Meter reading method and device of pointer instrument, electronic equipment and computer program product

Abstract

The invention is suitable for the technical field of artificial intelligence, and provides a meter reading method and device of a pointer meter, electronic equipment and a computer program product. The method comprises the following steps: acquiring an initial image comprising a pointer instrument; determining a first scale line and a first pointer rotation center point of the pointer instrument according to the initial image; according to the first scale line and the first pointer rotation center point, performing normalization processing on the initial image to obtain a target image; according to the target image, determining a second scale line, a second pointer rotation center point, a pointer tip point, a scale value and a measurement unit of the pointer instrument; and determining the reading of the pointer instrument according to the second scale line, the second pointer rotation center point, the pointer tip point, the scale value and the measurement unit. Through the method, the reading of the pointer instrument can be automatically identified, manual meter reading of the pointer instrument is not needed, and the safety risk of meter reading personnel is reduced.

Description

Technical Field

[0001] This application belongs to the field of artificial intelligence technology, and in particular relates to a method, device, electronic device and computer program product for reading pointer instruments. Background Technology

[0002] Currently, pointer meters are usually read manually. This manual reading method can pose safety hazards in some scenarios. For example, in nuclear power plants, some pointer meters are located in areas with certain safety risks, and manual reading may pose safety hazards to the personnel reading the meters, increasing their safety risks. Summary of the Invention

[0003] In view of this, embodiments of this application provide a method, apparatus, electronic device, and computer program product for reading pointer meters to solve the technical problem of high safety risks for existing meter readers.

[0004] In a first aspect, embodiments of this application provide a method for reading a pointer meter, including: Acquire an initial image including the pointer meter; Based on the initial image, determine the first scale line and the first pointer rotation center point of the pointer instrument; The initial image is normalized based on the first scale line and the first pointer rotation center point to obtain the target image; Based on the target image, determine the second scale line, the second pointer rotation center point, the pointer tip point, the scale value, and the unit of measurement of the pointer instrument; The reading of the pointer instrument is determined based on the second scale line, the second pointer rotation center point, the pointer tip point, the scale value, and the unit of measurement.

[0005] Optionally, the step of normalizing the initial image based on the first scale line and the first pointer rotation center point to obtain the target image includes: The actual shape of the pointer instrument is determined based on the first scale line; Based on the first scale line, the actual shape of the pointer instrument, and the rotation center point of the first pointer, the initial image is subjected to distortion correction processing; Based on the first scale line and the first pointer rotation center point, the initial image after distortion correction is subjected to polar coordinate transformation to obtain the target image.

[0006] Optionally, the second scale line, the second pointer rotation center point, and the pointer tip point are determined in the following manner: Multimodal features of the target image are extracted by a pre-trained feature extraction model, and probability heatmaps corresponding to the second scale line, the second pointer rotation center point, and the pointer tip point are generated by a pre-trained pyramid network based on the multimodal features. Based on the probability heatmap corresponding to the second scale line, the first preliminary position corresponding to the second scale line is determined, and the first correction amount corresponding to the first preliminary position is determined by a pre-trained coordinate regression branch model. Based on the first preliminary position and the first correction amount, the second scale line is determined. Based on the probability heatmap corresponding to the second pointer rotation center point, the second preliminary position corresponding to the second pointer rotation center point is determined, and the second correction amount corresponding to the second preliminary position is determined through the coordinate regression branch model. Based on the second preliminary position and the second correction amount, the second pointer rotation center point is determined. Based on the probability heatmap corresponding to the pointer tip, the third preliminary position corresponding to the pointer tip is determined, and the third correction amount corresponding to the third preliminary position is determined through the coordinate regression branch model. Based on the third preliminary position and the third correction amount, the pointer tip is determined.

[0007] Optionally, after determining the second scale line, the second pointer rotation center point, the pointer tip point, the scale value, and the unit of measurement of the pointer instrument based on the target image, the method further includes: Determine whether the distance between the second pointer rotation center point and the pointer tip point is within the distance range, and determine whether the distance between the second pointer rotation center point and the geometric center point of the pointer instrument is less than a preset distance threshold. If both are true, then the verification of the second pointer rotation center point and the pointer tip point is confirmed to be successful.

[0008] Optionally, after determining the second scale line, the second pointer rotation center point, the pointer tip point, the scale value, and the unit of measurement of the pointer instrument based on the target image, the method further includes: Two adjacent second scale lines in each of the second scale lines are defined as a scale line combination, resulting in several scale line combinations; For each of the scale line combinations, determine the angle difference corresponding to each scale line combination to obtain the angle difference corresponding to each scale line combination. If the angle difference corresponding to each of the aforementioned scale line combinations is within the range of angle difference, then the second scale line verification is confirmed to be successful.

