A method, device, equipment and storage medium for generating monitoring deployment points

Abstract

The embodiments of the present application provide a method, device, equipment and storage medium for generating monitoring deployment points, which relate to the field of artificial intelligence technology, including: obtaining a grain warehouse image; performing object recognition on the grain warehouse image to obtain different types of target objects; determining the monitoring deployment points of each target object in the grain warehouse image according to the monitoring deployment rules of each target object, and setting the annotation information of each monitoring deployment point in the grain warehouse image. In the embodiments of the present application, by performing object recognition on the grain warehouse image, the different types of target objects in the grain warehouse image can be accurately identified, so that monitoring deployment can be performed according to the target objects in the subsequent process; by monitoring and deploying the target objects according to the monitoring deployment rules of the target objects, it is no longer necessary to manually monitor and deploy the target objects, thereby improving the efficiency and accuracy of the monitoring deployment.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method, device, equipment and storage medium for generating monitoring deployment points. Background Art

[0002] As food safety supervision requirements become increasingly stringent, governments at all levels are paying more and more attention to the grain industry, and are tracking and supervising the entire chain of grain storage, storage, and transportation. Especially in the grain storage stage, due to the long time, strict supervision is required for the grain storage stage. Therefore, it is necessary to deploy monitoring in the grain depot to achieve supervision of the grain depot.

[0003] However, currently, monitoring of grain depots is usually done by installing monitoring equipment in a corner of the depot, but there is no relevant technical support for where to install monitoring equipment in the depot. In addition, when installing monitoring equipment in a grain depot, if the layout point map is not clear, it is impossible to accurately install the monitoring equipment according to the preset rules. Summary of the invention

[0004] The embodiments of the present application provide a method, apparatus, device and storage medium for generating monitoring deployment points, which can improve the efficiency of monitoring deployment points.

[0005] In a first aspect, an embodiment of the present application provides a method for generating monitoring deployment points, including:

[0006] Get images of grain depots;

[0007] Performing object recognition on the grain depot image to obtain different types of target objects;

[0008] According to the monitoring layout rules for each target object, the monitoring layout points of each target object in the grain warehouse image are determined, and the annotation information of each monitoring layout point is set in the grain warehouse image.

[0009] In an embodiment of the present application, by performing object recognition on the grain warehouse image, different types of target objects in the grain warehouse image can be accurately identified so that monitoring can be subsequently deployed according to the target objects; by monitoring the target objects according to the monitoring deployment rules of the target objects, it is no longer necessary to manually monitor the target objects, thereby improving the efficiency and accuracy of the monitoring deployment.

[0010] Optionally, determining the monitoring layout point of each target object in the grain depot image according to the monitoring layout rule of each target object includes:

[0011] For any target object, if the monitoring layout rule of the target object is a required attribute, the monitoring layout point of the target object in the grain warehouse image is determined according to the monitoring function indicated by the monitoring layout rule of the target object.

[0012] In the embodiment of the present application, when the attribute of the monitoring deployment rule of the target object is a required attribute, monitoring deployment is performed on the target object to avoid missing the monitoring deployment of the target object, thereby improving the accuracy of the monitoring deployment.

[0013] Optionally, determining the monitoring layout point of each target object in the grain depot image according to the monitoring layout rule of each target object includes:

[0014] For any target object, if the monitoring layout rule of the target object is an optional attribute, it is determined whether the monitoring layout points set in the grain warehouse image meet the monitoring function indicated by the monitoring layout rule of the target object. If not, monitoring layout points that meet the monitoring function are set in the grain warehouse image.

[0015] In the embodiment of the present application, when the attributes of the monitoring deployment rules of the target object are optional attributes, the monitoring deployment of the target object can be performed according to the actual situation, thereby improving the flexibility of the monitoring deployment.

[0016] Optionally, before performing object recognition on the grain depot image, the method further includes:

[0017] The grain warehouse image is enhanced by an image processing model; the loss function corresponding to the image processing model is determined by a first loss value corresponding to the pixel value and a second loss value corresponding to the structural similarity.

