A method, device and apparatus for reading an instrument

Through the image acquisition module and recognition algorithm, instrument data is automatically collected and identified, which solves the problem of low manual meter reading efficiency and realizes efficient, accurate and automated reading and reporting of instrument data.

CN113743395BActive Publication Date: 2024-11-26SEAWAY TECHNOLOGY CO LTD
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202111010264.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-08-31
Publication Date
2024-11-26
Estimated Expiration
2041-08-31

AI Technical Summary

Technical Problem

In complex industrial application environments, manual meter reading methods lead to large amounts of labor, untimely data reporting, and it is difficult to achieve efficient and accurate detection of large-scale meters.

Method used

The image data of the instrument is collected through the image acquisition module, the target instrument reading recognition algorithm is used to identify the data results, and the image data and recognition results are sent to the destination address to realize automatic reading and reporting.

Benefits of technology

It improves the efficiency of instrument reading, simplifies the data acquisition and transmission process, reduces the system transmission delay and energy consumption, and achieves efficient and accurate detection of a variety of instruments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113743395B_ABST
    Figure CN113743395B_ABST
Patent Text Reader

Abstract

The present application provides a meter reading method, equipment and device; wherein the method comprises: collecting image data of the dial of the monitored target meter; applying the target meter reading recognition algorithm to recognize the data result indicated by the target meter contained in the image data; and sending the image data and the data result to a destination address. In the embodiment of the present application, by collecting the image data of the instrument panel, the data result indicated by the instrument panel in the image data is automatically recognized, and the recognition result is sent to a specified address, thereby realizing automatic reading and reporting of the meter data, which has a positive effect of being simple and efficient compared with the manual meter reading method in the prior art.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of image recognition and processing, and in particular to an instrument reading method, equipment and device. Background Art

[0002] In some complex industrial application environments, various instruments are often installed to monitor environmental conditions, such as pressure gauges on liquid and gas transport pipelines, and industrial electric meters in factories. If the readings of various instruments are taken by personnel walking along the transport pipelines to read the meters, there will be problems such as high labor intensity, untimely data reporting, and easy errors. For example, in some instrument detection scenarios, in order to detect the measurement accuracy of each instrument, the staff needs to continuously simulate the test environment for testing, and need to repeatedly read and analyze the instrument detection data. Similarly, if manual meter reading and recording are used in this scenario, it is difficult to achieve efficient and accurate detection of a large number of instruments at the same time. Summary of the invention

[0003] In view of this, the present application provides a meter reading recognition method, module and device, so as to at least achieve the purpose of improving the meter reading efficiency of the instrument.

[0004] Specifically, the present application is implemented through the following technical solutions:

[0005] In a first aspect, an embodiment of the present application provides a method for reading an instrument, the method comprising:

[0006] Collect image data of the monitored target instrument;

[0007] Applying a target instrument reading recognition algorithm to recognize the data result indicated by the target instrument contained in the image data;

[0008] The image data and the data result are sent to a destination address.

[0009] In a second aspect, an embodiment of the present application provides a device for identifying readings of a meter, the device comprising:

[0010] Mobile carrier;

[0011] And, an image reading acquisition module for identifying the reading of the instrument using the method described in the first aspect above;

[0012] The image acquisition module is installed on the mobile carrier.

[0013] In a third aspect, an embodiment of the present application provides a device for reading an instrument, the device comprising:

[0014] An image acquisition module is used to acquire image data of the monitored target instrument;

[0015] An identification module, used for applying a target instrument reading identification algorithm to identify a data result indicated by a target instrument contained in the image data;

[0016] The push module is used to send the image data and the data result to a destination address.

[0017] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the image recognition method described in any embodiment of the first aspect above.

[0018] In a fifth aspect, an embodiment of the present application provides a computer device, which includes at least a memory and a processor; the memory is connected to the processor via a communication bus, and is used to store computer instructions executable by the processor; the processor is used to read computer instructions from the memory to implement the steps of the image recognition method described in any embodiment of the first aspect above.

