Camera-based direct-reading smart gas meter based on edge computing artificial intelligence recognition

Abstract

The present invention belongs to the technical field of gas meters, and particularly relates to a camera-based direct-reading smart gas meter based on edge calculation artificial intelligence recognition. The camera-based direct-reading smart gas meter comprises a main control unit (MCU), an optical photographing unit, a safety logic function unit, a power supply and power supply detection unit, an hour hand battery, an hour hand chip, a valve control unit, a human-machine interaction unit, a communication unit, and connection relationships thereof. In the present invention, a picture is directly recognized as digits by means of edge computing artificial intelligence recognition at a gas meter device end, and the digits are transmitted to a server, such that the volume of transmitted data is one ten-thousandth of the original data volume; gray-scale pictures are used for training, such that a program file formed after the training is smaller; edge sharpening processing is performed on the picture, such that the impact of light spots can be effectively removed; and a camera performs capturing in a 90-degree direction of the side face of a counter, such that the light path is simple, the front view is not affected, the requirement for manufacturing precision is low, and the cost is low.

Description

A camera-based direct-reading smart gas meter based on edge computing and artificial intelligence recognition Technical Field

[0001] The present invention relates to the technical field of gas meters, and in particular to a camera-based direct-reading smart gas meter based on edge computing and artificial intelligence recognition. Background Art

[0002] The smart gas meter is composed of a control circuit with a single-chip microprocessor as the core, an LCD display, a sensor device, a control valve, a base meter, a gas alarm, etc. It has an automatic charging function, one meter and one card for each household, and implements network management.

[0003] Current direct-reading smart gas meters generally use AI to identify the image of the character wheel. However, the image of the character wheel needs to be sent to the main server for the number to be recognized, which wastes a lot of bandwidth and traffic. This method also requires high bandwidth and processing speed of the server. Directly using color images for training results in large program files after training, which takes up a lot of program space. The lack of edge sharpening processing makes it easy to be affected by light interference. Shooting directly from above the counter has a complex optical path and requires a reflective system, which requires high manufacturing precision and high cost.

[0004] Summary of the Invention

[0005] The purpose of the present invention is to solve the technical problems existing in the background technology. To this end, a camera direct-reading smart gas meter based on edge computing artificial intelligence recognition is provided.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0007] A camera-based direct-reading smart gas meter based on edge computing artificial intelligence recognition includes an MCU main control unit and an optical camera unit, the MCU main control unit and the optical camera unit are connected, and the optical camera unit includes a camera and a fill light;

[0008] The process of identifying the character wheel on the gas meter counter includes:

[0009] Use a camera to take a picture of the character wheel on the counter, and use a fill light to shoot the character wheel;

[0010] Perform edge sharpening and grayscale processing on the character wheel image;

[0011] Use grayscale word wheel images for training;

[0012] The MCU main control unit recognizes the digital information corresponding to the character wheel image and transmits the digital information to the main server.

[0013] The following is a technical solution further defined by the present invention: the camera shoots from the side direction facing the middle position of the character wheel on the counter, the shooting angle of the camera is between 45°-75°, and the angle between the fill light and the character wheel is between 20°-45°.

[0014] The following is a technical solution further limited by the present invention, which also includes a security logic function unit, which is connected to the MCU main control unit and is used for analyzing and processing security events.

[0015] The following is a technical solution further limited by the present invention, which also includes a power supply and power supply detection unit, a clock hand battery, and a clock hand chip. The power supply and power supply detection unit are connected to the MCU main control unit, the clock hand battery is connected to the clock hand chip, and the clock hand chip is connected to the MCU main control unit.

[0016] The following is a technical solution further defined by the present invention, which also includes a valve control unit, wherein the valve control unit includes a valve drive circuit and a motor valve, the valve drive circuit is connected to the motor valve, and the valve drive circuit is connected to the MCU main control unit.

[0017] The following is a technical solution further limited by the present invention, which also includes a human-computer interaction unit, which includes a display screen, a speaker and a button. The display screen, the speaker and the button are all connected to the MCU main control unit, and the human-computer interaction unit is connected to the user end.