[0018] In the embodiment of the present application, the grain warehouse image is made clearer through image processing, and the target object of the grain warehouse image can be identified more accurately, thereby avoiding the problem of incorrect monitoring deployment due to incorrect target object identification.

[0019] Optionally, after setting the annotation information of each monitoring deployment point in the grain depot image, the method further includes:

[0020] Displays images of grain depots with labeled information;

[0021] For any marked information, the marked information is operated, and the modified grain warehouse image with the marked information is saved.

[0022] In an embodiment of the present application, after displaying a grain warehouse image with annotation information, the annotation information can be modified. By modifying the annotation information, the monitoring layout of the target object can be changed, thereby improving the flexibility of the monitoring layout.

[0023] Optionally, the operating any annotation information includes:

[0024] Get the trigger instruction for any annotation information;

[0025] Based on the trigger instruction, display at least one operation button;

[0026] In response to an operation on at least one operation button, the annotation information is operated.

[0027] In the embodiment of the present application, by obtaining a trigger instruction, the marking information can be operated, and the monitoring deployment can be operated by operating the marking information, thereby improving the flexibility of the monitoring deployment.

[0028] In a second aspect, an embodiment of the present application provides a device for generating monitoring deployment points, including:

[0029] An acquisition module is used to acquire images of grain depots;

[0030] A processing module is used to perform object recognition on the grain depot image to obtain different types of target objects;

[0031] The determination module is used to determine the monitoring layout points of each target object in the grain warehouse image according to the monitoring layout rules of each target object, and set the annotation information of each monitoring layout point in the grain warehouse image.

[0032] Optionally, the determining module is specifically used to:

[0033] For any target object, if the monitoring layout rule of the target object is a required attribute, the monitoring layout point of the target object in the grain warehouse image is determined according to the monitoring function indicated by the monitoring layout rule of the target object.

[0034] Optionally, the determining module is specifically used to:

[0035] For any target object, if the monitoring layout rule of the target object is an optional attribute, it is determined whether the monitoring layout points set in the grain warehouse image meet the monitoring function indicated by the monitoring layout rule of the target object. If not, monitoring layout points that meet the monitoring function are set in the grain warehouse image.

[0036] Optionally, the processing module is specifically used for:

[0037] The grain warehouse image is enhanced by an image processing model; the loss function corresponding to the image processing model is determined by a first loss value corresponding to the pixel value and a second loss value corresponding to the structural similarity.

[0038] Optionally, the determining module is further used for:

[0039] Displays images of grain depots with labeled information;

[0040] For any marking information, the marking information is modified, and the modified grain warehouse image with the marking information is saved.

[0041] Optionally, the determining module is specifically used to:

[0042] Get the trigger instruction for any annotation information;

[0043] Based on the trigger instruction, display at least one operation button;

[0044] In response to an operation on at least one operation button, the annotation information is modified.

[0045] In a third aspect, an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the program.

[0046] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program executable by a computer device, wherein when the program is run on the computer device, the computer device executes the steps of the above method.

[0047] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a computer program stored on a computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer device, the computer device executes the steps of the above method.

[0048] In an embodiment of the present application, by performing object recognition on the grain warehouse image, different types of target objects in the grain warehouse image can be accurately identified so that monitoring can be subsequently deployed according to the target objects; by monitoring the target objects according to the monitoring deployment rules of the target objects, it is no longer necessary to manually monitor the target objects, thereby improving the efficiency and accuracy of the monitoring deployment. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0050] Figure 1A system architecture diagram provided for an embodiment of the present application;

[0051] Figure 2 A flowchart of a method for generating monitoring deployment points provided in an embodiment of the present application;

[0052] Figure 3 A schematic diagram of a process for generating annotation information for a grain storage image provided in an embodiment of the present application;

[0053] Figure 4 A schematic diagram of a process for operating the annotation information of a grain depot image provided in an embodiment of the present application;

[0054] Figure 5 A schematic diagram of the structure of a device for generating monitoring deployment points provided in an embodiment of the present application;

[0055] Figure 6 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and beneficial effects of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0057] To facilitate understanding of this solution, the application scenario of this solution is introduced below.

