Gas concentration recognition system and method, robot, electronic equipment and readable storage medium

Abstract

The invention relates to the technical field of image recognition, and discloses a gas concentration recognition system and method, a robot, electronic equipment and a readable storage medium, and the system comprises an image ROI extraction unit which is used for intercepting a digital display area from a scene image; an image correction unit for providing a standardized image; the illumination normalization and binarization unit is used for separating a digital region from a background region through adaptive threshold processing and morphological operation to generate a binary image; and the nixie tube segmentation and identification unit is used for outputting a gas concentration value after digital decoding. In the scheme, the digital display area of the gas monitoring instrument is accurately intercepted through the image ROI extraction unit, and irrelevant background interference is reduced; the problem of image inclination caused by shooting angle deviation is solved through the image correction unit; efficient separation of a digital region and a background is realized through an illumination normalization and binarization unit; features are extracted through a nixie tube segmentation and identification unit and required sensor readings are generated.

Description

Technical Field

[0001] This invention relates to the field of image recognition technology, and in particular to a gas concentration recognition system, method, robot, electronic device, and readable storage medium. Background Technology

[0002] Grain warehouses are enclosed spaces and are fumigated with phosphine gas to kill pests. Traditional grain warehouse inspections rely on staff entering the warehouse to take photos and obtain sensor readings. However, complex lighting conditions, tilted instrument installation angles, and image noise interference within grain warehouses affect the accuracy of sensor readings. Summary of the Invention

[0003] In view of this, the present invention provides a gas concentration identification system, method, robot, electronic device, and readable storage medium that obtains accurate and clear readings by correcting the obtained sensor photographs.

[0004] To achieve the above objectives, the present invention provides the following technical solution:

[0005] A gas concentration identification system, comprising:

[0006] The image ROI extraction unit is used to extract the digital display area from the scene image;

[0007] The image correction unit is used to perform perspective transformation on the digital display area and output a regular front view to provide a standardized image;

[0008] The illumination normalization and binarization unit is used to perform illumination equalization processing on the standardized image and separate the digital region from the background region through adaptive thresholding and morphological operations to generate a binary image.

[0009] The digital tube segmentation and recognition unit is used to segment the binary image into individual digital tube regions according to a certain ratio, and output the gas concentration value after digital decoding based on seven-segment code feature matching.

[0010] Preferably, the image ROI extraction unit is configured to extract the ROI region of the instrument in a specified coordinate manner and adjust the scaling ratio according to the original size of the ROI region.

[0011] Preferably, the image correction unit is configured to calibrate and arrange the four corner points of the digital display area in a fixed order, calculate the perspective transformation matrix based on the sorted corner point coordinates and the preset output size, and correct the digital display area into a regular front view through perspective transformation.

[0012] Preferably, the digital tube segmentation and recognition unit is configured to add left and right black border compensation to the binary image, divide it into n digital tube regions according to the n equal division ratio, extract the seven-segment code features of each digital tube region, match and generate the corresponding numbers, and concatenate them to convert them into the gas concentration value.

[0013] The present invention also provides a robot, including the aforementioned gas concentration recognition system, and further comprising:

[0014] A mobile vehicle, which is self-powered, is used to provide a load-bearing foundation;

[0015] The telescopic pole is fixed to the traveling vehicle in a vertical position and has an adjustment end for moving in the vertical direction;

[0016] The joint is rotated and fixed to the adjustment end, and has a first posture and a second posture with different elevation angles;

[0017] A visible light camera is fixed to the rotating joint and moves synchronously with the rotating joint. The visible light camera is used to acquire real-world images of the front of the vehicle.

[0018] An infrared camera is fixed to the rotating joint and moves synchronously with the rotating joint. The infrared camera is used to acquire infrared images of the front of the vehicle.

[0019] A gas concentration sensor is fixed to the vehicle and used to acquire information about the gas concentration in the environment.

[0020] A forward-facing camera sensor is fixed to the front of the vehicle and is used to acquire real-world video of the front of the vehicle.

[0021] The communication device is fixed to the vehicle and is connected to the visible light camera, the infrared camera, the gas concentration sensor, and the forward-looking camera sensor.

[0022] Preferably, the traveling vehicle is equipped with an external bracket, and there are two external brackets located on both sides of the telescopic rod.

[0023] Preferably, the roof of the vehicle has an inwardly extending gas channel, and the gas concentration sensor is fixed inside the vehicle and exposed to the outside through the gas channel.

[0024] This invention also discloses a gas concentration identification method, comprising:

[0025] Collect images of grain warehouse scenes

[0026] Based on preset coordinates, the digital display area of ​​the instrument is captured and the scale is adaptively adjusted.