[0019] An instrument reading method, device and apparatus provided in the embodiments of the present application directly collect image data of a monitored target instrument; based on the collected image data, a target instrument reading recognition algorithm is applied to identify the data result indicated by the target instrument contained in the image data; after identifying the data result indicated by the instrument, the collected image data and the read data result are sent to a destination address; in the embodiments of the present application, by collecting image data of the instrument panel, the data result indicated by the instrument panel in the image data is automatically recognized, and the recognition result is sent to a specified address, thereby realizing automatic reading and reporting of instrument data, which has a positive effect of being simple and efficient compared to the manual meter reading method in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a schematic diagram of an application scenario of a method for reading an instrument in an image, shown in an exemplary embodiment of the present application;

[0021] Figure 2 It is a flowchart of a method for reading an instrument shown in an exemplary embodiment of the present application;

[0022] Figure 3 It is a flowchart of another instrument reading method shown in an exemplary embodiment of the present application;

[0023] Figure 4 is a schematic diagram of a single instrument detection method based on SURF feature matching shown in an exemplary embodiment of the present application;

[0024] Figure 5 It is a schematic diagram of a meter reading recognition device shown in an exemplary embodiment of the present application;

[0025] Figure 6 It is a structural schematic diagram of a reading recognition device of an instrument shown in an exemplary embodiment of the present application;

[0026] Figure 7 It is a structural schematic diagram of a computer device shown in an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0027] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0028] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0029] It should be understood that although the terms first, second, third, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0030] Considering the existing technology, in some complex industrial application environments and instrument test scenarios, if manual meter reading is used to read and record various meters, there are problems such as large workload and untimely data reporting. Therefore, this application provides an instrument reading method, equipment and device.

[0031] Figure 1 is a schematic diagram of an application scenario of an instrument reading method shown in an exemplary embodiment of the present application; Figure 1As shown, in this embodiment, the image acquisition module 10 is used to collect image data of the monitored dashboard 20, automatically identify the data results indicated by the dashboard based on the collected image data, and push the collected image data and the obtained data results to a server 30 whose address is a user-specified http address.

[0032] All the meter body recognition and reading recognition algorithms in this application are integrated into the image acquisition module, realizing end-side perception and end-side computing. In addition, the image acquisition module provided in this application is an edge end with the characteristics of being close to the data source, and data processing, prediction and analysis are performed on the image acquisition module to reduce system transmission delay and energy consumption.

[0033] Figure 2 is a flow chart of a meter reading method shown in an exemplary embodiment of the present application; Figure 2 As shown, the method is applied to the above-mentioned image acquisition module, and the method includes the following steps S100-S104:

[0034] S100: The image acquisition module acquires image data of a dial of a monitored target instrument.

[0035] In this embodiment, the image acquisition module takes a picture of the dial of the monitored target instrument. The photographing may be triggered in a variety of ways, such as manually controlling the triggering to take the picture, or automatically triggering the photographing at a scheduled time.

[0036] S102: applying a target instrument reading recognition algorithm to recognize the data result indicated by the target instrument contained in the image data.

[0037] In a possible embodiment of the present application, the above-mentioned image acquisition module is provided with a browser client, and the user can log in to the browser client to perform basic parameter configuration, recognition algorithm management and other operations on the image acquisition module; for example, adding a recognition algorithm, deleting a recognition algorithm, or replacing and upgrading a recognition algorithm, etc. In addition, the image acquisition module has multiple digital table recognition algorithms and multiple pointer table recognition algorithms built in.

[0038] In this embodiment, the user can set the current default instrument detection mode of the image acquisition module on the client, whether to read a specific type of instrument or to be able to read different types of instruments in general.

[0039] Figure 3 is a flow chart of another instrument reading method shown in an exemplary embodiment of the present application; Figure 3 As shown, in this embodiment, before the above step S102, the method further includes the following step S101:

[0040] S101, determining whether the current working mode is in a mode for identifying a meter body of a specified type;

[0041] If yes, then the above step S102 specifically includes the following steps S1021-S1022:

[0042] S1021: Use a meter body detection algorithm adapted to the specified type of meter body to locate a target meter from the image data.

[0043] S1022: Apply an identification algorithm adapted to the meter body of the specified type to identify the data result indicated by the target meter.

