Method for identifying identity and state of molten iron tank car based on visual identification and related equipment

Abstract

The invention discloses a molten iron tank car identity and state recognition method based on visual recognition and related equipment, and relates to the field of metal smelting, the method comprises the steps that color two-dimensional code image information of an identity recognition label is obtained, the identity recognition label is connected to a molten iron tank car base, and the identity recognition label is a light-emitting label; the color two-dimensional code image information is input into a tank car identity and state recognition model to obtain identity information and state information of the current molten iron tank car, and the state information comprises temperature information and weight information.

Description

Technical Field

[0001] The present specification relates to the field of metal smelting, and more specifically, the present application relates to a method for identifying the identity and status of a molten iron tank car based on visual recognition and related equipment. Background Art

[0002] With the improvement of industrial automation level, the demand for logistics management in the steel manufacturing process is increasing. In the production process of steel mills, molten iron tank trucks are key means of transportation, and their identity recognition and status monitoring have become an important part of ensuring the smooth production process. Traditional molten iron tank truck identification methods mostly rely on barcodes or ordinary QR codes for identity identification, but these methods are susceptible to interference in harsh environments, and recognition efficiency and accuracy are difficult to guarantee. In addition, traditional methods often find it difficult to simultaneously obtain real-time status information of molten iron tank trucks, such as temperature and weight, and cannot meet high-precision, all-round monitoring needs. In order to at least solve some of the above problems, it is urgent to provide a molten iron tank truck identity and status recognition method based on visual recognition. Summary of the invention

[0003] A series of simplified concepts are introduced in the Summary of the Invention section, which will be further described in detail in the Detailed Description of the Invention section. The Summary of the Invention section of this application does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the scope of protection of the claimed technical solution.

[0004] In the first aspect, the present application proposes a method for identifying the identity and state of a molten iron tank car based on visual recognition, comprising:

[0005] Obtaining color two-dimensional code image information of an identity recognition label, wherein the identity recognition label is connected to the base of the molten iron tank car, and the identity recognition label is a luminous label;

[0006] The color two-dimensional code image information is input into the tank car identity and status recognition model to obtain the identity information and status information of the current molten iron tank car, wherein the status information includes temperature information and weight information.

[0007] In a feasible implementation, the above-mentioned color two-dimensional code image includes a positioning area, an identity recognition area, a status recognition area and a correction area. The above-mentioned positioning area and the above-mentioned identity recognition area are white light-emitting areas, the above-mentioned status recognition area and the correction area are color light-emitting areas, the above-mentioned correction area includes a red light-emitting unit, a green light-emitting unit and a blue light-emitting unit, the above-mentioned status recognition area includes a temperature information light-emitting unit and a weight information light-emitting unit, the light-emitting shapes corresponding to the above-mentioned temperature information light-emitting unit and the weight information light-emitting unit are different, the above-mentioned positioning area and the above-mentioned identity recognition area are diagonally arranged, and the above-mentioned status recognition area and the above-mentioned correction area are diagonally arranged.

[0008] In a feasible implementation, the tank truck identity and status recognition model includes an image preprocessing module, an image region segmentation module, an identity information recognition module and a status information recognition module;

[0009] The above-mentioned color QR code image information is input into the tank car identity and status recognition model to obtain the identity information and status information of the current molten iron tank car, including:

[0010] Inputting the two-dimensional code image information into the image preprocessing module for preprocessing to obtain preprocessed image information, wherein the preprocessing operation includes a color correction operation and a shape correction operation;

[0011] The pre-processed image information is input into the image region segmentation module, and the positioning is performed based on the positioning area, and the image region is segmented to obtain the image information of the identity recognition area, the image information of the state recognition area, and the image information of the correction area;

[0012] Input the above-mentioned identity recognition area image information into the identity information recognition module to obtain identity information, wherein the above-mentioned identity information is determined based on the arrangement rule of the light-up units of the identity recognition area image;

[0013] The state recognition area image information and the correction area image information are input into the state information recognition module to obtain the temperature information and weight information.

[0014] In a feasible implementation manner, the above-mentioned inputting the above-mentioned two-dimensional code image information into the above-mentioned image preprocessing module for preprocessing operation to obtain preprocessed image information includes:

[0015] Obtaining the RGB value of the red light-emitting unit, the RGB value of the green light-emitting unit, and the RGB value of the blue light-emitting unit corresponding to the red light-emitting unit, the green light-emitting unit, and the blue light-emitting unit in the correction area in the two-dimensional code image;

[0016] Based on the RGB value of the red light-emitting unit, the RGB value of the green light-emitting unit, and the RGB value of the blue light-emitting unit, the first color image corresponding to the temperature information light-emitting unit and the second color image corresponding to the weight information light-emitting unit are corrected in RGB value;

[0017] Based on the original image information corresponding to the positioning area and the positioning area image in the two-dimensional code image, perspective transformation is applied to perform correction to obtain pre-processed image information after color correction and graphic correction.

