly and the focal length of the image according to the size and distance of the target to be measured, and gradually block stray light through the layered circular apertures of the objective lens diaphragm; It should be noted that by adjusting the position of the zoom lens group and the focal length of the image according to the size and distance of the target to be measured, flexible imaging of different targets can be achieved. At the same time, the layered circular opening diaphragms of the objective lens diaphragm gradually block stray light, reducing ambient light interference and improving the signal-to-noise ratio of the imaging system. This makes the imaging results clear and accurate, providing a high-quality image foundation for subsequent target feature extraction and analysis. S4. The detector module collects the optical image of the target to be measured and converts it into a digital image signal and outputs it to the edge computing module; It should be noted that the detector module collects optical images of the target to be measured and converts them into digital image signals, which are then output to the edge computing module. This achieves efficient conversion from optical signals to digital signals, providing the necessary conditions for subsequent digital image processing. The use of high-performance detector modules ensures that the collected images have high resolution and high frame rate, thereby improving the real-time performance and accuracy of the entire detection system. S5. The edge computing module performs low-light enhancement, high-light suppression, image segmentation, and target feature extraction on the digital image signal. It then performs defect identification, dimensional measurement, and condition monitoring on the extracted target features. It should be noted that the edge computing module performs image processing operations on digital image signals, including low-light enhancement, high-light suppression, image segmentation, and target feature extraction. These processing steps can improve the overall image quality and accurately identify target areas and feature information. The extracted target features are then used for defect identification, dimensional measurement, and status monitoring. Detailed inspection data for each target can be obtained, providing a key basis for quality control and equipment maintenance in industrial production. S6. Fusing the step-by-step detection results of different targets to be detected and synchronously displaying multi-target detection data; It should be noted that the step-by-step detection results of different targets to be tested are fused, and the multi-target detection data are displayed synchronously, so that operators can intuitively view the detection results of multiple targets in a unified interface; data fusion and synchronous display not only improve the readability and ease of use of the detection results, but also make it easier for operators to promptly discover and deal with problems in multiple targets, thereby realizing efficient synchronous monitoring of multiple targets.

[0028] This embodiment achieves high-precision detection of targets of different sizes and distances, while effectively suppressing the interference of stray light, improving image quality, and thus realizing high signal-to-noise synchronous detection of multiple targets; providing a basis for subsequent defect identification, dimensional measurement, and status monitoring, ensuring the efficiency and safety of industrial production.