[0058] As people's quality of life improves, food safety has received more and more attention and concern. The country has carried out full-link tracking and supervision of grain production, storage, custody, and transportation to ensure the safety of food consumption. During the grain storage stage, in order to conduct all-weather and all-round supervision of grain, the monitoring equipment in the grain storage silo needs to be deployed according to the rules. At present, when supervising grain storage, the monitoring equipment is generally deployed manually, and the locations where monitoring equipment needs to be deployed are marked through empirical analysis or granary structure. When it is necessary to follow the rules, such as the national information technology specifications for safe grain storage, or the company has its own regulations on safe grain storage, it is still only possible to deploy monitoring equipment by comparing with the regulations or specifications manually, and it is impossible to automatically generate the points that need to be deployed according to the specifications or regulations. The embodiment of the present application provides a method for generating monitoring deployment points, and the specific operating steps are as follows:

[0059] First, this application obtains the image of the grain warehouse where monitoring equipment needs to be deployed, and generates the grain warehouse image with the same proportion as the monitoring deployment rules. Then, the grain warehouse image is preprocessed, such as noise reduction, contrast enhancement, etc., to ensure the accuracy of subsequent image recognition and analysis. The grain warehouse image is then recognized through computer vision technology to identify different types of target objects in the grain warehouse image, such as warehouses, main roads, entrances and exits, office buildings and other areas. Finally, the grain warehouse image is compared with the monitoring deployment rules to determine the points in the grain warehouse image that need to be monitored, and annotation information is added to the monitoring deployment points, thereby completing the automatic monitoring deployment of the grain warehouse image according to the rules.

[0060] See also Figure 1 , is a system architecture diagram provided in an embodiment of the present application, the system architecture includes a terminal device 101 and a server 102.

[0061] The terminal device 101 is pre-installed with a service application for text matching, wherein the service application is a client application, a web application, a small program application, etc. The terminal device 101 can be a smart phone, a POS machine, a desktop notebook, a computer, etc., but is not limited thereto.

[0062] Server 102 is the backend server for business applications. Server 102 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), as well as big data and artificial intelligence platforms.

[0063] See also Figure 2 , is a flow chart of a method for generating monitoring deployment points provided in an embodiment of the present application, comprising the following steps:

[0064] Step 201: Acquire a grain depot image.

[0065] Specifically, the grain depot image is a high-definition plan view of the grain depot, generally a bird's-eye view. The grain depot image should capture the internal structure of the grain depot, including the warehouse, main roads, entrances and exits, office buildings and other areas of the grain depot. Therefore, the general resolution of the grain depot image is recommended to be above 1920*1080. When acquiring the grain depot image, the overall structure of the grain depot can be photographed by a drone, and all structures of the grain depot should be photographed.

[0066] Step 202: Perform object recognition on the grain warehouse image to obtain different types of target objects.

[0067] Specifically, the objects in the grain warehouse image are divided into multiple types, such as warehouses, main roads, entrances and exits, office buildings, etc., which are different types of objects. By performing object recognition on the grain warehouse image, the objects that need to be monitored are obtained as target objects. For example, if the warehouse needs to be monitored, the warehouse will be taken as the target object.

[0068] Step 203: determine the monitoring layout points of each target object in the grain warehouse image according to the monitoring layout rules of each target object, and set the annotation information of each monitoring layout point in the grain warehouse image.