[0044] In this embodiment, the above-mentioned meter body detection algorithm is a single target detection algorithm. If the image acquisition module is in a mode of performing data recognition on a specific type of meter, after acquiring the image, the image acquisition module applies the specified meter body detection algorithm to locate the target meter from the image data, and then applies the specified recognition algorithm to identify the data result currently indicated by the target meter.

[0045] If not, the above step S102 specifically includes the following steps S1021′-S1023′:

[0046] S1021′: load a universal meter body type recognition algorithm, and use the universal meter body type recognition algorithm to recognize the meter body type and meter position of the target meter contained in the image data.

[0047] S1022′: Determine an instrument reading recognition algorithm that is compatible with the target instrument according to the meter body type of the target instrument.

[0048] S1023′: after determining the position of the meter, apply the meter reading recognition algorithm to recognize the data result indicated by the target meter.

[0049] The above-mentioned universal meter type recognition algorithm is a multi-target detection algorithm, which is obtained by model training based on the CenterNet network as the infrastructure.

[0050] Furthermore, in an embodiment of the present application, the user can set the working mode of the image acquisition device in advance. When the image acquisition device is reading the dashboard data results, if the user has set the type of meter body to be identified in advance, the image acquisition device will detect the dashboard according to the meter body type specified by the user and the recognition algorithm of the meter body type during the reading process.

[0051] Furthermore, in one embodiment of the present application, before applying the target instrument reading recognition algorithm to recognize the data result indicated by the target instrument contained in the image data, the method further includes the following steps A10-A20:

[0052] Step A10, receiving configuration information sent by the client; the configuration information is generated by the client in response to the user selecting the type of monitored instrument in the browser.

[0053] The user configures the working mode of the image acquisition module on the client side, and the user can select the meter body detection algorithm and meter reading recognition algorithm to be executed by the image acquisition module according to the type of meter to be detected.

[0054] Step A20: setting the current working mode to a mode for identifying a meter body of a specified type based on the configuration information.

[0055] In one embodiment of the present application, in the above step S1021, the target instrument is located from the image data using a meter body detection algorithm adapted to the meter body type, which specifically includes the following step S1021′:

[0056] S1021′: Use a template matching method based on SURF features to locate the meter body, and locate the target meter from the image data.

[0057] In the embodiment of the present application, for single instrument detection, a template matching method based on SURF features is used to locate the meter body. This method is common to all instrument types and can avoid the process of training a detection model separately for each instrument type, greatly reducing the workload of algorithm modeling.

[0058] Reference Figure 4 As shown, in this embodiment, in the process of detecting a single meter body, the template matching method of SURF features is used to locate the meter body. For example, SURF feature points and feature factors are first extracted from the template image of the meter to be inspected as a reference standard. When inspecting a specified meter, the image acquisition module first takes a photo of the target meter, captures an image, extracts SURF feature points and feature factors from the image, performs feature matching on the SURF feature points and feature factors and the SURF feature points and feature factors in the reference standard, and calculates the transformation relationship between the feature matching points, and finally obtains the position of the target meter (the meter to be inspected) in the image.

[0059] In one embodiment of the present application, in the above-mentioned meter reading process, if the target meter is an LCD digital meter, the data result indicated by the target meter is identified, including the following steps B10-B60:

[0060] Step B10: input the image data into the pre-trained Yolov5m network structure to obtain the position coordinates of each character on the dashboard in the image.

[0061] Step B20, obtaining the maximum height of a single character by calculation and comparison, as the maximum height interval threshold max_height of a single line of digits.

[0062] Step B30, obtaining the maximum coordinate value ymax and the minimum coordinate value ymin of all characters in the Y direction by calculation and comparison.

[0063] Step B40, obtain the number of character rows n = int((ymax-ymin) / / max_height).

[0064] Step B50, divide the Y-axis direction into multiple rows of grids with an interval of (ymax-ymin) / n.

[0065] Step B60, determine which characters in each row of the grid have their center points falling in this area, and sort them from small to large according to the horizontal coordinate x_center of the center points to obtain the complete reading of the characters in the last row.

