Thermos cup liner detection method and device based on special projection of 3D camera

Abstract

The present disclosure proposes a method and device for detecting the inner liner of a thermos cup based on special projection of a 3D camera. The method obtains a detection image of at least one surface of the inner liner of the thermos cup to be tested. The detection image is a projected image of at least one surface of the inner liner of the thermos cup to be tested captured by the 3D camera. Since the projected image is obtained by projecting a preset image onto at least one surface of the inner liner of the thermos cup to be tested using a projection device, and the preset image is obtained by the projection device based on target brightness, rather than determining the brightness based on current, the accuracy of the target brightness can be improved to a certain extent; finally, based on the detection image, the size of the inner liner of the thermos cup to be tested is calculated; based on the relationship between the size and the preset standard size, it is determined whether the inner liner of the thermos cup to be tested is qualified, thereby improving the accuracy of the detection result.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a method and device for detecting the inner liner of a thermos cup based on special projection of a 3D camera. Background Art

[0002] During the thermos production process, the welding and vacuuming of the liner significantly impact the thermal insulation performance of the thermos. During the manufacturing process, the liner may undergo slight deformation due to various factors, such as temperature and pressure. Therefore, prior to welding, the liner must be inspected to ensure precise alignment.

[0003] However, in related technologies, 3D structure measurement typically utilizes 3D structured light measurement, a technique used in 3D scanning. A 3D structured light camera typically utilizes a combination of several industrial visible light cameras and a projector (also referred to as an optical machine or projection device, though this distinction will not be made hereafter). The measurement principle of this system is to first project a designed grating-coded pattern onto the inner surface of a thermos cup using a projector. This pattern is then captured synchronously by a camera. A phase decoding algorithm is then applied to the captured grating image set, using this phase information to match pixel homonymous points. Triangulation is then used to reconstruct a 3D point cloud of the measured object.

[0004] In practical applications, the quality of the captured fringe pattern determines the accuracy and density of 3D reconstruction. Before leaving the factory, thermos liner products must undergo a conformity assessment. To improve efficiency, these products are typically measured across multiple production lines. This requires not only the accuracy of each camera's measurement but also the consistency of the inspected liner. This means that the parameters of the corresponding 3D cameras on a single production line must be identical.

[0005] Currently, 3D cameras primarily control the brightness of projected stripes by controlling the brightness of the light engine. Related technologies adjust brightness by varying the current of the light engine's light source or by using pulse-width modulation (PWM). However, light sources can vary between the same light engine model. Therefore, even if two light engines are controlled to project with the same current, the brightness of the projected stripes can vary. Therefore, a new detection method is urgently needed to ensure consistent brightness across the light engine and improve detection accuracy. Summary of the Invention

[0006] The present disclosure proposes a method and device for detecting the inner liner of a thermos cup based on special projection of a 3D camera.

[0007] In a first aspect of the present disclosure, an embodiment provides a method for detecting the inner liner of a thermos cup based on special projection of a 3D camera. The method is applied to a system for detecting the inner liner of a thermos cup based on special projection of a 3D camera. The detection system includes a projection device, a 3D camera, and a processor. The 3D camera includes an image acquisition device and a projection device. The method includes:

[0008] Acquire a detection image of at least one surface of the inner liner of the thermos cup to be tested; the detection image is a projection image of at least one surface of the inner liner of the thermos cup to be tested acquired by the image acquisition device; the projection image is obtained by projecting a preset image onto at least one surface of the inner liner of the thermos cup to be tested using the projection device; the preset image is obtained by projecting the projection device based on a target brightness;

[0009] Based on the detection image, the size of the inner liner of the thermos cup to be tested is calculated;

[0010] Based on the relationship between the size and the preset standard size, it is determined whether the inner liner of the thermos cup to be tested is qualified.

[0011] In the embodiment of the present disclosure, the projecting device is used to project a preset image onto at least one surface of the inner liner of the thermos cup to be tested, including:

[0012] Calibrate the projection device to obtain a target brightness percentage current relationship corresponding to the projection device;

[0013] According to the target brightness percentage current relationship, a target current corresponding to the pre-acquired target brightness is determined, and a preset image is projected onto at least one surface of the inner liner of the thermos cup to be tested using the target current.

[0014] In the embodiment of the present disclosure, calibrating the projection device to obtain the target brightness percentage current relationship corresponding to the projection device includes:

[0015] Acquire a projection image set of the projection device at a current level ranging from a first threshold to a second threshold, where the second threshold is greater than the first threshold;

[0016] For any projection image, calculating the average grayscale value of the projection image;

[0017] The ratio of the average grayscale value of the projected image to the pre-acquired maximum standard grayscale value is calculated to obtain the target brightness percentage current relationship corresponding to each current level of the projection device. The maximum standard grayscale value is the average grayscale value of the projected image of the standard camera when the current level is the second threshold.