[0009] Optionally, after determining the second scale line, the second pointer rotation center point, the pointer tip point, the scale value, and the unit of measurement of the pointer instrument based on the target image, the method further includes: Determine whether the distribution of each scale value conforms to the preset scale distribution pattern, and determine whether each scale value is within the preset scale value range. If they are, then determine that each scale value has passed the verification. Determine whether the unit of measurement is a preset unit of measurement; if so, determine that the unit of measurement has passed verification.

[0010] Optionally, determining the reading of the pointer instrument based on the second scale line, the second pointer rotation center point, the pointer tip, the scale value, and the unit of measurement includes: Based on the rotation center point of the second pointer, a target coordinate system is constructed, and the first coordinates of each of the second scale lines in the target coordinate system, the second coordinates of the pointer tip in the target coordinate system, and the third coordinates of the rotation center point of the second pointer in the target coordinate system are determined. Based on the second coordinate and the third coordinate, determine the angle between the pointer tip and a preset axis in the target coordinate system; Based on the first coordinate and the scale value, determine the unit scale value corresponding to each unit of the included angle; The reading of the pointer instrument is determined based on the included angle, the unit scale value, and the unit of measurement.

[0011] Secondly, embodiments of this application provide a meter reading device for a pointer instrument, comprising: An image acquisition unit is used to acquire an initial image, including the pointer instrument. The first determining unit is used to determine the first scale line and the first pointer rotation center point of the pointer instrument based on the initial image. An image processing unit is configured to normalize the initial image based on the first scale line and the first pointer rotation center point to obtain a target image; The second determining unit is used to determine the second scale line, the second pointer rotation center point, the pointer tip point, the scale value, and the unit of measurement of the pointer instrument based on the target image. The third determining unit is used to determine the reading of the pointer instrument based on the second scale line, the second pointer rotation center point, the pointer tip point, the scale value, and the unit of measurement.

[0012] Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the reading method of the pointer instrument as described in any of the first aspects above.

[0013] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the meter reading method for a pointer instrument as described in any of the first aspects above.

[0014] Fifthly, embodiments of this application provide a computer program product that, when run on a control device, causes the control device to perform the steps of the meter reading method for a pointer instrument as described in any of the first aspects above.

[0015] The reading method, apparatus, electronic device, and computer program product of the pointer meter provided in this application have the following beneficial effects: In the meter reading method of the pointer meter provided in this application embodiment, an initial image including the pointer meter is first acquired. Then, based on the initial image, the first scale line and the first pointer rotation center point of the pointer meter are determined. Next, based on the first scale line and the first pointer rotation center point, the initial image is normalized to obtain a target image. Then, based on the target image, the second scale line, the second pointer rotation center point, the pointer tip, the scale value, and the unit of measurement of the pointer meter are determined. Finally, based on the second scale line, the second pointer rotation center point, the pointer tip, the scale value, and the unit of measurement, the reading of the pointer meter is determined. Through this method, electronic devices can automatically identify the reading of the pointer meter, eliminating the need for manual meter reading and reducing the safety risks for meter readers. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 A flowchart illustrating the implementation of the meter reading method for the pointer instrument provided in this application embodiment; Figure 2 A schematic diagram of a pointer instrument provided for an embodiment of this application; Figure 3 A flowchart illustrating the implementation of the method for determining pointer instrument readings provided in this application embodiment; Figure 4 A schematic diagram of the structure of a reading device for a pointer meter provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0018] It should be noted that the terminology used in the embodiments of this application is only for explaining specific embodiments of this application and is not intended to limit this application. In the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more, "at least one" or "one or more" means one, two or more. The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0019] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0020] The instrument reading method for pointer meters provided in this application can be executed by an electronic device, which may include, but is not limited to, electronic devices such as laptops, desktop computers, tablets, and mobile phones.

[0021] The pointer meter reading method provided in this application can be applied to any scenario requiring pointer meter reading. For example, in a nuclear power plant, some pointer meters may be located in positions with certain safety risks. Manually reading these meters may pose a safety hazard to the personnel reading them. In this case, the various steps of the pointer meter reading method provided in this application can be executed by electronic devices, thereby enabling the electronic devices to identify the pointer meter readings and reducing the safety risks for the personnel reading the meters.

[0022] Please see Figure 1 , Figure 1 This is a flowchart illustrating the implementation of a meter reading method for a pointer instrument provided in this application. The meter reading method for a pointer instrument provided in this application may include steps S101 to S105, as detailed below: In S101, an initial image including pointer instruments is acquired.

[0023] In this embodiment, the electronic device can first acquire an image including a pointer meter using a preset camera. After acquiring the image including the pointer meter, the electronic device can filter out initial images that meet preset requirements.

[0024] For example, an electronic device may acquire one or more of the following metrics of an image: sharpness, illumination uniformity, noise interference, and occlusion.

[0025] Specifically, electronic devices can determine the sharpness of an image by calculating the edge gradient values. For example, if the edge gradient values ​​of the initial image are higher than a preset gradient value threshold, the image sharpness can be determined to meet the requirements. If the edge gradient values ​​of the image are lower than or equal to the preset gradient value threshold, the image sharpness can be determined to not meet the requirements.