[0069] Specifically, the monitoring deployment rules specify the objects that need to be monitored. For example, the monitoring deployment rules specify that warehouses and entrances and exits need to be monitored, while main roads and office buildings do not need to be monitored. According to the monitoring deployment rules, the target objects are determined, that is, the monitoring deployment points of the warehouses and entrances and exits that need to be monitored are determined, and then each monitoring deployment point is marked in the grain warehouse image to obtain the marking information, such as marking the warehouses and entrances and exits to obtain the marking information of the warehouses and entrances and exits.

[0070] In an embodiment of the present application, by performing object recognition on the grain warehouse image, different types of target objects in the grain warehouse image can be accurately identified so that monitoring can be subsequently deployed according to the target objects; by monitoring the target objects according to the monitoring deployment rules of the target objects, it is no longer necessary to manually monitor the target objects, thereby improving the efficiency and accuracy of the monitoring deployment.

[0071] In some embodiments, the monitoring layout points of each target object in the grain warehouse image are determined according to the monitoring layout rules of each target object, including: for any target object, if the monitoring layout rule of the target object is a required attribute, then the monitoring layout points of the target object in the grain warehouse image are determined according to the monitoring function indicated by the monitoring layout rule of the target object.

[0072] Specifically, the monitoring deployment rules of the target object contain mandatory attributes, that is, the target object must be monitored. The attributes of the monitoring deployment rules of the target object include multiple types. If the monitoring deployment rules of the target object are mandatory attributes, the monitoring function indicated by the target object in the monitoring deployment rules is determined to determine the monitoring deployment point of the target object in the grain warehouse image. The monitoring function explains the main purpose of the target object. Through the monitoring function, it can be determined whether the target object needs to be monitored and the reason for the monitoring. A target object corresponds to at least one monitoring function, and each monitoring function has its own attributes. When any monitoring function in the target object has a mandatory attribute, the target object must be monitored.

[0073] For example, as shown in Table 1, it is a monitoring deployment rule, including target objects, monitoring functions, and attributes. Each target object has its corresponding monitoring function. For example, when the target object is an entrance or exit, the monitoring functions are "personnel entry and exit monitoring" and "vehicle entry and exit license plate recognition". Among them, the attributes when the monitoring function is "personnel entry and exit monitoring" are required attributes. Therefore, the entrances and exits must be monitored.

[0074] In the embodiment of the present application, when the attribute of the monitoring deployment rule of the target object is a required attribute, monitoring deployment is performed on the target object to avoid missing the monitoring deployment of the target object, thereby improving the accuracy of the monitoring deployment.

[0075] In some embodiments, it includes: determining the monitoring layout points of each target object in the grain warehouse image according to the monitoring layout rules of each target object, including: for any target object, if the monitoring layout rule of the target object is an optional attribute, determining whether the monitoring layout points set in the grain warehouse image meet the monitoring function indicated by the monitoring layout rule of the target object; if not, setting monitoring layout points that meet the monitoring function in the grain warehouse image.

[0076] Specifically, the monitoring deployment rule of the target object contains optional attributes, that is, there is no mandatory requirement for whether the target object is to be monitored. If the monitoring deployment rule of the target object is an optional attribute, the monitoring equipment that has been monitored in the grain warehouse image is determined. If the monitoring equipment can meet the monitoring function indicated by the monitoring deployment rule, the target object does not need to be monitored; if the monitoring equipment cannot meet the monitoring function indicated by the monitoring deployment rule, the target object needs to be monitored.

[0077] For example, as shown in Table 1, for a monitoring deployment rule, when the target object is an entrance and exit, one of the corresponding monitoring functions is "vehicle in and out license plate recognition", and this monitoring function is an optional attribute. Therefore, the entrance and exit can be monitored, but because another monitoring function of the entrance and exit is "personnel in and out monitoring", which is a required attribute, the "entrance and exit" must be monitored. When the target object is "settlement room", it has only one corresponding monitoring function, which is "in and out business settlement process monitoring", and this monitoring function is an optional attribute. Therefore, the target object is "settlement room" and can be monitored or not.

