Label labeling method, device and system, electronic equipment and storage medium
By using target cameras and electronic equipment in the production workshop to automatically identify and mark product forms on the production line, the cumbersome problem of manual labeling is solved, automatic labeling is realized, and production efficiency and time management are improved.
Patent Information
- Application Number
- CN202410942077.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2024-06-26
- Filing Date
- 2024-07-12
- Publication Date
- 2024-11-15
AI Technical Summary
In the production workshop, video previews cannot automatically label products, resulting in cumbersome manual labeling, which consumes a lot of time and labor costs.
The target image on the production line is taken through the target camera, and the different production stages and forms of the products are automatically identified and marked with electronic devices, including sheets and rolls, reducing the workload of manual labeling.
The automated labeling process is realized, reducing manual workload, and users can quickly understand the product attribute status and carry out the next steps in a timely manner, saving time.
Smart Images

Figure CN118968515A_ABST
Abstract
Description
[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office on June 26, 2024, with application number 202410842558.8 and application name “Labeling method, device, system, electronic device and storage medium”, all contents of which are incorporated by reference in this application. Technical Field
[0002] The present application relates to the field of image recognition technology, and in particular to a labeling method, device, system, electronic device and storage medium. Background Art
[0003] In the production workshop, various products in the production process need to be previewed by video. The ordinary preview method can only search for videos for preview by itself, and it is impossible to mark the products in the video.
[0004] In order to improve inspection efficiency, it is necessary to mark the products in the video screen. Currently, this can only be done manually to add labels corresponding to the products in the video screen. However, the workshop situation is complicated, there are many video points, and the workload of video labeling is large, which requires a lot of manpower and time costs. Summary of the invention
[0005] The present application provides a label marking method, device, system, electronic device and storage medium for automatically marking labels corresponding to products and distinguishing different production stages of products on the same production line.
[0006] In order to achieve the above technical objectives, this application adopts the following technical solutions:
[0007] In a first aspect, an embodiment of the present application provides a label marking method, the method comprising:
[0008] Acquire a target image captured by a target camera at a shooting point on a target production line. The target camera is used to capture a production process on the target production line. The production process includes processing a sheet into a roll. The target production line includes products in various forms, including sheets and rolls.
[0009] Identify the target-shaped product in the target image, and annotate the label corresponding to the target-shaped product in the target image, where the label is used to characterize the properties of the product.
[0010] The technical solution provided by the present application brings at least the following beneficial effects: the electronic device automatically identifies products of different forms at different production stages in the target image, and marks the labels corresponding to the products of the target form in the target image. The label marking process is automatically performed by the electronic device, and the user does not need to manually mark the labels in the target image, thereby reducing the manual workload. Since the label represents the properties of the product, the user can quickly and clearly know the property status of each product through the different labels in the target image, distinguish the different production stages of the products on the production line, and know whether the sheet or roll has been produced, so that the user can perform the next operation in time. For example, after identifying the roll, the user can first prepare the packaging materials of the roll, and can directly package the roll after the production is completed, without waiting for the preparation process of the packaging materials, saving the user's time.
[0011] In one possible implementation, a product of a target shape in a target image is identified, and a label corresponding to the product of the target shape is marked in the target image, including: detecting the thickness of a roll in the target image, and if the thickness of the roll is greater than or equal to a preset length, determining that the roll is identified in the target image, and marking the label of the roll in the target image.
[0012] In one possible implementation, detecting the thickness of a roll in a target image includes: identifying a sheet from the target image; starting roll identification when the position of the sheet exceeds a preset area; detecting a radius or diameter of an area at the bottom of the roll in the target image based on a pre-calibrated center position of a circle at the bottom of the roll; and determining the radius or diameter of the area at the bottom of the roll as the thickness of the roll.
[0013] In a possible implementation, the method also includes: obtaining multiple sample images taken by a sample camera, the sample camera is used to shoot the roll, the sample camera is set according to a preset posture, and the shooting picture of the sample camera includes the bottom of the roll; under the preset posture, training a preset algorithm based on the multiple sample images to obtain a trained roll recognition algorithm, so that the target camera used to shoot the roll on the target production line, when set according to the preset posture, can recognize the roll through the roll recognition algorithm.
[0014] In one possible implementation, the attributes of the product include the shape of the product, and the attributes of the product also include at least one of the material, width, thickness of the current roll, target thickness of the roll, current temperature, current humidity, roller speed, time since rolling started, and time required to reach the target thickness.
[0015] In one possible implementation, a plurality of sensors are provided at the production location of the product, and the sensors are used to detect parameters in the product production process; the method further includes: establishing an association relationship between a label corresponding to the product and a target camera that identifies the product in a captured image and a plurality of sensors provided at the product production location; based on target images captured by the plurality of target cameras after labeling, generating and displaying a panoramic image corresponding to the target production line, wherein the panoramic image includes a plurality of labels corresponding to products of different forms.
[0016] In one possible implementation, a product of one form on a target production line corresponds to at least one label; the method also includes: receiving a first selection operation of the user on the target label, the target label being any label included in the panoramic image; in response to the first selection operation, based on the association relationship, displaying a captured image of a target camera associated with the target label, and parameters in the product production process corresponding to the target label measured by each sensor associated with the target label.
[0017] In one possible implementation, the method also includes: receiving a second selection operation of the user for the target production line; in response to the second selection operation, displaying, in sequence, according to the production order of the products on the target production line, the video images taken by the target camera associated with the label corresponding to the product, and the parameters of the product production process measured by each sensor associated with the label corresponding to the product.
[0018] In one possible implementation, the method also includes: when the parameters detected by the sensor associated with the tag exceed the preset parameter range, generating a prompt message and changing the display form of the label in the panoramic image; receiving a third selection operation from the user for the label after the display form is changed; and in response to the third selection operation, displaying the prompt message, the prompt message being used to indicate that the parameters detected by the sensor associated with the tag exceed the preset parameter range.