[0029] Furthermore, as a refinement and expansion of the specific implementation of the above embodiment, in order to fully illustrate the specific implementation process of this embodiment, another multi-target high signal-to-noise synchronous detection method based on zoom imaging and stray light suppression is provided, which includes the following steps: S1. According to the size and distance of the target to be measured, adjust the parallel beam diameter and resolution plate type of the simulated target module to generate a simulated target with corresponding field of view angle and angular resolution; the specific steps of step S1 are as follows: S11. Determine the size of the target to be measured based on the application scenario and adjust the diameter of the variable aperture to match the size of the target to be measured; It should be noted that the diameter range of the variable aperture is 10mm to 50mm. 10mm corresponds to targets with a small field of view, such as instrument readings or part defect detection in industrial equipment, and 50mm corresponds to targets with a large field of view, such as fault monitoring of industrial equipment or inspection of large parts. S12. Determine the angular resolution requirements of the target to be measured according to the application scenario and select the resolution board type; Specifically, the resolution plate includes an A plate and a B plate; Plate A has 0.1mm line pairs, simulating instrument scale readings and minor defects in industrial parts; Plate B has 1mm line pairs, simulating industrial part size boundaries and equipment fault identification features; S13. Adjust the variable aperture diaphragm to the selected diameter and install the selected resolution plate to generate a simulated target with the corresponding field of view angle and angular resolution; S2. Adjust the simulated light source module so that the light beam generated by the xenon lamp is reflected by the parabolic reflector to form a parallel beam incident on the simulated target. The specific steps of step S2 are as follows: S21. Start the xenon lamp and preheat it until the output state change amplitude is less than the set threshold; S22. Adjust the position and angle of the parabolic reflector so that the beam generated by the xenon lamp is reflected by the parabolic reflector to form a parallel beam; S23. Calibrate the direction of the parallel beam so that the parallel beam is incident on the simulated target; S3. Adjust the position of the zoom lens group and the focal length of the imaging according to the size and distance of the target to be measured, and block stray light step by step through the layered circular opening diaphragm of the objective diaphragm; the specific steps of step S3 are as follows: S31. According to the distance and size of the target to be measured, the electric adjustment zoom lens group moves along the guide rail until the target position, thereby adjusting the focal length of the imaging system; It should be noted that the zoom lens set has a continuous electric zoom range of 30-150mm. The wide-range target corresponds to a short focal length of 30mm, and the small-range target corresponds to a long focal length of 150mm. The movement accuracy is better than ±5μm, and the zoom time is <0.5s. S32. Use a three-layer objective lens aperture to gradually attenuate stray light; It should be noted that the objective lens adopts a three-layer circular aperture with an opening diameter ratio of 1:0.8:0.6. Through the proportional reduction design, the edge diffraction light generated by the outer aperture is blocked and attenuated by the inner aperture, reducing the interference of ambient light; S33. Real-time compensation of aberrations caused by movement of the zoom lens group by the focusing lens group; It should be noted that real-time compensation can ensure that the image plane drift is less than 0.01mm; S4. The detector module collects the optical image of the target to be measured and converts it into a digital image signal and outputs it to the edge computing module; the specific steps of step S4 are as follows: S41. Select a CMOS industrial camera that meets the pixel requirements for the detector module. For example, the detector module uses a 20-megapixel CMOS industrial camera to capture optical images with high resolution and high frame rate. The image acquisition frame rate is 30fps and supports HDR mode to adapt to image acquisition under different lighting conditions. S42. The detector module is set at the focal plane of the imaging system; S43. The optical image of the analog target is collected by the detector module, and after converting the digital signal image, it is transmitted to the edge computing module through the interface; It should be noted that the interface uses a high-speed interface, such as USB3.0 / GigE interface; S5. The edge computing module performs low-light enhancement, high-light suppression, image segmentation, and target feature extraction on the digital image signal. It then performs defect identification, dimensional measurement, and condition monitoring on the extracted target features. The specific steps of step S5 are as follows: S51. The edge computing module first uses the Retinex algorithm to enhance low-light areas and the U-Net algorithm to suppress high-light areas on the digital signal image to complete preprocessing. Specifically, the Retinex algorithm is used to enhance low-light areas: The image I(x,y) Split into lighting L(x,y) and the reflected component R(x,y) : I ( x , y )= L ( x , y )⋅ R ( x , y ) Estimate the illumination component by logarithmic transformation and Gaussian filtering:

[0030] Among them, the final enhanced image:

[0031] Among them, CLAHE is a function of limiting contrast adaptive histogram equalization to further optimize the dynamic range; Use the U-Net algorithm to suppress high-light areas: U-Net implements image segmentation through an encoder-decoder structure; the encoder part extracts features through convolution and downsampling, and the decoder part restores spatial resolution through upsampling and skip connections; The loss function uses Dice coefficient loss:

[0032] Among them, p i is the predicted probability, g i is the true label; It should be noted that low-light enhancement improves the brightness and contrast of the image in low-light areas, while high-light area suppression prevents overexposure and improves the overall signal-to-noise ratio of the image. S52. Use the deep learning convolutional neural network (RCNN) algorithm to extract target features from the preprocessed digital signal image and identify the target area and feature information; S53. Classify and identify the extracted target features according to the application scenario, use the pre-configured defect recognition model, dimensional measurement algorithm and condition monitoring model to perform defect recognition, dimensional measurement and condition monitoring respectively, and obtain detailed detection data for each target to be measured; S6. The step-by-step detection results of different targets to be tested are integrated and the multi-target detection data is displayed synchronously; the specific steps of step S6 are as follows: S61. Determine whether all targets to be tested have completed detection; If yes, go to step S63; If not, proceed to step S62; S62. The detection results of different targets to be tested are cached in chronological order, and the same target type is associated by timestamp, the detection of the next target to be tested is started, and the process returns to step S1; S63. After the detection results of each target are integrated, they are output in the display interface of the edge module according to the preset refresh frequency; It should be noted that the detection results of each target to be measured are fused according to the display requirements, for example, multi-target data are updated synchronously in columns, such as displaying instrument readings on the left and part defects on the right.

