Pressure sensor detection method, device and equipment based on image recognition

By automatically detecting pressure sensors based on image recognition, the problems of low sensor detection efficiency and low accuracy are solved, and efficient and accurate sensor detection is achieved.

CN113065538BActive Publication Date: 2025-08-19WUHAN FINEMEMS INC
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202110273847.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-03-12
Publication Date
2025-08-19
Estimated Expiration
2041-03-12

AI Technical Summary

Technical Problem

In the prior art, sensor detection efficiency is low and the accuracy is not high, so it is impossible to detect a large number of pressure sensors efficiently at the same time.

Method used

Using an image recognition method, automatic detection is achieved by obtaining the pressure value corresponding to the pressure source and the target instrument image, identifying the dial reading and comparing it.

Benefits of technology

It improves sensor detection efficiency and accuracy, can identify multiple pressure sensors at the same time, reduces manual intervention, and improves the degree of automation of detection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113065538B_ABST
    Figure CN113065538B_ABST
Patent Text Reader

Abstract

The present invention belongs to the field of sensor technology and discloses a method, device, and apparatus for detecting pressure sensors based on image recognition. The method comprises: obtaining a pressure value corresponding to a pressure source and a target instrument image; obtaining a target dial reading based on the target instrument image; comparing the target dial reading with the pressure value corresponding to the pressure source to obtain dial accuracy; and obtaining a detection result based on the dial accuracy. This method enables automated detection of pressure sensors. Because the dial is automatically read using image information, multiple pressure sensors can be accurately identified simultaneously, thereby improving sensor detection efficiency and the accuracy of pressure sensor detection.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of sensor technology, and in particular to a pressure sensor detection method, device and equipment based on image recognition. Background Art

[0002] With the continuous development of automation technology, the production efficiency of sensors continues to improve, and the efficiency of the detection and verification links in the corresponding sensor production process also needs to be improved urgently.

[0003] Current testing methods often involve applying a constant pressure through a pressure source, then visually comparing the dial reading to see if it reaches the target value. However, due to the large production volume and the human eye's tendency to fatigue, the accuracy of this comparison is low. Furthermore, visually comparing each sensor individually is inefficient, making it impossible to simultaneously test a large number of pressure sensors.

[0004] The above content is only used to assist in understanding the technical solution of the present invention and does not constitute an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of the present invention is to provide a pressure sensor detection method, device and equipment based on image recognition, aiming to solve the technical problems of low efficiency and low accuracy of sensor detection in the existing technology.

[0006] To achieve the above object, the present invention provides a pressure sensor detection method based on image recognition, the method comprising the following steps:

[0007] Obtain the pressure value corresponding to the pressure source and the target instrument image;

[0008] Obtaining a target dial reading according to the target instrument image;

[0009] Comparing the target dial reading with the pressure value corresponding to the pressure source to obtain the dial accuracy;

[0010] A test result is obtained according to the dial accuracy.

[0011] Optionally, the step of obtaining a target dial reading according to the target instrument image includes:

[0012] Performing feature recognition on the target instrument image to determine the instrument position;

[0013] Performing image segmentation on the target instrument image according to the instrument position to obtain a corresponding dial image;

[0014] A target dial reading is obtained according to the corresponding dial image.

[0015] Optionally, the step of obtaining a target dial reading according to the corresponding dial image includes:

[0016] Obtaining the posture features of the dial image;

[0017] Correcting the dial image according to the posture feature to obtain a corrected image;

[0018] Performing pointer recognition on the correction image to obtain the pointer deflection angle;

[0019] A target dial reading is obtained according to the pointer deflection angle.

[0020] Optionally, the step before obtaining the pressure value corresponding to the pressure source and the target instrument image further includes:

[0021] At the beginning of the test, initial parameters are generated so that the pressure source performs corresponding operations on the target instrument according to the initial parameters and feeds back a test status signal;

[0022] Generating a detection parameter according to the detection state signal, and controlling a pressure source to generate a pressure corresponding to a pressure value according to the detection parameter, so that the target instrument reaches a preset pressure value according to the pressure;

[0023] Optionally, after the step of obtaining a target dial reading according to the target instrument image, the method further includes:

[0024] Generate a constant pressure signal to keep the pressure value of the pressure source constant;

[0025] Acquire a second target instrument image at a preset time interval;

[0026] obtaining a second target dial reading according to the second target instrument image;

[0027] Comparing the target dial reading with the second target dial reading to obtain a sealing test result;

[0028] Accordingly, the step of obtaining a test result according to the dial accuracy includes:

[0029] The test results are obtained based on the dial accuracy and sealing test results.