[0019] In one possible implementation, if a product of the target form is identified in both the first target image and the second target image, the product of the target form is located at a first position in the first target image, and the product of the target form is located at a second position in the second target image, then a label corresponding to the product of the target form in the panoramic image obtained based on the first target image is marked at the first position, and a label corresponding to the product of the target form in the panoramic image obtained based on the second target image is marked at the second position, and the first target image and the second target image are two images of the target production line taken by the same camera at different times.
[0020] In a second aspect, the present application provides a label marking device, including an acquisition module and a processing module;
[0021] The acquisition module is used to acquire a target image captured by a target camera at a shooting point on a target production line. The target camera is used to capture a production process on the target production line. The production process includes processing a sheet into a roll. The target production line includes products in various forms, including sheets and rolls.
[0022] The processing module is used to identify the product of the target shape in the target image, and mark the label corresponding to the product of the target shape in the target image, and the label is used to characterize the property of the product.
[0023] In a possible implementation, the processing module is specifically used to: detect the thickness of the roll in the target image, if the thickness of the roll is greater than or equal to a preset length, determine that the roll is recognized in the target image, and mark a label of the roll in the target image.
[0024] In one possible implementation, the processing module is specifically used to: identify a sheet object from a target image; start to identify a roll object when the position of the sheet object exceeds a preset area; detect the radius or diameter of the bottom area of the roll in the target image based on a pre-calibrated center position of the bottom circle of the roll; and determine the radius or diameter of the bottom area of the roll as the thickness of the roll.
[0025] In one possible implementation, the acquisition module is also used to acquire multiple sample images taken by a sample camera, the sample camera is used to photograph the roll, the sample camera is set according to a preset posture, and the shooting picture of the sample camera includes the bottom of the roll; the processing module is also used to train a preset algorithm based on the multiple sample images under the preset posture to obtain a trained roll recognition algorithm, so that the target camera used to photograph the roll on the target production line can recognize the roll through the roll recognition algorithm when it is set according to the preset posture.
[0026] In one possible implementation, the attributes of the product include the shape of the product, and the attributes of the product also include at least one of the material, width, thickness of the current roll, target thickness of the roll, current temperature, current humidity, roller speed, time since rolling started, and time required to reach the target thickness.
[0027] In a possible implementation, a plurality of sensors are provided at the production location of the product, and the sensors are used to detect parameters in the product production process; the processing module is also used to: establish an association relationship between a label corresponding to the product and a target camera that identifies the product in the captured image and a plurality of sensors provided at the product generation location; based on the target images captured by the plurality of target cameras after labeling, a panoramic image corresponding to the target production line is generated, and the panoramic image includes a plurality of labels corresponding to products of different forms; the label labeling device also includes a display module, and the display module is used to display the panoramic image corresponding to the target generation line.
[0028] In one possible implementation, a product of a certain form on a target production line corresponds to at least one label; the acquisition module is further used to receive a first selection operation of the user on the target label, where the target label is any label included in the panoramic image; the display module is further used to, in response to the first selection operation, display the captured image of the target camera associated with the target label, as well as the parameters of the product production process corresponding to the target label measured by each sensor associated with the target label based on the association relationship.
[0029] In one possible implementation, a second selection operation of the user for the target production line is received; in response to the second selection operation, video images taken by the target camera associated with the label corresponding to the product and parameters in the product production process measured by various sensors associated with the label corresponding to the product are displayed in sequence according to the production order of the products on the target production line.
[0030] In one possible implementation, the processing module is also used to generate a prompt message and change the display form of the label in the panoramic image when the parameters detected by the sensor associated with the tag exceed the preset parameter range; the acquisition module is also used to receive a third selection operation from the user on the label after the display form is changed; the display module is also used to display a prompt message in response to the third selection operation, and the prompt message is used to indicate that the parameters detected by the sensor associated with the tag exceed the preset parameter range.
[0031] In one possible implementation, if a product of the target form is identified in both the first target image and the second target image, the product of the target form is located at a first position in the first target image, and the product of the target form is located at a second position in the second target image, then a label corresponding to the product of the target form in the panoramic image obtained based on the first target image is marked at the first position, and a label corresponding to the product of the target form in the panoramic image obtained based on the second target image is marked at the second position, and the first target image and the second target image are two images of the target production line taken by the same camera at different times.
[0032] In a third aspect, the present application provides a label marking system, including: a target camera and an electronic device; the target camera is used to photograph the production process on the target production line; the electronic device is used to execute any one of the label marking methods provided in the first aspect above.
[0033] In a fourth aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement any one of the labeling methods provided in the first aspect.
[0034] In a fifth aspect, the present application provides a computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement any one of the labeling methods provided in the first aspect above.
[0035] In a sixth aspect, the present application provides a computer program product, including computer instructions, which, when executed by a processor, implement any one of the labeling methods provided in the first aspect above.
[0036] For the specific description of the second to sixth aspects and their various implementations in the present application, reference may be made to the detailed description in the first aspect and its various implementations; and for the beneficial effects of the second to sixth aspects and their various implementations, reference may be made to the beneficial effects analysis in the first aspect and its various implementations, which will not be repeated here.
[0037] These and other aspects of the present application will become more apparent from the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] Figure 1 A structural diagram of a label marking system provided in an embodiment of the present application;
[0039] Figure 2 A schematic diagram of the hardware structure of a computing device provided in an embodiment of the present application;
[0040] Figure 3 A flowchart of a label marking method provided in an embodiment of the present application;
[0041] Figure 4 A schematic diagram of an application scenario of a label marking method provided in an embodiment of the present application Figure 1 ;
[0042] Figure 5 A schematic diagram of an application scenario of a label marking method provided in an embodiment of the present application Figure 2 ;
[0043] Figure 6 A schematic diagram of an application scenario of a label marking method provided in an embodiment of the present application Figure 3 ;
[0044] Figure 7 A schematic diagram of an application scenario of a label marking method provided in an embodiment of the present application Figure 4 ;
[0045] Figure 8 A schematic diagram of an application scenario of a label marking method provided in an embodiment of the present application Figure 5 ;
[0046] Fig. 9A schematic diagram of an application scenario of a label marking method provided in an embodiment of the present application Figure 6 ;
[0047] Fig.10 A schematic diagram of an application scenario of a label marking method provided in an embodiment of the present application Figure 7 ;
[0048] Fig.11 A schematic diagram of the structure of a label marking device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0049] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0050] It should be noted that, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way. The terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present application, unless otherwise specified, "multiple" means two or more.
