Pointer type pressure gauge reading method and device and computer storage medium
The reading results of pointer pressure gauge are extracted through image processing technology, which solves the problems of inefficient and insufficient accuracy of traditional manual readings, and achieves efficient and accurate pressure gauge readings, which are suitable for complex lighting conditions and different models of pressure gauge.
Patent Information
- Application Number
- CN202411828093.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-12
- Publication Date
- 2025-05-09
AI Technical Summary
The reading of the traditional pointer pressure gauge relies on manual observation, is inefficient and susceptible to human factors. Especially in environments where light is insufficient or changes are large, the reading accuracy cannot be guaranteed.
By collecting images of pointer pressure gauge, image processing and analysis are used to use image processing technology to construct a difference image between the pointer-free image and the image to be identified, the pointer part is extracted, and efficient and accurate image recognition and matching is achieved through template matching and accelerated robust feature pointing technology. Combined with the weighted calculation of fitted pointer lines and zero-point lines, the reading results are obtained.
It improves the accuracy and efficiency of pointer pressure gauge readings, reduces errors caused by human factors, is suitable for various models and specifications of pressure gauges, and can provide auxiliary light sources according to different lighting conditions to ensure image quality.
Smart Images
Figure CN119964133A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of industrial pressure gauge reading recognition, in particular to a pointer-type pressure gauge reading method, a reading device and a computer storage medium. Background Art
[0002] As a traditional pressure measuring instrument, pointer pressure gauge is widely used in industrial production, mechanical equipment operation monitoring and daily life. However, the reading of traditional pointer pressure gauge usually relies on manual observation and judgment, which is not only inefficient, but also easily affected by human factors, resulting in reading errors. Especially in environments with insufficient light or large changes in light, manual reading is more difficult and accuracy cannot be guaranteed.
[0003] With the continuous development of computer vision and image processing technology, automated and intelligent pointer pressure gauge reading devices and methods have gradually become possible. The image of the pointer pressure gauge is collected by the image acquisition module, and the image is processed and analyzed by the image processing unit, so that the reading result of the pressure gauge can be automatically obtained. This automated reading method not only improves the reading efficiency, but also reduces the errors caused by human factors and improves the accuracy of the reading.
[0004] However, in practical applications, the image acquisition and processing of pointer pressure gauges still face some challenges. For example, since pressure gauges are usually installed in complex industrial environments, the lighting conditions may not be ideal, resulting in poor quality of the acquired images, which affects subsequent image processing and analysis. In addition, the dial designs of pressure gauges of different models and specifications vary, and the shape, color, and scale of the pointer may also vary, which increases the difficulty of image processing. Summary of the invention
[0005] In order to solve the above technical problems, the present invention provides a pointer pressure gauge reading method, a reading device and a computer storage medium. The pointer pressure gauge reading method comprises the following steps: S1: Collect the image of the pointer pressure gauge; S2: Based on the pointer pressure gauge image, perform image processing on the image to be identified to obtain a pressure gauge reading result; Wherein, in step S2, the method for obtaining the pressure gauge reading result is as follows: S21: The pointer pressure gauge image includes two images with the pointer at different positions acquired under the same lighting conditions, which are respectively recorded as a first template image and a second template image, and a fitting pointer line of the image to be identified is obtained based on the first template image and the second template image; S22: sequentially selecting a pointer pressure gauge image from a template library constructed in advance, recording it as a third template image, extracting feature points of the third template image and the image to be identified, and calculating the similarity of feature points of different images and the distribution of feature points to obtain a third template image that meets the screening condition as the best matching template; S23: acquiring the zero point position of the best matching template by identifying the zero point template and the zero point line at the zero point, so as to obtain the zero point line of the image to be identified; S24: performing weighted calculation on the fitting pointer line and the zero point line to obtain an instrument reading result of the image to be identified.
[0006] In one embodiment of the present invention, in step S21, the method for obtaining the fitting pointer line is as follows: S211: calculating the average value of pixel values of the pixel points at the same position in the first template image and the second template image, and constructing a new average value image according to the average values of all pixel points, that is, a pointer-free image; S212: fitting the image without the pointer and the image to be identified to obtain an image with only the pointer; S213: Convert the pointer image only into a binary image, identify the pointer edge in the binary image, obtain two edge lines, fit the intersection of the two edge lines, and use the line connecting the intersection and the center of the dial as the final fitted pointer line.