[0030] Optionally, the step of obtaining a test result according to the dial accuracy includes:

[0031] Get the preset product rating mapping relationship table;

[0032] Matching the dial accuracy with the preset product rating mapping relationship table and obtaining a matching result;

[0033] The matching result is used as the detection result.

[0034] Optionally, after the step of obtaining a test result according to the dial accuracy, the method further includes:

[0035] Determine whether there are any unqualified instrument test results based on the test results;

[0036] If there is a test result of an unqualified instrument, the location information of the unqualified instrument is obtained according to the test result of the unqualified instrument;

[0037] Alarm information is generated according to the location information, so that the alarm device issues an alarm according to the alarm information.

[0038] In addition, to achieve the above-mentioned purpose, the present invention further proposes a pressure sensor detection device based on image recognition, the pressure sensor detection device based on image recognition comprising:

[0039] An acquisition module is used to obtain the pressure value corresponding to the pressure source and the target instrument image;

[0040] a processing module, configured to obtain a target dial reading based on the target instrument image;

[0041] The processing module is further configured to compare the target dial reading with a pressure value corresponding to a pressure source to obtain dial accuracy;

[0042] A result module is used to obtain a detection result according to the accuracy of the dial.

[0043] In addition, to achieve the above-mentioned purpose, the present invention also proposes a pressure sensor detection device based on image recognition, and the pressure sensor detection device based on image recognition includes: a memory, a processor, and a pressure sensor detection program based on image recognition stored on the memory and runnable on the processor, and the pressure sensor detection program based on image recognition is configured to implement the steps of the pressure sensor detection method based on image recognition as described above.

[0044] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, on which a pressure sensor detection program based on image recognition is stored. When the pressure sensor detection program based on image recognition is executed by a processor, the steps of the pressure sensor detection method based on image recognition as described above are implemented.

[0045] The present invention obtains the pressure value corresponding to the pressure source and a target instrument image; obtains a target dial reading based on the target instrument image; compares the target dial reading with the pressure value corresponding to the pressure source to determine the dial accuracy; and obtains a test result based on the dial accuracy. This achieves automated pressure sensor testing. Because the dial reading is automatically read based on image information, multiple pressure sensors can be accurately identified simultaneously, thereby improving sensor testing efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a structural diagram of a pressure sensor detection device based on image recognition in a hardware operating environment involved in an embodiment of the present invention;

[0047] Figure 2 This is a flow chart of a first embodiment of a pressure sensor detection method based on image recognition according to the present invention;

[0048] Figure 3 This is a schematic diagram of a detection image according to an embodiment of a pressure sensor detection method based on image recognition according to the present invention;

[0049] Figure 4 This is a flow chart of a second embodiment of a pressure sensor detection method based on image recognition according to the present invention;

[0050] Figure 5 This is a structural block diagram of the first embodiment of the pressure sensor detection device based on image recognition of the present invention.

[0051] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0052] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0053] Reference Figure 1 , Figure 1 This is a structural diagram of a pressure sensor detection device based on image recognition in the hardware operating environment involved in an embodiment of the present invention.

[0054] like Figure 1As shown, the pressure sensor detection device based on image recognition may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0055] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the pressure sensor detection device based on image recognition, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0056] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a pressure sensor detection program based on image recognition.

[0057] exist Figure 1 In the image recognition-based pressure sensor detection device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the image recognition-based pressure sensor detection device of the present invention can be set in the image recognition-based pressure sensor detection device, and the image recognition-based pressure sensor detection device calls the image recognition-based pressure sensor detection program stored in the memory 1005 through the processor 1001, and executes the image recognition-based pressure sensor detection method provided by the embodiment of the present invention.