[0078] In the embodiment of the present application, when the attributes of the monitoring deployment rules of the target object are optional attributes, the monitoring deployment of the target object can be performed according to the actual situation, thereby improving the flexibility of the monitoring deployment.

[0079]

[0080] Table 1

[0081] In some embodiments, before performing object recognition on the grain storage image, the method further includes:

[0082] The grain warehouse image is enhanced by an image processing model; the loss function corresponding to the image processing model is determined by a first loss value corresponding to the pixel value and a second loss value corresponding to the structural similarity.

[0083] Specifically, after obtaining the grain depot image, it is necessary to perform preprocessing, such as noise reduction and image quality enhancement, on the grain depot image, so as to facilitate the subsequent extraction of the target object in the grain depot image. When performing image enhancement processing on the grain depot image, an image processing model, such as a deep learning model, can be used to enhance the image through algorithms such as mean filtering, median filtering, and Gaussian filtering. When training the image processing model, the constructed loss function can include mean square error (MSE for short) and structural similarity index (SSIM for short). The mean square error enhances the grain depot image according to the pixels of the grain depot image, and the structural similarity index can retain the details and texture information of the image, avoid excessive smoothing of the grain depot image caused by using the mean square error calculation formula, and can be used to optimize the structural fidelity of the image. The specific construction of the loss function is shown in formula (1) and formula (2).

[0084] Formula (1) is a loss function constructed based on mean square error, as shown below:

[0085]

[0086] Among them, L MSE is the first loss value constructed based on the mean square error, N is the total number of pixels in the grain depot image, and I original is the grain depot image without image enhancement processing, I predicted This is the grain warehouse image that has been enhanced.

[0087] Formula (2) is a loss function constructed based on the structural similarity index, as shown below:

[0088] L SSIM =1-SSIM(I original ,I predicted )...Formula (2)

[0089] Among them, L SSIM is the second loss value constructed based on the structural similarity index.

[0090] In order to consider both pixel error and structural fidelity, the mean square error and structural similarity index can be combined to form a weighted loss function, as shown in formula (3):

[0091] L total=α*L MSE +β*L SSIM ...Formula (3)

[0092] Among them, L total is a weighted loss function, α and β are hyperparameters used to adjust the weights of the two.

[0093] In the embodiment of the present application, the grain warehouse image is made clearer through image processing, and the target object of the grain warehouse image can be identified more accurately, thereby avoiding the problem of incorrect monitoring deployment due to incorrect target object identification.

[0094] In some embodiments, after setting the annotation information of each monitoring deployment point in the grain warehouse image, such as Figure 3 As shown, the following steps are also included:

[0095] Step 301: Display the grain warehouse image with labeled information.

[0096] Specifically, after setting annotation information for the monitoring deployment points of the grain warehouse image, the grain warehouse image with the annotation information is displayed. The annotation information represents the target object that needs to be monitored, such as marking a red dot at the location of the target object. After marking the target object, annotation information can also be filled in at the marked location, such as the number of recommended monitoring deployments, the type of monitoring equipment, etc., to form annotation information.

[0097] Step 302: for any marked information, operate on the marked information and save the grain warehouse image with the marked information after the operation.

[0098] Specifically, when the grain warehouse image with marked information is displayed, if the marked information needs to be operated, the specific operation can be "view", "modify", "delete", etc. Manually adjust according to actual needs, such as adjusting the number and location of monitoring equipment, etc. After adjusting the marked information, save the operated marked information to ensure the flexibility and effectiveness of the monitoring layout points.

[0099] In an embodiment of the present application, after displaying a grain warehouse image with annotation information, the annotation information can be modified. By modifying the annotation information, the monitoring layout of the target object can be changed, thereby improving the flexibility of the monitoring layout.

[0100] In some embodiments, for any annotation information, the annotation information is modified, such as Figure 4 As shown, the following steps are included:

[0101] Step 401: Obtain a trigger instruction for any annotation information.

[0102] Step 402: Based on the trigger instruction, display at least one operation button.