[0018] In a feasible implementation manner, the state recognition area image information and the correction area image information are input into the state information recognition module to obtain the temperature information and weight information;

[0019] The state recognition area image information and the correction area image information are input into the state information recognition module, and the corresponding relationship between RGB value and temperature information and the corresponding relationship between RGB value and weight are retrieved to obtain the temperature information and weight information.

[0020] In a feasible implementation, it also includes:

[0021] Obtaining distance information between a camera unit or an inspection terminal and the molten iron tank car, wherein the camera unit is a camera that shoots color two-dimensional code image information at a fixed position, and the inspection terminal is an intelligent terminal corresponding to dynamic inspection personnel along the transportation route;

[0022] When the distance information is less than or equal to the preset distance, the luminous sign is controlled to light up.

[0023] In a feasible implementation, it also includes:

[0024] Determine the initial brightness of the identity sign light-emitting unit based on the brightness time curve and the current time;

[0025] Get the current brightness information corresponding to the above positioning area image,

[0026] Based on the current brightness information corresponding to the positioning area image and the standard brightness information at this moment, the brightness information of all the light-emitting units of the identity identification sign is adjusted so that the two-dimensional code image information can be clearly captured.

[0027] In the second aspect, the present application proposes a device for identifying the identity and state of a molten iron tank car based on visual recognition, comprising:

[0028] A first acquisition unit is used to acquire color two-dimensional code image information of an identity recognition label, wherein the identity recognition label is connected to the base of the molten iron tank car, and the identity recognition label is a luminous label;

[0029] The second acquisition unit is used to input the above-mentioned color two-dimensional code image information into the tank car identity and status recognition model to obtain the identity information and status information of the current molten iron tank car, wherein the above-mentioned status information includes temperature information and weight information.

[0030] In a third aspect, an electronic device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is used to implement the steps of the method for identifying the identity and status of a molten iron tank car based on visual recognition as described in any one of the first aspects above when executing the computer program stored in the memory.

[0031] In a fourth aspect, the present application further proposes a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, it implements the method for identifying the identity and status of a molten iron tank car based on visual recognition according to any one of the first aspects.

[0032] In summary, the method for identifying the identity and status of a molten iron tank car based on visual recognition proposed in the embodiment of the present application includes: obtaining the color two-dimensional code image information of the identity identification sign, wherein the above-mentioned identity identification sign is connected to the base of the molten iron tank car, and the above-mentioned identity identification sign is a luminous sign; inputting the above-mentioned color two-dimensional code image information into the tank car identity and status recognition model to obtain the identity information and status information of the current molten iron tank car, wherein the above-mentioned status information includes temperature information and weight information. The method proposed in the embodiment of the present application adopts a luminous sign as an identity identification sign. Through this design, the color two-dimensional code image information can be stably obtained even in insufficient light or complex environment, thereby improving the reliability and accuracy of recognition. This scheme identifies the identity of the molten iron tank car through the color two-dimensional code image information. Compared with the traditional barcode or monochrome two-dimensional code, the color two-dimensional code can accommodate more information, further improving the information storage capacity and recognition accuracy. The embodiment of the present application proposes to input the color two-dimensional code image information into the tank car identity and status recognition model, thereby simultaneously obtaining the identity information and status information (including temperature and weight) of the molten iron tank car. This integrated recognition of multi-dimensional information has greatly improved the all-round monitoring capability of molten iron tank trucks, making production management more intelligent and efficient. Due to the use of luminous signs and advanced image processing technology, this solution can still maintain a stable recognition effect in harsh environments such as high temperature and dust, ensuring the safe transportation of molten iron tank trucks and the smooth progress of production processes. Through the above improvements, the method proposed in the embodiment of the present application significantly improves the efficiency and accuracy of identity recognition and status monitoring of molten iron tank trucks, providing strong support for the automation and intelligent management of steel production. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present specification. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0034] Figure 1 A schematic diagram of a process for identifying the identity and state of a molten iron tank car based on visual recognition provided in an embodiment of the present application;

[0035] Figure 2 A color QR code image information of an identity identification label provided in an embodiment of the present application;

[0036] Figure 3 A schematic diagram of the structure of a molten iron tank car identity and state recognition device based on visual recognition provided in an embodiment of the present application;

[0037] Figure 4 A schematic diagram of the structure of an electronic device for identifying the identity and status of a molten iron tank car based on visual recognition provided in an embodiment of the present application. DETAILED DESCRIPTION

[0038] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0039] See also Figure 1 , which is a schematic diagram of a process of identifying the identity and state of a molten iron tank car based on visual recognition provided in an embodiment of the present application, and may specifically include:

[0040] S110, obtaining color two-dimensional code image information of an identity recognition label, wherein the identity recognition label is connected to the base of the molten iron tank car, and the identity recognition label is a luminous label;

[0041] Exemplarily, first, the color QR code image information is obtained from the identification label connected to the base of the molten iron ladle car. The identification label is a luminous label that can provide stable image information acquisition conditions when the ambient light is insufficient. The color QR code image information is used for further identity and status identification.