[0051] In the production workshop, various products in the production process need to be previewed by video. The ordinary preview method can only search for videos for preview by itself, and it is impossible to mark the products in the video.
[0052] In order to improve inspection efficiency, it is necessary to mark the products in the video screen. Currently, this can only be done manually to add labels corresponding to the products in the video screen. However, the workshop situation is complicated, there are many video points, and the workload of video labeling is large, which requires a lot of manpower and time costs.
[0053] In this regard, the embodiment of the present application provides a labeling method, by automatically identifying products of different forms at different production stages in the target image, marking the labels corresponding to the products of the target form in the target image, the labeling process is automatically performed by the electronic device, and the user does not need to manually mark the labels in the target image, thereby reducing the manual workload. Since the label represents the properties of the product, the user can quickly and clearly know the property status of each product through the different labels in the target image, distinguish whether the sheet or roll has been produced on the production line, and then the user can perform the next operation in time, saving the user's time. For example, after identifying the roll, the user sees the label corresponding to the roll marked in the target image, then the user can first prepare the packaging material of the roll, and after the roll is produced, it can be directly packaged without waiting for the preparation process of the packaging material. For another example, after identifying the roll, the user can also prepare the stacking position of the roll, and after the roll is produced, it can be directly placed in the stacking position prepared in advance.
[0054] Please refer to Figure 1 , which shows a schematic diagram of the structure of a label marking system to which the label marking method provided in this application is applicable. Figure 1 As shown, the label marking system 1 may include: a target camera 10 and an electronic device 20 .
[0055] Wherein, a communication connection is established between the target camera 10 and the electronic device 20. It should be understood that the connection method can be a wireless connection, such as a Bluetooth connection, a wireless fidelity (Wi-Fi) connection, etc.; or, the connection method can also be a wired connection, such as an optical fiber connection, etc., which is not limited to this. Exemplarily, the target camera 10 and the electronic device 20 can be connected to the Internet through a router, thereby realizing the communication connection between the target camera 10 and the electronic device 20.
[0056] In some embodiments, the target camera 10 is used to output the captured target image to the electronic device 20. For example, target cameras are set up above the production line of the product, and these target cameras can capture the products on the production line. When labeling is required, the target camera 10 can send the captured target image to the electronic device 20, and then the electronic device 20 detects the target image, determines what kind of product exists in it, and marks the location of the product in the target image with the label corresponding to the product under the target production category corresponding to the production line.
[0057] In some embodiments, the electronic device 20 is used to identify the target image, obtain the product contained in the target image, and mark the label corresponding to the product of the target shape in the target image.
[0058] In some embodiments, the electronic device 20 is further configured to generate and display a panoramic image containing labels based on the target images captured by each target camera after the labels are annotated.
[0059] In some embodiments, the electronic device 20 may include a processor. The processor is used to identify products in the target image, label the target image, and generate a panoramic image. The processor may be a central processing unit (CPU), a general-purpose processor network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof. The processor may also be other devices with processing functions, such as circuits, devices, or software modules, and the embodiments of the present application do not impose any restrictions on this.
[0060] In some embodiments, the labeling system 1 may also include a sensor, which is used to detect parameters in the product production process. For example, the sensor may be a temperature sensor that detects the temperature of the production workshop, or detects the temperature when the product changes form. For another example, the sensor may be a humidity sensor that detects the humidity in the production workshop. For another example, the sensor may also be a photosensitive sensor that can determine whether a product has passed through by the intensity of light received. For another example, the sensor may also be a pressure sensor that can detect whether a product has passed through by changes in pressure. It should be understood that the sensor may also include other devices for detecting parameters in the product production process, and the embodiments of the present application do not impose specific restrictions on this.
[0061] Optionally, the electronic device 20 may further include a memory for storing the target image from the target camera 10, parameters detected by the sensor, etc., and then the processor may retrieve the target image, parameters, etc. from the memory and display them to the user.
[0062] In some embodiments, the electronic device 20 may further include an interactive device, which is used to implement interaction with the user. For example, the interactive device is a display, which can display the panoramic image generated by the electronic device to the user. For another example, the interactive device can receive the user's selection operation of a tag in the panoramic image, and then the electronic device displays the image captured by the target camera 10 associated with the tag selected by the user through the interactive device.
[0063] In some embodiments, the electronic device 20 may also be connected to a prompt device, which is used to display the prompt information generated by the electronic device 20 to the user. For example, the prompt device is a speaker, and when the parameter detected by the sensor exceeds the preset parameter threshold, the electronic device generates prompt information in text form, and then the electronic device controls the speaker to play the audio of the prompt information in text form. For another example, the prompt device may be a display, and the electronic device generates prompt information in image form, and then the electronic device controls the display to display the prompt information in image form.
[0064] In some embodiments, the target camera 10 and the electronic device 20 may be as follows: Figure 1 As shown, they are two independent devices, or the target camera 10 and the electronic device 20 can be integrated into the same device.
[0065] In some embodiments, the labeling system 1 may include one or more target cameras 10 .
[0066] In some embodiments, the target camera 10 may be any device capable of capturing images, such as a video camera, a still camera, a ball camera, etc. The embodiment of the present application does not limit the specific form of the target camera 10.
[0067] In some embodiments, the electronic device 20 may be a single server or a server cluster, or the electronic device 20 may be a terminal device, such as a personal computer (PC), a notebook computer, a mobile device, a tablet computer, a laptop computer, etc. The specific form of the electronic device 20 is not limited in the embodiments of the present application.
[0068] The hardware structure of the electronic device 20 includes: Figure 2 The computing device shown in FIG. Figure 2 Taking the computing device shown as an example, the hardware structure of the electronic device 20 is introduced.
[0069] like Figure 2 As shown, the computing device may include a processor 201, a memory 202, a communication interface 203, and a bus 204. The processor 201, the memory 202, and the communication interface 203 may be connected via a bus 204.