[0007] In one embodiment of the present invention, in step S212, the method of obtaining only the pointer image is as follows: S2121: Aligning the pixel coordinates of the pointer-free image and the image to be identified to obtain the pointer-free image after coordinate alignment and the image to be identified after coordinate alignment; S2122: Subtract the pixel value of the corresponding position in the coordinate-aligned pointer-free image from each pixel value of the coordinate-aligned image to be identified, to obtain a difference image; S2123: Perform morphological processing on the difference image to complete the pointer edge and remove noise points to obtain an image containing only the pointer.
[0008] In one embodiment of the present invention, in step S22, the method for obtaining the best matching template is as follows: S221: extracting accelerated robust feature points of the third template image and the image to be recognized respectively, and calculating a feature descriptor for each accelerated robust feature point, wherein the feature descriptor contains data information on local image texture and gradient direction intensity distribution; S222: Calculate the similarity between the feature descriptor of the third template image and the feature descriptor of the image to be identified, and select a third template image that satisfies the conditions of high similarity with the image to be identified, a number of feature points exceeding a specified threshold and being evenly distributed, i.e., the best matching template.
[0009] In one embodiment of the present invention, the method comprises step S3: providing an auxiliary light source during the image acquisition process according to the pressure gauge reading identification requirement.
[0010] Based on the same inventive concept of the above-mentioned pointer pressure gauge reading method, the present invention also provides a pointer pressure gauge reading device, which includes: An image acquisition module, the image acquisition module is used to collect an image of a pointer-type pressure gauge; An image processing unit, the image processing unit being used to obtain a reading result based on the pointer pressure gauge image; And a central control module, the central control module is connected to the image processing unit, the central control module sends a pressure gauge template and a zero point identification task instruction and a pressure gauge reading task instruction to the image processing unit, and the image processing unit feeds back the reading result to the central control module.
[0011] In one embodiment of the present invention, the device further comprises a light source control module, and the light source control module is used to provide an auxiliary light source to the image acquisition module according to the pressure gauge reading recognition requirement of the image processing unit.
[0012] In one embodiment of the present invention, the central control module is connected to the image acquisition module. After receiving the image shooting instruction from the central control module, the image acquisition module captures the pointer-type pressure form frame image data or continuous frame video data according to the image shooting instruction, and feeds the data back to the central control module.
[0013] In one embodiment of the present invention, the light source control module is installed on a pointer-type pressure gauge.
[0014] The present invention also provides a computer storage medium, wherein the computer storage medium stores a computer software product, wherein the computer software product includes several instructions for enabling a computer device to execute the above-mentioned pointer pressure gauge reading method.
[0015] The above technical solution of the present invention has the following advantages compared with the prior art: The present invention constructs a pointer-free image and performs difference calculation between the image to be identified to accurately extract the pointer part, and uses template matching and accelerated robust feature point technology to achieve efficient and accurate image recognition and matching. At the same time, it combines the weighted calculation of the fitted pointer line and the zero point line to improve the reading accuracy, and can provide auxiliary light sources according to different lighting conditions to ensure image quality. It is suitable for reading tasks of pointer pressure gauges of various models and specifications. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] In order to make the content of the present invention more clearly understood, the present invention is further described in detail below according to specific embodiments of the present invention in conjunction with the accompanying drawings, wherein: Figure 1 It is a flow chart of the method for reading a pointer pressure gauge provided in the first embodiment of the present invention; Figure 2 is a flow chart of a method for obtaining a pressure gauge reading result provided in Embodiment 1 of the present invention; Figure 3 is a flow chart of a method for obtaining a fitting pointer line provided in the first embodiment of the present invention; Figure 4 is a flow chart of a method for obtaining the best matching template provided in the first embodiment of the present invention; Figure 5 It is a schematic structural diagram of a pointer-type pressure gauge reading device provided in the second embodiment of the present invention; Figure 6 It is a schematic diagram of the operation flow of the pointer type pressure gauge reading device provided in the second embodiment of the present invention; Description of the accompanying drawings in the specification: 10, image acquisition module; 20, image processing unit; 30, central control module; 40, light source control module. DETAILED DESCRIPTION
[0017] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments so that those skilled in the art can better understand the present invention and implement it, but the embodiments are not intended to limit the present invention.