[0018] In an embodiment of the present disclosure, the method further includes:

[0019] For any projected image, if the average grayscale value of the projected image is greater than or equal to the historical average grayscale value, a projection device error message is generated;

[0020] If the average grayscale value of the projected image is less than the historical average grayscale value, calculating the ratio of the average grayscale value of the projected image to the standard grayscale value corresponding to the corresponding current level;

[0021] Calculate the mean of the ratios corresponding to each current level; and calculate the standard deviation of the ratios corresponding to each current level;

[0022] For the average grayscale value corresponding to any current level, if the average grayscale value is greater than a preset threshold, a projection device error message is generated; the preset threshold is the sum of the mean and the preset threshold, and the preset threshold is the standard deviation of the preset multiple.

[0023] In an embodiment of the present disclosure, determining a target current corresponding to a pre-acquired target brightness according to the target brightness-percentage-current relationship includes:

[0024] Determine the percentage of the grayscale value corresponding to the target brightness to the maximum standard grayscale value;

[0025] A target current is determined based on the relationship between the percentage and the target brightness percentage current.

[0026] In an embodiment of the present disclosure, the projected image set corresponding to each current level from the first threshold to the second threshold when the projection device is in a preset environment is obtained, and the preset environment is an opaque environment.

[0027] In an embodiment of the present disclosure, the first threshold is greater than the minimum current allowed by the projection device, and the second threshold is less than the maximum current allowed by the projection device.

[0028] In an embodiment of the present disclosure, if the shape of the thermos flask liner to be tested is cylindrical, detection images of two surfaces of the thermos flask liner to be tested are obtained, and the dimensions include a first diameter and a second diameter. Determining whether the thermos flask liner to be tested is qualified based on the relationship between the dimensions and the preset standard dimensions includes:

[0029] Comparing a first difference between the first diameter and the second diameter with a first preset error to obtain first deformation data of the inner liner of the thermos cup to be tested;

[0030] If the first deformation data is qualified, calculating a second difference between the first diameter and a preset standard diameter; and calculating a third difference between the second diameter and the preset standard diameter;

[0031] Comparing the second difference with a second preset error to obtain second deformation data; and comparing the third difference with the second preset error to obtain third deformation data;

[0032] Based on the second deformation data and the third deformation data, it is determined whether the inner liner of the thermos cup to be tested is qualified.

[0033] In the embodiment of the present disclosure, the step of comparing the difference between the first diameter and the second diameter with a first preset error to obtain first deformation data of the inner liner of the thermos cup to be tested includes:

[0034] If the difference between the first diameter and the second diameter is greater than the first preset error, the first deformation data of the inner liner of the thermos cup to be tested is unqualified;

[0035] If the difference between the first diameter and the second diameter is greater than the first preset error, the first deformation data of the inner liner of the thermos cup to be tested is qualified.

[0036] A second aspect of the present disclosure provides a device for detecting the inner liner of a thermos cup based on special projection of a 3D camera. The device is applied to a system for detecting the inner liner of a thermos cup based on special projection of a 3D camera. The detection system includes a projection device, a 3D camera, and a processor. The 3D camera includes an image acquisition device and a projection device. The device includes:

[0037] A detection image acquisition module is used to acquire a detection image of at least one surface of the inner liner of the thermos cup to be tested; the detection image is a projection image of at least one surface of the inner liner of the thermos cup to be tested acquired by the image acquisition device; the projection image is obtained by projecting a preset image onto at least one surface of the inner liner of the thermos cup to be tested using the projection device; the preset image is obtained by projecting the projection device based on a target brightness;

[0038] A size calculation module, configured to calculate the size of the inner liner of the thermos cup to be tested based on the detection image;

[0039] The determination module is used to determine whether the inner liner of the thermos cup to be tested is qualified based on the relationship between the size and the preset standard size.

[0040] An embodiment of the third aspect of the present disclosure provides a thermos cup liner detection system based on special projection of a 3D camera, comprising a projection device, an image acquisition device, a memory, a processor, and a computer program stored in the memory, wherein the processor implements the method described in the first aspect or any optional embodiment of the first aspect when executing the computer program.

[0041] An embodiment of the fourth aspect of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, wherein the program is executed by a processor to implement the method described in the first aspect and any optional implementation manner of the first aspect.

[0042] The technical solutions provided in the embodiments of the present disclosure have at least the following technical effects or advantages:

[0043] A detection image of at least one surface of the thermos flask liner to be tested is obtained, and the detection image is a projection image of at least one surface of the thermos flask liner to be tested acquired by an image acquisition device. Since the projection image is obtained by projecting a preset image onto at least one surface of the thermos flask liner to be tested using a projection device, and the preset image is obtained by the projection device based on target brightness, rather than determining the brightness based on current, the accuracy of the target brightness can be improved to a certain extent; finally, based on the detection image, the size of the thermos flask liner to be tested is calculated; based on the relationship between the size and the preset standard size, it is determined whether the thermos flask liner to be tested is qualified, thereby improving the accuracy of the detection result.