[0070] The processor 201 is the control center of the computing device, and can be a processor or a general term for multiple processing elements. For example, the processor 201 can be a general-purpose central processing unit (CPU) or other general-purpose processors. Among them, the general-purpose processor can be a microprocessor or any conventional processor.
[0071] As an embodiment, the processor 201 may include one or more CPUs, such as Figure 2 CPU 0 and CPU 1 are shown in .
[0072] The memory 202 may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.
[0073] In a possible implementation, the memory 202 may exist independently of the processor 201, and the memory 202 may be connected to the processor 201 via a bus 204 to store instructions or program codes. When the processor 201 calls and executes the instructions or program codes stored in the memory 202, the model deployment method provided in the embodiment of the present application can be implemented.
[0074] In another possible implementation, the memory 202 may also be integrated with the processor 201 .
[0075] The communication interface 203 is used for connecting the computing device to other devices through a communication network, which may be Ethernet, a radio access network (RAN), a wireless local area network (WLAN), etc. The communication interface 203 may include a receiving unit for receiving data and a sending unit for sending data.
[0076] The bus 204 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0077] It should be pointed out that Figure 2 The structure shown in the figure does not constitute a limitation on the computing device, except Figure 2 In addition to the components shown, the computing device may include more or fewer components than shown, or combine certain components, or arrange the components differently.
[0078] The implementation of the embodiments of the present application will be described in detail below with reference to the accompanying drawings.
[0079] The label marking method provided in the embodiment of the present application can be executed by the electronic device 20 in the label marking system 1, and the application scenario of the present application is a scenario in which a sheet-like object is processed into a roll-like object. For example, the application scenario of the present application can be the production process of electrical steel, where the raw materials are first converted into steel sheets and then rolled into steel rolls, or it can be the production scenario of other metal materials. For another example, the application scenario of the present application can also be the production process of paper rolls, where the raw materials are first converted into paper sheets and then rolled into paper rolls. For another example, the application scenario of the present application can also be the production process of plastic film, where the raw materials are first converted into plastic film sheets and then rolled into plastic film rolls.
[0080] like Figure 3 As shown, the embodiment of the present application provides a label marking method, which includes the following steps:
[0081] S101, obtaining a target image captured by a target camera at a shooting point on a target production line.
[0082] The target camera is used to shoot the production process on the target production line. The production process includes processing sheets into rolls. The target production line contains products in various forms, including sheets and rolls.
[0083] For example, the target production line may be a steel coil production line, where raw materials are produced into steel sheets, the steel sheets are rolled into steel coils, and the steel coils are then stacked at a preset location.
[0084] In some embodiments, each form of product may correspond to multiple cameras with different shooting points and angles of view. For example, the target production line is a steel coil production line, and the products in the target production line include steel sheets and steel coils. Figure 4 , multiple images of the production location of a steel sheet X (hereinafter and in the drawings of the specification, X represents a steel sheet) at multiple shooting points and different shooting angles are shown. Figure 5 , multiple images of the production location of a steel coil Y (Y in the following text and in the drawings of the specification represents a steel coil) at multiple shooting points and different shooting angles are shown.
[0085] S102: Identify a product of a target shape in a target image, and mark a label corresponding to the product of the target shape in the target image.
[0086] In some embodiments, the label is an editable control, and the specific display form can be text, image, etc.
[0087] In some embodiments, step S102 can be specifically implemented as follows: the electronic device detects the thickness of the roll in the target image, and if the thickness of the roll is greater than or equal to a preset length, determines that the roll is recognized in the target image, and marks a label of the roll in the target image.
[0088] Specifically, the thickness of the roll can be characterized by the radius or diameter of the bottom of the roll. The electronic device detects the thickness of the roll in the target image, which can be specifically implemented as follows: the electronic device detects the radius or diameter of the bottom area of the roll in the target image based on the pre-calibrated center position of the bottom of the roll; and determines the radius or diameter of the bottom area of the roll as the thickness of the roll.
[0089] For example, the bottom center of the rolled object is pre-marked in the shooting picture of camera a, such as Figure 6 As shown, Figure 6 The middle dot is the center of the bottom of the coil, and the electronic equipment detects the radius of the bottom of the coil. Figure 6 The middle dotted line shows a radius at the bottom of the steel coil. If the measured radius exceeds the preset length, it means that the steel coil has been rolled to a certain thickness. For example, the preset length is 15 cm, and the electronic device measures the radius of the bottom of the steel coil to be 20 cm. The electronic device can determine that the steel coil has been detected, and then the electronic device marks the position of the steel coil in the image with a label Y corresponding to the steel coil.
[0090] It should be understood that when the thickness of the roll is characterized by the radius of the bottom of the roll, it corresponds to a first preset length, and when the radius of the bottom of the roll is greater than the first preset length, it is determined that the roll is recognized in the target image; when the thickness of the roll is characterized by the diameter of the bottom of the roll, it corresponds to a second preset length, and when the diameter of the bottom of the roll is greater than the second preset length, it is determined that the roll is recognized in the target image; then the second preset length should be twice the first preset length.
[0091] In this way, by setting a preset length to compare the radius of the bottom area of the roll, the electronic device can determine whether the thickness of the roll reaches the preset thickness. When the thickness of the roll reaches the preset thickness, the identification result of the roll is more accurate.
[0092] In some embodiments, the electronic device identifies a sheet from a target image; when the location of the sheet exceeds a preset area, the electronic device begins to identify a roll. The target image for identifying the sheet is the same as or different from the target image for identifying the roll. For example, some cameras have a large shooting angle, and such cameras can capture both sheets and rolls in the same production line. The electronic device can identify sheets and rolls in an image captured by such cameras based on the image.
[0093] For example, the sheet is a steel sheet, the roll is a steel coil, camera a is set up at the steel sheet production location, camera b is set up at the steel coil production location, the electronic device identifies the sheet from the image taken by camera a, and the electronic device marks the label X corresponding to the steel sheet at the location of the sheet in the image taken by camera a. If the sheet exceeds the preset area, such as Figure 7 As shown, the steel sheet has crossed the position of the dotted line marked in the figure, that is, the steel sheet has exceeded the preset area, indicating that the steel sheet has reached the position of the coiled steel sheet. At this time, the electronic device can start to identify the steel coil, and then the electronic device identifies the image taken by camera b.