[0058] The embodiment of the present invention provides a pressure sensor detection method based on image recognition, referring to Figure 2 , Figure 2 This is a flow chart of a first embodiment of a pressure sensor detection method based on image recognition according to the present invention.

[0059] In this embodiment, the pressure sensor detection method based on image recognition includes the following steps:

[0060] Step S10: Obtain the pressure value corresponding to the pressure source and the target instrument image.

[0061] It should be understood that the executor of this embodiment is a pressure sensor detection system, which can be a control system composed of a central controller and a server, or a device with the same or similar functions as the control system. In this embodiment, the control system composed of a central controller and a server is used as an example for explanation.

[0062] It is understood that this embodiment is used during the testing phase of the pressure sensor production process, primarily for batch testing of pressure sensors to meet the testing requirements of mass-produced pressure sensors. During the manufacturing, assembly, and packaging of pressure sensors, problems such as incorrect sensor installation, poor sealing, and dial display malfunctions may occur. If substandard products enter the market, they could result in significant losses. Therefore, testing using this embodiment can effectively reduce the flow of substandard products into the market.

[0063] It should be understood that the pressure source is a device that provides pressure for the pressure sensor to detect. The type of pressure source varies depending on the type of pressure sensor and can be set according to actual circumstances. For example, if the pressure sensor to be detected is an air pressure sensor, the pressure source can be an air pump; if the pressure sensor to be detected is a hydraulic pressure sensor, the pressure source can be a liquid pump; if the pressure sensor to be detected is a load cell, the pressure source can be an extrusion device. This embodiment does not limit the type of pressure sensor.

[0064] Furthermore, the pressure value is the amount of pressure provided by the pressure source, and a relatively accurate pressure reading can be obtained based on the sensor within the pressure source. Furthermore, the target instrument image is an image captured by the image acquisition device of a test bench, test stand, or device on which the pressure sensor is placed. This image includes an image of the pressure sensor dial, and the value within the pressure sensor can be read based on this dial. This embodiment is primarily used for testing and calibrating pressure sensors with external displays or display dials.

[0065] In this embodiment, at the beginning of the detection, initial parameters are generated so that the pressure source performs corresponding operations on the target instrument according to the initial parameters and feeds back a detection status signal; detection parameters are generated according to the detection status signal, and the pressure source is controlled to generate a pressure of the corresponding pressure value according to the detection parameters, so that the target instrument reaches a preset pressure value according to the pressure.

[0066] It should be understood that the initial parameters are parameters that control the pressure source to reach an initial state after the test begins. These parameters may include instructions for controlling the combination of the pressure source and the pressure sensor, or parameters for controlling the pressure source to reach an initial pressure value. The initial state is a state in which both the pressure source and the pressure sensor meet the test requirements. For example, the pressure source and the pressure sensor are fully combined, and the pressure values of the pressure source and the pressure sensor both reach the initial pressure value. The initial pressure value can be set according to the specific test requirements, which is not limited in this embodiment. For example, the pressure sensor can be tested at 1 standard atmosphere.

[0067] It can be understood that the detection parameters are the parameter information needed in the detection. For example, this model of pressure sensor needs to detect the corresponding pressure readings at 0 scale, 1 / 3 full scale, 1 / 2 full scale and full scale, so as to control the pressure source to pressurize the pressure sensor in sequence according to the above parameters. When the pressure provided by the pressure source is stable at the above specified pressure, the pressure sensor reading is detected by collecting image information.

[0068] In a more specific implementation, this embodiment is used to illustrate the steps for detecting each pressure sensor. Therefore, the application scenario of this embodiment can be to detect only one pressure sensor at a time, or to detect multiple pressure sensors at a time. When the application scenario is to detect multiple pressure sensors at a time, this embodiment describes the steps for detecting each sensor in the same detection.

[0069] Step S20: obtaining a target dial reading according to the target instrument image.

[0070] It should be understood that the target dial reading is the dial reading of the pressure sensor being tested. By collecting the image of the dial of the pressure sensor being tested, the specific position of the dial in the image can be identified based on the dial feature recognition, such as Figure 3 As shown, the image in the feature frame is the target instrument image, and then the image content is identified based on image recognition technology. The image recognition technology can be to read the pointer on the dial based on pointer recognition, or to obtain the reading of the digital dial based on digital recognition. Digital recognition technology is relatively common in this technical field and will not be elaborated in this embodiment.