[0018] Embodiment 1
[0019] See also Figure 1 As shown, the present invention provides a method for reading a pointer pressure gauge, the method comprising the following steps: S1: Collect the image of the pointer pressure gauge; S2: Based on the pointer pressure gauge image, perform image processing on the image to be identified to obtain a pressure gauge reading result; Among them, in step S2, based on the pointer pressure gauge image, the image to be identified is subjected to image processing operation to obtain the pressure gauge reading result. Figure 2 As shown below: S21: The pointer pressure gauge image includes two images with the pointer at different positions acquired under the same lighting conditions, which are respectively recorded as a first template image and a second template image, and a fitting pointer line of the image to be identified is obtained based on the first template image and the second template image; S22: sequentially selecting a pointer pressure gauge image from a template library constructed in advance, recording it as a third template image, extracting feature points of the third template image and the image to be identified, and calculating the similarity of feature points of different images and the distribution of feature points to obtain a third template image that meets the screening condition as the best matching template; S23: acquiring the zero point position of the best matching template by identifying the zero point template and the zero point line at the zero point, so as to obtain the zero point line of the image to be identified; S24: Perform weighted calculation on the fitting pointer line and the zero point line to obtain the instrument reading result of the image to be identified :
[0020] in, is the range of the pressure gauge, is the angle between the dial center line and the zero point line, is the angle between the fitting pointer line and the zero point line.
[0021] It can be seen from the above technical solutions that the present invention comprehensively uses advanced technologies such as template matching, difference calculation, morphological processing and accelerated robust feature point recognition to achieve accurate processing and reading recognition of pointer pressure gauge images under complex lighting conditions, which not only improves the accuracy of the readings, but also enhances the applicability and robustness of the method.
[0022] like Figure 3 As shown, in step S21, based on the first template image and the second template image, a fitting pointer line of the image to be identified is obtained, and the method is as follows: S211: calculating the average value of pixel values of the pixel points at the same position in the first template image and the second template image, and constructing a new average value image according to the average values of all pixel points, that is, a pointer-free image; S212: fitting the image without the pointer and the image to be identified to obtain an image with only the pointer; S213: Convert the pointer image only into a binary image, identify the pointer edge in the binary image, obtain two edge lines, fit the intersection of the two edge lines, and use the line connecting the intersection and the center of the dial as the final fitted pointer line.
[0023] Furthermore, in step S212, the method of obtaining only the pointer image is as follows: S2121: Aligning the pixel coordinates of the pointer-free image and the image to be identified to obtain the pointer-free image after coordinate alignment and the image to be identified after coordinate alignment; S2122: Subtract the pixel value of the corresponding position in the coordinate-aligned pointer-free image from each pixel value of the coordinate-aligned image to be identified, to obtain a difference image; S2123: Perform morphological processing on the difference image to complete the pointer edge and remove noise points to obtain an image containing only the pointer.
[0024] like Figure 4 As shown, in step S22, feature points of the third template image and the image to be identified are extracted, and the third template image that meets the screening conditions is obtained as the best matching template by calculating the similarity of the feature points of different images and the distribution of the feature points. The specific method is as follows: S221: extracting accelerated robust feature points of the third template image and the image to be identified respectively by using a SURF algorithm, and calculating a feature descriptor for each accelerated robust feature point, wherein the feature descriptor includes data information on local image texture and gradient direction intensity distribution; S222: Calculate the similarity between the feature descriptor of the third template image and the feature descriptor of the image to be identified, and select a third template image that satisfies the conditions of high similarity with the image to be identified, a number of feature points exceeding a specified threshold and being evenly distributed, i.e., the best matching template.
[0025] Furthermore, the method comprises step S3: providing an auxiliary light source during the image acquisition process according to the pressure gauge reading identification requirement.
[0026] Embodiment 2
[0027] Based on the same inventive concept of the pointer pressure gauge reading method described in the first embodiment, the present invention also provides a pointer pressure gauge reading device, such as Figure 5 As shown, the device comprises: An image acquisition module 10, wherein the image acquisition module 10 is used to acquire an image of a pointer pressure gauge; An image processing unit 20, the image processing unit 20 is used to obtain a reading result based on the pointer pressure gauge image; And a central control module 30, the central control module 30 is connected to the image processing unit 20, the central control module 30 sends a pressure gauge template and a zero point identification task instruction and a pressure gauge reading task instruction to the image processing unit 20, and the image processing unit 20 feeds back the reading result to the central control module.