[0027] Based on preset corner coordinates, the digital display area is corrected into a regular front view through four-point perspective transformation;

[0028] Perform illumination equalization processing on the front view;

[0029] Binary images are generated using adaptive thresholding and morphological operations;

[0030] Extract the seven-segment code features from the binary image to generate the actual gas concentration value.

[0031] The present invention also provides an electronic device, comprising:

[0032] Memory, used to store computer programs;

[0033] A processor is used to implement the steps of the aforementioned gas concentration recognition method when executing the computer program.

[0034] The present invention also provides a readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the aforementioned gas concentration identification method.

[0035] As can be seen from the above technical solutions, the gas concentration recognition system provided by the present invention accurately extracts the digital display area of ​​the gas monitoring instrument through the image ROI extraction unit, reducing irrelevant background interference; solves the image tilt problem caused by shooting angle deviation through the image correction unit; achieves efficient separation of digital area and background through illumination normalization and binarization unit; and extracts features and generates the required sensor readings through digital tube segmentation and recognition unit. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, 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 the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 This is a structural block diagram illustrating a gas concentration identification system according to one embodiment;

[0038] Figure 2 This is a schematic diagram illustrating the structure of a robot according to one embodiment;

[0039] Figure 3 This is a flowchart illustrating a gas concentration identification method according to one embodiment;

[0040] Figure 4This is a structural block diagram of an electronic device according to one embodiment;

[0041] Figure 5 This is a schematic diagram of the specific structure of an electronic device according to one embodiment.

[0042] Figure label:

[0043] 1. Image ROI extraction unit; 2. Image correction unit; 3. Illumination normalization and binarization unit; 4. Digital tube segmentation and recognition unit; 5. Walking vehicle; 51. Platform; 52. Tracked walking mechanism; 53. Telescopic rod; 54. Adjustment end; 55. Rotary joint; 56. Gas channel; 57. Communication device; 58. External bracket; 6. Visible light camera; 61. Infrared camera; 62. Gas concentration sensor; 63. Forward-looking camera sensor; 7. Memory; 71. Computer program; 72. Data; 73. Operating system; 8. Processor; 9. Electronic equipment; 91. Power supply; 92. Wired or wireless network interface; 93. Input / output interface. Detailed Implementation

[0044] This invention discloses a gas concentration identification system, method, robot, electronic device, and readable storage medium, which can correct the obtained sensor photos to obtain accurate and clear readings.

[0045] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0046] Exemplary embodiments of this disclosure provide a gas concentration identification system, method, robot, electronic device, and readable storage medium, such as Figure 1 As shown, Figure 1 This is a structural block diagram illustrating a gas concentration identification system according to one embodiment; Figure 2 This is a schematic diagram illustrating the structure of a robot according to one embodiment; Figure 3 This is a flowchart illustrating a gas concentration identification method according to one embodiment; Figure 4 This is a structural block diagram of an electronic device according to one embodiment; Figure 5 This is a schematic diagram illustrating the specific structure of an electronic device according to one embodiment. The following is in conjunction with... Figures 1 to 5 To explain.

[0047] The specific embodiments described below are intended to help those skilled in the art understand this embodiment, but this embodiment is not limited to the specific embodiments described below.

[0048] This disclosure provides a gas concentration identification system according to an embodiment, referring to... Figure 1 The gas concentration identification system includes:

[0049] Image ROI extraction unit 1 is used to extract the digital display area from the scene image;

[0050] Image correction unit 2 is used to perform perspective transformation on the digital display area and output a regular front view to provide a standardized image;

[0051] The illumination normalization and binarization unit 3 is used to perform illumination equalization processing on the standardized image and separate the digital region from the background region through adaptive thresholding and morphological operations to generate a binary image.

[0052] The digital tube segmentation and recognition unit 4 is used to segment the binary image into individual digital tube regions according to the proportion, and output the gas concentration value after digital decoding based on seven-segment code feature matching.

[0053] For example, refer to Figure 1 Image ROI extraction unit 1 is configured to extract the ROI region of the instrument using specified coordinates. For example, considering the fixed position of the instrument in the captured image, the ROI region of the instrument is extracted using a coordinate specification method, and a boundary check mechanism is used to avoid image cropping errors caused by coordinate out-of-bounds errors.

[0054] Image ROI extraction unit 1 is also configured to adjust the scaling ratio according to the original size of the ROI region. For example, the scaling ratio is adaptively adjusted according to the original size of the ROI region: when the maximum side length of the ROI is less than 600 pixels, a 2x scale magnification is used based on a bicubic interpolation algorithm to ensure that the details of the digital display area are clear and to provide sufficient resolution support for subsequent processing.