[0094] In this way, when a sheet object is detected and the position of the sheet object exceeds the preset area, the electronic device starts to identify the roll object. The electronic device does not need to run the roll object identification algorithm all the time, which can save some computing power resources.
[0095] In some embodiments, the electronic device obtains multiple sample images taken by a sample camera, the sample camera is used to shoot rolls, the sample camera is set according to a preset posture, and the shooting picture of the sample camera includes the bottom of the roll; the electronic device trains a preset algorithm based on the multiple sample images at the preset posture to obtain a trained roll recognition algorithm, so that the target camera used to shoot rolls on the target production line can recognize the roll through the roll recognition algorithm when it is set according to the preset posture.
[0096] Optionally, the method for the electronic device to detect the radius of the bottom of the steel coil can be that the user pre-acquires multiple images with calibrated lengths of the radius of the bottom of the steel coil, trains these images to obtain a radius recognition model for outputting the radius of the bottom of the steel coil, and then deploys the trained radius recognition model to the electronic device. After the electronic device acquires the image of the bottom of the steel coil, it uses the trained radius recognition model to identify the radius of the bottom of the steel coil in the image. The method for the electronic device to detect the diameter of the bottom of the steel coil is logically the same as the method for the electronic device to detect the radius of the bottom of the steel coil, which will not be repeated here.
[0097] Optionally, the shooting posture of the target camera used to shoot the roll may not be facing the bottom of the roll. The principle of roll recognition is: if a cylinder is recognized from the image, the radius of the bottom of the cylinder is determined, and then it is judged whether the radius exceeds a preset length. If the radius is greater than or equal to the preset length, the electronic device determines that a roll is recognized in the image.
[0098] Optionally, when the optical axis of the camera used to photograph the bottom of the steel coil is perpendicular to the plane where the bottom of the steel coil is located, if the camera installation position and shooting posture are pre-set, and the position of the center of the bottom of the steel coil in the image taken by the camera is pre-marked, the user can measure the pixel distances corresponding to radii of different lengths in the image taken by the camera in advance, and store the correspondence between the measured pixel distances and the radius lengths in the electronic device. When the electronic device obtains the image of the bottom of the steel coil, the electronic device can finally determine the radius length of the bottom of the steel coil captured in the image based on the pixel distance between the pixel points on the boundary of the bottom of the steel coil and the pixel points corresponding to the pre-marked center of the bottom of the steel coil, as well as the correspondence between the pixel distance and the radius length. The logic for determining the diameter length of the bottom of the steel coil is similar and will not be repeated here.
[0099] In some embodiments, the properties of the product include the shape of the product, and the properties of the product also include at least one of the material, width, thickness of the current roll, target thickness of the roll, current temperature, current humidity, roller speed, time since rolling started, and time required to reach the target thickness.
[0100] In some embodiments, a product of a certain form on a target production line corresponds to at least one label. For example, if the length of a steel sheet is relatively long, multiple labels X may be marked in the area where the steel sheet is located in the target image.
[0101] In some embodiments, a plurality of sensors are provided at the production location of the product, and the sensors are used to detect parameters in the product production process; the electronic device also establishes an association relationship between the label corresponding to the product and the target camera that recognizes the product in the captured image and the plurality of sensors provided at the product generation location, and then the electronic device can generate and display a panoramic image corresponding to the target production line based on the target images captured by the plurality of target cameras after the labeling, wherein the panoramic image includes a plurality of labels corresponding to products of different forms.
[0102] For example, camera 1 and camera 2 are both used to shoot steel sheets. The location of the steel sheet in the panoramic image is marked with a label X corresponding to the steel sheet. Temperature sensor a, humidity sensor b, and pressure sensor c are all used to collect relevant parameters of the steel sheet. The electronic device then establishes an association between label X and camera 1, camera 2, temperature sensor a, humidity sensor b, and pressure sensor c. When the user selects label X in the panoramic image, the electronic device determines that the steel sheet is associated with camera 1, camera 2, temperature sensor a, humidity sensor b, and pressure sensor c based on the association relationship, and then the electronic device displays the images taken by camera 1 and camera 2, respectively, as well as the parameters measured by temperature sensor a, humidity sensor b, and pressure sensor c. The electronic device can also display the material of the steel sheet, the width of the steel sheet, the length of time the steel sheet has been generated, and so on. When the user selects label Y in the panoramic image, the electronic device determines the cameras and sensors associated with the steel coil based on the association relationship, and then displays the shooting images of each camera associated with the steel coil, the parameters measured by each associated sensor, the current thickness of the steel coil identified by the electronic device, the preset target thickness of the steel coil, the roller speed during steel coil production, the length of time the steel coil has been rolled, and the time predicted by the electronic device for the steel coil to reach the target thickness.
[0103] In this way, the label corresponding to the product is associated with the target camera that photographs the product and multiple sensors corresponding to the product. Then, the electronic device can display the images and measured parameters of the product production process based on the target camera and sensor associated with the label, so that users can have a further understanding of the product production process.
[0104] In some embodiments, one or more production lines may be included in the panoramic image.
[0105] For a panoramic picture of a production line in a panoramic image, if a plurality of target cameras with different shooting points and shooting angles are set up at the production position of each product in the production line, then when generating a panoramic image corresponding to the production line, a target camera is determined from the target cameras associated with each product, and a panoramic picture corresponding to the production line is generated based on the picture taken by the determined target camera corresponding to each product.