[0026] Specifically, electronic devices can determine the uniformity of illumination of an image by analyzing its grayscale histogram. For example, if the sum of the proportions of a first region with grayscale values ​​greater than a first preset grayscale value threshold and a second region with grayscale values ​​less than a second preset grayscale value threshold in the image's grayscale histogram is less than a preset first proportion threshold, then the uniformity of illumination of the image can be determined to meet the requirements. If the sum of the proportions of the first and second regions in the image's grayscale histogram is greater than or equal to the preset first proportion threshold, then the uniformity of illumination of the image can be determined to not meet the requirements.

[0027] Specifically, electronic devices can perform noise detection on images to determine the noise pixels in the image. If the proportion of noise pixels in the image is less than a preset second proportion threshold, it can be determined that the noise interference of the image meets the requirements. If the proportion of noise pixels in the image is greater than or equal to the preset second proportion threshold, it can be determined that the noise interference of the image does not meet the requirements.

[0028] Specifically, electronic devices can perform target region integrity analysis on images to determine the occluded area of ​​pointer instruments in the image. If the occluded area of ​​pointer instruments in the image is less than a preset area threshold, the occlusion level of the image can be determined to meet the requirements. If the occluded area of ​​pointer instruments in the image is greater than or equal to the preset area threshold, the occlusion level of the image can be determined to not meet the requirements.

[0029] Electronic devices can determine an image as the initial image if it meets the requirements for sharpness, uniformity of illumination, noise interference, and degree of occlusion.

[0030] In S102, the first scale line of the pointer instrument and the first pointer rotation center point are determined based on the initial image.

[0031] In this implementation, after the initial image is determined, the electronic device can first determine the first scale line of the pointer instrument and the first pointer rotation center point based on the initial image.

[0032] The first scale line is the scale line of the pointer instrument in the initial image. In practical applications, there can be multiple scale lines in the initial image.

[0033] The first pointer rotation center point is the pointer rotation center point of the pointer instrument in the initial image. In practical applications, the number of pointer rotation center points in the initial image can be one.

[0034] Please see Figure 2 , Figure 2 This is a schematic diagram of a pointer instrument provided in an embodiment of this application. Figure 2 As shown, the pointer instrument can have multiple first scale lines, and the pointer instrument can have one first pointer rotation center point, and the pointer of the pointer instrument rotates around the first pointer rotation center point.

[0035] In one possible implementation, the electronic device can determine the individual first scale lines and the first pointer rotation center point of the pointer instrument in the following way: Multimodal features of the initial image are extracted by a pre-trained feature extraction model, and probability heatmaps corresponding to the first tick line and the first pointer rotation center point are generated by a pre-trained pyramid network based on the multimodal features of the initial image. After determining the probability heatmap corresponding to the first scale line, the initial position of the first scale line is determined based on the probability heatmap. The correction amount corresponding to the initial position of the first scale line is determined through a pre-trained coordinate regression branch model. Based on the initial position and the corresponding correction amount, the first scale line is determined.

[0036] After determining the probability heatmap corresponding to the first pointer rotation center point, the initial position corresponding to the first pointer rotation center point is determined based on the probability heatmap. The correction amount corresponding to the initial position corresponding to the first pointer rotation center point is determined through a pre-trained coordinate regression branch model. Finally, the first pointer rotation center point is determined based on the initial position and the corresponding correction amount.

[0037] In S103, the initial image is normalized based on the first scale line and the first pointer rotation center point to obtain the target image.

[0038] In this embodiment of the application, after determining the first scale line and the first pointer rotation center point, the electronic device can normalize the initial image based on the first scale line and the first pointer rotation center point to obtain the target image in the following manner: First, the electronic device can determine the actual shape of the pointer instrument based on the first scale line. For example, the actual shape of the pointer instrument can be circular or elliptical.

[0039] After determining the actual shape of the pointer instrument, the electronic device can perform distortion correction processing on the initial image based on the first scale line, the actual shape of the pointer instrument, and the first pointer rotation center point. For example, if the actual shape of the pointer instrument is determined to be circular, while the pointer instrument in the initial image is elliptical, it can be considered that the pointer instrument in the initial image has been distorted. Therefore, distortion correction processing can be performed on the initial image based on the first scale line, the actual shape of the pointer instrument, and the first pointer rotation center point to correct the pointer instrument in the initial image from an ellipse to a circle.

[0040] After distortion correction of the initial image, the electronic device can perform polar coordinate transformation on the distortion-corrected initial image based on the first scale line and the first pointer rotation center point to obtain the target image. For example, the electronic device can use the first pointer rotation center point as the pole and the direction of the target scale line (e.g., the 0 scale line) in the first scale line as the polar axis direction to perform polar coordinate transformation on the distortion-corrected initial image, thereby obtaining the target image.

[0041] In S104, based on the target image, the second scale line of the pointer instrument, the second pointer rotation center point, the pointer tip point, the scale value, and the unit of measurement are determined.