[0071] In a specific implementation, the dial in the feature frame is locked by performing feature recognition on the target instrument image, and then the dial in the feature frame is digitally recognized. For example, the dial is scanned to determine the feature area of each number, and the numbers in the feature area are separated into single numbers to obtain the digital area corresponding to each number; the pixels in each feature area are grayscaled, and if the grayscale of the pixel is greater than a preset value, the feature value of the pixel is set to 1, otherwise it is 0; the feature values of all sampled pixels in the feature area are summed according to the set sampling row interval, and the number to be recognized is matched with the number in the character library according to the summation result to obtain the corresponding digital result, and then the digital results are combined in the order of the feature areas to obtain the dial reading.

[0072] Step S30: Compare the target dial reading with the pressure value corresponding to the pressure source to obtain the dial accuracy.

[0073] It should be understood that the accuracy described in this embodiment is the instrument's reference error, which is used to test the instrument's accuracy. A very large reference error may indicate a significant quality issue with the instrument, requiring repair. The reference error is the absolute error divided by the sensor's full-scale range, then multiplied by 100%. Therefore, the absolute error can be calculated by comparing the dial reading with the pressure value corresponding to the pressure source. By then obtaining the maximum range value of the measured instrument from a server or storage device, the dial's reference error can be fully calculated.

[0074] Step S40: Obtaining a detection result according to the dial accuracy.

[0075] It should be understood that the test results are indicators used to assess product quality, and further operations need to be performed based on the test results in other subsequent processes. For example: after obtaining the test results, the products are classified according to the test results, usually into good products, defective products and waste products, and then products of different quality grades are put into different processing processes.

[0076] In this embodiment, a preset product rating mapping relationship table is obtained; the dial accuracy is matched with the preset product rating mapping relationship table to obtain a matching result; and the matching result is used as a detection result.

[0077] Furthermore, product quality levels can be set based on production process requirements. For example, products with an accuracy error of less than 5% are considered good, while those with an error greater than 10% are considered rejects and require repair or calibration in a repair shop. Test results can include specific accuracy values for detailed analysis, as well as product quality levels for intuitive quality assessment and subsequent production line yield calculations.

[0078] In this embodiment, a constant air pressure signal is generated to keep the pressure value of the pressure source unchanged; a second target instrument image is acquired at a preset time interval; a second target dial reading is obtained based on the second target instrument image; the target dial reading is compared with the second target dial reading to obtain a sealing test result; accordingly, the step of obtaining a test result based on the dial accuracy includes: obtaining a test result based on the dial accuracy and the sealing test result.

[0079] It should be noted that sensor quality testing can also include testing the sensor's sealing. When testing a pressure sensor used to detect fluid media, the pressure source is maintained constant—meaning no new fluid is added to the pressure source or pressure sensor cavity for a period of time—and the pressure sensor reading is observed to see if there is a change. If the pressure sensor reading decreases, it indicates a fluid leak and the sensor's sealing is unqualified.

[0080] In this embodiment, it is determined whether there are any test results of unqualified instruments based on the test results; if there are any test results of unqualified instruments, the location information of the unqualified instruments is obtained based on the test results of the unqualified instruments; and alarm information is generated based on the location information, so that the alarm device issues an alarm based on the alarm information.

[0081] It is important to understand that when a failed instrument is detected, an alarm must be issued to alert the outside world to the presence of a failed pressure sensor. This is because if the pressure sensor is not processed after reading the test report, it may have already entered other processes, otherwise the efficiency of the entire test process will be affected. The alarm can promptly notify other people or equipment of the presence of a failed product, allowing it to be promptly captured for repair or calibration.