[0103] Step 403: In response to an operation on at least one operation button, operate the annotation information.

[0104] Specifically, when performing operations such as "viewing", "modifying" and "deleting" the annotation information, the mouse can be hovered over the annotation information that needs to be operated. After the mouse clicks the annotation information, the trigger instruction for operating the annotation information will be triggered. At this time, multiple operation buttons will appear, namely the "view" annotation information button, the "modify" annotation information button, the "delete" annotation information button, etc. If you need to view the annotation information, click the "view" annotation information button to display the annotation information, such as "there are 3 monitoring points" and "the type of monitoring equipment is A"; if you need to modify the annotation information, click the "modify" annotation information button to modify the number of monitoring points or the type of monitoring equipment; if you need to delete the annotation information, click the "delete" annotation information button to delete the corresponding annotation information.

[0105] In the embodiment of the present application, by obtaining a trigger instruction, the marking information can be operated, and the monitoring deployment can be operated by operating the marking information, thereby improving the flexibility of the monitoring deployment.

[0106] Based on the same technical concept, the embodiment of the present application provides a device for generating monitoring deployment points, such as Figure 5 As shown, the device 500 includes:

[0107] An acquisition module 501 is used to acquire a grain depot image;

[0108] The processing module 502 is used to perform object recognition on the grain depot image to obtain different types of target objects;

[0109] The determination module 503 is used to determine the monitoring layout point of each target object in the grain warehouse image according to the monitoring layout rule of each target object, and set the annotation information of each monitoring layout point in the grain warehouse image.

[0110] Optionally, the determining module 503 is specifically configured to:

[0111] For any target object, if the monitoring layout rule of the target object is a required attribute, the monitoring layout point of the target object in the grain warehouse image is determined according to the monitoring function indicated by the monitoring layout rule of the target object.

[0112] Optionally, the determining module 503 is specifically configured to:

[0113] For any target object, if the monitoring layout rule of the target object is an optional attribute, it is determined whether the monitoring layout points set in the grain warehouse image meet the monitoring function indicated by the monitoring layout rule of the target object. If not, monitoring layout points that meet the monitoring function are set in the grain warehouse image.

[0114] Optionally, the processing module 502 is specifically configured to:

[0115] The grain warehouse image is enhanced by an image processing model; the loss function corresponding to the image processing model is determined by a first loss value corresponding to the pixel value and a second loss value corresponding to the structural similarity.

[0116] Optionally, the determining module 503 is further configured to:

[0117] Displays images of grain depots with labeled information;

[0118] For any marked information, the marked information is operated, and the modified grain warehouse image with the marked information is saved.

[0119] Optionally, the determining module 503 is specifically configured to:

[0120] Get the trigger instruction for any annotation information;

[0121] Based on the trigger instruction, display at least one operation button;

[0122] In response to an operation on at least one operation button, the annotation information is operated.

[0123] Based on the same technical concept, the embodiment of the present application provides a computer device, which may be a terminal or a server, such as Figure 6 As shown, it includes at least one processor 601 and a memory 602 connected to the at least one processor. The specific connection medium between the processor 601 and the memory 602 is not limited in the embodiment of the present application. Figure 6 For example, the processor 601 and the memory 602 are connected via a bus. The bus can be divided into an address bus, a data bus, a control bus, and the like.

[0124] In the embodiment of the present application, the memory 602 stores instructions that can be executed by at least one processor 601. The at least one processor 601 can execute the steps included in the above-mentioned monitoring deployment points by executing the instructions stored in the memory 602.

[0125] The processor 601 is the control center of the computer device, and can use various interfaces and lines to connect various parts of the computer device, by running or executing instructions stored in the memory 602 and calling data stored in the memory 602. Optionally, the processor 601 may include one or more processing units, and the processor 601 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 601. In some embodiments, the processor 601 and the memory 602 may be implemented on the same chip, and in some embodiments, they may also be implemented separately on independent chips.

