Non-contact liquid filling detection system suitable for non-transparent container

CN119085792APending Publication Date: 2024-12-06HARBIN ENG UNIV
View PDF 12 Cites 0 Cited by

Patent Information

Application Number
CN202411242052.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-05
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The prior art is difficult to efficiently detect liquid filling in non-transparent containers, and the applicability of traditional optical detection and contact detection in closed, complex production environments is reduced.

Method used

The non-contact liquid filling detection system is adopted, and image data is collected outside the container using an infrared detector, pre-processing and liquid filling height calculation are performed through the image processing module, and detection results are determined in combination with the interactive touch display module.

Benefits of technology

It realizes effective detection of liquid filling conditions in non-transparent containers, expands the scope of inspection application, reduces equipment complexity and power consumption, and ensures the safety and accuracy of inspection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119085792A_ABST
    Figure CN119085792A_ABST
Patent Text Reader

Abstract

The invention discloses a non-contact liquid filling detection system suitable for a non-transparent container, and relates to the technical field of photoelectric detection, and the non-contact liquid filling detection system specifically comprises the following steps: S1, collecting image data through an image collection module; s2, an image processing module preprocesses the image data collected in the step S1 and calculates the height of the liquid filling level to obtain the height value of the liquid filling level, and the height value of the liquid filling level is input into an interactive touch display module; s3, the interactive touch display module carries out detection result judgment on the height value of the liquid filling level; according to the non-contact liquid filling detection system suitable for the non-transparent container, image acquisition is carried out outside the non-transparent container to be detected, and image data of the non-transparent container are updated in real time, so that the non-transparent container can be detected without contacting the container and liquid in the container; and the filling condition of the liquid in the non-transparent container is effectively detected.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of photoelectric detection, and in particular to a non-contact liquid filling detection system suitable for non-transparent containers. Background Art

[0002] With the continuous development of modern industry, the accuracy of liquid filling process is becoming more and more important, especially in industries with extremely high quality and safety requirements such as pharmaceuticals, chemicals and food. The filling accuracy of liquids may be directly related to product quality, production efficiency and safety. Traditional liquid filling detection mostly relies on technologies such as optical sensors and liquid level sensors. These technologies are very mature in transparent or translucent containers and can provide relatively accurate detection results. However, with the diversification of production processes, more and more liquids need to be stored in non-transparent containers, and the requirements for liquid purity are becoming more and more stringent, which greatly reduces the applicability of traditional optical detection and contact detection. Therefore, in a closed and complex production environment, how to efficiently detect the filling status of liquids in non-transparent containers has become a major challenge.

[0003] Chinese patent CN202410719240.0 is a device and method for measuring the volume of liquid in a transparent container. The measuring device includes a light source, a container placement unit, an image acquisition device, a signal processing unit, and a pixel-to-physical object mapping relationship calibration unit; the method for measuring using the aforementioned measuring device includes: acquiring the original image through light source irradiation and image acquisition equipment, and generating an image feature histogram after preprocessing; using an unsupervised clustering method to divide the histogram data into an upper portion without liquid and a lower portion containing liquid image; performing image boundary analysis on each portion to obtain data information on the center position of the transparent container; based on this, performing image segmentation processing on the lower portion of the liquid image to determine the image boundaries of the curved liquid surface, pure liquid, and the bottom of the transparent container, and finally slicing and splicing to obtain a binary image; then generating a three-dimensional model, and obtaining the volume of the liquid to be measured based on the pixel-to-physical object mapping relationship.

[0004] Although the device realizes non-contact liquid volume measurement, it is suitable for liquid detection in transparent containers, but not for liquid detection in non-transparent containers. In addition, it requires additional light source to assist in measurement, which increases the complexity and power consumption of the device.

[0005] Therefore, a non-contact liquid filling detection system suitable for a non-transparent container is provided to solve the above problems. Summary of the invention

[0006] The purpose of the present invention is to provide a non-contact liquid filling detection system suitable for non-transparent containers, which can effectively detect the liquid filling status in non-transparent containers without contacting the containers and the liquid inside the containers, thereby solving the problems caused by the limitation of container transparency in the prior art.