[0042] In this embodiment of the application, after obtaining the target image, the electronic device determines the second scale line of the pointer instrument, the second pointer rotation center point, the pointer tip point, the scale value, and the unit of measurement based on the target image.

[0043] It should be noted that the difference between the second scale line and the first scale line is that the first scale line is the scale line of the pointer instrument in the initial image, while the second scale line is the scale line of the pointer instrument in the target image; the difference between the second pointer rotation center point and the first pointer rotation center point is that the first pointer rotation center point is the pointer rotation center point of the pointer instrument in the initial image, while the second pointer rotation center point is the pointer rotation center point of the pointer instrument in the target image.

[0044] The pointer tip is the tip of the pointer of the pointer instrument in the target image.

[0045] The scale values ​​are the values ​​corresponding to certain second scale lines of the pointer instrument in the target image.

[0046] The second graduation mark, the center point of the second pointer rotation, the pointer tip, the graduation value, and the unit of measurement of the pointer instrument can all be found in the reference. Figure 2 It should be noted that, Figure 2 The unit of measurement is megapascal (MPa).

[0047] In one possible implementation, the electronic device can determine the second scale line, the second pointer rotation center point, and the pointer tip of the pointer instrument based on the target image in the following way: Multimodal features of the target image are extracted by a pre-trained feature extraction model, and probability heatmaps corresponding to the second scale line, the second pointer rotation center point, and the pointer tip point are generated by a pre-trained pyramid network based on the multimodal features.

[0048] After determining the probability heatmap corresponding to the second scale line, the first preliminary position corresponding to the second scale line can be determined based on the probability heatmap. The first correction amount corresponding to the first preliminary position can be determined through a pre-trained coordinate regression branch model. The second scale line can then be determined based on the first preliminary position and the first correction amount. After determining the probability heatmap corresponding to the second pointer rotation center point, the second preliminary position corresponding to the second pointer rotation center point can be determined based on the probability heatmap. The second correction amount corresponding to the second preliminary position can be determined through the coordinate regression branch model. The second pointer rotation center point can be determined based on the second preliminary position and the second correction amount. After determining the probability heatmap corresponding to the pointer tip, the third preliminary position corresponding to the pointer tip can be determined based on the probability heatmap. The third correction value corresponding to the third preliminary position can be determined through the coordinate regression branch model. Based on the third preliminary position and the third correction value, the pointer tip can be determined.

[0049] In one possible implementation, the electronic device can determine the scale value by performing text recognition processing on the target image to obtain the semantic information and position information corresponding to each character in the target image. Then, for each character, based on the semantic information corresponding to the character, it is determined whether the character is a scale value. If so, based on the position information corresponding to the character, the second scale line corresponding to the character is determined, thereby determining each scale value and the second scale line corresponding to each scale value.

[0050] In one possible implementation, the electronic device can determine the unit of measurement by performing text recognition processing on the target image to obtain the semantic and positional information corresponding to each character in the target image. Then, for each character, it determines whether the character is a unit of measurement based on the semantic information corresponding to the character. If so, the semantic information corresponding to the character is determined as the unit of measurement.

[0051] In one possible implementation, after determining the second scale line, the second pointer rotation center point, the pointer tip, the scale value, and the unit of measurement of the pointer instrument, the electronic device can verify the second pointer rotation center point and the pointer tip point in the following way: Determine whether the distance between the second pointer rotation center point and the pointer tip point is within the distance range, and determine whether the distance between the second pointer rotation center point and the geometric center point of the pointer instrument is less than the preset distance threshold. If both are true, then the verification of the second pointer rotation center point and the pointer tip point is confirmed to be successful.

[0052] The preset range can be determined by the user based on the actual distance between the center point of pointer rotation and the tip point of pointer in the actual pointer instrument and input into the electronic device. For example, if the actual distance between the center point of pointer rotation and the tip point of pointer in the actual pointer instrument is 10, then (9, 11) can be determined as the preset range.

[0053] The geometric center point of the pointer instrument can be determined by the electronic device based on the target image. For example, if the pointer instrument in the target image is a target circle, then the geometric center point of the pointer instrument is the center of the target circle.

[0054] The distance threshold can be determined by the user according to actual needs and input into the electronic device.

[0055] In one possible implementation, after determining the second scale line, the second pointer rotation center point, the pointer tip, the scale value, and the unit of measurement of the pointer instrument, the electronic device can verify the second scale line in the following way: Each pair of adjacent second scale lines is defined as a scale line combination, resulting in several scale line combinations. For each scale line combination, the angle difference corresponding to each scale line combination is determined, resulting in the angle difference corresponding to each scale line combination. If the angle difference corresponding to each scale line combination is within the angle difference range, then the second scale line is verified as passed.

[0056] The angle difference range can be determined by the user based on the angle difference between the various scale lines in the actual pointer instrument and input into the electronic device. For example, if the angle difference between the various scale lines in the actual pointer instrument is 15°, then (14°, 16°) can be determined as the angle difference range.