[0033] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0034] like Figure 2As shown, the following is an embodiment of the multi-target high signal-noise synchronous detection system based on zoom imaging and stray light suppression provided by an embodiment of the present disclosure. This system and the multi-target high signal-noise synchronous detection method based on zoom imaging and stray light suppression in the above-mentioned embodiments belong to the same inventive concept. For details not fully described in the embodiment of the multi-target high signal-noise synchronous detection system based on zoom imaging and stray light suppression, please refer to the above-mentioned embodiment of the multi-target high signal-noise synchronous detection method based on zoom imaging and stray light suppression.

[0035] The system includes: The target simulation module includes a variable aperture 3 and a resolution plate 4; the variable aperture 3 is used to adjust the beam diameter to simulate targets with different field angles, and the resolution plate 4 is used to provide different line pairs to simulate angular resolution; The simulated light source module includes a xenon lamp 1 and a parabolic reflector 2 to generate a parallel light beam for the target to be measured; Zoom imaging and stray light suppression module, including: The objective lens aperture 6 includes several layers of proportional reduction apertures, which are used to gradually attenuate stray light; The objective lens group 7 is used to receive the light beam from the target to be measured and form a primary image. The focal length is fixed and it cooperates with the zoom lens group 8 to achieve continuous zooming; The zoom lens group 8 is used to adjust the focal length by moving the electric displacement device 9; Focusing lens group 11, used for aberration compensation; The detector module 12 adopts a CMOS industrial camera and is set at the focal plane of the imaging system; The edge computing module 13 performs low-light enhancement, high-light suppression, image segmentation, and target feature extraction on the image, and then performs defect recognition, size measurement, and status monitoring on the extracted target features; The edge computing module 13 is equipped with a display device to output the detection results of the target to be measured; It should be noted that, as shown in the figure, the light emitted by the xenon lamp 1 forms a parallel beam after passing through the parabolic reflector 2 to irradiate the variable aperture 3 to simulate the field of view angle, passes through the resolution plate 4 to simulate the angular resolution, and then passes through the collimating lens 5, enters the objective lens diaphragm 6 to eliminate stray light, and then enters the objective lens group 7 of the imaging system, the magnification lens group 8 set on the electric displacement device, and then passes through the field of view diaphragm 10, reaches the focusing lens group 11 for aberration compensation, and finally reaches the industrial camera of the detector module 10. The industrial camera provides the collected image to the edge computing module 13 for processing, extracts the target features, and displays the processing results.

[0036] This embodiment realizes multi-target high signal-to-noise synchronous detection of industrial equipment and parts through the interactive collaboration of the target simulation module, simulated light source module, zoom imaging and stray light suppression module, detector module and edge computing module, thereby improving the efficiency and accuracy of industrial detection and reducing the safety hazards of manual detection.

[0037] The multi-target high signal-to-noise synchronous detection method based on zoom imaging and stray light suppression provided in the embodiment of the present application can be applied to electronic devices. Those skilled in the art will understand that the electronic device structure involved in the embodiment of the present invention does not constitute a limitation on the electronic device, and the electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange components differently. In the embodiment of the present invention, the electronic device includes but is not limited to a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of the present application described and / or required herein.

[0038] The electronic device may include a processor, an external memory interface, an internal memory, a universal serial bus (USB) interface, a charging management module, a power management module, a battery, a wireless communication module, an audio module, a speaker, a microphone, a sensor module, a button, a camera, a display, and a SIM card interface, etc.

[0039] It is understood that the structures illustrated in the embodiments of the present application do not constitute specific limitations on the electronic device. In other embodiments of the present application, the electronic device may include more or fewer components than shown, or combine or separate certain components, or arrange the components differently. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0040] A processor may include one or more processing units, such as a central processing unit (CPU), an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors.

[0041] The processor can be the nerve center and command center of the electronic device. The controller can generate operation control signals based on the instruction opcode and timing signal to complete the control of instruction fetching and execution.

[0042] The processor may also include a memory for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. This memory can store instructions or data that the processor has just used or is reusing. If the processor needs to use the instruction or data again, it can directly call it from the memory. This avoids repeated accesses, reduces processor latency, and thus improves system efficiency.