[0044] Additional aspects and advantages of the present disclosure will be given in part in the description below and in part will be obvious from the description below, or will be learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present disclosure. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0046] Figure 1 A flowchart of a method for detecting the inner liner of a thermos cup based on special projection of a 3D camera provided by an embodiment of the present disclosure is shown;

[0047] Figure 2 A schematic diagram of a correction scene for a method for detecting the inner liner of a thermos cup based on special projection of a 3D camera provided by an embodiment of the present disclosure is shown;

[0048] Figure 3 A schematic diagram showing the relationship between brightness percentage and current in a method for detecting the inner liner of a thermos cup based on special projection of a 3D camera provided by an embodiment of the present disclosure is shown;

[0049] Figure 4 A schematic diagram showing the relationship between brightness percentage and current in a method for detecting the inner liner of a thermos cup based on special projection of a 3D camera provided by an embodiment of the present disclosure is shown;

[0050] Figure 5A schematic diagram of a detection production line of a method for detecting the inner liner of a thermos cup based on special projection of a 3D camera provided by an embodiment of the present disclosure is shown;

[0051] Figure 6 A schematic structural diagram of a thermos cup liner detection device based on special projection of a 3D camera according to another embodiment of the present disclosure is shown;

[0052] Figure 7 A schematic structural diagram of a thermos cup liner detection system based on special projection of a 3D camera provided by an embodiment of the present disclosure is shown;

[0053] Figure 8 A schematic diagram of a storage medium provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0054] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0055] It should be noted that, unless otherwise specified, the technical or scientific terms used in the present disclosure should have the common meanings understood by those skilled in the art to which the present disclosure belongs.

[0056] In the thermos flask production process, welding and vacuuming the inner liner are key steps. To ensure the insulation effect after welding, the diameter and deformation of the stainless steel inner liner must first be accurately measured. The diameter and shape of the inner liner determine the tightness and effectiveness of welding to the outer wall. If the inner liner is deformed, it may cause an uneven gap between the outer wall and the inner liner during welding, affecting the formation of the vacuum layer and the insulation performance. During the manufacturing process, the inner liner is affected by factors such as temperature, pressure, and the material's inherent properties, and is prone to slight deformation. Especially before welding, the dimensional error and deformation of the inner liner must be monitored using precision measuring equipment. If the test results are unsatisfactory, the welding step can be skipped in time to ensure the docking accuracy of the inner and outer walls during welding, avoid poor welding, and ensure that the vacuum seal achieves the desired effect. Therefore, measuring the diameter of the inner liner and detecting its deformation play a crucial role in the ultimate insulation effect of the thermos flask.

[0057] In related technologies, 3D structure measurement in 3D scanning measurement is usually used for the measurement of 3D structures. 3D cameras mainly adjust the internal optical machine to project stripes onto the surface of the object to be measured, and then the corresponding internal ordinary camera collects the stripe pattern to complete phase analysis and 3D reconstruction. The 3D camera contains a variety of sensors, of which the optical machine and camera are the most important sensors. The 3D camera acquisition control methods mainly control the brightness of the optical machine projection, the camera exposure time, and the camera gain to control the quality of the collected image, of which controlling the brightness of the optical machine projection is the most commonly used control method. At present, 3D cameras use the simplest method of adjusting the current value of the light source when controlling the brightness of the optical machine projection. This control method is not a problem for the single 3D camera working mode, but for precision instrument measurement, especially in the case of multi-production line linkage, it is impossible to establish a unified standard for the measurement results under different production lines.

[0058] For example, if the same current value is set for fringe projection, different 3D cameras will project different fringe brightness onto the object under test due to differences in their internal optical power. The images captured by the conventional camera inside the 3D camera will also be different, resulting in different measurement results. This, due to differences in production lines, makes it impossible to guarantee consistent measurement of the object under test. For example, if production lines 1 and 2 are each equipped with the same 3D camera model and measuring workpieces in a darkroom, with identical acquisition parameters, the measurement results from lines 1 and 2 cannot be compared due to the differences in the 3D cameras on lines 1 and 2. Specifically, workpiece 1 is measured on line 1 and measures dimension 1, while workpiece 2 is measured on line 2 and measures dimension 2. When sorting the sizes of workpieces 1 and 2, if the reference measurement values ​​for dimension 1 are greater than dimension 2, theoretically, workpiece 1 should be larger than workpiece 2. However, in practice, due to differences in measurement equipment, workpiece 2 may be larger than dimension 1. The cause of this problem is the poor performance consistency of the 3D cameras on the two production lines. To address this, there are two approaches: 1. All workpieces are measured using the same 3D camera, but this affects work efficiency to a certain extent; 2. Minimize the differences between the two 3D cameras to ensure consistent performance. Because it is difficult to maintain consistent optical power between different optical engines, setting the current value of the LED light source cannot ensure consistent brightness of the projected stripes.

[0059] In view of this, the embodiment of the present application proposes a method for detecting the inner liner of a thermos cup based on special projection of a 3D camera to solve the above problems, such as Figure 1 The method for detecting the inner liner of a thermos cup based on special projection of a 3D camera according to an embodiment of the present disclosure is applied to a detection system for the inner liner of a thermos cup based on special projection of a 3D camera. The detection system includes a projection device, a 3D camera, and a processor. The 3D camera includes an image acquisition device and a projection device, and may include the following steps:

[0060] In step S11, a detection image of at least one surface of the inner liner of the thermos cup to be tested is obtained.