[0018] The following is a technical solution further defined by the present invention, which also includes a communication unit, wherein the communication unit is connected to the MCU main control unit, and the MCU main control unit establishes a communication connection with the main server through the communication unit, and a communication connection is established between the main server and the user end.

[0019] Compared with the prior art, the present invention has the following technical effects:

[0020] 1. This invention uses edge computing artificial intelligence recognition on the gas meter device to directly recognize images into numbers and transmit the numbers to the server. The amount of data transmitted is one ten-thousandth of the original amount.

[0021] 2. Use grayscale images for training, and the resulting program file is smaller;

[0022] 3. Sharpening the edges of the image can effectively remove the effect of light spots;

[0023] 4. The camera shoots at 90° from the side of the counter. The optical path is simple and does not affect the front view. The manufacturing precision requirement is low and the cost is low.

[0024] The present invention will be further described below with reference to the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0026] FIG1 is a block diagram of the present invention;

[0027] FIG2 is a schematic diagram showing the positional relationship between the camera and the character wheel of the present invention;

[0028] FIG3 is a schematic diagram showing the positional relationship between the camera, the character wheel, and the fill light of the present invention;

[0029] FIG4 is a schematic diagram of a grayscale character wheel without edge sharpening;

[0030] FIG5 is a schematic diagram of a grayscale character wheel for edge sharpening according to the present invention. DETAILED DESCRIPTION

[0031] To make the above-mentioned objects, features, and advantages of the present invention more readily apparent, specific embodiments of the present invention are described in detail below with reference to the accompanying drawings. The following description sets forth numerous specific details to facilitate a full understanding of the present invention. However, the present invention can be implemented in many other ways than those described herein, and those skilled in the art may make similar modifications without departing from the scope of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0032] In the embodiments of the present invention, unless otherwise specified or limited, the terms "connected" and "communication connection" should be understood in a broad sense. For example, they can refer to electrical connection, direct connection, indirect connection through an intermediate medium, internal communication between two components, or interaction between two components. Those skilled in the art will understand the specific meanings of the above terms in the embodiments of the present invention based on specific circumstances.

[0033] As shown in Figure 1, a camera-based direct-reading smart gas meter based on edge computing artificial intelligence recognition is provided, including an MCU main control unit, an optical camera unit, a safety logic function unit, a power supply and power detection unit, a clock battery, a clock chip, a valve control unit, a human-computer interaction unit and a communication unit.

[0034] The MCU main control unit is connected to the optical camera unit, which includes a camera and a fill light.

[0035] The process of identifying the character wheel on the gas meter counter includes:

[0036] A camera is used to capture an image of the character wheel on the counter, and a fill light is used to fill in the light for photographing the character wheel. Specifically, the camera is used to photograph from the side facing the middle of the character wheel on the counter (i.e., the camera is used to photograph from a 90° angle from the side of the counter). For example, if the counter has seven character wheels, the center line of the camera needs to face the middle of the fourth character wheel. In this way, the shooting light path is simple, does not affect the front view, requires low manufacturing precision, and is low in cost. The shooting angle of the camera is between 45° and 75°, preferably 60°, that is, the character wheel is within the shooting angle of the camera. The angle between the fill light and the character wheel is between 20° and 45°, preferably 30°, as shown in Figures 2 and 3.

[0037] Perform edge sharpening and grayscale processing on the wheel image. Edge sharpening can effectively remove the effect of light spots. As shown in Figures 4 and 5, the changes before and after edge sharpening can be clearly compared.

[0038] Use grayscale word wheel images for training, and the resulting program file is smaller;

[0039] The MCU main control unit recognizes the digital information corresponding to the character wheel image and transmits the digital information to the main server.

[0040] Therefore, edge computing artificial intelligence recognition is used on the gas meter device to directly identify the image into numbers, and the numbers are transmitted to the server. The amount of data transmitted is one ten-thousandth of the original amount.