[0082] Furthermore, the position information can be obtained by first determining the position of the instrument by obtaining the pixel coordinates of the feature frame on the image, and then converting the coordinates according to the internal parameters of the image acquisition device to obtain the actual position of the instrument. The internal parameters of the image acquisition device are obtained by calibrating the correspondence between the position of the detection platform and the pixel coordinates of the camera during the calibration phase after the installation of the camera. Figure 3After obtaining the actual position of the instrument, the detection position number of the instrument is determined through the mapping relationship table between the detection position and the actual position. For example, when the pixel coordinates of the four corners of the identified feature frame are (121, 100), (151, 100), (121, 70), and (151, 70), by searching the detection position mapping relationship table in the server, it can be determined that the actual position of the pressure sensor is at the second detection position. The pressure sensor can then be matched with the detection position. If the pressure sensor at the second detection position fails, an alarm message for the detection position is generated to indicate that the pressure sensor at the second detection position fails, and then corresponding processing is performed.

[0083] This embodiment obtains the pressure value corresponding to the pressure source and a target instrument image; obtains a target dial reading based on the target instrument image; compares the target dial reading with the pressure value corresponding to the pressure source to determine the dial accuracy; and obtains a test result based on the dial accuracy. This achieves automated pressure sensor testing. Because the dial reading is automatically read based on image information, multiple pressure sensors can be accurately identified simultaneously, thereby improving sensor testing efficiency and accuracy.

[0084] refer to Figure 4 , Figure 4 This is a flow chart of a second embodiment of a pressure sensor detection method based on image recognition according to the present invention.

[0085] Based on the first embodiment described above, the pressure sensor detection method based on image recognition in this embodiment, in step S20, specifically includes:

[0086] Step S21: performing feature recognition on the target instrument image to determine the instrument position.

[0087] It should be understood that the instrument can be identified and the position and range of the feature frame can be determined through instrument feature recognition, such as Figure 3 The feature recognition may be shape recognition, for example, recognizing a circle or sector within a preset size range to identify a circular dial or a sector-shaped dial; or it may be landmark recognition, for example, recognizing a specific symbol on the dial to obtain a feature frame centered on the corresponding symbol. This embodiment does not limit the feature recognition method.

[0088] In addition, the position of the instrument is determined by first obtaining the pixel coordinates of the feature frame on the image, and then converting the coordinates according to the internal parameters of the image acquisition device to obtain the actual position of the instrument. The internal parameters of the image acquisition device are obtained by calibrating the correspondence between the position of the detection platform and the pixel coordinates of the camera during the calibration phase after the installation of the camera. Figure 3After obtaining the actual position of the instrument, the detection position number of the instrument is determined using the mapping relationship table between detection position and actual position. For example, if the pixel coordinates of the four corners of the identified feature frame are (121, 100), (151, 100), (121, 70), and (151, 70), the actual position of the pressure sensor can be determined to be at the second detection position by searching the detection position mapping relationship table in the server. The pressure sensor can then be mapped to the detection position.

[0089] Step S22: performing image segmentation on the target instrument image according to the instrument position to obtain a corresponding dial image.

[0090] It should be understood that image segmentation is to extract the image content in the feature frame of the corresponding position to form a corresponding dial image. Each dial image has a corresponding position instrument position, that is, Figure 3 Therefore, by extracting the content in the corresponding feature frame, it can be ensured that the subsequent image recognition process only processes the image within the feature frame, ensuring the accuracy of image processing and preventing interference from surrounding invalid image information.

[0091] Step S23: obtaining a target dial reading according to the corresponding dial image.

[0092] It should be understood that the target dial reading can be obtained based on the dial image by using image recognition technology to perform pointer recognition on the dial within the feature frame. Since only the dial image is recognized, it will not be affected by other dials or other image information on the test table, so as to obtain a more accurate dial reading.

[0093] In this embodiment, the posture features of the dial image are obtained; the dial image is corrected according to the posture features to obtain a corrected image; the pointer is identified on the corrected image to obtain a pointer deflection angle; and the target dial reading is obtained according to the pointer deflection angle.

[0094] It should be understood that the dial image is corrected, that is, no matter what direction the dial is placed in, all dial images can be corrected to a consistent direction for identification through image correction, which improves the accuracy of subsequent pointer identification, reduces the error of image recognition, reduces the placement requirements of the pressure sensor, and improves the overall efficiency of the detection process. The posture feature is a characteristic image on the dial that can be used to reflect the posture of the dial, for example: an image composed of the 0 scale and the 0 scale line in a circular dial, or an image of the manufacturer's logo on the dial. After the recognition is completed, the deflection angle or tilt of the pressure sensor is obtained by comparing the difference between the posture feature of the detected pressure sensor and the pre-set posture feature, and then the image is corrected by adjusting the image by rotating and scaling.