[0007] To achieve the above object, the present invention provides a non-contact liquid filling detection system for a non-transparent container, which specifically includes the following steps:

[0008] S1: Collect image data through the image acquisition module;

[0009] S2: the image processing module pre-processes the image data collected in step S1 and calculates the liquid filling level height to obtain the liquid filling level height value, and inputs the liquid filling level height value into the interactive touch display module;

[0010] S3: The interactive touch display module determines the detection result of the height value of the liquid filling level.

[0011] Preferably, the image acquisition module is connected to the image processing module, the image processing module is connected to the interactive touch display module, and the detection system is also provided with a power supply module for supplying power to the detection system.

[0012] Preferably, in step S1, the image acquisition module includes an image detection module and a data transmission module, the image detection module includes an infrared detector and a data conversion module, and collecting image data specifically includes the following steps:

[0013] S11: The infrared detector collects image data outside the container;

[0014] S12: The data conversion module converts the image data, converts the analog signal into a digital signal, and obtains a digital image;

[0015] S13: The data transmission module transmits the digital image to the image processing module.

[0016] Preferably, in step S2, the specific process of the image processing module preprocessing the image data is as follows:

[0017] Step 1: Use the convolution kernel to perform Gaussian filtering on the digital image;

[0018] Step 2: Perform histogram equalization on the Gaussian filtered image to obtain an enhanced image.

[0019] Preferably, in step S2, the specific process of the image processing module calculating the liquid filling level is as follows:

[0020] S21: Binarize the image enhanced in step 2 to obtain a binary image;

[0021] S22: Perform morphological processing on the binary image S21 to obtain a result image;

[0022] S23: Counting the total grayscale values ​​of pixels in the result image of S22 row by row;

[0023] S24: Set the middle area of ​​the result image of S22, calculate the difference between the grayscale values ​​of two adjacent rows of pixels in the result image in the middle area, compare the differences and find the two rows of pixel grayscale values ​​with the largest difference, and calculate the horizontal coordinate average value of the two rows of pixel grayscale values ​​as the height value of the liquid filling level.

[0024] Preferably, in step S21, the image processing module performs binarization processing on the enhanced image. The specific process is as follows:

[0025] S211: Calculate the grayscale histogram of the enhanced image, and calculate the threshold of the enhanced image by the maximum inter-class variance method. The original image has L grayscale levels, and the number of pixels with grayscale level i is n. i , the total number of pixels in the image is N, calculate the probability P of the pixel at gray level i appearing i for:

[0026]

[0027] Among them, P i The following conditions are met:

[0028]

[0029] Set the current threshold as T, divide the gray level of the pixel, and divide the gray level of the pixel [0,2,…,T] into the foreground C 0 , the grayscale of the pixel with grayscale level [T+1,…,L-1] is divided into background C 1 , C 0 The probability of occurrenceω 0 and mean μ 0 and C 1 The probability of occurrenceω 1 and mean μ 1 Calculated by the following formula:

[0030]

[0031]

[0032] Where ω(T) is the probability of the foreground appearing, μ(T) is the cumulative mean, and μ s (T) is the global mean, the cumulative mean μ(T) and the global mean μ s (T) is calculated by the following formula:

[0033]

[0034] Traverse the gray levels from 0 to L-1, and calculate the gray level one by one when it is the threshold T. 0 With background C 1 The between-class variance Between-class variance Calculated by the following formula:

[0035]

[0036] Compare all inter-class variances and make the threshold T with the largest inter-class variance the threshold for image binarization;

[0037] S212: Judge the pixels of the enhanced image one by one, and compare the pixels with the threshold calculated in S211. When the grayscale value of the pixel is less than the threshold, the pixel is recorded as 0. When the grayscale value of the pixel is greater than the threshold, the pixel is recorded as 1. After the traversal is completed, a binary image is obtained.

[0038] Preferably, in step S22, the image processing module performs morphological processing on the binary image, and the specific process is as follows:

[0039] S221: dilate the binary image, slide the convolution kernel on the binary image, align the convolution kernel and the center position to the pixel points of the binary image, and if at least one pixel point in the area covered by the convolution kernel is white, the center pixel point is set to white;

[0040] S222: performing corrosion processing on the binary image after the dilation processing in S221, using the convolution kernel in S221 to slide on the binary image after the dilation processing, if there are black pixels in the area covered by the convolution kernel, the center pixel is set to black, otherwise the center pixel remains white.