[0041] The security logic function unit is connected to the MCU main control unit and is used to analyze and process security events, including gas meter open circuits, short circuits, valve failures, and so on. The power supply and power detection unit is connected to the MCU main control unit, the clock battery is connected to the clock chip, and the clock chip is connected to the MCU main control unit. The valve control unit includes a valve drive circuit and a motor valve, which is connected to the motor valve, and the valve drive circuit is connected to the MCU main control unit. The human-computer interaction unit includes a display, speaker, and buttons, all of which are connected to the MCU main control unit. The human-computer interaction unit is connected to the user end. The communication unit is connected to the MCU main control unit, and the MCU main control unit establishes a communication connection with the main server through the communication unit, and the main server and the user end communicate with each other.

[0042] In summary, the gas meter realizes event analysis and processing, data storage, and data transmission through the MCU main control unit and the safety logic function unit. It realizes interactive functions such as data presentation, alarm reminders, information query, and on-site operation through human-computer interaction units such as display screens, speakers (buzzers), and buttons. It realizes data transmission, clock calibration, and remote control with the main server (MIS management information system / data management platform / mobile phone APP) through channels. The gas meter with a valve control unit realizes valve switch control through the valve drive circuit.

[0043] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Any person skilled in the art can utilize the methods and technical contents disclosed above to make many possible variations and modifications to the technical solutions of the present invention without departing from the scope of the technical solutions of the present invention, or modify them into equivalent embodiments with equivalent variations. Therefore, any equivalent variations made in accordance with the shape, structure, and principles of the present invention without departing from the content of the technical solutions of the present invention should be included in the scope of protection of the present invention.

Claims

1. A camera-based direct-reading smart gas meter based on edge computing artificial intelligence recognition, characterized in that: It includes an MCU main control unit and an optical camera unit, wherein the MCU main control unit and the optical camera unit are connected, and the optical camera unit includes a camera and a fill light; The process of identifying the character wheel on the gas meter counter includes: Use the camera to take a picture of the character wheel on the counter, and use a fill light to fill in the light and take a picture of the character wheel; Perform edge sharpening and grayscale processing on the character wheel image; Use grayscale word wheel images for training; The MCU main control unit recognizes the digital information corresponding to the character wheel image and transmits the digital information to the main server.

2. According to claim 1, a camera direct reading smart gas meter based on edge computing artificial intelligence recognition is characterized in that: The camera shoots from the side direction facing the middle position of the character wheel on the counter. The shooting angle of the camera is between 45°-75°, and the angle between the fill light and the character wheel is between 20°-45°.

3. According to claim 1, a camera-based direct-reading smart gas meter based on edge computing artificial intelligence recognition is characterized in that: It also includes a safety logic function unit, which is connected to the MCU main control unit and is used for analyzing and processing security events.

4. The camera-based direct-reading smart gas meter based on edge computing artificial intelligence recognition according to claim 1 is characterized in that: It also includes a power supply and power supply detection unit, a clock hand battery, and a clock hand chip. The power supply and power supply detection unit are connected to the MCU main control unit, the clock hand battery is connected to the clock hand chip, and the clock hand chip is connected to the MCU main control unit.

5. The camera-based direct-reading smart gas meter based on edge computing artificial intelligence recognition according to claim 1 is characterized in that: It also includes a valve control unit, which includes a valve drive circuit and a motor valve. The valve drive circuit is connected to the motor valve, and the valve drive circuit is connected to the MCU main control unit.

6. The camera-based direct-reading smart gas meter based on edge computing artificial intelligence recognition according to claim 1 is characterized in that: It also includes a human-computer interaction unit, which includes a display screen, a speaker and buttons. The display screen, the speaker and the buttons are all connected to the MCU main control unit, and the human-computer interaction unit is connected to the user end.

7. The camera-based direct-reading smart gas meter based on edge computing artificial intelligence recognition according to claim 1 is characterized in that: It also includes a communication unit, which is connected to the MCU main control unit. The MCU main control unit establishes a communication connection with the main server through the communication unit, and the main server and the user end are communicated with each other.

Images