[0095] In a specific implementation, by correcting the dial image, it can be ensured that normal detection can be performed even when the dial is tilted or the placement angle is deviated, and the direction of the dial image of each pressure sensor is corrected to the preset direction of image recognition.

[0096] Pointer recognition is performed on the correction image to obtain the pointer deflection angle; the target dial reading is obtained based on the pointer deflection angle. After the calibration is completed, the 0 scale angle information of the corresponding instrument can be obtained based on the pre-acquired instrument model, the current pointer angular position can be obtained through pointer recognition, and then the pointer deflection angle can be obtained based on the 0 scale and the angle of the pointer position. The current dial reading can be obtained through the pre-acquired instrument range information and the pointer deflection angle. The silhouette method can also be used to obtain the pointer deflection angle by first storing the pointing angle of the pointer under no pressure and then obtaining the angle that the current pointer points to. This embodiment does not limit the method for obtaining the pointer deflection angle, and only uses the above two methods as examples. In addition, pointer recognition can be obtained by recognizing straight line segments, and then blurring the line segments that do not meet the predetermined length to obtain the pointer image.

[0097] It can be understood that this step improves the accuracy of the subsequent pointer recognition step, reduces the error of image recognition, reduces the placement requirements of the pressure sensor, and improves the overall efficiency of the detection process.

[0098] In this embodiment, before the step of obtaining the target dial reading based on the corresponding dial image, it includes: performing feature recognition on the dial image to obtain dial features; determining the dial model based on the dial features; accordingly, the step of obtaining the target dial reading based on the corresponding dial image also includes: obtaining the target dial reading based on the corresponding dial image and the dial type.

[0099] Furthermore, posture features of the dial image are obtained according to the dial type; the dial image is corrected according to the posture features to obtain a corrected image; pointer recognition is performed on the corrected image according to the dial type to obtain a pointer deflection angle; and a target dial reading is obtained according to the pointer deflection angle.

[0100] It should be understood that during the testing process, different models and specifications of sensors may appear in the same testing batch. If a unified testing strategy is used, it will be impossible to detect pressure sensors of different models. Therefore, as mentioned above, the dial model is determined by identifying the dial features. The dial features can be determined by dial size, shape, type number, identification symbol, or a combination of the above features, such as Figure 3As shown, for example, the dial type can be preliminarily identified based on the dial shape, and the dial size can be compared for instruments with the same dial shape, and further identification information can be used based on the identification information on the dial. This embodiment is not limited to this.

[0101] In addition, the model of the instrument can be obtained by comparing the identified dial features with the dial features pre-stored in the server, and then the corresponding dial scale, range information, pointer features or detection parameters can be read according to the instrument model for subsequent detection work.

[0102] It should be understood that the detection parameters are the parameter information needed for detection. For example, this model of pressure sensor needs to detect the pressure readings at 0 scale, 1 / 3 full scale, 1 / 2 full scale and full scale.

[0103] It can be understood that this step performs feature recognition on the dial image to obtain dial features; determines the dial model based on the dial features; and obtains the target dial reading based on the corresponding dial image and dial type. This enables the simultaneous testing of different instrument models using the same test bench, improving testing flexibility and addressing a wider range of testing scenarios.

[0104] This embodiment performs feature recognition on the target instrument image to determine the instrument location; then segments the target instrument image based on the instrument location to obtain a corresponding dial image; and finally, obtains the target dial reading based on the corresponding dial image. By accurately acquiring the instrument location and then segmenting each instrument image to obtain a corresponding dial image, the same image acquisition device can be used to test multiple pressure sensors, improving pressure sensor testing efficiency while also reducing the impact of irrelevant image information on the instrument image and enhancing detection accuracy.

[0105] In addition, an embodiment of the present invention also proposes a storage medium, which stores a pressure sensor detection program based on image recognition. When the pressure sensor detection program based on image recognition is executed by a processor, the steps of the pressure sensor detection method based on image recognition as described above are implemented.

[0106] Reference Figure 5 , Figure 5 This is a structural block diagram of the first embodiment of the pressure sensor detection device based on image recognition of the present invention.