[0041] Preferably, in step S24, the middle area is set to an area of ​​20% to 80% of the longitudinal length from the top of the result image to the bottom of the result image. If the total pixel height of the result image is H, the portion from the 0.2H line to the 0.8H line of the result image is recorded as the middle area of ​​the result image.

[0042] Preferably, in step S3, the interactive touch display module includes a determination module and an early warning module. The early warning module is controlled by the determination module. The determination module performs a detection result determination on the height value of the liquid filling level. The specific process is as follows:

[0043] S31: setting and storing a height standard value of the liquid filling level and an allowable error range of the height value of the liquid filling level in the determination module;

[0044] S32: Obtaining the height value of the liquid filling level obtained by the image processing module in S24;

[0045] S33: Calculate the difference between the height value of the liquid filling level and the height standard value of the liquid filling level, and compare the difference with the allowable error range of the height value of the liquid filling level. If the difference is not within the allowable error range of the height value of the liquid filling level, drive the warning module to send a warning signal.

[0046] Preferably, the infrared detector is configured as a short-wave infrared detector.

[0047] Therefore, the present invention adopts the above-mentioned non-contact liquid filling detection system for non-transparent containers, which has the following beneficial effects:

[0048] (1) The present invention has strong applicability and utilizes a short-wave infrared detector that can penetrate materials to detect the interior, thereby realizing the collection of image data of the interior of a non-transparent container, thereby expanding the scope of application of the detection system.

[0049] (2) The present invention has low power consumption and does not require additional light sources, thereby reducing the complexity and power consumption of the detection system.

[0050] (3) The present invention has high safety. The image acquisition and image processing processes are completed outside the container, and a non-contact detection method is used to avoid contamination of the liquid during the detection process.

[0051] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a detection flow chart of a non-contact liquid filling detection system applicable to a non-transparent container of the present invention;

[0053] Figure 2 It is a structural schematic diagram of a non-contact liquid filling detection system applicable to a non-transparent container of the present invention;

[0054] Figure 3 It is a flow chart of preprocessing image data in a non-contact liquid filling detection system applicable to a non-transparent container of the present invention;

[0055] Figure 4 It is a 3×3 convolution kernel used in a non-contact liquid filling detection system for a non-transparent container of the present invention when performing Gaussian filtering;

[0056] Figure 5 It is a flow chart of calculating the threshold of an enhanced image by using the maximum inter-class variance method in a non-contact liquid filling detection system applicable to a non-transparent container of the present invention;

[0057] Figure 6 It is a 3×3 convolution kernel used in the non-contact liquid filling detection system suitable for non-transparent containers during corrosion and expansion. DETAILED DESCRIPTION

[0058] The technical solution of the present invention is further described below through the accompanying drawings and embodiments.

[0059] Unless otherwise defined, technical or scientific terms used in the present invention shall have the common meanings understood by one having ordinary skills in the field to which the present invention belongs.

[0060] The words "include" or "comprises" and the like used in the present invention mean that the elements before the word include the elements listed after the word, and do not exclude the possibility of also including other elements. The orientation or position relationship indicated by the terms "inside", "outside", "upper", "lower", etc. is based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation of the present invention. When the absolute position of the described object changes, the relative position relationship may also change accordingly. In the present invention, unless otherwise clearly specified and limited, the terms "attachment" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral body; it can be a direct connection, or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances.

[0061] Example

[0062] like Figure 1 As shown, the present invention provides a non-contact liquid filling detection system for a non-transparent container, which specifically includes the following steps:

[0063] S1: Collect image data through the image acquisition module;

[0064] S2: the image processing module pre-processes the image data collected in step S1 and calculates the liquid filling level height to obtain the liquid filling level height value, and inputs the liquid filling level height value into the interactive touch display module;

[0065] S3: The interactive touch display module determines the detection result of the height value of the liquid filling level.

[0066] like Figure 2As shown, the image acquisition module is connected to the image processing module, and the image processing module is connected to the interactive touch display module. The image acquisition module includes an image detection module and a data transmission module. The image detection module includes an infrared detector and a data conversion module. The interactive touch display module includes a determination module and an early warning module. The early warning module includes a prompt light and a buzzer. The early warning module is controlled by the determination module. The determination module determines the detection result of the height value of the liquid filling level. A power supply module is also provided in the detection system for powering the detection system.

