Grain surface change detection method and equipment based on cloud service mode, and medium
Through the method of grain surface abnormal movement detection based on cloud service mode, using cameras and sensors combined with deep learning models to identify grain surface abnormal movement, the problems of low detection efficiency and lack of intelligence in the existing technology are solved, and the rapid development of mice and pests is achieved Identification and real-time response improves management efficiency and reduces costs.
Patent Information
- Application Number
- CN202411279481.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-12
- Publication Date
- 2024-12-20
AI Technical Summary
In the existing technology, rat and pest detection in grain warehouses mainly relies on physical blocking measures, is inefficient, lacks intelligent and automatic monitoring, and cannot achieve real-time response.
The grain surface abnormal movement detection method based on cloud service mode is adopted, baseline images are taken through the camera, vibration data is collected in combination with sensors, deep learning models and edge detection algorithms are used to identify grain surface abnormal movements, and images and data are compared in real time, trigger early warnings and send alarm information .
It realizes rapid and accurate identification of rats and pests, improves detection efficiency, reduces manual intervention, reduces management costs, avoids blind spots in traditional physical methods, and provides scientific and reasonable prevention and control plans and resource allocation plans.
Smart Images
Figure CN119169529A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of technical grain and flour detection, and in particular to a method, device and medium for detecting grain and flour changes based on a cloud service model. Background Art
[0002] Grain warehouses are key areas for storing grain, but rodents and pests often become a big problem here. They not only damage the stored grain, but also pose a threat to human health. When they move around in the grain warehouse, they will eat a lot of grain, causing serious economic losses. According to statistics, the loss of grain caused by rats is huge every year, especially in Asia, where rice production can decrease by 5%, about 300 million tons of rice, which is equivalent to the annual food ration of 1.8 billion people.
[0003] The current detection measures generally involve installing metal mesh or rat-proof panels at key locations such as doors, windows, vents, and pipes in granaries, and reasonably arranging mousetraps, mousecages, or electronic mousetraps inside the granaries to use physical means such as insect-proof nets and boards to block the entry of pests.
[0004] Through the above analysis, the problems and defects of the prior art are as follows:
[0005] The existing technologies for detecting rodents, pests, etc. mostly rely on physical blocking measures, which are inefficient, have a low level of intelligence, and lack a comprehensive automatic monitoring and real-time response system. Summary of the invention
[0006] The embodiments of the present application provide a method, device and medium for detecting abnormal grain movement based on a cloud service model, which can solve the problems in the prior art that the detection of rodents, pests, etc. is mostly physical blocking measures, which are inefficient, have a low degree of intelligence, and lack a comprehensive automatic monitoring and real-time response system.
[0007] In a first aspect, an embodiment of the present application provides a method for detecting grain surface movement based on a cloud service model, the method comprising: photographing the grain surface to obtain a baseline image of the grain surface, and configuring corresponding baseline images for multiple cameras of multiple granaries; capturing the grain surface at preset time intervals, and comparing the captured image with the baseline image to determine whether there is any movement on the grain surface; if there is any movement, checking real-time in and out-of-warehouse business data to determine whether the granary is in operation; if the granary is not in operation, triggering a grain surface movement warning, and sending an alarm message to the management personnel.
[0008] In one implementation of the present application, after photographing the grain surface and obtaining a baseline image of the grain surface, the method also includes: installing sensors and monitors at the center, edge, bottom and corners of the granary; collecting vibration data in real time through sensors and monitors, the monitor includes a pest monitor, and the sensor includes a temperature sensor and a vibration sensor; when the vibration data is collected and the granary is not in operation, triggering an abnormal movement warning of the grain surface, and uploading the vibration data to a cloud server.
[0009] In one implementation of the present application, the grain surface is captured at preset time intervals, and the captured image is compared with the baseline image to determine whether there is any movement on the grain surface. Specifically, the captured image is uploaded to a cloud server, and the captured image is semantically segmented through a deep learning model to identify the grain surface, granary wall, and ground, and assign corresponding labels; edge detection algorithm is used to extract edge information of the grain surface; and shape matching algorithm is used to determine whether the edge information is concave or tilted.
[0010] In one implementation of the present application, the method also includes: converting the baseline image and the captured image into the HSV space, extracting the color masks of the baseline image and the captured image according to a preset color range; respectively calculating the average hue, saturation, and brightness values of the color masks of the baseline image and the captured image, and comparing them.