[0043] The electronic device implements the multi-target high signal-to-noise synchronous detection method based on zoom imaging and stray light suppression of the present application, which adjusts the parallel beam diameter and resolution plate type of the simulated target module according to the size and distance of the target to be measured to generate a simulated target with corresponding field of view angle and angular resolution; adjusts the simulated light source module so that the light beam generated by the xenon lamp is reflected by the parabolic reflector to form a parallel beam incident on the simulated target; adjusts the position of the zoom lens group and the focal length of the imaging according to the size and distance of the target to be measured, and blocks stray light step by step through the layered circular opening diaphragm of the objective lens diaphragm; the detector module collects the optical image of the target to be measured and converts it into a digital image. The digital image signal is output to the edge computing module; the edge computing module performs low-light enhancement, high-light suppression, image segmentation and target feature extraction on the digital image signal, and then performs defect recognition, size measurement and status monitoring on the extracted target features; the step-by-step detection results of different targets to be measured are integrated, and the technical solution of synchronously displaying multi-target detection data is achieved through zoom imaging and stray light suppression technology. Multi-target high signal-to-noise synchronous detection of industrial equipment and parts is achieved, which solves the problems of low efficiency, strong subjectivity and difficulty in quantifying data of traditional detection methods, improves the efficiency and accuracy of industrial detection, and reduces the safety hazards of manual detection.

[0044] The storage medium provided in the present application stores a program product that can implement a multi-target high signal-to-noise synchronous detection method based on zoom imaging and stray light suppression.

[0045] The multi-target high signal-to-noise synchronous detection method based on zoom imaging and stray light suppression includes: adjusting the parallel beam diameter and resolution plate type of the simulated target module according to the size and distance of the target to be measured, and generating a simulated target with a corresponding field of view angle and angular resolution; adjusting the simulated light source module so that the light beam generated by the xenon lamp is reflected by the parabolic reflector to form a parallel beam incident on the simulated target; adjusting the position of the zoom lens group and the focal length of the imaging according to the size and distance of the target to be measured, and gradually blocking stray light through the layered circular opening diaphragm of the objective lens diaphragm; the detector module collects the optical image of the target to be measured, and converts it into a digital image signal and outputs it to the edge computing module; the edge computing module performs low-light enhancement, high-light suppression, image segmentation and target feature extraction on the digital image signal, and then performs defect recognition, size measurement and status monitoring on the extracted target features; the step-by-step detection results of different targets to be measured are integrated, and the multi-target detection data is synchronously displayed.

[0046] In some possible embodiments, the multi-target high signal-to-noise synchronous detection method based on zoom imaging and stray light suppression disclosed herein can be implemented in the form of a program product, which includes program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps of various exemplary embodiments of the present disclosure described in the above "Exemplary Method" section of this specification.

[0047] The storage medium of the present disclosure can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, a system, device or component of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0048] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A multi-target high signal-to-noise synchronous detection method based on zoom imaging and stray light suppression, characterized in that: The steps include: S1. Adjust the parallel beam diameter and resolution plate type of the simulated target module according to the size and distance of the target to be measured, and generate a simulated target with the corresponding field of view angle and angular resolution; S2. Adjust the simulated light source module so that the light beam generated by the xenon lamp is reflected by the parabolic reflector to form a parallel beam incident on the simulated target; S3. Adjust the position of the zoom lens assembly and the focal length of the image according to the size and distance of the target to be measured, and gradually block stray light through the layered circular apertures of the objective lens diaphragm; S4. The detector module collects the optical image of the target to be measured and converts it into a digital image signal and outputs it to the edge computing module; S5. The edge computing module performs low-light enhancement, high-light suppression, image segmentation, and target feature extraction on the digital image signal. It then performs defect identification, dimensional measurement, and condition monitoring on the extracted target features. S6. Fuse the step-by-step detection results of different targets to be detected and synchronously display the multi-target detection data.

2. The multi-target high signal-to-noise synchronous detection method based on zoom imaging and stray light suppression according to claim 1, characterized in that: The specific steps of step S1 are as follows: S11. Determine the size of the target to be measured based on the application scenario and adjust the diameter of the variable aperture to match the size of the target to be measured; S12. Determine the angular resolution requirements of the target to be measured according to the application scenario and select the resolution board type; S13. Adjust the variable aperture diaphragm to the selected diameter and install the selected resolution plate to generate a simulated target with corresponding field of view angle and angular resolution.