[0057] In one possible implementation, after determining the second scale line, the second pointer rotation center point, the pointer tip, the scale value, and the unit of measurement of the pointer instrument, the electronic device can verify the scale value and the unit of measurement in the following way: Determine whether the distribution of each scale value conforms to the preset scale distribution pattern, and determine whether each scale value is within the preset scale value range. If so, then the verification of each scale value is confirmed to be successful. Determine if the unit of measurement is the preset unit of measurement; if so, confirm that the unit of measurement has passed verification.

[0058] The preset scale distribution pattern can be determined by the user based on the angle difference between the positions of adjacent scale values ​​in the actual pointer instrument and input into the electronic device. For example, if the angle difference between the positions of adjacent scale values ​​in the actual pointer instrument is 30°, the scale distribution pattern can be determined as follows: the angle difference between the positions of adjacent scale values ​​is within the preset angle difference range, such as (29°, 31°). If the angle difference between the positions of adjacent scale values ​​is within the preset angle difference range, it can be determined whether the distribution of each scale value conforms to the preset scale distribution pattern.

[0059] The preset scale value range can be input by the user into the electronic device according to the actual situation. For example, the preset scale value range is less than or equal to 50. If all scale values ​​are less than 50, it can be determined that all scale values ​​are within the preset scale value range.

[0060] The preset unit of measurement can be entered by the user into the electronic device according to the actual situation. For example, the preset unit of measurement can be kilopascal (kPa) or megapascal (MPa). If the detected unit of measurement is kilopascal (kPa) or megapascal (MPa), then the unit of measurement can be determined to be the preset unit of measurement.

[0061] It should be noted that if any one or more of the following verifications of the pointer instrument's second scale line, second pointer rotation center point, pointer tip point, scale value, and unit of measurement fail, the steps corresponding to S101 to S104 can be re-executed to re-determine the pointer instrument's second scale line, second pointer rotation center point, pointer tip point, scale value, and unit of measurement, and the verification of the pointer instrument's second scale line, second pointer rotation center point, pointer tip point, scale value, and unit of measurement can continue.

[0062] In S105, the reading of the pointer instrument is determined based on the second scale line, the center point of rotation of the second pointer, the pointer tip, the scale value, and the unit of measurement.

[0063] In this embodiment of the application, after determining the second scale line, the second pointer rotation center point, the pointer tip point, the scale value, and the unit of measurement of the pointer instrument, if it is confirmed that the second scale line, the second pointer rotation center point, the pointer tip point, the scale value, and the unit of measurement of the pointer instrument have all been verified, the reading of the pointer instrument can be determined based on the second scale line, the second pointer rotation center point, the pointer tip point, the scale value, and the unit of measurement.

[0064] In one possible implementation, the electronic device can be via, for example... Figure 3 The method shown determines the reading of a pointer instrument. Please refer to [link / reference]. Figure 3 , Figure 3 This is a flowchart illustrating the implementation of a method for determining pointer instrument readings provided in an embodiment of this application. The method for determining pointer instrument readings provided in an embodiment of this application may include steps S201 to S204, as detailed below: In S201, a target coordinate system is constructed based on the rotation center point of the second pointer, and the first coordinates of each second scale line in the target coordinate system, the second coordinates of the pointer tip in the target coordinate system, and the third coordinates of the rotation center point of the second pointer in the target coordinate system are determined.

[0065] In this embodiment of the application, for example, the electronic device can use the rotation center point of the second pointer as the origin and the axis where the second scale line with a scale value of 0 is located as a preset axis (e.g., the x-axis) to construct a target coordinate system. After constructing the target coordinate system, the first coordinates of each second scale line in the target coordinate system, the second coordinates of the pointer tip in the target coordinate system, and the third coordinates of the rotation center point of the second pointer in the target coordinate system are determined. It should be noted that when the rotation center point of the second pointer is used as the origin to construct the target coordinate system, the corresponding third coordinate is (0, 0).

[0066] In S202, the angle between the pointer tip and the preset axis in the target coordinate system is determined based on the second and third coordinates.

[0067] In this embodiment of the application, since the preset axis in the target coordinate system is the axis where the second scale line with a scale value of 0 is located, the angle between the pointer tip and the preset axis in the target coordinate system is also the angle between the pointer tip and the second scale line with a scale value of 0 on the target coordinate axis.

[0068] In S203, the unit scale value corresponding to each unit angle is determined based on the first coordinate and the scale value.

[0069] In this embodiment of the application, the electronic device can determine the first coordinate corresponding to the second scale line corresponding to any two scale values, and determine the included angle between the second scale lines corresponding to the two scale values ​​based on the first coordinate corresponding to the second scale line. It can also determine the difference between the scale values ​​corresponding to the two scale values ​​based on the two scale values, and finally determine the unit scale value corresponding to each unit angle based on the included angle between the second scale lines corresponding to the two scale values ​​and the difference between the corresponding scale values.