[0061] The detection image is a projection image of at least one surface of the inner liner of the thermos cup to be tested acquired by the image acquisition device; the projection image is obtained by projecting a preset image onto at least one surface of the inner liner of the thermos cup to be tested using the projection device; the preset image is obtained by projecting the projection device based on the target brightness;

[0062] For example, when testing a thermos flask liner, a preset image can be projected onto the flask liner, and an image of the projected flask liner can be captured. This captured image is used as a test image, and the test image is used to determine whether the flask liner is qualified. The preset image can be a geometric pattern, barcode, or other image that determines target brightness. This embodiment of the present application does not limit the specific form of the preset image, and those skilled in the art can determine it based on actual conditions, provided that the clarity of the preset image is ensured.

[0063] Aim the projection device at the inner surface of the thermos flask to be tested. Adjust the focus and angle to ensure that the preset image completely covers the inner surface of the thermos flask to be tested. Project the preset image onto the inner surface of the thermos flask to be tested. During the projection process, monitor the quality and brightness of the projected image to ensure that it meets the preset requirements.

[0064] Aim the 3D camera at the surface of the thermos liner to be tested. Adjust parameters such as focus, exposure time, and white balance to ensure optimal image clarity and color reproduction. While projecting the preset image, start the 3D camera to capture images of the thermos liner to be tested. Ensure the device remains stable during the capture process to avoid image blur or distortion.

[0065] In step S12, the size of the inner liner of the thermos cup to be tested is calculated based on the detection image;

[0066] For example, the test image can be denoised to eliminate noise and interference. Image enhancement operations, such as sharpening edges and increasing contrast, can then be performed to more accurately identify the contours and features of the thermos liner under test. Edge detection algorithms (such as the Sobel operator and Canny edge detection) can be used to identify the edges of the thermos liner under test. Edge detection helps determine the contours and dimensions of the thermos liner under test.

[0067] Extract features of the thermos liner under test, such as shape, color, and texture, from the preprocessed image. Use machine learning or deep learning algorithms (such as convolutional neural networks (CNNs)) to train and learn these extracted features to accurately identify the thermos liner under test. Once the target object is identified, further analysis of its dimensions can be performed.

[0068] In step S13, based on the relationship between the size and the preset standard size, it is determined whether the inner liner of the thermos cup to be tested is qualified.

[0069] For example, each dimension of the thermos liner to be tested is compared with a corresponding preset standard dimension. This comparison takes into account the allowable error range. Based on the comparison results, if the dimension of the thermos liner to be tested is within the preset standard dimension and its error range, the dimension is considered qualified. After comparing all dimensions, if all meet the requirements, the thermos liner to be tested is considered qualified; if any dimension fails to meet the requirements, the thermos liner to be tested is considered unqualified.

[0070] The embodiment of the present disclosure provides a method for detecting the inner liner of a thermos cup based on special projection of a 3D camera, which obtains a detection image of at least one surface of the inner liner of the thermos cup to be tested. The detection image is a projection image of at least one surface of the inner liner of the thermos cup to be tested acquired by an image acquisition device. Since the projection image is obtained by projecting a preset image onto at least one surface of the inner liner of the thermos cup to be tested using a projection device, and the preset image is obtained by the projection device based on target brightness, rather than determining the brightness based on current, the accuracy of the target brightness can be improved to a certain extent; finally, based on the detection image, the size of the inner liner of the thermos cup to be tested is calculated; based on the relationship between the size and the preset standard size, it is determined whether the inner liner of the thermos cup to be tested is qualified, thereby improving the accuracy of the detection result.

[0071] In some embodiments, projecting a preset image can be achieved by: calibrating the projection device to obtain the target brightness percentage current relationship corresponding to the projection device; determining the target current corresponding to the pre-acquired target brightness based on the target brightness percentage current relationship, and projecting the preset image onto at least one surface of the inner liner of the thermos cup to be tested with the target current.

[0072] Exemplarily, the projection device for projecting the light source is a projection device for controlling light photography in a 3D camera, such as an optical machine.

[0073] The embodiment of the present application proposes a special light source projection strategy. When controlling the 3D camera projection, the current value is not directly used for control. Instead, the light machine is controlled to project stripes by specifying the brightness percentage. By pre-establishing a set of brightness percentage reference systems, it is ensured that the same model of 3D cameras can control the light machine to adjust the corresponding current value to produce stripes with consistent brightness when selecting the same brightness percentage, thereby eliminating individual differences.

[0074] Typically, the internal optical engine of a 3D camera is divided into 0-255 levels based on the optical engine current range. This application names the current level LA value. In the embodiments of this application, LA value is used to quantify the current value. The higher the LA value, the greater the corresponding current value, and the greater the brightness value of the optical engine projection. If the optical engine is used at a large LA value for a long time, it will often affect the life of the optical engine. Therefore, two values ​​S1 and S2 can be selected as the recommended operating range when using it. These two values ​​can vary depending on the model of the 3D camera, but the value of S2 must be less than 255.

[0075] Before using a 3D camera, calibrate it. Specifically, project using the projection device to obtain the brightness corresponding to each current level. The brightness percentage can be the percentage of each current level relative to a reference brightness. The reference brightness can be the brightness corresponding to any current level. In the embodiment of the present application, brightness is calculated based on the grayscale value corresponding to the projected image projected by the projection device captured by the 3D camera. After obtaining each brightness percentage, a mapping relationship between the percentage and the current level is established, thereby obtaining the target brightness-percentage-current relationship.