[0042] S120. Input the color two-dimensional code image information into a tank car identity and status recognition model to obtain the identity information and status information of the current molten iron tank car, wherein the status information includes temperature information and weight information.

[0043] Exemplarily, the obtained color QR code image information is then input into the tank car identity and status recognition model. Through the model, the identity information and status information of the current molten iron tank car can be accurately identified. The status information includes temperature information and weight information related to the molten iron tank car, which is crucial to the safety and efficiency of the molten iron transportation process.

[0044] In summary, the method proposed in the embodiment of the present application adopts a luminous sign as an identification sign. Through this design, even in the case of insufficient light or complex environment, the color two-dimensional code image information can be stably obtained, which improves the reliability and accuracy of identification. This scheme uses color two-dimensional code image information to identify the identity of the molten iron tank car. Compared with traditional barcodes or monochrome two-dimensional codes, color two-dimensional codes can accommodate more information, further improving the information storage capacity and recognition accuracy. The embodiment of the present application proposes to input the color two-dimensional code image information into the tank car identity and status recognition model, so as to simultaneously obtain the identity information and status information (including temperature and weight) of the molten iron tank car. This integrated recognition of multi-dimensional information greatly improves the all-round monitoring capability of the molten iron tank car, making production management more intelligent and efficient. Due to the use of luminous signs and advanced image processing technology, this scheme can still maintain a stable recognition effect in harsh environments such as high temperature and dust, ensuring the safe transportation of the molten iron tank car and the smooth progress of the production process. Through the above improvements, the method proposed in the embodiment of the present application significantly improves the efficiency and accuracy of the identity recognition and status monitoring of the molten iron tank car, and provides strong support for the automation and intelligent management of steel production.

[0045] In some examples, the color QR code image includes a positioning area, an identity recognition area, a status recognition area and a correction area. The positioning area and the identity recognition area are white light-emitting areas, the status recognition area and the correction area are color light-emitting areas, the correction area includes a red light-emitting unit, a green light-emitting unit and a blue light-emitting unit, the status recognition area includes a temperature information light-emitting unit and a weight information light-emitting unit, the temperature information light-emitting unit and the weight information light-emitting unit have different corresponding light-emitting shapes, the positioning area and the identity recognition area are diagonally arranged, and the status recognition area and the correction area are diagonally arranged.

[0046] Exemplarily, the color QR code image consists of four main areas, each of which has a specific function:

[0047] Positioning area: used to assist in determining the location of the QR code image, ensuring that the image can be correctly identified and parsed when captured by the camera. This area is white luminous to enhance visibility in low light conditions. Figure 2 The white square in the upper left corner.

[0048] Identity recognition area: It stores the identity information of the molten iron tank car. It is also a white luminous area. Like the positioning area, it has a better display effect in a low-contrast environment. See the white dot area in the lower right corner of the figure.

[0049] Status identification area: It is a color luminous area, which contains two key luminous units: Figure 2 Upper right center area.

[0050] Temperature information light-emitting unit: used to display the temperature information of the molten iron tank car. The light-emitting shape of this unit is designed to be a specific shape for easy identification. Figure 2 The circular light unit on the upper right.

[0051] Weight information light-emitting unit: used to display the weight information of the molten iron tank car. Compared with the temperature information light-emitting unit, the light-emitting shape of the weight information light-emitting unit is different to distinguish the two status information. Figure 2 The square light unit on the upper right.

[0052] Correction area: It is also a color luminous area, used for color correction of images. The correction area contains three luminous units, such as Figure 2 Lower left corner, red light-emitting unit, green light-emitting unit, and blue light-emitting unit: These units provide standard red, green, and blue (RGB) color reference values. The system can use this color information to correct color distortion in the image and ensure the accuracy of subsequent recognition.

[0053] The positioning area and identity recognition area are set at the diagonal position of the QR code image. This layout helps provide a stable reference frame during image processing, ensuring that all information in the image can be accurately located. The status recognition area and correction area are also set at the diagonal position of the QR code image. This diagonal layout design ensures that the optical characteristics of each area can be evenly distributed during the image capture and processing process, improving the accuracy of image recognition.

[0054] This embodiment carefully designs the color QR code image so that the system can accurately and stably identify the identity information and status information of the hot metal ladle under different environmental conditions. By introducing white luminous areas and color luminous areas in the QR code image and reasonably arranging different areas, this embodiment ensures high visibility and recognition accuracy of the identity information and status information when the camera is shooting. This design effectively improves the traceability and management efficiency of hot metal ladle in industrial environments.