[0011] In one implementation of the present application, the method also includes: converting the baseline image and the captured image into grayscale images, extracting texture features of the baseline image and the captured image; calculating the distance measurement of the texture features; if the distance measurement exceeds an abnormal threshold, triggering a grain surface movement warning.
[0012] In one implementation of the present application, corresponding baseline images are configured for multiple cameras of multiple granaries, specifically including: assigning a unique identifier to each camera; and associating the corresponding baseline image with the identifier and storing it in a database of a cloud server.
[0013] In one implementation of the present application, when there is no operation in the granary, after the grain surface movement warning is triggered, the method also includes: when the temperature is higher than the temperature threshold or the humidity is higher than the humidity threshold, increasing the preset capture frequency; continuously monitoring the grain surface through the cloud service platform, and evaluating the current capture frequency; according to the evaluation results, automatically or manually increasing or decreasing the preset capture frequency, temperature threshold and humidity threshold.
[0014] In one implementation of the present application, after uploading the captured image to the cloud server, the method also includes: preprocessing the captured image and distributing it to the nodes in the distributed computing framework; the nodes perform real-time and parallel calculations on the preprocessed image, and summarize the calculation results to the main node.
[0015] In the second aspect, an embodiment of the present application also provides a grain surface movement detection device based on a cloud service model, the device comprising at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can: photograph the grain surface to obtain a baseline image of the grain surface, and configure corresponding baseline images for multiple cameras of multiple granaries; capture the grain surface at preset time intervals, and compare the captured image with the baseline image to determine whether there is any movement on the grain surface; in the event of any movement, check real-time inbound and outbound business data to determine whether the granary is in operation; in the event of no operation in the granary, trigger a grain surface movement warning, and send an alarm message to the management personnel.
[0016] On the third aspect, the embodiments of the present application also provide a non-volatile computer storage medium for detecting grain surface movement based on a cloud service model, storing computer executable instructions, and the computer executable instructions are set to: photograph the grain surface to obtain a baseline image of the grain surface, and configure corresponding baseline images for multiple cameras of multiple granaries; capture the grain surface at preset time intervals, and compare the captured image with the baseline image to determine whether there is any movement on the grain surface; if there is any movement, check real-time in and out of warehouse business data to determine whether the granary is in operation; if the granary is not in operation, trigger a grain surface movement warning and send an alarm message to the management personnel.
[0017] The embodiments of the present application provide a method, device and medium for detecting grain surface movement based on a cloud service model, which introduces intelligent monitoring technology to achieve rapid and accurate identification of targets such as rodents and pests, greatly improving detection efficiency. This non-contact detection method not only reduces the need for manual intervention, but also avoids the blind spots that may exist in traditional physical methods; by checking grain surface movement, color and texture characteristics, the grain surface is monitored from multiple angles; once targets such as rodents and pests are found, the system can immediately issue an alarm and trigger the corresponding processing mechanism; reduce manpower input and management costs; adopt non-chemical and harmless prevention and control methods to reduce pollution and damage to the environment. It helps managers understand the distribution, activity patterns and other information of targets such as rodents and pests, so as to formulate more scientific and reasonable prevention and control plans and resource allocation plans to improve management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0019] Figure 1 A flow chart of a grain and flour movement detection method based on a cloud service model provided in an embodiment of the present application;
[0020] Figure 2 A baseline image and a captured image of a grain surface movement detection method based on a cloud service model provided in an embodiment of the present application;
[0021] Figure 3 A schematic diagram of the internal structure of a grain and flour movement detection device based on a cloud service model provided in an embodiment of the present application. DETAILED DESCRIPTION
[0022] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. 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 making creative work are within the scope of protection of the present application.
[0023] The embodiments of the present application provide a method, device and medium for detecting abnormal grain movement based on a cloud service model, which solves the problem that the existing technology for detecting rodents, pests, etc. mostly relies on physical blocking measures, has low efficiency, low intelligence, and lacks a comprehensive automatic monitoring and real-time response system.
[0024] The technical solution proposed in the embodiments of the present application is described in detail below with reference to the accompanying drawings.
[0025] Figure 1 The following is a flow chart of a grain surface change detection method based on a cloud service model provided in an embodiment of the present application. Figure 1 As shown, a method for detecting grain and flour changes based on a cloud service model provided in an embodiment of the present application specifically includes the following steps:
[0026] Step 10: photograph the grain surface to obtain a baseline image of the grain surface, and configure corresponding baseline images for multiple cameras of multiple granaries;
[0027] In this step, if Figure 2 As shown in the figure, high-definition cameras should be reasonably arranged inside the granary to ensure that all key areas are covered, such as the surface of the grain pile. The cameras should have night vision function and high resolution so that they can capture clear images under different lighting conditions.