[0055] Image correction unit 2 is configured to calibrate and arrange the four corner points of the digital display area in a fixed order. For example, the coordinates of the four corner points of the instrument's digital display area within the ROI area are pre-calibrated, and the disordered corner points are arranged in a fixed order of "top left - top right - bottom right - bottom left" using a corner point sorting algorithm to ensure the consistency of the transformation reference. In other embodiments, the arrangement order can also be other methods, as long as the order is fixed.

[0056] Image correction unit 2 calculates the perspective transformation matrix based on the sorted corner coordinates and the preset output size, and corrects the digital display area into a regular front view through perspective transformation, thereby eliminating the influence of angle deviation on subsequent unit processing. The corrected image size is standardized to ensure the uniformity of the digital display area shape under different shooting scenarios.

[0057] The illumination normalization and binarization unit 3 applies color space conversion methods (RGB space and LAB space) and contrast-limited adaptive histogram equalization algorithm (CLAHE) to the standardized image to equalize the brightness channel of the standardized image, thereby suppressing interference such as uneven illumination and reflection in the grain warehouse and improving image contrast.

[0058] The digital tube segmentation and recognition unit 4 is configured to add left and right black border compensation to the binary image, and divide it into n digital tube regions according to an n-equal ratio. After extracting the seven-segment code features of each digital tube region, it matches and generates the corresponding numbers, which are then concatenated and converted into gas concentration values. For example, existing 3-digit digital tubes have the problem of uneven display area segmentation. The digital tube segmentation and recognition unit 4 is used to add fixed-width black borders on the left and right sides of the binary image, and based on the compensated image width, divide it into 3 independent digital tube regions in a 1:1:1 ratio to ensure that the aspect ratio of each digital tube is consistent, providing standardized input for seven-segment code feature extraction.

[0059] In this embodiment, the image ROI extraction unit 1 accurately captures the digital display area of ​​the gas monitoring instrument, reducing interference from irrelevant backgrounds; the image correction unit 2 solves the image tilt problem caused by shooting angle deviation; the illumination normalization and binarization unit 3 achieves efficient separation of the digital area from the background; and the digital tube segmentation and recognition unit 4 extracts features and generates the required sensor readings.

[0060] This disclosure also provides a robot according to one embodiment, with reference to... Figure 1 Including the aforementioned gas concentration identification system, it also includes:

[0061] The traveling vehicle 5 is self-powered and is used to provide a load-bearing foundation;

[0062] The telescopic pole 53 is fixed to the traveling vehicle 5 in a vertical position and has an adjustment end 54 for moving in the vertical direction;

[0063] Rotate joint 55, fix it to adjustment end 54, and have a first posture and a second posture with different elevation angles;

[0064] Visible light camera 6 is fixed to rotating joint 55 and moves synchronously with rotating joint 55. Visible light camera 6 is used to acquire real-world images in front of the traveling vehicle 5.

[0065] Infrared camera 61 is fixed to rotating joint 55 and moves synchronously with rotating joint 55. Infrared camera 61 is used to acquire infrared images in front of the traveling vehicle 5.

[0066] Gas concentration sensor 62 is fixed to the mobile vehicle 5 and used to acquire information on the gas concentration in the environment;

[0067] A forward-facing camera sensor 63 is fixed to the front of the vehicle 5 and is used to acquire real-world video of the front of the vehicle 5.

[0068] The communication device 57 is fixed to the vehicle 5 and is connected to the visible light camera 6, the infrared camera 61, the gas concentration sensor 62, and the forward-looking camera sensor 63.