3. The multi-target high signal-to-noise synchronous detection method based on zoom imaging and stray light suppression according to claim 2, characterized in that: The specific steps of step S2 are as follows: S21. Start the xenon lamp and preheat it until the output state change amplitude is less than the set threshold; S22. Adjust the position and angle of the parabolic reflector so that the beam generated by the xenon lamp is reflected by the parabolic reflector to form a parallel beam; S23. Calibrate the direction of the parallel beam so that the parallel beam is incident on the simulated target.

4. The multi-target high signal-to-noise synchronous detection method based on zoom imaging and stray light suppression according to claim 3, characterized in that: The specific steps of step S3 are as follows: S31. According to the distance and size of the target to be measured, the electric adjustment zoom lens group moves along the guide rail until the target position, thereby adjusting the focal length of the imaging system; S32. Use a three-layer objective lens aperture to gradually attenuate stray light; S33. The aberration caused by the movement of the zoom lens group is compensated in real time by the focusing lens group.

5. The multi-target high signal-to-noise synchronous detection method based on zoom imaging and stray light suppression according to claim 4, characterized in that: The specific steps of step S4 are as follows: S41. Select a CMOS industrial camera that meets the pixel requirements for the detector module. S42. The detector module is set at the focal plane of the imaging system; S43. The detector module collects the optical image of the analog target, converts it into a digital signal image, and transmits it to the edge computing module through the interface.

6. The multi-target high signal-to-noise synchronous detection method based on zoom imaging and stray light suppression according to claim 5, characterized in that: The specific steps of step S5 are as follows: S51. The edge computing module first uses the Retinex algorithm to enhance low-light areas and the U-Net algorithm to suppress high-light areas on the digital signal image to complete preprocessing. S52. Use the deep learning convolutional neural network (RCNN) algorithm to extract target features from the preprocessed digital signal image and identify the target area and feature information; S53. Classify and identify the extracted target features according to the application scenario, and use the pre-configured defect recognition model, dimension measurement algorithm, and condition monitoring model to perform defect recognition, dimension measurement, and condition monitoring, respectively, to obtain detailed detection data for each target to be measured.

7. The multi-target high signal-to-noise synchronous detection method based on zoom imaging and stray light suppression according to claim 6, characterized in that: The specific steps of step S6 are as follows: S61. Determine whether all targets to be tested have completed detection; If yes, go to step S63; If not, proceed to step S62; S62. The detection results of different targets to be tested are cached in chronological order, and the same target type is associated by timestamp, the detection of the next target to be tested is started, and the process returns to step S1; S63. After the detection results of each target are integrated, they are output on the display interface of the edge module according to a preset refresh frequency.

8. A multi-target high signal-to-noise synchronous detection system based on zoom imaging and stray light suppression, characterized in that: include: The target simulation module to be measured includes a variable aperture diaphragm and a resolution plate; The variable aperture diaphragm is used to adjust the beam diameter to simulate targets with different field angles, and the resolution plate is used to provide different line pairs to simulate angular resolution; The simulated light source module includes a xenon lamp and a parabolic reflector to generate a parallel light beam for the target to be measured; Zoom imaging and stray light suppression module, including: The objective lens aperture includes several layers of proportional reduction apertures, which are used to gradually attenuate stray light; The objective lens group is used to receive the light beam from the target to be measured and form a primary image. The focal length is fixed and it cooperates with the zoom lens group to achieve continuous zooming; A zoom lens group, used to adjust the focal length by moving the electric position device; Focusing lens group, used for aberration compensation; The detector module uses a CMOS industrial camera and is set at the focal plane of the imaging system; The edge computing module performs low-light enhancement, high-light suppression, image segmentation, and target feature extraction on images, and then performs defect recognition, dimension measurement, and status monitoring on the extracted target features.

9. An electronic device, characterized in that: The invention comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the multi-target high signal-to-noise synchronous detection method based on zoom imaging and stray light suppression are implemented as claimed in any one of claims 1 to 7.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the multi-target high signal-to-noise synchronous detection method based on zoom imaging and stray light suppression are implemented as described in any one of claims 1 to 7.

Images