[0028] Furthermore, the device also includes a light source control module 40, which is installed on a pointer pressure gauge and is used to identify the demand based on the pressure gauge reading of the image processing unit 20 and provide an auxiliary light source to the image acquisition module 10 to reduce the impact of ambient light on the captured image.
[0029] Furthermore, the central control module 30 is connected to the image acquisition module 10. After receiving the image shooting instruction from the central control module 30, the image acquisition module 10 captures pointer-type pressure form frame image data or continuous frame video data according to the image shooting instruction, and feeds the data back to the central control module 30.
[0030] Preferably, the image acquisition module 10 is a high-definition camera. The central control module 30 is a Raspberry Pi processor, which uses a CM4 core board and designs relevant interface circuits, including a Type-C power supply / burning interface, a level conversion circuit, a BOOT conversion circuit, a USB 2.0 interface, an RS485 circuit, a display interface circuit, and a camera interface circuit. The image acquisition module 10 can capture image data in real time, trigger the image processing unit 20 to use advanced algorithms for rapid processing, and display it in real time on a 4.2-inch IPS touch screen through a graphical user interface (GUI), such as a window or dialog box, including the current timestamp and accurate recognition results.
[0031] The Raspberry Pi processor is provided with three function keys: A shooting trigger key T, an instrument calibration key R and a calibration control key Q, wherein the shooting trigger key T is used to immediately issue an image capture instruction to the image acquisition module 10; the instrument calibration key R and the calibration control key Q are used to issue a pressure gauge template and a zero point recognition task instruction and a pressure gauge reading task instruction to the image processing unit 20 respectively; Among them, the instrument calibration key R is used for the calibration process of dial template configuration, zero scale line adjustment and range setting; the calibration control key Q is used to start or terminate the pressure gauge reading calibration process, realizing operational convenience and precise control.
[0032] The above function keys allow users to trigger corresponding key commands through precise input on the physical keyboard. Then, the Raspberry Pi processor quickly parses these commands and sends clear control signals to its associated hardware components or software modules to ensure smooth operation and efficient coordination of the entire system.
[0033] See also Figure 6 As shown, the operation flow of using the reading device to identify the pressure gauge reading is further described as follows: First, the parameters of the high-definition camera (image acquisition module 10) are initialized; Secondly, the user controls the relevant modules to perform corresponding tasks by triggering the function keys of the Raspberry Pi processor, including: when the shooting trigger key T is triggered, the high-definition camera receives the image capture instruction, and takes two images with the pointer at different positions under the same lighting conditions, which are recorded as the first template image photo1 and the second template image photo2 respectively; when the instrument calibration key R is triggered, the image processing unit 20 receives the pressure gauge template and zero point recognition task instruction, and uses the template photo photo1 to perform model matching and zero point line recognition operations; when the calibration control key Q is triggered, the image processing unit 20 receives the pressure gauge reading task instruction, and filters out the pointer-free image brightest in combination with the template photos photo1 and photo2, and based on the pointer-free image brightest, in combination with the image frame acquired in real time by the camera, filters out the pointer-only image of the current image frame, processes the pointer-only image to obtain the pointer line of the current image frame, calculates the angle between the center line of the dial and the zero point line, and the angle between the pointer line and the zero point line, and obtains the current instrument reading by weighted calculation. :
[0034] in, is the range of the pressure gauge, is the angle between the dial center line and the zero point line, is the angle between the fitting pointer line and the zero point line; Finally, the current meter reading The readings are displayed on the graphical user interface of the Raspberry Pi processor, including the acquisition time.
[0035] In the above technical scheme, the image processing unit 20 uses the template photo photo1 to perform model matching and zero-point line recognition operations, which is the same as the method for obtaining the best matching template and zero-point line of the image to be recognized in Example 1; correspondingly, the method for the image processing unit 20 to obtain the pointer line of the current image frame is the same as the method for obtaining the fitting pointer line of the image to be recognized in Example 1, so it will not be repeated here.
[0036] Embodiment 3
[0037] The present invention also provides a computer storage medium, which stores a computer software product. The computer software product includes several instructions for enabling a computer device to execute the pointer pressure gauge reading method described in the above-mentioned embodiment 1.
[0038] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
[0039] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0040] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0041] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0042] Obviously, the above embodiments are merely examples for clear explanation and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived from these are still within the protection scope of the invention.