[0055] In some examples, the tank truck identity and status recognition model includes an image preprocessing module, an image region segmentation module, an identity information recognition module, and a status information recognition module;

[0056] The above-mentioned color QR code image information is input into the tank car identity and status recognition model to obtain the identity information and status information of the current molten iron tank car, including:

[0057] Inputting the two-dimensional code image information into the image preprocessing module for preprocessing to obtain preprocessed image information, wherein the preprocessing operation includes a color correction operation and a shape correction operation;

[0058] The pre-processed image information is input into the image region segmentation module, and the positioning is performed based on the positioning area, and the image region is segmented to obtain the image information of the identity recognition area, the image information of the state recognition area, and the image information of the correction area;

[0059] Input the above-mentioned identity recognition area image information into the identity information recognition module to obtain identity information, wherein the above-mentioned identity information is determined based on the arrangement rule of the light-up units of the identity recognition area image;

[0060] The state recognition area image information and the correction area image information are input into the state information recognition module to obtain the temperature information and weight information.

[0061] Exemplarily, the acquired color QR code image information is input into the image preprocessing module for preprocessing operation. This module is responsible for performing two main preprocessing operations on the input QR code image to ensure the accuracy of the image in subsequent processing:

[0062] Color correction operation: Use the RGB light-emitting unit information in the correction area to correct the color of the image, eliminate color deviation that may occur during the shooting process, and ensure the accuracy of color information.

[0063] Shape correction operation: By performing perspective transformation and other operations on the QR code image, the image distortion caused by shooting angle or other factors can be corrected to ensure that the shape of the image meets the standard.

[0064] After these preprocessing operations, the system generates preprocessed image information, which will be used in subsequent recognition steps.

[0065] The pre-processed image information is input into the image region segmentation module. In this step, the system first performs a positioning operation based on the positioning area in the QR code image to determine the exact position of the QR code image in the entire image. Subsequently, the system performs region segmentation on the QR code image, specifically dividing it into the following regions: identity recognition area image information, status recognition area image information, and correction area image information. This region segmentation helps the system process information in different regions separately, ensuring that the information in each region can be accurately extracted and analyzed.

[0066] Next, the system inputs the image information of the identity recognition area into the identity information recognition module. In this module, the system determines and extracts the identity information of the molten iron tank car by analyzing the arrangement pattern of the image lighting units in the identity recognition area. These lighting units encode the tank car's identity information in a specific arrangement. By identifying these arrangement patterns, the system can accurately determine the unique identity of the tank car.

[0067] At the same time, the system inputs the image information of the state recognition area and the image information of the correction area into the state information recognition module. In this module, the system first uses the color information of the correction area to further color correct the image of the state recognition area to ensure the accuracy of the color information. Then, the system extracts the temperature information and weight information related to the molten iron tank car by analyzing the color and shape of the light-emitting unit in the state recognition area.

[0068] Temperature information: Determined by the color and shape of the temperature information light-emitting unit, the system decodes it according to the correspondence between the preset RGB value and the temperature.

[0069] Weight information: Determined by the color and shape of the weight information light-emitting unit, the system analyzes it through the correspondence between the preset RGB value and the weight.

[0070] The method proposed in the embodiment of the present application successfully obtains the identity information and status information of the molten iron tank car by inputting the color two-dimensional code image information into the tank car identity and status recognition model, and then goes through multiple steps such as image preprocessing, image region segmentation, identity information recognition and status information recognition. This method makes full use of the color correction and shape correction operations in the image preprocessing module, combined with region segmentation and a special recognition module, to achieve efficient and accurate recognition of the molten iron tank car. This solution not only improves the recognition accuracy, but also ensures stability and reliability in complex industrial environments.

[0071] In some examples, the inputting of the two-dimensional code image information into the image preprocessing module for preprocessing to obtain preprocessed image information includes:

[0072] Obtaining the RGB value of the red light-emitting unit, the RGB value of the green light-emitting unit, and the RGB value of the blue light-emitting unit corresponding to the red light-emitting unit, the green light-emitting unit, and the blue light-emitting unit in the correction area in the two-dimensional code image;

[0073] Based on the RGB value of the red light-emitting unit, the RGB value of the green light-emitting unit, and the RGB value of the blue light-emitting unit, the first color image corresponding to the temperature information light-emitting unit and the second color image corresponding to the weight information light-emitting unit are corrected in RGB value;

[0074] Based on the original image information corresponding to the positioning area and the positioning area image in the two-dimensional code image, perspective transformation is applied to perform correction to obtain pre-processed image information after color correction and graphic correction.

[0075] Exemplarily, the preprocessing operation in the embodiment of the present application is completed by inputting the two-dimensional code image information into the image preprocessing module. The operation includes two parts: color correction and shape correction to ensure that the image information finally obtained is accurate and reliable.

[0076] First, the RGB values ​​corresponding to the red light-emitting unit, green light-emitting unit, and blue light-emitting unit are obtained from the correction area in the two-dimensional code image. These light-emitting units provide standard color reference values ​​for subsequent color correction operations. Specifically:

[0077] RGB value of the red light-emitting unit: represents the color information of the red light-emitting unit in the calibration area.

[0078] RGB value of the green light-emitting unit: represents the color information of the green light-emitting unit in the calibration area.

[0079] RGB value of the blue light-emitting unit: represents the color information of the blue light-emitting unit in the calibration area.