[0107] like Figure 5 As shown, the pressure sensor detection device based on image recognition proposed in an embodiment of the present invention includes:

[0108] An acquisition module 10 is used to acquire the pressure value corresponding to the pressure source and the target instrument image;

[0109] A processing module 20 is configured to obtain a target dial reading based on the target instrument image;

[0110] The processing module 20 is further configured to compare the target dial reading with the pressure value corresponding to the pressure source to obtain the dial accuracy;

[0111] The result module 30 is used to obtain a detection result according to the accuracy of the dial.

[0112] This embodiment utilizes an acquisition module 10 to acquire the pressure value corresponding to the pressure source and a target instrument image; a processing module 20 to obtain a target dial reading based on the target instrument image; and finally, a result module 30 to obtain a test result based on the dial accuracy. This achieves automated pressure sensor testing. Automatic dial readings based on image information allow for accurate identification of multiple pressure sensors simultaneously, thereby improving sensor testing efficiency and accuracy.

[0113] In one embodiment, the processing module 20 is further used to perform feature recognition on the target instrument image to determine the instrument position; perform image segmentation on the target instrument image according to the instrument position to obtain a corresponding dial image; and obtain a target dial reading based on the corresponding dial image.

[0114] In one embodiment, the processing module 20 is further used to obtain posture features of the dial image; correct the dial image according to the posture features to obtain a corrected image; perform pointer recognition on the corrected image to obtain a pointer deflection angle; and obtain a target dial reading based on the pointer deflection angle.

[0115] In one embodiment, the processing module 20 is also used to generate initial parameters at the beginning of the detection, so that the pressure source performs corresponding operations on the target instrument according to the initial parameters and feeds back a detection status signal; generates detection parameters according to the detection status signal, and controls the pressure source to generate pressure of the corresponding pressure value according to the detection parameters, so that the target instrument reaches a preset pressure value according to the pressure.

[0116] In one embodiment, the processing module 20 is further used to generate a constant air pressure signal so that the pressure source maintains a constant pressure value; obtain a second target instrument image at a preset time interval; obtain a second target dial reading based on the second target instrument image; compare the target dial reading with the second target dial reading to obtain a sealing test result; the result module 30 is further used to obtain a test result based on the dial accuracy and the sealing test result.

[0117] In one embodiment, the result module 30 is further configured to obtain a preset product rating mapping relationship table; match the dial accuracy with the preset product rating mapping relationship table to obtain a matching result; and use the matching result as a detection result.

[0118] In one embodiment, the result module 30 is further used to determine whether there is a test result of an unqualified instrument based on the test results; if there is a test result of an unqualified instrument, obtain the location information of the unqualified instrument based on the test result of the unqualified instrument; and generate alarm information based on the location information, so that the alarm device can sound an alarm based on the alarm information.

[0119] It should be understood that the above is only an example and does not constitute any limitation to the technical solution of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any limitation on this.

[0120] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of it according to actual needs to achieve the purpose of the embodiment scheme, and no limitation is made here.

[0121] In addition, for technical details not fully described in this embodiment, reference can be made to the pressure sensor detection method based on image recognition provided in any embodiment of the present invention, and will not be repeated here.

[0122] In addition, it should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0123] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0124] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, or of course by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0125] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A pressure sensor detection method based on image recognition, characterized in that: The pressure sensor detection method based on image recognition includes: Obtain the pressure value corresponding to the pressure source and the target instrument image; Obtaining a target dial reading based on the target instrument image, scanning the dial to determine a characteristic region of each digit, summing the characteristic values of all sampled pixel points in the characteristic region according to a set sampling row interval, matching the digit to be recognized with the digits in the character library based on the summation result to obtain a corresponding digital result, and then combining the digital results according to the order of the characteristic regions to obtain the dial reading; Comparing the target dial reading with the pressure value corresponding to the pressure source to obtain the dial accuracy; Obtaining a test result according to the dial accuracy; The step before obtaining the pressure value corresponding to the pressure source and the target instrument image also includes: At the beginning of the test, initial parameters are generated so that the pressure source performs corresponding operations on the target instrument according to the initial parameters and feeds back a test status signal; Generating a detection parameter according to the detection state signal, and controlling a pressure source to generate a pressure corresponding to a pressure value according to the detection parameter, so that the target instrument reaches a preset pressure value according to the pressure; After the step of obtaining a target dial reading according to the target instrument image, the method further includes: Generate a constant pressure signal to keep the pressure value of the pressure source constant; Acquire a second target instrument image at a preset time interval; obtaining a second target dial reading according to the second target instrument image; Comparing the target dial reading with the second target dial reading to obtain a sealing test result; Accordingly, the step of obtaining a test result according to the dial accuracy includes: The test results are obtained based on the dial accuracy and sealing test results.