[0028] As an optional embodiment, after photographing the grain surface and obtaining a baseline image of the grain surface, the method may also include: installing sensors and monitors at the center, edge, bottom and corners of the granary; collecting vibration data in real time through the sensors and monitors, the monitor includes a pest monitor, and the sensor includes a temperature sensor and a vibration sensor; when the vibration data is collected and the granary is not in operation, triggering an abnormal movement warning of the grain surface, and uploading the vibration data to the cloud server.
[0029] In this step, mice like to move around at the foot of the wall and the side of the wall, so sensors and monitors are placed at the edge, bottom and corners of the granary. Just in case, sensors and monitors are also set up in the center. The pest monitor can assist in determining whether there are mice active in the granary. Through intelligent equipment, the number, type, density and other conditions of pests in the granary are monitored in real time, and possible hazards in the granary can be discovered and dealt with in a timely manner.
[0030] As an optional embodiment, configuring corresponding baseline images for multiple cameras of multiple granaries may specifically include: Step 101: assigning a unique identifier to each camera; Step 102: associating the corresponding baseline image with the identifier and storing it in a database of a cloud server.
[0031] In this step, remote monitoring of the grain surface can be achieved through cloud services. No matter where the grain warehouse is located, as long as the network connection is stable, the image and video data of the grain surface can be obtained in real time, and abnormal movement detection can be performed; the baseline may be different for different camera angles. The corresponding baseline image is associated with the identifier and stored in the database of the cloud server, which can maximize the detection of grain surface movement problems.
[0032] Step 20: Capture the grain surface at a preset time interval, and compare the captured image with the baseline image to determine whether there is any abnormality in the grain surface;
[0033] As an optional embodiment, the grain surface is captured at preset time intervals, and the captured image is compared with the baseline image to determine whether there is any movement on the grain surface. Specifically, the method may include: Step 201: uploading the captured image to a cloud server, performing semantic segmentation on the captured image through a deep learning model, identifying the grain surface, granary wall, and ground, and assigning corresponding labels; Step 202: extracting edge information of the grain surface using an edge detection algorithm; Step 203: determining whether the edge information is concave or tilted using a shape matching algorithm.
[0034] In this step, a pre-trained deep learning model is deployed on the cloud server. For example, the grain surface, walls and ground of the wheat pile are identified and marked with different colors or contour lines respectively. The model classifies the input image at the pixel level, outputs the category label of each pixel, and generates a segmentation map containing each category area. The Canny, Sobel and other edge detection algorithms are used on the grain surface area obtained after semantic segmentation to identify and highlight the area with obvious brightness changes in the image, that is, the edge of the grain surface. By comparing the current grain surface edge information with the baseline edge information, the offset and curvature changes are calculated, and it is determined that the current grain surface has changed, and the corresponding alarm information is generated.
[0035] As an optional embodiment, the method may also include: Step 204: converting the baseline image and the captured image into the HSV space, and extracting the color masks of the baseline image and the captured image according to a preset color range; Step 205: respectively calculating the average hue, saturation, and brightness values of the color masks of the baseline image and the captured image, and comparing them.
[0036] In this step, the average hue, saturation, and brightness values of the baseline image and the captured image color mask are calculated in order to detect mice, pests, and mouse excrement. For example, in the HSV space, the color area of wheat can be segmented according to the hue (H) and saturation (S) range of wheat, and the color feature values of the captured image color mask under the same light are compared with the color feature values of the baseline image color mask. If the change exceeds the preset threshold, it is determined that the grain surface is abnormal.
[0037] As an optional embodiment, the method may also include: step 206: converting the baseline image and the captured image into grayscale images, and extracting texture features of the baseline image and the captured image; step 207: calculating the distance measurement of the texture features; step 208: if the distance measurement exceeds the abnormal threshold, triggering a grain surface movement warning.
[0038] In this step, the texture characteristics are checked to see whether the grain surface has deteriorated.
[0039] Step 30: In case of any abnormal changes, check the real-time inbound and outbound business data to determine whether the granary is in operation.
[0040] In this step, the cloud server obtains real-time in-and-out warehouse business data from the database, and determines whether the current granary is in operation based on the real-time in-and-out warehouse business data; the vibration sensor can also be turned off when the granary is operating.