[0080] These RGB values ​​will be used to correct other color image information in the QR code image to eliminate color deviation caused by ambient light or camera performance.

[0081] Next, based on the RGB values ​​of the red light emitting unit, the green light emitting unit and the blue light emitting unit obtained from the calibration area, the RGB values ​​of the first color image corresponding to the temperature information light emitting unit and the second color image corresponding to the weight information light emitting unit are corrected.

[0082] The RGB value of the first color image (ie, the image corresponding to the temperature information light emitting unit) is corrected to ensure that the temperature information in the image reflects the real color and temperature data.

[0083] The RGB value of the second color image (ie, the image corresponding to the weight information light-emitting unit) is corrected to ensure that the weight information in the image reflects the real color and weight data.

[0084] Through this correction operation, the system can eliminate errors caused by lighting changes or color distortion during image capture, ensuring the accuracy of temperature and weight information.

[0085] After completing the color correction, the system then processes the positioning area in the QR code image. Based on the original image information corresponding to the positioning area, the image is corrected by applying perspective transformation. The specific steps of this operation include:

[0086] Identify the position and shape of the positioning area in the QR code image. Apply perspective transformation to correct the positioning area image to eliminate shape errors caused by camera angle or image distortion.

[0087] Through this perspective transformation correction operation, the system can obtain pre-processed image information after color correction and shape correction. This image information will be used for subsequent identity and status recognition to ensure the accuracy and reliability of the recognition results.

[0088] The method proposed in the embodiment of the present application realizes high-precision preprocessing of image information by color correction and perspective transformation correction of the two-dimensional code image information. The specific operation includes obtaining the RGB values ​​of the red, green, and blue light-emitting units from the correction area, correcting the color images of the temperature information light-emitting unit and the weight information light-emitting unit based on these RGB values, and applying perspective transformation to the positioning area for shape correction. The preprocessed image information finally generated provides an accurate and reliable data basis for the subsequent processing of the tank car identity and status recognition model. This method greatly improves the accuracy and stability of the identity and status recognition of the molten iron tank car, ensuring the safety and efficiency in the industrial production process.

[0089] In some examples, the state recognition area image information and the correction area image information are input into the state information recognition module to obtain the temperature information and weight information;

[0090] The state recognition area image information and the correction area image information are input into the state information recognition module, and the corresponding relationship between RGB value and temperature information and the corresponding relationship between RGB value and weight are retrieved to obtain the temperature information and weight information.

[0091] For example, in the embodiment of the present application, the state recognition area image information and the correction area image information are input into the state information recognition module to obtain the temperature information and weight information of the molten iron tank car. The information of these two areas plays a key role in the recognition process:

[0092] Status recognition area image information: contains images corresponding to the temperature information light-emitting unit and the weight information light-emitting unit. These light-emitting units use different colors and shapes to indicate the current temperature and weight status of the molten iron tank car.

[0093] Correction area image information: provides standard color reference values ​​to correct image color deviations in the status recognition area to ensure the accuracy of information recognition.

[0094] In the status information recognition module, the system retrieves the correspondence between RGB value and temperature information and the correspondence between RGB value and weight information. These correspondences are established by the system through pre-calibration. The specific operations are as follows:

[0095] According to the preset color calibration table, the system matches the RGB value of the temperature information light-emitting unit in the status recognition area with the specific temperature information. Different RGB values ​​correspond to different temperature ranges, so that the system can directly obtain the current temperature information by reading the color of the light-emitting unit.

[0096] Similarly, the system converts the RGB value of the weight information light-emitting unit in the status identification area into specific weight information through the calibration relationship between RGB value and weight. Different RGB values ​​correspond to different weight values, so the system can determine the current weight of the molten iron tank car by analyzing the color of the light-emitting unit.

[0097] By inputting the state recognition area image information and the correction area image information into the state information recognition module, the system first corrects the RGB value in the state recognition area based on the correction area image information to ensure the accuracy of the color information. Then, the system converts the RGB value of the temperature information light-emitting unit into the actual temperature information by retrieving the correspondence between the RGB value and the temperature information. Similarly, by retrieving the correspondence between the RGB value and the weight information, the RGB value of the weight information light-emitting unit is converted into the actual weight information.

[0098] The embodiment of the present application successfully realizes accurate recognition of the temperature and weight status of the molten iron tank car by inputting the image information of the state recognition area and the image information of the correction area into the state information recognition module, and combining the pre-set correspondence between the RGB value and the temperature information and the weight information. This method utilizes the standard color reference provided by the correction area to ensure the accuracy of the information under different ambient light, and directly obtains the key state data of the molten iron tank car through the correspondence between the RGB value and the specific state information, providing reliable technical support for monitoring and management in the industrial production process.

[0099] In some examples, this also includes:

[0100] Obtaining distance information between a camera unit or an inspection terminal and the molten iron tank car, wherein the camera unit is a camera that shoots color two-dimensional code image information at a fixed position, and the inspection terminal is an intelligent terminal corresponding to dynamic inspection personnel along the transportation route;

[0101] When the distance information is less than or equal to the preset distance, the luminous sign is controlled to light up.