[0106] For example, the production line is a steel coil production line, which includes four product generation nodes: the raw material delivery point, the steel sheet production point, the steel coil production point and the steel coil stacking point. Cameras 1 and 2 are set up at the raw material delivery point, cameras 3, 4 and 5 are set up at the steel sheet production point, cameras 6, 7 and 8 are set up at the steel coil production point, and cameras 9 and 10 are set up at the steel coil stacking point. When generating the panoramic picture corresponding to the production line, select one camera from the cameras set up at the raw material delivery point (assuming that camera 1 is selected), select one camera from the cameras set up at the steel sheet production point (assuming that camera 4 is selected), select one camera from the cameras set up at the steel coil production point (assuming that camera 8 is selected), and select one camera from the cameras set up at the steel coil stacking point (assuming that camera 10 is selected). Then, the panoramic picture corresponding to the production line is generated based on the pictures taken by camera 1, camera 4, camera 8 and camera 10 respectively.
[0107] In some embodiments, if a product of the target form is identified in both the first target image and the second target image, the product of the target form is located at a first position in the first target image, and the product of the target form is located at a second position in the second target image, then a label corresponding to the product of the target form in the panoramic image obtained based on the first target image is marked at the first position, and a label corresponding to the product of the target form in the panoramic image obtained based on the second target image is marked at the second position, and the first target image and the second target image are two images of the target production line taken by the same camera at different times.
[0108] For example, Figure 8 The panoramic image 1 generated based on the first target image is shown. The electronic device marks a label X corresponding to the steel sheet at the first position of the panoramic image 1. If the steel sheet moves from the first position to the second position after a period of time, the second target image captured at this time generates a panoramic image 2, as shown in FIG. Fig. 9 As shown, the position of the label X marked by the electronic device in the panoramic image 2 is at the second position in the panoramic image 2 .
[0109] In this way, the position of the label and the position of the product must overlap. When a user sees the label, he or she is seeing the product, and the correlation between the label and the product is stronger.
[0110] In some embodiments, the electronic device receives a first selection operation of a target tag by a user, where the target tag is any tag included in the panoramic image; the electronic device responds to the first selection operation, based on the association relationship, by displaying a captured image of a target camera associated with the target tag, as well as parameters in a product production process corresponding to the target tag measured by various sensors associated with the target tag.
[0111] For example, Fig. 9The panoramic image 2 shown includes a label X corresponding to the steel sheet and a label Y corresponding to the steel coil. Label X is associated with camera a and camera b, as well as temperature sensor c and humidity sensor d. If the user clicks on label X, the electronic device determines the camera and sensor associated with label X based on the association relationship of label X, such as Fig.10 As shown, the electronic device displays a display page of the camera images and sensor-measured parameters associated with tag X, including images taken by camera a and camera b respectively, the temperature value measured by temperature sensor c, and the humidity value measured by humidity sensor d.
[0112] In this way, the cameras and sensors related to the product are associated with the tags corresponding to the product. The user only needs to select the tag corresponding to the product he wants to view to obtain the images and parameters of the product's production process, making it convenient for the user to view and manage the product.
[0113] In some embodiments, the electronic device can also receive a second selection operation of the user on the target production line; then, in response to the second selection operation, the electronic device displays the video images taken by the target camera associated with the label corresponding to the product, and the parameters of the product production process measured by each sensor associated with the label corresponding to the product, in sequence, according to the production order of the products on the target production line.
[0114] Exemplarily, the panoramic image includes production line 1, production line 2 and production line 3. If the user wants to view the production process of the products in production line 3, the user's second selection operation for production line 3 can be an operation in which the user inputs the identification information corresponding to production line 3 in the electronic device, or an operation in which the user directly clicks on the control corresponding to production line 3. Then the electronic device displays the images taken by the camera associated with the labels corresponding to the products on production line 3 and the parameters measured by the sensor in sequence according to the production order of the products on production line 3.
[0115] In this way, the user only needs to enter the target information category corresponding to the production line he wants to view, and the electronic device can automatically display the production process of each product on the production line to meet the user's inspection needs for the products on the production line.
[0116] In some embodiments, when the parameters detected by the sensor associated with the tag exceed the preset parameter range, the electronic device generates a prompt message and changes the display form of the label in the panoramic image; the electronic device receives a third selection operation from the user on the label after the display form is changed; the electronic device displays the prompt message in response to the third selection operation, and the prompt message is used to indicate that the parameters detected by the sensor associated with the tag exceed the preset parameter range.
[0117] Changing the label display form may include changing the label size, color, brightness, lines, etc. For example, changing the label from a first color to a second color, flashing the label, increasing the label brightness, adding a dotted frame to the label, etc. It is also possible to change whether the label is expanded or not. When the user chooses to expand the label, the detailed information of the label is displayed. If the user chooses to collapse the label, only the abbreviated information of the label is displayed, and the detailed information of the label is not displayed.
[0118] Exemplarily, a temperature sensor is provided on the steel sheet transmission track, and the label corresponding to the steel sheet in the panoramic image is associated with this temperature sensor. If the preset temperature threshold is 100°C, and the temperature measured by the temperature sensor is 120°C, then the electronic device receives the temperature value measured by the temperature sensor, determines that it exceeds the preset temperature threshold, and generates a prompt message "The temperature of the steel sheet transmission track is 120°C, which exceeds the preset temperature threshold. Please check the cause of the high temperature!" At the same time, the label prompts the user by changing color, flashing, adding a border, etc. For example, if the label is blue, the electronic device changes the color of the label to red after determining that it exceeds the preset temperature threshold. When the user clicks the red label, the electronic device displays the generated prompt message.
[0119] In some embodiments, when the electronic device detects that the length of the bottom radius of the roll reaches the target length, the electronic device generates target prompt information and changes the display form of the roll label in the panoramic image. The electronic device receives a third selection operation from the user on the roll label after the display form is changed, and displays target prompt information in response to the third selection operation. The target prompt information is used to indicate that the roll on the current production line has been completed, so as to prompt the user to place the completed roll to a specific location.
[0120] For example, the target length is 1m, the electronic device obtains the image taken by the camera used to shoot the bottom of the roll, and recognizes that the radius length of the bottom of the roll in the image is 0.8m. At this time, the label corresponding to the roll in the panoramic image is blue, and the electronic device continues to identify each frame of the image taken by the camera used to shoot the bottom of the roll. When the electronic device detects that the radius length of the bottom of the roll is 1m, the electronic device controls the label corresponding to the roll to change to red, and generates a text prompt message "Roll production completed". When the user clicks the red roll label, the electronic device displays the text prompt message "Roll generation completed".