[0041] Step 40: When there is no operation in the granary, an early warning of abnormal grain movement is triggered and an alarm message is sent to the management personnel.
[0042] In this step, not only is the alarm information sent to the administrator in real time, an early warning sound is sounded in the warehouse in real time, but also when the camera detects the target object, harmless chemicals can be automatically sprayed on the target object, achieving rapid and effective prevention and control.
[0043] The cloud server analyzes and processes the baseline image and the captured image of the grain surface to determine whether any grain surface abnormality has occurred. After the server completes the request, it generates an http response, including a response header and a response body. The response status code and response content type are stored in the response header, and the response body contains specific response data. The server sends the generated response content to the client. The client receives the response information and determines whether a grain surface abnormality warning has occurred in combination with business data such as warehousing plans and warehousing documents, and performs logical processing to generate warning information. Users can view specific warning information on the client and can also query previous warning records.
[0044] As an optional embodiment, when the grain silo is not in operation, after the grain surface abnormal movement warning is triggered, the method may further include:
[0045] Step 50: When the temperature is higher than the temperature threshold or the humidity is higher than the humidity threshold, increase the preset snapshot frequency;
[0046] Step 60: Continuously monitor the grain surface through the cloud service platform and evaluate the current capture frequency;
[0047] Step 70: Automatically or manually increase or decrease the preset snapshot frequency, temperature threshold, and humidity threshold according to the evaluation result.
[0048] For example, if the abnormal situation continues to intensify or the environmental conditions continue to deteriorate, the system may further lower the abnormal threshold and increase the capture frequency; conversely, if the abnormal situation tends to stabilize or the environmental conditions improve, the system may appropriately increase the abnormal threshold and reduce the capture frequency.
[0049] As an optional embodiment, after uploading the captured image to the cloud server, the method may also include: preprocessing the captured image and distributing it to nodes in a distributed computing framework; the nodes perform real-time and parallel calculations on the preprocessed image, and aggregating the calculation results to the main node.
[0050] In this step, the uploaded image data is processed in real time and in parallel using distributed computing frameworks such as Hadoop and Spark. These frameworks can divide the computing tasks into multiple small parts and assign them to multiple nodes in the cloud server cluster for simultaneous processing. The master node may dynamically adjust the threshold of anomaly detection.
[0051] The above is an embodiment of the method proposed in this application. Based on the same inventive concept, the embodiment of this application also provides a grain surface abnormality detection device based on a cloud service model, and its structure is as follows: Figure 3 shown.
[0052] Figure 3 The following is a schematic diagram of the internal structure of a grain surface abnormality detection device based on a cloud service model provided in an embodiment of the present application. Figure 3 As shown, the device includes:
[0053] at least one processor 301;
[0054] and, a memory 302 communicatively connected to at least one processor;
[0055] Among them, the memory 302 stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor 301 so that the at least one processor 301 can: photograph the grain surface to obtain a baseline image of the grain surface, and configure corresponding baseline images for multiple cameras of multiple granaries; capture the grain surface at preset time intervals, and compare the captured image with the baseline image to determine whether there is any change in the grain surface; if there is any change, check the real-time in and out warehouse business data to determine whether the granary is in operation; if the granary is not in operation, trigger a grain surface change warning and send an alarm message to the management personnel.
[0056] Some embodiments of the present application provide corresponding Figure 1 A non-volatile computer storage medium for grain surface movement detection based on a cloud service model stores computer executable instructions, wherein the computer executable instructions are configured to: photograph the grain surface to obtain a baseline image of the grain surface, and configure corresponding baseline images for multiple cameras of multiple granaries; capture the grain surface at preset time intervals, and compare the captured image with the baseline image to determine whether there is any movement on the grain surface; if there is any movement, check real-time in-and-out warehouse business data to determine whether the granary is in operation; if the granary is not in operation, trigger a grain surface movement warning and send an alarm message to a management personnel.
[0057] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the IoT device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.
[0058] The system and medium provided in the embodiments of the present application correspond one-to-one to the method. Therefore, the system and medium also have similar beneficial technical effects to the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the system and medium will not be repeated here.
[0059] 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.
[0060] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0061] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0062] 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.