[0102] Exemplarily, it is first necessary to obtain the distance information between the camera unit or the inspection terminal and the above-mentioned molten iron tank car.

[0103] Camera unit: This is a fixed-position camera, usually installed at a fixed position on the transportation route of the molten iron ladle or in a production workshop, specifically used to capture the color QR code image information of the molten iron ladle.

[0104] Inspection terminal: This is an intelligent terminal carried by personnel who conduct dynamic inspections along the transportation route. The terminal can obtain the status information of the molten iron tank car at any time.

[0105] After obtaining the above distance information, the system will determine whether the distance information is less than or equal to the preset distance. The preset distance refers to a distance threshold set by the system according to the specific scenario, which is used to determine when the distance is appropriate to initiate further operations. For example, the preset distance may be set to a certain number of meters to ensure that the camera unit or inspection terminal is within the range where the information of the molten iron tank car can be clearly captured.

[0106] If the above distance information meets the conditions, that is, it is less than or equal to the preset distance, the system will control the luminous sign to light up, and it will not light up when it is greater than the preset distance to avoid energy waste. The lighting of the luminous sign has the following important functions:

[0107] Enhanced recognition effect: Lighting up the luminous sign can ensure that the camera unit or inspection terminal can obtain the color QR code image information more clearly, especially in poor light or complex environment.

[0108] Guiding inspection personnel: For inspection terminals, the lighting of luminous signs can provide clear visual guidance for inspection personnel, enabling them to quickly locate and obtain the identity and status information of the molten iron tank car.

[0109] The embodiment of the present application further optimizes the method of identifying the identity and status of the molten iron tanker by introducing the steps of judging the distance information and controlling the lighting of the luminous sign. When the distance information meets the preset conditions, the system automatically controls the lighting of the luminous sign, thereby improving the accuracy of the camera unit or the inspection terminal in acquiring the color QR code image information. This improvement not only enhances the adaptability of the system in different environments, but also provides a more convenient operating experience for the inspection personnel, ensuring the accuracy and timeliness of the identification of the molten iron tanker.

[0110] In some examples, this also includes:

[0111] Determine the initial brightness of the identity sign light-emitting unit based on the brightness time curve and the current time;

[0112] Get the current brightness information corresponding to the above positioning area image,

[0113] Based on the current brightness information corresponding to the positioning area image and the standard brightness information at this moment, the brightness information of all the light-emitting units of the identity identification sign is adjusted so that the two-dimensional code image information can be clearly captured.

[0114] Exemplarily, it is first necessary to determine the initial brightness of the light-emitting unit of the identification sign based on the brightness time curve and the current time. The brightness time curve is pre-set to reflect the changing pattern of ambient brightness at different time periods of the day. According to the current time point, the system obtains the corresponding brightness value from the brightness time curve, and determines the initial brightness of the light-emitting unit on the identification sign based on this. The purpose of this step is to match the brightness of the light-emitting unit with the current ambient lighting conditions, thereby providing a lighting basis suitable for shooting.

[0115] Next, the system obtains the current brightness information corresponding to the positioning area image. The positioning area plays an auxiliary positioning role in the QR code image, and its brightness information can directly reflect the lighting conditions of the current shooting environment. By analyzing the brightness of the positioning area image, the system can understand the actual lighting level during shooting, thereby providing a basis for subsequent brightness adjustment.

[0116] After obtaining the current brightness information of the positioning area image, the system compares it with the standard brightness information at the moment. The standard brightness information is a reference value preset by the system, which represents the brightness required for the QR code image information to be clearly photographed under ideal lighting conditions. By comparing the difference between the current brightness information and the standard brightness information, the system can determine whether the current lighting is insufficient or too strong.

[0117] Based on the comparison results, the system adjusts the brightness information of all the light-emitting units of the above-mentioned identification sign. This step aims to increase or decrease the brightness of the light-emitting units so that the overall brightness of the QR code image information reaches the standard brightness level, thereby ensuring that the QR code image information can be clearly seen when shooting. This dynamic adjustment can adapt to changes in different ambient light and ensure that high-quality QR code images can be obtained under various shooting conditions.

[0118] The embodiment of the present application effectively improves the reliability of the identity and status recognition of the molten iron tank car by introducing a brightness adjustment mechanism. First, the system determines the initial brightness of the light-emitting unit of the identity identification sign according to the brightness time curve and the current time, and provides a basic brightness that is compatible with the ambient lighting. Then, by obtaining the current brightness information of the positioning area image and comparing it with the standard brightness information, the system dynamically adjusts the brightness of the light-emitting unit to ensure that the two-dimensional code image information can be clearly photographed under various lighting conditions. This method enhances the adaptability of the system in complex environments and ensures the accuracy and stability of the identity and status recognition of the molten iron tank car.