[0121] In this way, by changing the display form of the label, the user can quickly know the product with abnormal conditions. When the user selects the label with the changed display form, the electronic device can display prompt information, so that the user can know in detail what abnormal conditions have occurred in the product, and the user can manage the production process of the product in time.
[0122] Figure 3 The technical solution shown at least brings the following beneficial effects: by automatically identifying products of different forms at different production stages in the target image, marking the labels corresponding to the products of the target form in the target image, the label marking process is automatically performed by the electronic device, and the user does not need to manually mark the labels in the target image, thereby reducing the manual workload. Since the label represents the properties of the product, the user can quickly and clearly know the property status of each product through the different labels in the target image, and distinguish whether the sheet or roll has been produced on the production line, and then the user can perform the next operation in time, saving the user's time. For example, after identifying the roll, the user sees the label corresponding to the roll marked in the target image, and the user can first prepare the packaging material of the roll, and can directly package it after the roll is produced, without waiting for the preparation process of the packaging material. For another example, after identifying the roll, the user can also prepare the stacking position of the roll, and can directly place it in the stacking position prepared in advance after the roll is produced.
[0123] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. In order to achieve the above functions, it includes hardware structures and / or software modules corresponding to the execution of each function. It should be easy to realize that the technical goals in this field are combined with the units and algorithm steps of each example described in the embodiments disclosed in this article, and the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical goals can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0124] like Fig.11 As shown, the embodiment of the present application further provides a label marking device, which is used to execute the label marking method shown in the above method embodiment. The label marking device 400 includes: an acquisition module 401, a processing module 402 and a display module 403.
[0125] Among them, the acquisition module 401 is used to obtain the target image captured by the target camera at the shooting point on the target production line. The target camera is used to capture the production process on the target production line. The production process includes processing the sheet into a roll. The target production line includes products in various forms, and the products in various forms include sheets and rolls. The processing module 402 is used to identify the product of the target form in the target image, and mark the label corresponding to the product of the target form in the target image, and the label is used to characterize the properties of the product.
[0126] In a possible implementation, the processing module 402 is specifically used to: detect the thickness of the roll in the target image, if the thickness of the roll is greater than or equal to a preset length, determine that the roll is recognized in the target image, and mark a label of the roll in the target image.
[0127] In another possible implementation, the processing module 402 is specifically used to: identify a sheet object from a target image; start to identify a roll object when the position of the sheet object exceeds a preset area; detect the radius or diameter of the bottom area of the roll in the target image based on a pre-calibrated center position of the bottom circle of the roll; and determine the radius or diameter of the bottom area of the roll as the thickness of the roll.
[0128] In another possible implementation, the acquisition module 401 is also used to acquire multiple sample images taken by a sample camera, the sample camera is used to photograph the roll, the sample camera is set according to a preset posture, and the shooting picture of the sample camera includes the bottom of the roll; the processing module 402 is also used to train a preset algorithm based on the multiple sample images at a preset posture to obtain a trained roll recognition algorithm, so that the target camera used to photograph the roll on the target production line can recognize the roll through the roll recognition algorithm when it is set according to the preset posture.
[0129] In another possible implementation, the attributes of the product include the shape of the product, and the attributes of the product also include at least one of the material, width, thickness of the current roll, target thickness of the roll, current temperature, current humidity, roller speed, time since rolling started, and time required to reach the target thickness.
[0130] In another possible implementation, a plurality of sensors are provided at the production location of the product, and the sensors are used to detect parameters in the product production process; the processing module 402 is also used to: establish an association relationship between the label corresponding to the product and the target camera that identifies the product in the captured image and the plurality of sensors provided at the product generation location; based on the target images captured by the plurality of target cameras after labeling, generate a panoramic image corresponding to the target production line, and the panoramic image includes a plurality of labels corresponding to products of different forms; the display module 403 is used to display the panoramic image corresponding to the target generation line.
[0131] In another possible implementation, a product of a certain form on a target production line corresponds to at least one label; the acquisition module 401 is also used to receive a first selection operation of the user on the target label, where the target label is any label included in the panoramic image; the display module 403 is also used to, in response to the first selection operation, display the captured image of the target camera associated with the target label, and the parameters of the product production process corresponding to the target label measured by each sensor associated with the target label based on the association relationship.
[0132] In another possible implementation, a second selection operation of the user for the target production line is received; in response to the second selection operation, video images taken by the target camera associated with the label corresponding to the product and parameters in the product production process measured by various sensors associated with the label corresponding to the product are displayed in sequence according to the production order of the products on the target production line.
[0133] In another possible implementation, the processing module 402 is also used to generate a prompt message and change the display form of the label in the panoramic image when the parameters detected by the sensor associated with the tag exceed the preset parameter range; the acquisition module 401 is also used to receive a third selection operation from the user on the label after the display form is changed; the display module 403 is also used to display a prompt message in response to the third selection operation, and the prompt message is used to indicate that the parameters detected by the sensor associated with the tag exceed the preset parameter range.
[0134] In another possible implementation, if a product of the target form is identified in both the first target image and the second target image, the product of the target form is located at a first position in the first target image, and the product of the target form is located at a second position in the second target image, then the label corresponding to the product of the target form in the panoramic image obtained based on the first target image is marked at the first position, and the label corresponding to the product of the target form in the panoramic image obtained based on the second target image is marked at the second position, and the first target image and the second target image are two images obtained by the same camera taking pictures of the target production line at different times.
[0135] It should be noted that Fig.11 The division of modules in the example is schematic and is only a logical function division. There may be other division methods in actual implementation. For example, two or more functions may be integrated into one processing module. The above integrated modules may be implemented in the form of hardware or software function modules.
[0136] Another embodiment of the present application further provides an electronic device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the label marking method shown in the above embodiment.
[0137] In actual implementation, the acquisition module 401, the processing module 402 and the display module 403 can be implemented by the processor of the electronic device calling the computer program code in the memory. The specific execution process can refer to the description of the label marking method part above, which will not be repeated here.