[0070] For example, any two scale values ​​can be Figure 2 The scale values ​​5 and 10 shown can be determined by first determining the first coordinates corresponding to the second scale line of each scale value 5 and scale value 10, thereby determining the angle between the second scale lines corresponding to scale values ​​5 and 10 (for example, 60°). Since the difference between the scale values ​​5 and 10 is 5, the unit scale value corresponding to each unit angle can be determined to be 1 / 12.

[0071] In S204, the reading of the pointer instrument is determined based on the included angle, the unit scale value, and the unit of measurement.

[0072] In this embodiment of the application, after determining the angle between the pointer tip and the preset axis in the target coordinate system, and the unit scale value corresponding to each unit angle, the product of the angle between the pointer tip and the preset axis in the target coordinate system and the unit scale value corresponding to each unit angle can be determined as the digital part of the pointer instrument reading, and the unit of measurement can be determined as the unit part of the pointer instrument reading, thereby determining the pointer instrument reading.

[0073] For example, if the angle between the pointer tip and the preset axis in the target coordinate system is 120°, and the unit scale value corresponding to each unit angle is 1 / 12, and the unit of measurement is MPa, then the reading of the pointer instrument can be determined to be 10 MPa.

[0074] As can be seen from the above, in the meter reading method of the pointer meter provided in this application embodiment, an initial image including the pointer meter is first acquired. Then, based on the initial image, the first scale line and the first pointer rotation center point of the pointer meter are determined. Next, based on the first scale line and the first pointer rotation center point, the initial image is normalized to obtain a target image. Then, based on the target image, the second scale line, the second pointer rotation center point, the pointer tip, the scale value, and the unit of measurement of the pointer meter are determined. Finally, based on the second scale line, the second pointer rotation center point, the pointer tip, the scale value, and the unit of measurement, the reading of the pointer meter is determined. Through this method, electronic devices can automatically identify the reading of the pointer meter without manual reading, reducing the safety risks for meter readers.

[0075] Based on the meter reading method for pointer meters provided in the above embodiments, this application further provides a meter reading device for implementing the above method embodiments. Please refer to [link to relevant documentation]. Figure 4 , Figure 4 This is a schematic diagram of the structure of a reading device for a pointer instrument provided in an embodiment of this application. Figure 4 As shown, the meter reading device 40 of the pointer instrument may include: an image acquisition unit 41, a first determination unit 42, an image processing unit 43, a second determination unit 44, and a third determination unit 45. Wherein: The image acquisition unit 41 is used to acquire an initial image including the pointer instrument.

[0076] The first determining unit 42 is used to determine the first scale line and the first pointer rotation center point of the scale line pointer instrument based on the initial image of the scale line.

[0077] The image processing unit 43 is used to normalize the initial image of the scale line according to the first scale line and the rotation center point of the first pointer of the scale line to obtain the target image.

[0078] The second determining unit 44 is used to determine the second scale line, the second pointer rotation center point, the pointer tip point, the scale value, and the unit of measurement of the scale line pointer instrument based on the scale line target image.

[0079] The third determining unit 45 is used to determine the reading of the scale line pointer instrument based on the second scale line, the rotation center point of the second pointer of the scale line, the tip point of the pointer of the scale line, the scale value of the scale line, and the unit of measurement of the scale line.

[0080] Optionally, the image processing unit 43 is specifically used for: Determine the actual shape of the pointer instrument based on the first graduation line; Based on the actual shape of the first scale line, the scale line pointer instrument, and the rotation center point of the first scale line pointer, the initial image of the scale line is subjected to distortion correction processing. Based on the first scale line and the rotation center point of the first pointer of the scale line, polar coordinate transformation is performed on the initial image of the scale line after distortion correction to obtain the target image of the scale line.

[0081] Optionally, the second determining unit 44 is specifically used for: Multimodal features of the target image of the scale line are extracted by a pre-trained feature extraction model, and probability heatmaps corresponding to the second scale line, the rotation center point of the second pointer of the scale line, and the tip point of the pointer of the scale line are generated by a pre-trained pyramid network based on the multimodal features of the scale line. Based on the probability heatmap of the second scale line, the first preliminary position corresponding to the second scale line is determined, and the first correction amount corresponding to the first preliminary position of the scale line is determined through a pre-trained coordinate regression branch model. Based on the first preliminary position of the scale line and the first correction amount of the scale line, the second scale line is determined. Based on the probability heatmap of the scale line corresponding to the rotation center point of the second pointer of the scale line, the second preliminary position corresponding to the rotation center point of the second pointer of the scale line is determined, and the second correction amount corresponding to the second preliminary position of the scale line is determined through the scale line coordinate regression branch model. Based on the second preliminary position of the scale line and the second correction amount of the scale line, the rotation center point of the second pointer of the scale line is determined. Based on the probability heatmap of the scale line corresponding to the tip of the scale line pointer, the third preliminary position corresponding to the tip of the scale line pointer is determined, and the third correction amount corresponding to the third preliminary position of the scale line is determined through the scale line coordinate regression branch model. Based on the third preliminary position of the scale line and the third correction amount of the scale line, the tip of the scale line pointer is determined.