2. The method according to claim 1, wherein The step of obtaining a target dial reading according to the target instrument image comprises: Performing feature recognition on the target instrument image to determine the instrument position; Performing image segmentation on the target instrument image according to the instrument position to obtain a corresponding dial image; A target dial reading is obtained according to the corresponding dial image.

3. The method according to claim 2, wherein The step of obtaining a target dial reading according to the corresponding dial image includes: Obtaining the posture features of the dial image; Correcting the dial image according to the posture feature to obtain a corrected image; Performing pointer recognition on the correction image to obtain the pointer deflection angle; A target dial reading is obtained according to the pointer deflection angle.

4. The method according to claim 1, wherein The step of obtaining a test result according to the dial accuracy includes: Get the preset product rating mapping relationship table; Matching the dial accuracy with the preset product rating mapping relationship table and obtaining a matching result; The matching result is used as the detection result.

5. The method according to any one of claims 1 to 4, wherein After the step of obtaining the test result according to the dial accuracy, the method further includes: Determine whether there are any unqualified instrument test results based on the test results; If there is a test result of an unqualified instrument, the location information of the unqualified instrument is obtained according to the test result of the unqualified instrument; Alarm information is generated according to the location information, so that the alarm device issues an alarm according to the alarm information.

6. A pressure sensor detection device based on image recognition, characterized in that: The pressure sensor detection device based on image recognition includes: An acquisition module is used to obtain the pressure value corresponding to the pressure source and the target instrument image; a processing module for obtaining a target dial reading based on the target instrument image, scanning the dial to determine a characteristic region of each digit, summing characteristic values of all sampled pixels in the characteristic region according to a set sampling row interval, matching the digit to be recognized with the digits in the character library based on the summation result to obtain a corresponding numerical result, and then combining the numerical results according to the order of the characteristic regions to obtain the dial reading; The processing module is further configured to compare the target dial reading with the pressure value corresponding to the pressure source to obtain the dial accuracy; A result module, configured to obtain a test result based on the accuracy of the dial; The acquisition module is further configured to generate initial parameters at the start of detection, so that the pressure source performs corresponding operations on the target instrument according to the initial parameters and feeds back a detection status signal; Generating a detection parameter according to the detection state signal, and controlling a pressure source to generate a pressure corresponding to a pressure value according to the detection parameter, so that the target instrument reaches a preset pressure value according to the pressure; The processing module is further configured to generate a constant pressure signal so as to keep the pressure value of the pressure source constant; Acquire a second target instrument image at a preset time interval; obtaining a second target dial reading according to the second target instrument image; Comparing the target dial reading with the second target dial reading to obtain a sealing test result; Accordingly, the step of obtaining a test result according to the dial accuracy includes: The test results are obtained based on the dial accuracy and sealing test results.

7. A pressure sensor detection device based on image recognition, characterized in that: The device includes: a memory, a processor, and an image recognition-based pressure sensor detection program stored in the memory and executable on the processor, wherein the image recognition-based pressure sensor detection program is configured to implement the steps of the image recognition-based pressure sensor detection method according to any one of claims 1 to 5.

8. A storage medium, characterized in that: The storage medium stores a pressure sensor detection program based on image recognition, and when the pressure sensor detection program based on image recognition is executed by the processor, the steps of the pressure sensor detection method based on image recognition according to any one of claims 1 to 5 are implemented.

Citation Information

Patent Citations

  • Pointer type pressure gauge intelligent verification system and method

    CN111521321A

  • Instrument panel pointer reading identification method and device, computer equipment and storage medium

    CN112115893A