[0069] For example, refer to Figure 2The traveling vehicle 5 includes a tracked walking mechanism 52 for movement and a platform 51 as a support base. The bottom end of a telescopic rod 53 is fixed to the top surface of the platform 51, and the top end of the telescopic rod 53 extends vertically upward to form an adjustment end 54. The traveling vehicle 5 is divided into a front and a rear side according to its straight-line walking direction. A rotating joint 55 is fixed to the side wall of the top end of the telescopic rod 53 and is positioned facing the front of the traveling vehicle 5. The rotation axis of the rotating joint 55 is transverse and perpendicular to the straight-line walking direction of the traveling vehicle 5. The rotating joint 55 achieves the conversion between a first posture and a second posture by rotation. A visible light camera 6 is fixedly connected to the side of the rotating joint 55 away from the telescopic rod 53 and is positioned facing the front of the traveling vehicle 5. An infrared camera 61 is also fixedly connected to this side of the rotating joint 55 and is located below the visible light camera 6. The visible light camera 6 and the infrared camera 61 rotate synchronously with the rotation of the rotating joint 55, thereby capturing images from different angles and areas. The top surface of the traveling vehicle 5 has an inwardly extending gas channel 56. A gas concentration sensor 62 is fixed inside the traveling vehicle 5 and exposed to the outside through the gas channel 56. Specifically, the gas channel 56 is located on the top surface of the platform 51 and extends inward. The gas concentration sensor 62 is fixedly connected to the bottom end of the gas channel 56 inside the platform 51. There are two gas channels 56, both located on the side of the platform 51 closest to the front of the traveling vehicle 5. The two gas channels 56 are spaced apart on both sides of the telescopic rod 53 on the platform 51. Similarly, there are two gas concentration sensors 62, each fixed inside one of the two gas channels 56. A forward-looking camera sensor 63 is bolted to the side wall of the platform 51 corresponding to the front of the traveling vehicle 5 and is positioned facing the direction of travel when the traveling vehicle 5 moves in a straight line. A communication device 57 is fixedly connected inside the platform 51 and located on the side of the platform 51 corresponding to the rear of the traveling vehicle 5. The traveling vehicle 5 is fixed with an external bracket 58. There are two external brackets 58, which are bolted to the top surface of the platform 51 on both sides of the telescopic rod 53. The structure of the external bracket 58 is not limited. For example, when additional shooting devices are required under the current working conditions, the external bracket 58 can be a sleeve structure for fixing the camera, used to cover and bind the camera. When the working conditions require additional power, the external bracket 58 can be a box structure for fixing the battery.

[0070] The telescopic pole 53, rotating joint 55, visible light camera 6, infrared camera 61, gas concentration sensor 62, forward-looking camera sensor 63, and communication device 57 can all have their own power supply or be connected to the same external power supply, for example, the aforementioned electrical components can be powered by the traveling vehicle 5.

[0071] Reference Figure 3 An embodiment of this disclosure also provides a gas concentration identification method, including the following steps:

[0072] S100: Collect images of the grain warehouse scene.

[0073] S200: Based on preset coordinates, capture the digital display area of ​​the instrument and adaptively adjust the scale.

[0074] S300: Based on preset corner coordinates, the digital display area is corrected into a standardized front view through four-point perspective transformation.

[0075] S400, Perform illumination equalization processing on the front view.

[0076] S500 generates binary images through adaptive thresholding and morphological operations.

[0077] S600: Extract the seven-segment code features from the binary image to generate the actual gas concentration value.

[0078] For example, refer to Figure 3 Step S100 specifically includes: collecting images of the grain warehouse scene by a robot or by human and then transmitting them to the gas concentration recognition system.

[0079] Step S200 specifically includes: taking into account the fixed position of the instrument in the captured image, extracting the ROI region of the instrument using a coordinate specification method, and adaptively adjusting the scaling ratio according to the original size of the ROI region. For example, when the maximum side length of the ROI region is less than 600 pixels, a 2x scale magnification is adopted based on the bicubic interpolation algorithm.

[0080] Step S300 specifically includes: calibrating the coordinates of the four corner points of the digital display area of ​​the instrument within the ROI area; arranging the disordered corner points in a fixed order of "top left - top right - bottom right - bottom left" using a corner point sorting algorithm; then calculating the perspective transformation matrix based on the sorted corner point coordinates and the preset output size; and correcting the digital display area into a regular front view through perspective transformation.

[0081] Step S400 specifically includes: applying a color space conversion method (RGB space and LAB space) and a contrast-limited adaptive histogram equalization algorithm (CLAHE) to the standardized image to equalize the brightness channel of the standardized image.

[0082] Step S600 specifically includes: adding black borders of fixed width on the left and right sides of the binarized image; dividing the image into three independent digital tube regions in a 1:1:1 ratio based on the compensated image width, ensuring that the aspect ratio of each digital tube is consistent; then extracting the seven-segment code features of each digital tube region, matching and generating the corresponding numbers, and then concatenating them to convert them into actual gas concentration values.

[0083] This disclosure also provides an electronic device 9, with reference to... Figure 4 ,include:

[0084] Memory 7 is used to store computer program 71;

[0085] The processor 8 is used to execute the steps of the gas concentration recognition method of the above method embodiment when executing the computer program 71.