[0067] In step S1, the image detection module collects image data, specifically including the following steps:

[0068] S11: The infrared detector collects image data outside the container;

[0069] S12: The data conversion module converts the image data, converts the analog signal into a digital signal, and obtains a digital image for subsequent image preprocessing and calculation of the liquid filling height;

[0070] S13: The data transmission module transmits the digital image to the image processing module.

[0071] like Figure 3 As shown, in step S2, the image processing module pre-processes the image data. The specific process is as follows:

[0072] Step 1: Use Figure 4 The 3×3 convolution kernel shown in the figure performs Gaussian filtering on the digital image. The convolution kernel slides pixel by pixel on the entire image. For each pixel point, the weighted sum of all pixels in its neighborhood and the corresponding position of the convolution kernel is calculated. Taking the 3×3 convolution kernel as an example, for a certain pixel point in the image, the 8 neighboring pixels around it are taken, multiplied by the corresponding weight in the convolution kernel, and the results are added to finally obtain the smoothed value of the pixel. Since the weight of the central pixel is large, the pixel value in the neighborhood has little effect on the final result, which effectively suppresses the noise, while the edges and details of the image are relatively preserved.

[0073] Step 1: Perform histogram equalization on the Gaussian filtered image to obtain an enhanced image.

[0074] In step S2, the image processing module calculates the liquid filling level height in the following specific process:

[0075] S21: Binarize the image enhanced in step 2 to obtain a binary image;

[0076] S22: Perform morphological processing on the binary image S21 to obtain a result image;

[0077] S23: Counting the total grayscale values ​​of pixels in the result image of S22 row by row;

[0078] S24: Set the middle area of ​​the result image of S22, calculate the difference between the grayscale values ​​of two adjacent rows of pixels in the result image in the middle area, compare the differences and find the two rows of pixel grayscale values ​​with the largest difference, and calculate the horizontal coordinate average value of the two rows of pixel grayscale values ​​as the height value of the liquid filling level.

[0079] like Figure 5 As shown, in step S21, the image processing module performs binarization processing on the enhanced image. The specific process is as follows:

[0080] S211: Calculate the grayscale histogram of the enhanced image, and calculate the threshold of the enhanced image by the maximum inter-class variance method. The original image has L grayscale levels, and the number of pixels with grayscale level i is n. i , the total number of pixels in the image is N, calculate the probability P of the pixel at gray level i appearing i for:

[0081]

[0082] Among them, P i The following conditions are met:

[0083]

[0084] Set the current threshold as T, divide the gray level of the pixel, and divide the gray level of the pixel [0,2,…,T] into the foreground C 0 , the grayscale of the pixel with grayscale level [T+1,…,L-1] is divided into background C 1 , C 0 The probability of occurrenceω 0 and mean μ 0 and C 1 The probability of occurrenceω 1 and mean μ 1 Calculated by the following formula:

[0085]

[0086] Where ω(T) is the probability of the foreground appearing, μ(T) is the cumulative mean, and μ s (T) is the global mean, the cumulative mean μ(T) and the global mean μ s (T) is calculated by the following formula:

[0087]

[0088] Traverse the gray levels from 0 to L-1, and calculate the gray level one by one when it is the threshold T. 0 With background C1 The between-class variance Between-class variance Calculated by the following formula:

[0089]

[0090] Compare all inter-class variances and make the threshold T with the largest inter-class variance the threshold for image binarization;

[0091] S212: Judge the pixels of the enhanced image one by one, and compare the pixels with the threshold calculated in S211. When the grayscale value of the pixel is less than the threshold, the pixel is recorded as 0. When the grayscale value of the pixel is greater than the threshold, the pixel is recorded as 1. After the traversal is completed, a binary image is obtained.

[0092] In step S22, the image processing module performs morphological processing on the binary image. The specific process is as follows:

[0093] S221: dilate the binary image using Figure 6 The convolution kernel shown slides on the binary image, aligning the convolution kernel and the center position to the pixel points of the binary image. If at least one pixel point in the area covered by the convolution kernel is white, the center pixel point is set to white, filling the small holes inside the binary image and connecting the small gaps to make the image edge fuller. Since the dilation process may cause the image edge to over-expand and blur some details, the erosion process is performed next;

[0094] S222: perform corrosion processing on the binary image after dilation processing in S221, and use the convolution kernel in S221 to slide on the binary image after dilation processing. If there are black pixels in the area covered by the convolution kernel, the center pixel is set to black, otherwise the center pixel remains white to implement corrosion processing, correct the expanded boundary during the dilation process, return the edge to its original shape, retain the key contour features and eliminate isolated noise points. The whole process ensures that the edge of the image is smoother and continuous, and removes unnecessary noise and holes.