[0066] The Yolov5m network structure is obtained by training a model for multi-target detection using characters {"0", "1", "2", "3", "4", "5", "6", "7", "8", "9", "."} as 11 categories, and its network input size is 640*640.

[0067] Figure 5 is a schematic diagram of a meter reading recognition device shown in an exemplary embodiment of the present application; Figure 5 As shown, an instrument reading recognition device 400 provided in an embodiment of the present application includes:

[0068] An image acquisition module 10 for identifying the reading of the instrument using the above method;

[0069] and a mobile carrier 40;

[0070] The image acquisition module 10 is installed on a mobile carrier 40 .

[0071] In this embodiment, the above-mentioned mobile carrier can be an inspection vehicle, and then the image acquisition module can be fixed on the inspection vehicle to read instruments along transportation pipelines, power lines, etc.; or, in another possible embodiment of the present application, the above-mentioned mobile carrier can also be a drone, and the image acquisition module can be fixed on the drone, which can also realize the reading of instruments installed at specific locations or on high-altitude high-voltage lines, power towers, etc.

[0072] In an optional embodiment, in order to solve the problem of poor image acquisition quality under dark light or no light conditions, the camera of the image acquisition module is integrated with an infrared fill light module.

[0073] Figure 6 is a schematic diagram of a reading recognition device for an instrument shown in an exemplary embodiment of the present application; Figure 6 As shown, the device comprises:

[0074] The acquisition module 501 is used to acquire image data of the monitored target instrument;

[0075] An identification module 502 is used to apply a target instrument reading identification algorithm to identify the data result indicated by the target instrument contained in the image data;

[0076] The sending module 503 is used to send the image data and the data result to a destination address.

[0077] Optionally, the device further includes:

[0078] A judgment module, used to judge whether the current working mode is in a mode for identifying a meter body of a specified type;

[0079] The identification module 502 is specifically used for:

[0080] Loading a meter body detection algorithm corresponding to the specified type of meter body, and locating the target meter from the image data;

[0081] After the target meter is located, a recognition algorithm corresponding to the meter body category is applied to identify the data result indicated by the target meter.

[0082] Optionally, the identification module 502 is specifically configured to:

[0083] Loading a universal meter body type recognition algorithm, and applying the universal meter body type recognition algorithm to recognize the meter body type and meter position of the target meter contained in the image data;

[0084] Determining an instrument reading recognition algorithm adapted to the target instrument according to the meter body type of the target instrument;

[0085] After the position of the meter is determined, the meter reading recognition algorithm is applied to identify the data result indicated by the target meter.

[0086] Optionally, the above device further includes:

[0087] A receiving module, used to receive configuration information sent by a client; the configuration information is generated by the client in response to a user selecting a type of monitored instrument;

[0088] The setting module is used to set the current working mode to a mode for identifying a meter body of a specified type based on the configuration information.

[0089] Optionally, the identification module is further used to:

[0090] The single meter body detection algorithm of the specified type of meter body is loaded, and the meter body detection is performed by applying the template matching method based on the SURF feature, so as to locate the target meter from the image data.

[0091] Optionally, the identification module is further used to:

[0092] Input the image data into the pre-trained Yolov5m network structure to obtain the position coordinates of each character on the dashboard in the image;

[0093] The maximum height of a single character is obtained by calculation and comparison, which is used as the maximum height interval threshold max_height of a single line of numbers;

[0094] Obtain the maximum Y coordinate value ymax and the minimum Y coordinate value ymin of all characters by calculation and comparison;

[0095] Get the number of character lines n = int ((ymax-ymin) / / max_height);

[0096] Divide the Y-axis direction into multiple rows of grids according to the interval (ymax-ymin) / n;

[0097] Determine which characters in each row of the grid have their center points in this area, and sort them from small to large according to the horizontal coordinate x_center of the center points to get the complete reading of the characters in the last row;

[0098] The Yolov5m network structure is obtained by training a model for multi-target detection using characters {"0", "1", "2", "3", "4", "5", "6", "7", "8", "9", "."} as 11 categories, and its network input size is 640*640.