[0119] like Figure 3 As shown, this application proposes a molten iron tank car identity and state recognition device based on visual recognition, including:

[0120] A first acquisition unit 21 is used to acquire color two-dimensional code image information of an identity recognition label, wherein the identity recognition label is connected to the base of the molten iron tank car, and the identity recognition label is a luminous label;

[0121] The second acquisition unit 22 is used to input the color two-dimensional code image information into the tank car identity and status recognition model to obtain the identity information and status information of the current molten iron tank car, wherein the status information includes temperature information and weight information.

[0122] In some examples, the color QR code image includes a positioning area, an identity recognition area, a status recognition area and a correction area. The positioning area and the identity recognition area are white light-emitting areas, the status recognition area and the correction area are color light-emitting areas, the correction area includes a red light-emitting unit, a green light-emitting unit and a blue light-emitting unit, the status recognition area includes a temperature information light-emitting unit and a weight information light-emitting unit, the temperature information light-emitting unit and the weight information light-emitting unit have different corresponding light-emitting shapes, the positioning area and the identity recognition area are diagonally arranged, and the status recognition area and the correction area are diagonally arranged.

[0123] In some examples, the tank truck identity and status recognition model includes an image preprocessing module, an image region segmentation module, an identity information recognition module, and a status information recognition module;

[0124] The above-mentioned color QR code image information is input into the tank car identity and status recognition model to obtain the identity information and status information of the current molten iron tank car, including:

[0125] Inputting the two-dimensional code image information into the image preprocessing module for preprocessing to obtain preprocessed image information, wherein the preprocessing operation includes a color correction operation and a shape correction operation;

[0126] The pre-processed image information is input into the image region segmentation module, and the positioning is performed based on the positioning area, and the image region is segmented to obtain the image information of the identity recognition area, the image information of the state recognition area, and the image information of the correction area;

[0127] Input the above-mentioned identity recognition area image information into the identity information recognition module to obtain identity information, wherein the above-mentioned identity information is determined based on the arrangement rule of the light-up units of the identity recognition area image;

[0128] The state recognition area image information and the correction area image information are input into the state information recognition module to obtain the temperature information and weight information.

[0129] In some examples, the inputting of the two-dimensional code image information into the image preprocessing module for preprocessing to obtain preprocessed image information includes:

[0130] Obtaining the RGB value of the red light-emitting unit, the RGB value of the green light-emitting unit, and the RGB value of the blue light-emitting unit corresponding to the red light-emitting unit, the green light-emitting unit, and the blue light-emitting unit in the correction area in the two-dimensional code image;

[0131] Based on the RGB value of the red light-emitting unit, the RGB value of the green light-emitting unit, and the RGB value of the blue light-emitting unit, the first color image corresponding to the temperature information light-emitting unit and the second color image corresponding to the weight information light-emitting unit are corrected in RGB value;

[0132] Based on the original image information corresponding to the positioning area and the positioning area image in the two-dimensional code image, perspective transformation is applied to perform correction to obtain pre-processed image information after color correction and graphic correction.

[0133] In some examples, the state recognition area image information and the correction area image information are input into the state information recognition module to obtain the temperature information and weight information;

[0134] The state recognition area image information and the correction area image information are input into the state information recognition module, and the corresponding relationship between RGB value and temperature information and the corresponding relationship between RGB value and weight are retrieved to obtain the temperature information and weight information.

[0135] In some examples, this also includes:

[0136] Obtaining distance information between a camera unit or an inspection terminal and the molten iron tank car, wherein the camera unit is a camera that shoots color two-dimensional code image information at a fixed position, and the inspection terminal is an intelligent terminal corresponding to dynamic inspection personnel along the transportation route;

[0137] When the distance information is less than or equal to the preset distance, the luminous sign is controlled to light up.

[0138] In some examples, this also includes:

[0139] Determine the initial brightness of the identity sign light-emitting unit based on the brightness time curve and the current time;

[0140] Get the current brightness information corresponding to the above positioning area image,

[0141] Based on the current brightness information corresponding to the positioning area image and the standard brightness information at this moment, the brightness information of all the light-emitting units of the identity identification sign is adjusted so that the two-dimensional code image information can be clearly captured.

[0142] like Figure 4As shown, an embodiment of the present application also provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor. When the processor 320 executes the computer program 311, the steps of any one of the above-mentioned methods for identifying the identity and status of a molten iron tank car based on visual recognition are implemented.

[0143] Since the electronic device introduced in this embodiment is a device used to implement a molten iron tank car identity and status identification device based on visual recognition in the embodiment of the present application, based on the method introduced in the embodiment of the present application, the technical personnel in this field can understand the specific implementation mode of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present application is not introduced in detail here. As long as the equipment used by the technical personnel in this field to implement the method in the embodiment of the present application is within the scope of protection of this application.

[0144] In the specific implementation process, when the computer program 311 is executed by the processor, it can achieve Figure 1 Any implementation manner in the corresponding embodiments.

[0145] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0146] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0147] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0148] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0149] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0150] An embodiment of the present application also provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device executes the process of visual recognition-based identity and status recognition of a molten iron tank car in the corresponding embodiment.