[0082] Optionally, the second determining unit 44 is specifically used for: Determine whether the distance between the rotation center point of the second pointer of the scale line and the tip point of the scale line pointer is within the distance range, and determine whether the distance between the rotation center point of the second pointer of the scale line and the geometric center point of the scale line pointer instrument is less than the preset distance threshold. If both are true, then the verification of the rotation center point of the second pointer of the scale line and the tip point of the scale line pointer is confirmed to be successful.

[0083] Optionally, the second determining unit 44 is specifically used for: Each scale line is defined by taking two adjacent scale lines as a scale line combination, thus obtaining several scale line combinations. For each combination of scale lines, determine the angle difference corresponding to each combination of scale lines to obtain the angle difference corresponding to each combination of scale lines. If the angle difference corresponding to each combination of scale lines is within the range of angle difference, then the verification of the second scale line is confirmed.

[0084] Optionally, the second determining unit 44 is specifically used for: Determine whether the distribution of the scale values ​​of each scale line conforms to the preset scale distribution pattern, and determine whether the scale values ​​of each scale line are all within the preset scale value range. If they are, then the scale values ​​of each scale line are verified to be successful. Determine if the unit of measurement for the scale line is the preset unit of measurement. If so, confirm that the unit of measurement for the scale line has passed verification.

[0085] Optionally, the third determining unit 45 is specifically used for: Based on the rotation center point of the second pointer of the scale line, construct the target coordinate system, and determine the first coordinate of each second scale line in the scale line target coordinate system, the second coordinate of the pointer tip of the scale line in the scale line target coordinate system, and the third coordinate of the rotation center point of the second pointer of the scale line in the scale line target coordinate system. Determine the angle between the tip of the pointer and the preset axis in the target coordinate system of the scale line based on the second and third coordinates of the scale line. Based on the first coordinate of the scale line and the scale value, determine the unit scale value corresponding to each unit angle; The reading of the pointer instrument is determined based on the angle between the scale lines, the unit value of the scale line, and the unit of measurement of the scale line.

[0086] It should be noted that the information interaction and execution process between the above-mentioned units are based on the same concept as the method embodiments of this application. Their specific functions and technical effects can be referred to the method embodiments section, and will not be repeated here.

[0087] Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 5 As shown, the electronic device 5 provided in this embodiment may include: a processor 50, a memory 51, and a computer program 52 stored in the memory 51 and executable on the processor 50, such as a program for a meter reading method for a pointer meter. When the processor 50 executes the computer program 52, it implements the steps described above in the embodiment of the meter reading method for a pointer meter, for example... Figure 1 S101~S105 and shown Figure 3S201~S204 are shown. Alternatively, when processor 50 executes computer program 52, it implements the functions of each module / unit in the above-described embodiment of the pointer instrument reading device, for example... Figure 4 The functions of units 41-45 shown.

[0088] For example, the computer program 52 can be divided into one or more modules / units, one or more of which are stored in the memory 51 and executed by the processor 50 to complete this application. One or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program 52 in the electronic device 5. For example, the computer program 52 can be divided into an image acquisition unit 41, a first determining unit 42, an image processing unit 43, a second determining unit 44, and a third determining unit 45. For the specific functions of each unit, please refer to [link to relevant documentation]. Figure 4 The relevant descriptions in the corresponding embodiments are not repeated here.

[0089] Those skilled in the art will understand that Figure 5 This is merely an example of electronic device 5 and does not constitute a limitation on electronic device 5. It may include more or fewer components than shown, or combine certain components, or use different components.

[0090] The processor 50 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0091] The memory 51 can be an internal storage unit of the electronic device 5, such as a hard disk or RAM. The memory 51 can also be an external storage device of the electronic device 5, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, or flash card. Furthermore, the memory 51 can include both internal and external storage units of the electronic device 5. The memory 51 is used to store computer programs and other programs and data required by the electronic device. The memory 51 can also be used to temporarily store data that has been output or will be output.

[0092] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units is merely an example. In practical applications, the functions described above can be assigned to different functional units as needed, that is, the internal structure of the meter reading device of the pointer instrument can be divided into different functional units to complete all or part of the functions described above. The functional units in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0093] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the steps in the various method embodiments described above.

[0094] This application provides a computer program product that, when run on a terminal device, enables the terminal device to implement the steps described in the various method embodiments above.

[0095] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, refer to the relevant descriptions of other embodiments.

[0096] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0097] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for reading a pointer instrument, characterized in that, include: Acquire an initial image including the pointer meter; Based on the initial image, determine the first scale line and the first pointer rotation center point of the pointer instrument; The initial image is normalized based on the first scale line and the first pointer rotation center point to obtain the target image; Based on the target image, determine the second scale line, the second pointer rotation center point, the pointer tip point, the scale value, and the unit of measurement of the pointer instrument; The reading of the pointer instrument is determined based on the second scale line, the second pointer rotation center point, the pointer tip point, the scale value, and the unit of measurement.