[0095] In step S24, the middle area is set to an area of ​​20% to 80% of the vertical length from the top to the bottom of the result image. If the total pixel height of the result image is H, the portion from the 0.2H line to the 0.8H line of the result image is recorded as the middle area of ​​the result image.

[0096] In step S3, the interactive touch display module includes a determination module and an early warning module. The early warning module is controlled by the determination module. The determination module determines the detection result of the height value of the liquid filling level. The specific process is as follows:

[0097] S31: setting and storing a height standard value of the liquid filling level and an allowable error range of the height value of the liquid filling level in the determination module;

[0098] S32: Obtaining the height value of the liquid filling level obtained by the image processing module in S24;

[0099] S33: Calculate the difference between the height value of the liquid filling level and the height standard value of the liquid filling level, and compare the difference with the allowable error range of the height value of the liquid filling level. If the difference is not within the allowable error range of the height value of the liquid filling level, drive the warning module to send a warning signal.

[0100] The interactive touch display module of this solution can set the detection requirements according to actual needs. The interactive touch display module will not only display data information such as the current detected liquid filling height value, the height standard value set by the user and the acceptable error range, but also display the difference between the liquid filling height value and the height standard value to assist users in understanding the current filling error situation. At the same time, the early warning method can be set. In addition, the infrared detector is set to a short-wave infrared detector. The short-wave infrared detector has strong penetration and low light requirements. It can detect the filling situation of liquid inside non-transparent containers. If the detection system of this solution is used to detect the liquid filling of transparent containers, infrared detectors or visible light detectors of other bands can also be selected.

[0101] Therefore, the present invention adopts the above-mentioned non-contact liquid filling detection system suitable for non-transparent containers, which has strong applicability and uses a short-wave infrared detector that can penetrate materials to detect the inside to realize the collection of image data inside the non-transparent container, thereby expanding the scope of application of the detection system; low power consumption, no additional light source is required, and the complexity and power consumption of the detection system are reduced; high safety, image acquisition and image processing processes are completed outside the container, and non-contact detection methods are used to avoid contamination of the liquid during the detection process.

[0102] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. A non-contact liquid filling detection system suitable for non-transparent containers, characterized by: The specific steps include: S1: Collect image data through the image acquisition module; S2: the image processing module pre-processes the image data collected in step S1 and calculates the liquid filling level height to obtain the liquid filling level height value, and inputs the liquid filling level height value into the interactive touch display module; S3: The interactive touch display module determines the detection result of the height value of the liquid filling level.

2. A non-contact liquid filling detection system for non-transparent containers according to claim 1, characterized in that: The image acquisition module is connected to the image processing module, and the image processing module is connected to the interactive touch display module. The detection system is also provided with a power supply module for supplying power to the detection system.

3. A non-contact liquid filling detection system for non-transparent containers according to claim 1, characterized in that: In step S1, the image acquisition module includes an image detection module and a data transmission module. The image detection module includes an infrared detector and a data conversion module. The acquisition of image data specifically includes the following steps: S11: The infrared detector collects image data outside the container; S12: The data conversion module converts the image data, converts the analog signal into a digital signal, and obtains a digital image; S13: The data transmission module transmits the digital image to the image processing module.

4. A non-contact liquid filling detection system for non-transparent containers according to claim 1, characterized in that: In step S2, the image processing module preprocesses the image data. The specific process is as follows: Step 1: Use the convolution kernel to perform Gaussian filtering on the digital image; Step 2: Perform histogram equalization on the Gaussian filtered image to obtain an enhanced image.