[0076] In some embodiments, the environment in which the projection device projects during calibration may be a light-tight darkroom, and the projection device is used to project the projection image onto a white wall or projection screen in the darkroom to obtain a corresponding projection image.

[0077] In some embodiments, the above-mentioned target brightness percentage current relationship corresponding to the projection device can be obtained in the following manner: obtain a set of projection images of the projection device at current levels from a first threshold to a second threshold, the second threshold being greater than the first threshold; for any projection image, calculate the average grayscale value of the projection image; calculate the ratio of the average grayscale value of the projection image to the pre-acquired maximum standard grayscale value, and obtain the target brightness percentage current relationship corresponding to each current level of the projection device, the maximum standard grayscale value being the average grayscale value of the projection image of the standard camera when the current level is the second threshold.

[0078] Exemplarily, the standard camera is a standard device of the same model as the projection device of the light source to be projected, and the standard device is used as a reference during the calibration process of the projection device of the light source to be projected.

[0079] Based on this, a series of projected images are captured by adjusting the current level of the projection device from the first threshold to the second threshold. The current level can be adjusted in a loop or manually, and then the images are captured. For each projected image, the average grayscale value is calculated. The average grayscale value of the projected image produced by the standard camera at the second threshold current level is obtained as the maximum standard grayscale value. The ratio of the average grayscale value of the projected image at each current level to the maximum standard grayscale value is calculated to obtain the target brightness percentage.

[0080] In order to avoid damage to the projection device due to excessive or insufficient current and the projection device failing to reach the corresponding current level, the first threshold is greater than the minimum current allowed by the projection device and the second threshold is less than the maximum current allowed by the projection device.

[0081] In order to avoid poor quality of the collected projection image and affect the accuracy of the relationship between the brightness percentage and the current level, it is necessary to avoid overexposure of the projection image. Therefore, the grayscale value of the corresponding projection image does not exceed 255 grayscale values.

[0082] During the above-mentioned correction process, since the current level increases step by step from the first threshold to the second threshold, for any projected image, if the average grayscale value of the projected image is greater than or equal to the historical average grayscale value, a projection device error message is generated; if the average grayscale value of the projected image is less than the historical average grayscale value, the ratio of the average grayscale value of the projected image to the standard grayscale value corresponding to the corresponding current level is calculated; the mean of the ratios corresponding to each current level is calculated; and the standard deviation of the ratios corresponding to each current level is calculated; for the average grayscale value corresponding to any current level, if the average grayscale value is greater than the first preset threshold or less than the second preset threshold, a projection device error message is generated; the first preset threshold is the sum of the mean and the third preset threshold, the second preset threshold is the difference between the mean and the third preset threshold, and the third preset threshold is the product of the preset multiple and the standard deviation.

[0083] The historical average grayscale value here is the average grayscale value of the projection image corresponding to the previous current level corresponding to the current projection image.

[0084] The target brightness is the brightness that the projection device of the light source needs to project during application. After determining the target brightness-percentage-current relationship, the ratio of the target brightness to the maximum standard grayscale value is calculated and used as the target ratio. Based on the target ratio, the target current corresponding to the target ratio is determined in the target brightness-percentage-current relationship. Finally, the light source is projected at the target current.

[0085] Next, the above implementation method is described with a specific example.

[0086] First calculate the brightness percentage current relationship corresponding to the standard camera:

[0087] a. The standard camera is determined by using a camera whose internal optical mechanism is as close as possible to the designed optical power value as the standard camera (reference camera).

[0088] b. According to the working field of the standard camera, place it in a dark room, and the distance from the white wall should be consistent with the focal length of the standard camera, such as Figure 2 shown.

[0089] c. Set the standard camera's exposure time to a fixed value, exposure_time, and the gain to 0. Gradually adjust the LA value (current level) from S1 to S2. Project a pure white stripe image onto a white wall. Simultaneously, the standard camera captures images of the white wall, collecting a total of S2 - S1 + 1 images of the white wall. The exposure_time setting needs to be adjusted based on the 3D camera's performance. Ensure that none of the S2 - S1 + 1 images of the white wall are overexposed, meaning no pixels have grayscale values ​​exceeding 255. If this is the case, re-set the exposure_time setting.

[0090] d. Collect S2-S1+1 white wall pictures and calculate the average grayscale value of each picture. Use the average grayscale value of the picture to measure the brightness of the light machine fringe projection. The larger the average grayscale value, the brighter the fringe pattern of the light machine projection. In this way, the average grayscale value corresponding to each LA value is obtained. After obtaining all the grayscale values, determine whether the average grayscale value increases with the increase of LA value. If the grayscale value collected at any LA value is smaller than the current LA value, it means that there is a problem with the projection device, and it is necessary to find a qualified projection device and repeat the process from a to d. Figure 3 The discrete point diagram shown represents the one-to-one correspondence between the standard camera LA value and the fringe projection brightness.

[0091] e. For this standard camera, using the average grayscale value ST_N acquired when the LA value is S2 as a reference value, a brightness percentage table is calculated, as shown in Table 1.