2. The method according to claim 1, characterized in that, The step of normalizing the initial image based on the first scale line and the first pointer rotation center point to obtain the target image includes: The actual shape of the pointer instrument is determined based on the first scale line; Based on the first scale line, the actual shape of the pointer instrument, and the rotation center point of the first pointer, the initial image is subjected to distortion correction processing; Based on the first scale line and the first pointer rotation center point, the initial image after distortion correction is subjected to polar coordinate transformation to obtain the target image.

3. The method according to claim 1, characterized in that, The second scale line, the second pointer rotation center point, and the pointer tip point are determined in the following manner: Multimodal features of the target image are extracted by a pre-trained feature extraction model, and probability heatmaps corresponding to the second scale line, the second pointer rotation center point, and the pointer tip point are generated by a pre-trained pyramid network based on the multimodal features. Based on the probability heatmap corresponding to the second scale line, the first preliminary position corresponding to the second scale line is determined, and the first correction amount corresponding to the first preliminary position is determined by a pre-trained coordinate regression branch model. Based on the first preliminary position and the first correction amount, the second scale line is determined. Based on the probability heatmap corresponding to the second pointer rotation center point, the second preliminary position corresponding to the second pointer rotation center point is determined, and the second correction amount corresponding to the second preliminary position is determined through the coordinate regression branch model. Based on the second preliminary position and the second correction amount, the second pointer rotation center point is determined. Based on the probability heatmap corresponding to the pointer tip, the third preliminary position corresponding to the pointer tip is determined, and the third correction amount corresponding to the third preliminary position is determined through the coordinate regression branch model. Based on the third preliminary position and the third correction amount, the pointer tip is determined.

4. The method according to claim 1, characterized in that, After determining the second scale line, second pointer rotation center point, pointer tip point, scale value, and unit of measurement of the pointer instrument based on the target image, the method further includes: Determine whether the distance between the second pointer rotation center point and the pointer tip point is within the distance range, and determine whether the distance between the second pointer rotation center point and the geometric center point of the pointer instrument is less than a preset distance threshold. If both are true, then the verification of the second pointer rotation center point and the pointer tip point is confirmed to be successful.

5. The method according to claim 1, characterized in that, After determining the second scale line, second pointer rotation center point, pointer tip point, scale value, and unit of measurement of the pointer instrument based on the target image, the method further includes: Two adjacent second scale lines in each of the second scale lines are defined as a scale line combination, resulting in several scale line combinations; For each of the scale line combinations, determine the angle difference corresponding to each scale line combination to obtain the angle difference corresponding to each scale line combination. If the angle difference corresponding to each of the aforementioned scale line combinations is within the range of angle difference, then the second scale line verification is confirmed to be successful.

6. The method according to claim 1, characterized in that, After determining the second scale line, second pointer rotation center point, pointer tip point, scale value, and unit of measurement of the pointer instrument based on the target image, the method further includes: Determine whether the distribution of each scale value conforms to the preset scale distribution pattern, and determine whether each scale value is within the preset scale value range. If they are, then determine that each scale value has passed the verification. Determine whether the unit of measurement is a preset unit of measurement; if so, determine that the unit of measurement has passed verification.

7. The method according to any one of claims 1 to 6, characterized in that, Determining the reading of the pointer instrument based on the second scale line, the second pointer rotation center point, the pointer tip point, the scale value, and the unit of measurement includes: Based on the rotation center point of the second pointer, a target coordinate system is constructed, and the first coordinates of each of the second scale lines in the target coordinate system, the second coordinates of the pointer tip in the target coordinate system, and the third coordinates of the rotation center point of the second pointer in the target coordinate system are determined. Based on the second coordinate and the third coordinate, determine the angle between the pointer tip and a preset axis in the target coordinate system; Based on the first coordinate and the scale value, determine the unit scale value corresponding to each unit of the included angle; The reading of the pointer instrument is determined based on the included angle, the unit scale value, and the unit of measurement.

8. A reading device for a pointer instrument, characterized in that, include: An image acquisition unit is used to acquire an initial image, including the pointer instrument. The first determining unit is used to determine the first scale line and the first pointer rotation center point of the pointer instrument based on the initial image. An image processing unit is configured to normalize the initial image based on the first scale line and the first pointer rotation center point to obtain a target image; The second determining unit is used to determine the second scale line, the second pointer rotation center point, the pointer tip point, the scale value, and the unit of measurement of the pointer instrument based on the target image. The third determining unit is used to determine the reading of the pointer instrument based on the second scale line, the second pointer rotation center point, the pointer tip point, the scale value, and the unit of measurement.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements each step of the reading method of the pointer instrument as described in any one of claims 1 to 7.

10. A computer program product, characterized in that, When the computer program product is executed by a processor, it implements the steps of the reading method of the pointer instrument as described in any one of claims 1 to 7.

Images