5. A non-contact liquid filling detection system for non-transparent containers according to claim 4, characterized in that: In step S2, the image processing module calculates the liquid filling level height in the following specific process: S21: Binarize the image enhanced in step 2 to obtain a binary image; S22: Perform morphological processing on the binary image S21 to obtain a result image; S23: Counting the total grayscale values ​​of pixels in the result image of S22 row by row; S24: Set the middle area of ​​the result image of S22, calculate the difference between the grayscale values ​​of two adjacent rows of pixels in the result image in the middle area, compare the differences and find the two rows of pixel grayscale values ​​with the largest difference, and calculate the horizontal coordinate average value of the two rows of pixel grayscale values ​​as the height value of the liquid filling level.

6. A non-contact liquid filling detection system for non-transparent containers according to claim 5, characterized in that: In step S21, the image processing module performs binarization processing on the enhanced image. The specific process is as follows: S211: Calculate the grayscale histogram of the enhanced image, and calculate the threshold of the enhanced image by the maximum inter-class variance method. The original image has L grayscale levels, and the number of pixels with grayscale level i is n. i , the total number of pixels in the image is N, calculate the probability P of the pixel at gray level i appearing i for: Among them, P i The following conditions are met: Assume that the current threshold is T, divide the gray level of the pixel, divide the gray level of the pixel [0, 2, ..., T] into the foreground C0, divide the gray level of the pixel [T+1, ..., L-1] into the background C1, and the probability ω0 and mean μ0 of C0 and the probability ω1 and mean μ1 of C1 are calculated by the following formula: Where ω(T) is the probability of the foreground appearing, μ(T) is the cumulative mean, and μ s (T) is the global mean, the cumulative mean μ(T) and the global mean μ s (T) is calculated by the following formula: Traverse the gray levels from 0 to L-1, and calculate the inter-class variance of the foreground C0 and the background C1 when the gray level is the threshold T one by one Between-class variance Calculated by the following formula: Compare all inter-class variances and make the threshold T with the largest inter-class variance the threshold for image binarization; S212: Judge the pixels of the enhanced image one by one, and compare the pixels with the threshold calculated in S211. When the grayscale value of the pixel is less than the threshold, the pixel is recorded as 0. When the grayscale value of the pixel is greater than the threshold, the pixel is recorded as 1. After the traversal is completed, a binary image is obtained.

7. A non-contact liquid filling detection system for non-transparent containers according to claim 5, characterized in that: In step S22, the image processing module performs morphological processing on the binary image. The specific process is as follows: S221: dilate the binary image, slide the convolution kernel on the binary image, align the convolution kernel and the center position to the pixel points of the binary image, and if at least one pixel point in the area covered by the convolution kernel is white, the center pixel point is set to white; S222: performing corrosion processing on the binary image after the dilation processing in S221, using the convolution kernel in S221 to slide on the binary image after the dilation processing, if there are black pixels in the area covered by the convolution kernel, the center pixel is set to black, otherwise the center pixel remains white.

8. A non-contact liquid filling detection system for non-transparent containers according to claim 5, characterized in that: In step S24, the middle area is set to an area of ​​20% to 80% of the vertical length from the top to the bottom of the result image. If the total pixel height of the result image is H, the portion from the 0.2H line to the 0.8H line of the result image is recorded as the middle area of ​​the result image.

9. A non-contact liquid filling detection system for non-transparent containers according to claim 5, characterized in that: In step S3, the interactive touch display module includes a determination module and an early warning module. The early warning module is controlled by the determination module. The determination module determines the detection result of the height value of the liquid filling level. The specific process is as follows: S31: setting and storing a height standard value of the liquid filling level and an allowable error range of the height value of the liquid filling level in the determination module; S32: Obtaining the height value of the liquid filling level obtained by the image processing module in S24; S33: Calculate the difference between the height value of the liquid filling level and the height standard value of the liquid filling level, and compare the difference with the allowable error range of the height value of the liquid filling level. If the difference is not within the allowable error range of the height value of the liquid filling level, drive the warning module to send a warning signal.

10. A non-contact liquid filling detection system suitable for non-transparent containers according to claim 3, characterized in that: The infrared detector is set to be a short-wave infrared detector.

Citation Information

Patent Citations

  • Machine-vision based liquid level detection device and method

    CN102147281A

  • HOV lane vehicle passenger number detection method and device

    CN107657211A

  • Detecting device for foreign matters in transparent / semi-transparent product

    CN107957395A

  • Transformer oil level warning method and device, and terminal equipment

    CN110207784A

  • All-weather tunnel water level monitoring system and method based on infrared image detection

    CN111609898A