[0063] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0064] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0065] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0066] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0067] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims
1. A method for detecting grain and flour changes based on a cloud service model, characterized in that: The method comprises: Photograph the grain surface to obtain a baseline image of the grain surface, and configure corresponding baseline images for multiple cameras of multiple granaries; Taking snapshots of the grain surface at preset time intervals, and comparing the snapshot images with the baseline images to determine whether there are any abnormalities on the grain surface; In case of abnormal changes, check the real-time in-and-out business data to determine whether the granary is in operation; When there is no operation in the granary, an early warning of abnormal grain surface movement is triggered and an alarm message is sent to the management personnel.
2. According to the cloud service model of claim 1, the method for detecting abnormal grain movement is characterized in that: After photographing the grain surface to obtain a baseline image of the grain surface, the method further includes: Install sensors and monitors at the center, edges, bottom and corners of the silo; Collect vibration data in real time through sensors and monitors, the monitors include pest monitors, and the sensors include temperature sensors and vibration sensors; When vibration data is collected and the granary is not in operation, an early warning of abnormal grain surface movement is triggered, and the vibration data is uploaded to the cloud server.
3. According to the cloud service model-based grain and flour movement detection method of claim 1, it is characterized in that: The grain surface is captured at a preset time interval, and the captured image is compared with the baseline image to determine whether there is any abnormality on the grain surface, specifically including: The captured image is uploaded to a cloud server, and semantic segmentation is performed on the captured image through a deep learning model to identify the grain surface, granary wall, and ground, and assign corresponding labels; Extracting edge information of the grain surface using an edge detection algorithm; A shape matching algorithm is used to determine whether the edge information is sunken or tilted.
4. The method for detecting grain and flour changes based on a cloud service model according to claim 3 is characterized in that: The method further comprises: Convert the baseline image and the captured image into HSV space, and extract color masks of the baseline image and the captured image according to a preset color range; The average hue, saturation, and brightness values of the color masks of the baseline image and the captured image are calculated respectively, and compared.
5. The method for detecting grain and flour changes based on a cloud service model according to claim 3 is characterized in that: The method further comprises: Converting the baseline image and the captured image into grayscale images, and extracting texture features of the baseline image and the captured image; Calculating a distance metric of the texture feature; If the distance measurement exceeds the abnormal threshold, a grain surface movement warning is triggered.
6. The method for detecting grain and flour changes based on a cloud service model according to claim 1, characterized in that: And configure corresponding baseline images for multiple cameras in multiple granaries, including: Assign a unique identifier to each camera; The corresponding baseline image is associated with the identifier and stored in a database of the cloud server.
7. The method for detecting grain and flour changes based on a cloud service model according to claim 1, characterized in that: When there is no operation in the granary, after triggering the grain surface abnormal movement warning, the method further includes: When the temperature is higher than the temperature threshold or the humidity is higher than the humidity threshold, the preset snapshot frequency is increased; The grain surface is continuously monitored through the cloud service platform, and the current capture frequency is evaluated; Based on the evaluation results, automatically or manually increase or decrease the preset snapshot frequency, temperature threshold, and humidity threshold.
8. The method for detecting grain and flour changes based on a cloud service model according to claim 1, characterized in that: After uploading the captured image to the cloud server, the method further includes: Preprocessing the captured images and distributing them to nodes in a distributed computing framework; The nodes perform real-time and parallel calculations on the preprocessed images and aggregate the calculation results to the main node.
9. A grain surface change detection device based on a cloud service model, characterized in that: The device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: Photograph the grain surface to obtain a baseline image of the grain surface, and configure corresponding baseline images for multiple cameras of multiple granaries; Taking snapshots of the grain surface at preset time intervals, and comparing the snapshot images with the baseline images to determine whether there are any abnormalities on the grain surface; In case of abnormal changes, check the real-time in-and-out business data to determine whether the granary is in operation; When there is no operation in the granary, an early warning of abnormal grain surface movement is triggered and an alarm message is sent to the management personnel.
10. A non-volatile computer storage medium for detecting grain and flour changes based on a cloud service model, storing computer executable instructions, characterized in that: The computer executable instructions are configured to: photograph the grain surface to obtain a baseline image of the grain surface, and configure corresponding baseline images for multiple cameras of multiple granaries; Taking snapshots of the grain surface at preset time intervals, and comparing the snapshot images with the baseline images to determine whether there are any abnormalities on the grain surface; In case of abnormal changes, check the real-time in-and-out business data to determine whether the granary is in operation; When there is no operation in the granary, an early warning of abnormal grain surface movement is triggered and an alarm message is sent to the management personnel.