[0086] For example, refer to Figure 5 The electronic device 9 can vary considerably depending on its configuration or performance, and may include a processor (central processing unit, CPU) 8 (e.g., one or more processors) and a memory 7. The memory 7 stores one or more computer programs 71 or data 72. The memory 7 can be temporary or permanent storage, and the program stored in the memory 7 may include one or more modules (not shown in the illustration). Furthermore, the processor 8 may be configured to communicate with the memory 7 and execute a series of instructions stored in the memory 7 on the electronic device 9.

[0087] The electronic device 9 may also include one or more power supplies 91, one or more wired or wireless network interfaces 92, one or more input / output interfaces 93, and / or one or more operating devices.

[0088] The steps in the gas concentration identification method described above can be implemented by the structure of electronic device 9.

[0089] Corresponding to the above method embodiments, this application also provides a readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the aforementioned gas concentration identification method. Specific steps of this method can be found in the corresponding content disclosed in the foregoing embodiments, and will not be repeated here.

[0090] The readable storage medium may include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0091] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A gas concentration identification system, characterized in that, include: The image ROI extraction unit is used to extract the digital display area from the scene image; The image correction unit is used to perform perspective transformation on the digital display area and output a regular front view to provide a standardized image; The illumination normalization and binarization unit is used to perform illumination equalization processing on the standardized image and separate the digital region from the background region through adaptive thresholding and morphological operations to generate a binary image. The digital tube segmentation and recognition unit is used to segment the binary image into individual digital tube regions according to a certain ratio, and output the gas concentration value after digital decoding based on seven-segment code feature matching.

2. The gas concentration identification system according to claim 1, characterized in that, The image ROI extraction unit is configured to extract the ROI region of the instrument in a specified coordinate manner, and adjust the scaling ratio according to the original size of the ROI region.

3. The gas concentration identification system according to claim 2, characterized in that, The image correction unit is configured to calibrate and arrange the four corner points of the digital display area in a fixed order, calculate the perspective transformation matrix based on the sorted corner point coordinates and the preset output size, and correct the digital display area into a regular front view through perspective transformation.

4. The gas concentration identification system according to claim 3, characterized in that, The digital tube segmentation and recognition unit is configured to add left and right black border compensation to the binary image, divide it into n digital tube regions according to the n equal division ratio, extract the seven-segment code features of each digital tube region, match and generate the corresponding numbers, and concatenate them to convert them into the gas concentration value.

5. A robot, characterized in that, The gas concentration identification system according to any one of claims 1-4 further includes: The traveling vehicle (5) has self-driving power and is used to provide a load-bearing foundation; The telescopic rod (53) is fixed to the traveling vehicle (5) in a vertical position and has an adjustment end (54) for moving in the vertical direction. Rotate the joint (55), fix it to the adjustment end (54), and have a first posture and a second posture with different elevation angles; A visible light camera (6) is fixed to the rotating joint (55) and moves synchronously with the rotating joint (55). The visible light camera (6) is used to acquire real-scene images in front of the vehicle (5). An infrared camera (61) is fixed to the rotating joint (55) and moves synchronously with the rotating joint (55). The infrared camera (61) is used to acquire infrared images in front of the vehicle (5). A gas concentration sensor (62) is fixed to the vehicle (5) and used to acquire gas concentration information in the environment; A forward-facing camera sensor (63) is fixed to the front of the vehicle (5) and is used to acquire real-world video of the front of the vehicle (5); The communication device (57) is fixed to the vehicle (5) and is connected to the visible light camera (6), the infrared camera (61), the gas concentration sensor (62), and the forward-looking camera sensor (63).

6. The robot according to claim 5, characterized in that, The traveling vehicle (5) is fixed with an external bracket (58), and there are two external brackets (58) which are respectively located on both sides of the telescopic rod (53).

7. The robot according to claim 5, characterized in that, The top surface of the vehicle (5) is provided with an inwardly extending gas channel (56), and the gas concentration sensor (62) is fixed inside the vehicle (5) and exposed to the outside through the gas channel (56).

8. A method for identifying gas concentration, characterized in that, include: Collect images of the grain warehouse scene; Based on preset coordinates, the digital display area of ​​the instrument is captured and the scale is adaptively adjusted. Based on preset corner coordinates, the digital display area is corrected into a regular front view through four-point perspective transformation; Perform illumination equalization processing on the front view; Binary images are generated using adaptive thresholding and morphological operations; Extract the seven-segment code features from the binary image to generate the actual gas concentration value.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor is configured to implement the steps of the gas concentration identification method as described in claim 8 when executing the computer program.

10. A readable storage medium, characterized in that, The readable storage medium stores a computer program that, when executed by a processor, implements the steps of the gas concentration identification method as described in claim 8.

Images