[0138] Another embodiment of the present application further provides a computer-readable storage medium, on which computer instructions are stored. When the computer instructions are executed by a processor, the steps of the label marking method shown in the above embodiment are implemented.
[0139] In another embodiment of the present application, a computer program product is provided. The computer program product includes computer instructions. When the computer instructions are executed by a processor, the steps of the label marking method shown in the above embodiment are implemented.
[0140] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using a software program, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer execution instruction is 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 device. The computer instruction 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 instruction can be transmitted from a website site, computer, server or 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 can be accessed by the computer or a data storage device such as a server, data center, etc. that contains one or more servers that can be integrated with the medium. 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), etc.
[0141] The above are only specific implementations of the present application. Those skilled in the art may conceive of changes or substitutions based on the specific implementations provided by the present application, which should all be included in the protection scope of the present application.
Claims
1. A label marking method, characterized in that: include: Acquire a target image captured by a target camera at a shooting point on a target production line, wherein the target camera is used to capture a production process on the target production line, wherein the production process includes processing a sheet into a roll, and wherein the target production line includes products in various forms, wherein the products in various forms include sheets and rolls; A product of a target shape in the target image is identified, and a label corresponding to the product of the target shape is marked in the target image, wherein the label is used to characterize a property of the product.
2. The method according to claim 1, characterized in that The step of identifying a product of a target shape in the target image and marking a label corresponding to the product of the target shape in the target image includes: The thickness of the roll in the target image is detected. If the thickness of the roll is greater than or equal to a preset length, it is determined that the roll is recognized in the target image, and a label of the roll is marked in the target image.
3. The method according to claim 2, characterized in that The detecting the thickness of the rolled object in the target image comprises: identifying the sheet-like object from the target image; When the position of the sheet object exceeds the preset area, the roll object recognition starts; Based on the pre-calibrated center position of the bottom of the roll, detecting the radius or diameter of the bottom area of the roll in the target image; The radius or diameter of the bottom area of the roll is determined as the thickness of the roll.
4. The method according to claim 3, characterized in that The method further comprises: Acquire a plurality of sample images taken by a sample camera, wherein the sample camera is used to photograph the roll-like object, the sample camera is set according to a preset posture, and the photographed image of the sample camera includes the bottom of the roll-like object; Under the preset posture, the preset algorithm is trained based on the multiple sample images to obtain a trained roll recognition algorithm, so that the target camera used to shoot the roll on the target production line can recognize the roll through the roll recognition algorithm when it is set according to the preset posture.
5. The method according to any one of claims 1 to 4, characterized in that: The attributes of the product include the shape of the product, and the attributes of the product also include at least one of the material, width, thickness of the current roll, target thickness of the roll, current temperature, current humidity, roller speed, time since rolling started, and time required to reach the target thickness.
6. The method according to claim 1, characterized in that A plurality of sensors are provided at the production position of the product, and the sensors are used to detect parameters in the production process of the product; the method further comprises: Establishing an association relationship between the label corresponding to the product, a target camera that identifies the product in the captured image, and a plurality of sensors set at the product generation location; Based on the target images captured by the multiple target cameras after being labeled, a panoramic image corresponding to the target production line is generated and displayed, wherein the panoramic image includes multiple labels corresponding to products of different forms.
7. The method according to claim 6, characterized in that A product of one form on the target production line corresponds to at least one label; The method further comprises: receiving a first selection operation of a target tag by a user, wherein the target tag is any tag included in the panoramic image; In response to the first selection operation, based on the association relationship, a shooting picture of the target camera associated with the target tag and parameters in the production process of the product corresponding to the target tag measured by each sensor associated with the target tag are displayed.
8. The method according to claim 6, characterized in that The method further comprises: receiving a second selection operation of the user on the target production line; In response to the second selection operation, the video images taken by the target camera associated with the label corresponding to the product and the parameters in the production process of the product measured by each sensor associated with the label corresponding to the product are displayed in sequence according to the production order of the products on the target production line.
9. The method according to claim 6, characterized in that The method further comprises: When the parameter detected by the sensor associated with the tag exceeds a preset parameter range, a prompt message is generated, and a display form of the tag in the panoramic image is changed; Receiving a third selection operation from the user on the label after the display form is changed; In response to the third selection operation, prompt information is displayed, where the prompt information is used to indicate that the parameter detected by the sensor associated with the tag exceeds a preset parameter range.
10. The method according to claim 6, characterized in that If a product of target form is identified in both the first target image and the second target image, and the product of target form is located at a first position in the first target image, and the product of target form is located at a second position in the second target image, then a label corresponding to the product of target form in the panoramic image obtained based on the first target image is marked at the first position, and a label corresponding to the product of target form in the panoramic image obtained based on the second target image is marked at the second position, and the first target image and the second target image are two images obtained by the same camera taking pictures of the target production line at different times.
11. A label marking device, characterized in that: Includes an acquisition module and a processing module; The acquisition module is used to acquire a target image captured by a target camera at a shooting point on a target production line, wherein the target camera is used to capture a production process on the target production line, wherein the production process includes processing a sheet into a roll, and wherein the target production line includes products in various forms, wherein the products in various forms include sheets and rolls; The processing module is used to identify a product of a target form in the target image, and mark a label corresponding to the product of the target form in the target image, wherein the label is used to characterize a property of the product.
12. A label marking system, characterized in that: include: Target cameras and electronics; The target camera is used to photograph the production process on the target production line; The electronic device is used to execute the method described in any one of claims 1 to 10.
13. An electronic device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 10.
14. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the computer instructions are executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.
15. A computer program product comprising computer instructions, characterized in that When the computer instructions are executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.
Citation Information
Patent Citations
Coil shape detection device and method based on hot rolled steel coil end face three-dimensional point cloud
CN115100118A
Automatic object marking method and system
CN118247695A
System and method for preventing loss of personal information security and biometric data for monitoring biometric data
KR1020240007545A
Identification tag and related identification tag system
US20050108912A1
Augmented reality for sensor applications
US20180253876A1