[0151] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or a data center that includes one or more available media integration. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)), etc.

[0152] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0153] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0154] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0155] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0156] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0157] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for identifying the identity and state of a molten iron tank car based on visual recognition, characterized in that: include: Obtaining color two-dimensional code image information of an identity recognition label, wherein the identity recognition label is connected to the base of the molten iron tank car, and the identity recognition label is a luminous label; The color two-dimensional code image information is input into the tank car identity and status recognition model to obtain the identity information and status information of the current molten iron tank car, wherein the status information includes temperature information and weight information.

2. The method according to claim 1, characterized in that: The color two-dimensional code image includes a positioning area, an identity recognition area, a status recognition area and a correction area. The positioning area and the identity recognition area are white light-emitting areas, the status recognition area and the correction area are color light-emitting areas, the correction area includes a red light-emitting unit, a green light-emitting unit and a blue light-emitting unit, the status recognition area includes a temperature information light-emitting unit and a weight information light-emitting unit, and the temperature information light-emitting unit and the weight information light-emitting unit have different corresponding light-emitting shapes. The positioning area and the identity recognition area are diagonally arranged, and the status recognition area and the correction area are diagonally arranged.

3. The method according to claim 2, characterized in that The tank truck identity and status recognition model includes an image preprocessing module, an image region segmentation module, an identity information recognition module and a status information recognition module; The step of inputting the color two-dimensional code image information into the tank car identity and status recognition model to obtain the identity information and status information of the current molten iron tank car includes: Inputting the two-dimensional code image information into the image preprocessing module for preprocessing operation to obtain preprocessed image information, wherein the preprocessing operation includes a color correction operation and a shape correction operation; Inputting the preprocessed image information into an image region segmentation module, positioning is performed based on the positioning area, and image region segmentation is performed to obtain image information of the identity recognition area, image information of the state recognition area, and image information of the correction area; Inputting the identity recognition area image information into an identity information recognition module to obtain identity information, wherein the identity information is determined based on the arrangement rule of the light-up units in the identity recognition area image; The state recognition area image information and the correction area image information are input into the state information recognition module to obtain the temperature information and the weight information.

4. The method according to claim 3, characterized in that The step of inputting the two-dimensional code image information into the image preprocessing module for preprocessing to obtain preprocessed image information includes: Obtaining the RGB value of the red light-emitting unit, the RGB value of the green light-emitting unit, and the RGB value of the blue light-emitting unit corresponding to the red light-emitting unit, the green light-emitting unit, and the blue light-emitting unit in the correction area in the two-dimensional code image; Based on the RGB value of the red light-emitting unit, the RGB value of the green light-emitting unit, and the RGB value of the blue light-emitting unit, the first color image corresponding to the temperature information light-emitting unit and the second color image corresponding to the weight information light-emitting unit are corrected in RGB value; Based on the original image information corresponding to the positioning area and the positioning area image in the two-dimensional code image, perspective transformation is applied to perform correction to obtain pre-processed image information after color correction and graphic correction.

5. The method according to claim 3, characterized in that: The state recognition area image information and the correction area image information are input into the state information recognition module to obtain the temperature information and the weight information; The state recognition area image information and the correction area image information are input into the state information recognition module, and the corresponding relationship between RGB value and temperature information and the corresponding relationship between RGB value and weight are retrieved to obtain the temperature information and weight information.

6. The method according to claim 1, characterized in that Also includes: Obtaining distance information between a camera unit or an inspection terminal and the molten iron tank car, wherein the camera unit is a camera that shoots color two-dimensional code image information at a fixed position, and the inspection terminal is an intelligent terminal corresponding to dynamic inspection personnel along the transportation route; When the distance information is less than or equal to the preset distance, the luminous sign is controlled to light up.

7. The method according to claim 2, characterized in that Also includes: Determine the initial brightness of the identity sign light-emitting unit based on the brightness time curve and the current time; Obtaining current brightness information corresponding to the positioning area image, Based on the current brightness information corresponding to the positioning area image and the standard brightness information at this moment, the brightness information of all the light-emitting units of the identity identification sign is adjusted so that the two-dimensional code image information can be clearly photographed.

8. A device for identifying the identity and state of a molten iron tank car based on visual recognition, characterized in that: include: A first acquisition unit is used to acquire color two-dimensional code image information of an identity recognition label, wherein the identity recognition label is connected to the base of the molten iron tank car, and the identity recognition label is a luminous label; The second acquisition unit is used to input the color two-dimensional code image information into the tank car identity and status recognition model to obtain the identity information and status information of the current molten iron tank car, wherein the status information includes temperature information and weight information.

9. An electronic device, comprising: A memory and a processor, characterized in that the processor is used to implement the steps of the method for identifying the identity and status of a molten iron tank car based on visual recognition as described in any one of claims 1 to 7 when executing the computer program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for identifying the identity and state of a molten iron tank car based on visual recognition as described in any one of claims 1 to 7 are implemented.

Images