[0092] Table 1

[0093]

[0094] The process of calibrating the projection equipment of the projected light source:

[0095] A. Place the camera to be calibrated in a dark room, just as you would with a standard camera, at a distance from a white wall consistent with the focal length of the standard camera.

[0096] B. Set the camera's exposure time to a fixed value, exposure_time, and gain to 0. Gradually adjust the LA value from S1 to S2. Project the pure white stripe image onto the white wall. Simultaneously, the camera to be corrected captures photos of the white wall. Collect a total of N (N = S2 - S1 + 1, where N is assumed to be S2 - S1 + 1) images of the white wall.

[0097] C. Calculate the average grayscale value of the image captured at each LA value. If the grayscale value captured at any LA value is smaller than the current LA value, it indicates a problem with the optical machine. The camera to be calibrated needs to be repaired and no further processing will be performed.

[0098] D. After calculating the average grayscale value of the image captured at each LA value, compare it to the standard grayscale value of the standard camera, as shown in Table 2. For the N calculated "grayscale ratios for the same LA value," Local_ratio_i (i is any value between 1 and N), calculate the average value avg and standard deviation σ of the Local_ratio_i set. Iterate over all Local_ratio_i values. If the value is greater than avg + 3*σ or less than avg - 3*σ, it indicates a problem with the optical system. The camera to be calibrated requires repair and no further processing is required.

[0099] Table 2

[0100]

[0101] E. Obtain the average grayscale value of the image captured at each LA value and then calculate it with the standard grayscale value ST_N of the reference camera to obtain a brightness percentage table. As shown in Table 3, note that the brightness percentage calculation here uses the average grayscale value ST_N obtained by the reference camera at LA value S2 as the reference value. With the corresponding brightness percentage value at each LA value, a quadratic curve can be fitted, as shown in Table 3. Figure 7 shown.

[0102] Table 3

[0103]

[0104] Light projection based on target brightness:

[0105] To ensure the consistency of each projection device, when selecting the projection brightness, do not directly use the LA value for projection, but choose to use the brightness percentage for projection. When a 3D camera is used, a brightness percentage value is specified. Figure 4 The LA value corresponding to the brightness percentage shown is calculated from the LA quadratic curve. The camera then controls the optical engine to perform fringe projection and 3D reconstruction based on this LA value. This method, based on the special projection technology of 3D cameras, ensures the consistency of the projected fringe brightness between multiple cameras, thereby ensuring the consistency of operation.

[0106] In some embodiments, the shape of the thermos flask liner to be tested is cylindrical, and detection images of two surfaces of the thermos flask liner to be tested are obtained, and the dimensions include a first diameter and a second diameter. Determining whether the thermos flask liner to be tested is qualified based on the relationship between the dimensions and the preset standard dimensions can be achieved in the following manner: comparing the first difference between the first diameter and the second diameter with a first preset error to obtain first deformation data of the thermos flask liner to be tested; if the first deformation data is qualified, calculating the second difference between the first diameter and the preset standard diameter; and calculating the third difference between the second diameter and the preset standard diameter; comparing the second difference with the second preset error to obtain second deformation data; and comparing the third difference with the second preset error to obtain third deformation data; and determining whether the thermos flask liner to be tested is qualified based on the second deformation data and the third deformation data.

[0107] The step of comparing the difference between the first diameter and the second diameter with a first preset error to obtain first deformation data of the inner liner of the thermos cup to be tested includes:

[0108] If the difference between the first diameter and the second diameter is greater than the first preset error, the first deformation data of the inner liner of the thermos cup to be tested is unqualified;

[0109] If the difference between the first diameter and the second diameter is greater than the first preset error, the first deformation data of the inner liner of the thermos cup to be tested is qualified.

[0110] For example, Figure 5 As shown in the figure, on the production line of cylindrical thermos cups, the inner liner of the thermos cup to be tested arrives at the inspection area (darkroom). When the inner liner of the thermos cup to be tested arrives at the inspection area, the inspection is paused, and two 3D cameras respectively capture the left and right outer surfaces of the thermos cup inner liner to obtain two 3D point cloud data PointCloud_left and PointCloud_right;

[0111] Perform surface cylindrical fitting on the point cloud data PointCloud_left and PointCloud_right to obtain two fitting diameter data, the first diameter and the second diameter;

[0112] The first difference between the first and second diameters is calculated. If the absolute value of the first difference is greater than or equal to a first preset tolerance (set to 1mm), the inner shell is severely deformed. The shell is removed from the production line without further processing, and testing continues on other thermos bottles. If the absolute value of the first difference is greater than or equal to the first preset tolerance, the deformation is not severe. Next, the second difference between the first diameter and the preset standard diameter is calculated, as well as the third difference between the second diameter and the preset standard diameter.

[0113] If either the second deformation data or the third deformation data is greater than the set threshold 2 (set to 1mm), it means that the dimensional error of the inner liner is too large, and it will be removed from the production line without subsequent processing, and other thermos cups will continue to be tested; if either the second deformation data or the third deformation data is less than the set threshold 2, it means that the inner liner meets the production standards and can enter the subsequent welding and vacuuming stages.