[0126] Processor 601 can be a general-purpose processor, such as a central processing unit (CPU), a digital signal processor, an application-specific integrated circuit (ASIC), a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, and can implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of the present application. A general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware processor for execution, or can be executed by a combination of hardware and software modules in the processor.

[0127] The memory 602 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules. The memory 602 may include at least one type of storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory, a random access memory (Random Access Memory, RAM), a static random access memory (Static Random Access Memory, SRAM), a programmable read-only memory (Programmable Read Only Memory, PROM), a read-only memory (Read Only Memory, ROM), an electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), a magnetic memory, a disk, an optical disk, etc. The memory 602 is any other medium that can be used to carry or store a desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 602 in the embodiment of the present application can also be a circuit or any other device that can realize a storage function, for storing program instructions and / or data.

[0128] Based on the same inventive concept, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program that can be executed by a computer device. When the program runs on the computer device, the computer device executes the above-mentioned steps of monitoring the deployment points.

[0129] Based on the same inventive concept, an embodiment of the present application provides a computer program product, characterized in that the computer program product includes a computer program stored on a computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer device, the computer device performs the above-mentioned steps of monitoring the deployment points.

[0130] 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.

[0131] 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 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 processor, or other programmable data processing device to produce 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.

[0132] 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 including 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.

[0133] 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.

[0134] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for generating monitoring deployment points, characterized in that: include: Get images of grain depots; Performing object recognition on the grain depot image to obtain different types of target objects; According to the monitoring layout rules for each target object, the monitoring layout points of each target object in the grain warehouse image are determined, and the annotation information of each monitoring layout point is set in the grain warehouse image.

2. The method according to claim 1, characterized in that Determining the monitoring layout point of each target object in the grain depot image according to the monitoring layout rule of each target object includes: For any target object, if the monitoring layout rule of the target object is a required attribute, the monitoring layout point of the target object in the grain warehouse image is determined according to the monitoring function indicated by the monitoring layout rule of the target object.

3. The method according to claim 1, characterized in that include: Determining the monitoring layout point of each target object in the grain depot image according to the monitoring layout rule of each target object includes: For any target object, if the monitoring layout rule of the target object is an optional attribute, it is determined whether the monitoring layout points set in the grain warehouse image meet the monitoring function indicated by the monitoring layout rule of the target object. If not, monitoring layout points that meet the monitoring function are set in the grain warehouse image.

4. The method according to any one of claims 1 to 3, characterized in that: Before performing object recognition on the grain depot image, the method further includes: The grain warehouse image is enhanced by an image processing model; the loss function corresponding to the image processing model is determined by a first loss value corresponding to the pixel value and a second loss value corresponding to the structural similarity.

5. The method according to any one of claims 1 to 3, characterized in that: After setting the annotation information of each monitoring deployment point in the grain depot image, the method further includes: Displays images of grain depots with labeled information; For any marking information, the marking information is operated, and the grain warehouse image with the marking information after the operation is saved.

6. The method according to claim 5, characterized in that The operating of any annotation information includes: Get the trigger instruction for any annotation information; Based on the trigger instruction, display at least one operation button; In response to an operation on at least one operation button, the annotation information is operated.

7. A device for generating monitoring deployment points, characterized in that: include: An acquisition module is used to acquire grain depot images; A processing module is used to perform object recognition on the grain depot image to obtain different types of target objects; The determination module is used to determine the monitoring layout points of each target object in the grain warehouse image according to the monitoring layout rules of each target object, and set the annotation information of each monitoring layout point in the grain warehouse image.

8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium, characterized in that: It stores a computer program executable by a computer device, and when the program is run on the computer device, the computer device executes the steps of any method described in claims 1 to 6.

10. A computer program product, characterized in that The computer program product comprises a computer program stored on a computer-readable storage medium, wherein the computer program comprises program instructions, and when the program instructions are executed by a computer device, the computer device is caused to execute the steps of the method according to any one of claims 1 to 6.

Images