[0099] Optionally, the above-mentioned general body type recognition algorithm is a multi-target detection algorithm, which is obtained by model training based on the CenterNet network as the infrastructure.

[0100] In one embodiment of the present application, a computer-readable storage medium is further provided, on which a computer program is stored. When the program is executed by a processor, the steps of the image recognition method described in any of the above embodiments are implemented.

[0101] Figure 6Schematic diagram of a computer device shown in an embodiment of the present application. Figure 6 As shown, the computer device 600 includes at least a memory 602 and a processor 601; the memory 602 is connected to the processor 601 via a communication bus 603, and is used to store computer instructions executable by the processor 601; the processor 601 is used to read computer instructions from the memory 602 to implement the steps of the instrument reading method described in any of the above embodiments.

[0102] The implementation process of the functions and effects of each unit in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.

[0103] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application scheme. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0104] The embodiments of the subject matter and functional operations described in this specification may be implemented in the following: digital electronic circuits, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or a combination of one or more of them. The embodiments of the subject matter described in this specification may be implemented as one or more computer programs, i.e., one or more modules in computer program instructions encoded on a tangible non-temporary program carrier to be executed by a data processing device or to control the operation of the data processing device. Alternatively or additionally, the program instructions may be encoded on an artificially generated propagation signal, such as a machine-generated electrical, optical or electromagnetic signal, which is generated to encode information and transmit it to a suitable receiver device for execution by a data processing device. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of one or more of them.

[0105] The processes and logic flows described in this specification can be performed by one or more programmable computers executing one or more computer programs to perform corresponding functions by operating on input data and generating output. The processes and logic flows can also be performed by special purpose logic circuits, such as FPGAs (field programmable gate arrays) or ASICs (application-specific integrated circuits), and the apparatus can also be implemented as special purpose logic circuits.

[0106] Computers suitable for executing computer programs include, for example, general and / or special purpose microprocessors, or any other type of central processing unit. Typically, the central processing unit will receive instructions and data from a read-only memory and / or a random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Typically, the computer will also include one or more mass storage devices for storing data, such as magnetic disks, magneto-optical disks, or optical disks, or the computer will be operably coupled to such a mass storage device to receive data from it or to transmit data to it, or both. However, a computer does not necessarily have to have such a device.

[0107] Computer readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media and memory devices, including, for example, semiconductor memory devices (e.g., EPROM, EEPROM and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD ROM and DVD-ROM disks. The processor and memory may be supplemented by, or incorporated in, special purpose logic circuitry.

[0108] Although this specification includes many specific implementation details, these should not be interpreted as limiting the scope of any invention or the scope of protection claimed, but are mainly used to describe the features of the specific embodiments of specific inventions. Certain features described in multiple embodiments in this specification may also be implemented in combination in a single embodiment. On the other hand, the various features described in a single embodiment may also be implemented separately in multiple embodiments or in any suitable sub-combination. In addition, although features may work in certain combinations as described above and even initially claim protection, one or more features from the claimed combination may be removed from the combination in some cases, and the claimed combination may point to a sub-combination or a variation of a sub-combination.

[0109] Similarly, although operations are depicted in a particular order in the accompanying drawings, this should not be understood as requiring that these operations be performed in the particular order shown or performed sequentially, or requiring that all illustrated operations be performed to achieve the desired results. In some cases, multitasking and parallel processing may be advantageous. In addition, the separation of various system modules and components in the above-described embodiments should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product, or packaged into multiple software products.

[0110] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the particular order or sequential order shown to achieve the desired results. In some implementations, multitasking and parallel processing may be advantageous.

[0111] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for reading an instrument. It is characterized in that The method comprises: Collecting image data of the dial of the monitored target instrument; Determine whether the current working mode is in a mode for identifying a meter body of a specified type; If yes, applying a target meter reading recognition algorithm to recognize the data result indicated by the target meter contained in the image data includes: loading a meter body detection algorithm corresponding to the specified type of meter body to locate the target meter from the image data; after locating the target meter, applying a recognition algorithm corresponding to the meter body category to recognize the data result indicated by the target meter; If not, then applying the target meter reading recognition algorithm to recognize the data result indicated by the target meter contained in the image data includes: loading a universal meter body type recognition algorithm, and applying the universal meter body type recognition algorithm to recognize the meter body type and meter position of the target meter contained in the image data; The image data and the data result are sent to a destination address.