[0114] Corresponding to the implementation of the above-mentioned method for detecting the inner liner of a thermos cup based on special projection of a 3D camera, the embodiment of the present disclosure further provides a device for detecting the inner liner of a thermos cup based on special projection of a 3D camera, which is used to perform the above-mentioned method. Figure 1 The method for detecting the inner liner of a thermos cup based on special projection of a 3D camera of any embodiment is shown. The device is applied to a detection system for the inner liner of a thermos cup based on special projection of a 3D camera, the detection system comprising a projection device, a 3D camera and a processor, the 3D camera comprising an image acquisition device and a projection device, such as Figure 6 As shown, the device includes:

[0115] The detection image acquisition module 601 is used to acquire a detection image of at least one surface of the inner liner of the thermos cup to be tested; the detection image is a projection image of at least one surface of the inner liner of the thermos cup to be tested acquired by the image acquisition device; the projection image is obtained by projecting a preset image onto at least one surface of the inner liner of the thermos cup to be tested using the projection device; the preset image is obtained by projecting the projection device based on the target brightness;

[0116] A size calculation module 602 is configured to calculate the size of the inner liner of the thermos cup to be tested based on the detection image;

[0117] The determination module 603 is used to determine whether the inner liner of the thermos cup to be tested is qualified based on the relationship between the size and the preset standard size.

[0118] The thermos cup liner detection device based on special projection of 3D camera provided in the above-mentioned embodiment of the present disclosure and the thermos cup liner detection method based on special projection of 3D camera provided in the embodiment of the present disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0119] The present disclosure also provides a thermos cup liner detection system based on special projection of a 3D camera, which is used to perform the above-mentioned data transmission method. Figure 7 , which shows a schematic diagram of an electronic device provided by some embodiments of the present disclosure. Figure 7 As shown, the thermos cup liner detection system based on special projection of 3D camera includes: a processor 700, a memory 701, a bus 702, a communication interface 703 and a 3D camera 704, the processor 700, the communication interface 703 and the memory 701 are connected via the bus 702; the memory 701 stores a computer program that can be run on the processor 700, and the processor 700 executes the aforementioned Figure 1 The method provided in any embodiment is illustrated.

[0120] Memory 701 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage. Communication between the system network element and at least one other network element is achieved through at least one communication interface 703 (which may be wired or wireless), and may utilize the Internet, a wide area network, a local area network, a metropolitan area network, or the like.

[0121] The bus 702 can be an ISA bus, a PCI bus or an EISA bus. The bus can be divided into an address bus, a data bus, a control bus, etc. Among them, the memory 701 is used to store programs. After receiving the execution instruction, the processor 700 executes the program. Figure 1 The method disclosed in any of the illustrated embodiments may be applied to the processor 700 or implemented by the processor 700 .

[0122] The processor 700 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method may be completed by hardware integrated logic circuits or software instructions in the processor 700. The processor 700 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It may implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present disclosure. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present disclosure may be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium mature in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory 701 , and the processor 700 reads the information in the memory 701 and completes the steps of the above method in combination with its hardware.

[0123] The electronic device provided by the embodiment of the present disclosure and the data transmission method provided by the embodiment of the present disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented by them.

[0124] The present disclosure also provides a computer-readable storage medium corresponding to the data transmission method provided in the above embodiment. Figure 8 The computer-readable storage medium shown is a CD 30 on which a computer program (ie, a program product) is stored. When the computer program is run by a microprocessor, it executes the data transmission method provided by any of the aforementioned embodiments.

[0125] It should be noted that examples of computer-readable storage media may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0126] The computer-readable storage medium provided by the above-mentioned embodiments of the present disclosure and the data transmission method provided by the embodiments of the present disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0127] It should be noted that:

[0128] In the description provided herein, numerous specific details are described. However, it is understood that embodiments of the present disclosure can be practiced without these specific details. In some instances, well-known structures and technologies are not shown in detail so as not to obscure the understanding of this description.

[0129] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present disclosure, various features of the present disclosure are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed approach should not be interpreted as reflecting a schematic representation that the claimed disclosure requires more features than are expressly recited in each claim. Rather, as reflected in the claims below, inventive aspects lie in less than all of the features of the individual embodiments disclosed above. Accordingly, the claims that follow the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of the present disclosure.

[0130] Furthermore, those skilled in the art will appreciate that although some embodiments herein include certain features included in other embodiments but not other features, combinations of features from different embodiments are intended to be within the scope of this disclosure and to form different embodiments. For example, in the claims below, any of the claimed embodiments may be used in any combination.

[0131] The above are merely preferred embodiments of the present disclosure, but the scope of protection of the present disclosure is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this disclosure should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure should be based on the scope of protection of the claims.