Claims
1. A method for reading a pointer pressure gauge, characterized in that: The reading method comprises the following steps: S1: Collect the image of the pointer pressure gauge; S2: Based on the pointer pressure gauge image, perform image processing on the image to be identified to obtain a pressure gauge reading result; Wherein, in step S2, the method for obtaining the pressure gauge reading result is as follows: S21: The pointer pressure gauge image includes two images with the pointer at different positions acquired under the same lighting conditions, which are respectively recorded as a first template image and a second template image, and a fitting pointer line of the image to be identified is obtained based on the first template image and the second template image; S22: sequentially selecting a pointer pressure gauge image from a template library constructed in advance, recording it as a third template image, extracting feature points of the third template image and the image to be identified, and calculating the similarity of feature points of different images and the distribution of feature points to obtain a third template image that meets the screening condition as the best matching template; S23: acquiring the zero point position of the best matching template by identifying the zero point template and the zero point line at the zero point, so as to obtain the zero point line of the image to be identified; S24: performing weighted calculation on the fitting pointer line and the zero point line to obtain an instrument reading result of the image to be identified.
2. The method for reading a pointer pressure gauge according to claim 1, characterized in that: In step S21, the method for obtaining the fitting pointer line is as follows: S211: calculating the average value of pixel values of the pixel points at the same position in the first template image and the second template image, and constructing a new average value image according to the average values of all pixel points, that is, a pointer-free image; S212: fitting the image without the pointer and the image to be identified to obtain an image with only the pointer; S213: Convert the pointer image only into a binary image, identify the pointer edge in the binary image, obtain two edge lines, fit the intersection of the two edge lines, and use the line connecting the intersection and the center of the dial as the final fitted pointer line.
3. The method for reading a pointer pressure gauge according to claim 2, characterized in that: In step S212, the method of obtaining only the pointer image is as follows: S2121: Aligning the pixel coordinates of the pointer-free image and the image to be identified to obtain the pointer-free image after coordinate alignment and the image to be identified after coordinate alignment; S2122: Subtract the pixel value of the corresponding position in the coordinate-aligned pointer-free image from each pixel value of the coordinate-aligned image to be identified, to obtain a difference image; S2123: Perform morphological processing on the difference image to complete the pointer edge and remove noise points to obtain an image containing only the pointer.
4. The method for reading a pointer pressure gauge according to claim 1, characterized in that: In step S22, the method for obtaining the best matching template is as follows: S221: extracting accelerated robust feature points of the third template image and the image to be recognized respectively, and calculating a feature descriptor for each accelerated robust feature point, wherein the feature descriptor contains data information on local image texture and gradient direction intensity distribution; S222: Calculate the similarity between the feature descriptor of the third template image and the feature descriptor of the image to be identified, and select a third template image that satisfies the conditions of high similarity with the image to be identified, a number of feature points exceeding a specified threshold and being evenly distributed, i.e., the best matching template.
5. The method for reading a pointer pressure gauge according to claim 1, characterized in that: The method comprises step S3: providing an auxiliary light source during image acquisition according to the pressure gauge reading identification requirement.
6. A pointer pressure gauge reading device, characterized in that: Used to implement the pointer pressure gauge reading method according to any one of claims 1 to 5, the device comprises: An image acquisition module, the image acquisition module is used to collect an image of a pointer-type pressure gauge; An image processing unit, the image processing unit being used to obtain a reading result based on the pointer pressure gauge image; And a central control module, the central control module is connected to the image processing unit, the central control module sends a pressure gauge template and a zero point identification task instruction and a pressure gauge reading task instruction to the image processing unit, and the image processing unit feeds back the reading result to the central control module.
7. The pointer pressure gauge reading device according to claim 6, characterized in that: The device further comprises a light source control module, which is used to provide an auxiliary light source to the image acquisition module according to the pressure gauge reading identification requirement of the image processing unit.
8. The pointer pressure gauge reading device according to claim 6, characterized in that: The central control module is connected to the image acquisition module. After receiving the image shooting instruction from the central control module, the image acquisition module captures the pointer-type pressure form frame image data or continuous frame video data according to the image shooting instruction, and feeds the data back to the central control module.
9. The pointer pressure gauge reading device according to claim 7, characterized in that: The light source control module is installed on a pointer-type pressure gauge.
10. A computer storage medium, characterized in that: The computer storage medium stores a computer software product, and the computer software product includes several instructions for enabling a computer device to execute the pointer pressure gauge reading method described in any one of claims 1 to 5.