2. The method according to claim 1, It is characterized in that After loading a universal meter body type recognition algorithm and applying the universal meter body type recognition algorithm to recognize the meter body type and meter position of the target meter contained in the image data, the method further includes: Determining an instrument reading recognition algorithm adapted to the target instrument according to the meter body type of the target instrument; After the position of the meter is determined, the meter reading recognition algorithm is applied to identify the data result indicated by the target meter.

3. The method according to claim 1, It is characterized in that Before applying the target instrument reading recognition algorithm to recognize the data result indicated by the target instrument contained in the image data, the method further includes: Receiving configuration information sent by a client; the configuration information is generated by the client in response to a user selecting a type of monitored instrument; The current working mode is set to a mode for identifying a meter body of a specified type based on the configuration information.

4. The method according to claim 1, It is characterized in that The step of loading a meter body detection algorithm corresponding to the meter body of the specified type and locating the target meter from the image data includes: The single meter body detection algorithm of the specified type of meter body is loaded, and the meter body detection is performed by applying the template matching method based on the SURF feature, so as to locate the target meter from the image data.

5. The method according to claim 1 or 2, It is characterized in that If the target instrument is an LCD digital meter, the result of identifying the data indicated by the target instrument includes: Input the image data into the pre-trained Yolov5m network structure to obtain the position coordinates of each character on the dashboard in the image; The maximum height of a single character is obtained by calculation and comparison, which is used as the maximum height interval threshold max_height of a single line of numbers; Obtain the maximum Y coordinate value ymax and the minimum Y coordinate value ymin of all characters by calculation and comparison; Get the number of character lines n = int((ymax - ymin) / / max_height); Divide the Y-axis direction into multiple rows of grids according to the interval of (ymax-ymin) / n; Determine which characters in each row of the grid have their center points in this area, and sort them from small to large according to the horizontal coordinate x_center of the center points to get the complete reading of the characters in the last row; The Yolov5m network structure is obtained by training a model for multi-target detection using the characters {"0"," 1","2","3","4","5","6","7","8","9","."} as 11 categories, and its network input size is: 640*640.

6. The method according to claim 2, It is characterized in that The general body type recognition algorithm is a multi-target detection algorithm, which is obtained by model training based on the CenterNet network.

7. A device for identifying the readings of an instrument, It is characterized in that The device comprises: An image acquisition module for identifying the reading of an instrument using the method described in any one of claims 1 to 6 above; and, mobile carriers; Wherein, the image acquisition module is installed on the mobile carrier.

8. A device for identifying the reading of an instrument, It is characterized in that The device comprises: An acquisition module is used to acquire image data of the monitored target instrument; Determine whether the current working mode is in a mode for identifying a meter body of a specified type; An identification module, used for applying a target instrument reading identification algorithm to identify a data result indicated by a target instrument contained in the image data; If yes, applying a target meter reading recognition algorithm to recognize the data result indicated by the target meter contained in the image data includes: loading a meter body detection algorithm corresponding to the specified type of meter body to locate the target meter from the image data; after locating the target meter, applying a recognition algorithm corresponding to the meter body category to recognize the data result indicated by the target meter; If not, then applying the target meter reading recognition algorithm to recognize the data result indicated by the target meter contained in the image data includes: loading a universal meter body type recognition algorithm, and applying the universal meter body type recognition algorithm to recognize the meter body type and meter position of the target meter contained in the image data; The sending module is used to send the image data and the data result to a destination address.

9. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the program is executed by a processor, the steps of the image recognition method described in any one of claims 1 to 6 are implemented.

Citation Information

Patent Citations

  • Digital instrument reading identification method and device, equipment and medium

    CN110717462A

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

    CN112115893A

  • Pointer type instrument reading identification method and device, computer equipment and storage medium

    CN112115895A

  • Method, device, and equipment for object detection

    WO2021027710A1