Claims

1. A method for detecting the inner liner of a thermos cup based on special projection of a 3D camera, characterized in that: The method is applied to a thermos cup liner detection system based on special projection of a 3D camera. The detection system includes a 3D camera and a processor. The 3D camera includes an image acquisition device and a projection device. The method includes: Acquire a detection image of at least one surface of the inner liner of the thermos cup to be tested; the detection image is a projection image of at least one surface of the inner liner of the thermos cup to be tested acquired by the image acquisition device; the projection image is obtained by projecting a preset image onto at least one surface of the inner liner of the thermos cup to be tested using the projection device; the preset image is obtained by projecting the projection device based on a target brightness; Based on the detection image, the size of the inner liner of the thermos cup to be tested is calculated; Based on the relationship between the size and the preset standard size, determining whether the inner liner of the thermos cup to be tested is qualified; The method of projecting a preset image onto at least one surface of the inner liner of the thermos cup to be tested by using the projection device includes: Calibrate the projection device to obtain a target brightness percentage current relationship corresponding to the projection device; Determine the percentage of the grayscale value corresponding to the target brightness to the maximum standard grayscale value; determine the target current based on the relationship between the percentage and the target brightness percentage current, and project a preset image onto at least one surface of the inner liner of the thermos cup to be tested with the target current.

2. The method according to claim 1, characterized in that The step of calibrating the projection device to obtain a target brightness percentage current relationship corresponding to the projection device includes: Acquire a projection image set of the projection device at a current level ranging from a first threshold to a second threshold, where the second threshold is greater than the first threshold; For any projection image, calculating the average grayscale value of the projection image; The ratio of the average grayscale value of the projected image to the pre-acquired maximum standard grayscale value is calculated to obtain the target brightness percentage current relationship corresponding to each current level of the projection device. The maximum standard grayscale value is the average grayscale value of the projected image of the standard camera when the current level is the second threshold.

3. The method according to claim 2, characterized in that The method further comprises: For any projected image, if the average grayscale value of the projected image is greater than or equal to the historical average grayscale value, a projection device error message is generated; If the average grayscale value of the projected image is less than the historical average grayscale value, calculating the ratio of the average grayscale value of the projected image to the standard grayscale value corresponding to the corresponding current level; Calculate the mean of the ratios corresponding to each current level; and calculate the standard deviation of the ratios corresponding to each current level; For the average grayscale value corresponding to any current level, if the average grayscale value is greater than the first preset threshold or less than the second preset threshold, a projection device error message is generated; the first preset threshold is the sum of the mean and the third preset threshold, the second preset threshold is the difference between the mean and the third preset threshold, and the third preset threshold is the product of the preset multiple and the standard deviation.

4. The method according to claim 2, characterized in that The projected image set corresponding to each current level from a first threshold value to a second threshold value is obtained when the projection device is in a preset environment, and the preset environment is an opaque environment.

5. The method according to claim 2, characterized in that The first threshold is greater than a minimum current allowed by the projection device, and the second threshold is less than a maximum current allowed by the projection device.

6. The method according to claim 1, wherein Acquiring detection images of two surfaces of the thermos flask liner to be tested, wherein the dimensions include a first diameter and a second diameter; and determining whether the thermos flask liner to be tested is qualified based on a relationship between the dimensions and a preset standard dimension, including: Comparing a first difference between the first diameter and the second diameter with a first preset error to obtain first deformation data of the inner liner of the thermos cup to be tested; If the first deformation data is qualified, calculating a second difference between the first diameter and a preset standard diameter; and calculating a third difference between the second diameter and the preset standard diameter; Comparing the second difference with a second preset error to obtain second deformation data; and comparing the third difference with the second preset error to obtain third deformation data; Based on the second deformation data and the third deformation data, it is determined whether the inner liner of the thermos cup to be tested is qualified.

7. The method according to claim 6, characterized in that The step of comparing the difference between the first diameter and the second diameter with a first preset error to obtain first deformation data of the inner liner of the thermos cup to be tested includes: If the difference between the first diameter and the second diameter is greater than or equal to the first preset error, the first deformation data of the inner liner of the thermos cup to be tested is unqualified; If the difference between the first diameter and the second diameter is smaller than the first preset error, the first deformation data of the inner liner of the thermos cup to be tested is qualified.

8. A thermos cup liner detection device based on special projection of a 3D camera, characterized in that: The device is applied to a thermos cup liner detection system based on special projection of a 3D camera. The detection system includes a projection device, a 3D camera, and a processor. The 3D camera includes an image acquisition device and a projection device. The device includes: The detection image acquisition module is used to acquire a detection image of at least one surface of the inner liner of the thermos cup to be tested; the detection image is a projection image of at least one surface of the inner liner of the thermos cup to be tested acquired by the image acquisition device; the projection image is The preset image is obtained by projecting a preset image onto at least one surface of the inner liner of the thermos cup to be tested using the projection device; the preset image is obtained by projecting the preset image based on the target brightness by the projection device; A size calculation module, configured to calculate the size of the inner liner of the thermos cup to be tested based on the detection image; A determination module is configured to determine whether the inner liner of the thermos cup to be tested is qualified based on the relationship between the size and the preset standard size; wherein the projecting device is used to project a preset image onto at least one surface of the inner liner of the thermos cup to be tested, comprising: Calibrate the projection device to obtain a target brightness percentage current relationship corresponding to the projection device; Determine the percentage of the grayscale value corresponding to the target brightness to the maximum standard grayscale value; determine the target current based on the relationship between the percentage and the target brightness percentage current, and project a preset image onto at least one surface of the inner liner of the thermos cup to be tested with the target current.

Images