Pump station dispatching method, equipment and medium based on image recognition of farmland disaster conditions

Abstract

The present application provides a method for dispatching a pump station based on image recognition of farmland disaster conditions, the method comprising: when the category information of at least one first repaired image is a waterlogging category, determining at least one first shooting position information corresponding to at least one first repaired image; determining a target pump station according to at least one first shooting position information; performing image segmentation processing on at least one first repaired image to determine a waterlogged area and a non-waterlogged area of ​​at least one first repaired image; determining a first ratio information between the area sum of the waterlogged area of ​​at least one first repaired image and the area sum of all areas of at least one first repaired image; determining a target waterlogging level according to the first ratio information; and dispatching drainage of the target pump station according to the target waterlogging level. The present application can accurately control the drainage flow and improve the accuracy of drainage dispatching of the target pump station.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of image recognition technology, and in particular to a pump station scheduling method based on image recognition of farmland disaster conditions. Background Art

[0002] Farmland is prone to waterlogging. When waterlogging occurs in farmland, it is necessary to drain the water from the farmland. The solution for draining water from farmland is generally to use the slope of the ditch for self-drainage.

[0003] Since the drainage speed of the ditch slope is slow, in order to speed up the drainage speed, a drainage pump station is built to drain the flood water through the drainage pump in the drainage pump station. However, the opening and closing of the drainage pump is often determined by the experience of the on-site personnel, and there is no solution for scheduling the drainage in the drainage pump station in the relevant technology. Summary of the invention

[0004] The embodiments of the present application provide a method, device and medium for dispatching a pump station based on image recognition of the disaster situation of farmland, so as to solve the problem that there is no solution for dispatching drainage in a drainage pump station in the related art.

[0005] In a first aspect, an embodiment of the present application provides a method for dispatching a pump station based on image recognition of farmland disaster conditions, comprising:

[0006] Acquire a plurality of initial images obtained by photographing multiple farmland areas respectively, and perform image definition restoration processing on the plurality of initial images respectively to obtain a plurality of restored images;

[0007] Using a classification network model, performing category recognition on each of the multiple repaired images to obtain category information of the multiple repaired images;

[0008] When the category information of the plurality of repaired images are all normal categories, outputting prompt information; the prompt information is used to indicate that no water supply and drainage treatment of the pump station is required;

[0009] In a case where the category information of at least one first restored image among the category information of the plurality of restored images is a waterlogging category, determining at least one first shooting position information corresponding to the at least one first restored image;

[0010] Determining a target pumping station corresponding to the at least one first shooting position information according to the at least one first shooting position information;

[0011] Performing image segmentation processing on the at least one first restored image to determine a waterlogged area and a non-waterlogged area of ​​the at least one first restored image;

[0012] Determine first ratio information between the sum of the areas of the waterlogged areas of the at least one first restored image and the sum of the areas of the entire areas of the at least one first restored image;

[0013] Determining a target waterlogging level according to the first ratio information;

[0014] The drainage of the target pump station is scheduled according to the target flood level.

[0015] In some embodiments, the acquiring of multiple initial images obtained by photographing multiple farmland areas respectively includes:

[0016] Obtain Y original images captured by Y cameras associated with each farmland area in the multiple farmland areas; Y is an integer greater than or equal to 2;

[0017] Splicing the Y original images of each farmland area to obtain a spliced ​​image of each farmland area;

[0018] A downsampling network model is used to downsample the stitched image of each farmland area to obtain an initial image of each farmland area.

[0019] In some embodiments, the scheduling of drainage of the target pump station according to the target flooding level includes:

[0020] Acquire the water level information of the first fore pool of the target pump station collected by the first photoelectric liquid level sensor, and the water level information of the first rear pool of the target pump station collected by the second photoelectric liquid level sensor;

[0021] Determine the total drainage flow of the pump of the target pump station according to the target flooding level and a first water level difference value of the first front pool water level information minus the first back pool water level information;

[0022] According to the total drainage flow of the water pumps, the operation of M drainage water pumps in the target pumping station is controlled; M is an integer greater than or equal to 2.

[0023] In some embodiments, the method further comprises:

[0024] When the category information of at least one second restored image in the category information of the plurality of restored images is a drought category, obtaining at least one second shooting position information corresponding to the at least one second restored image;

[0025] Determining, according to the at least one second shooting location information, a designated pumping station corresponding to the at least one second shooting location information;

[0026] Performing image segmentation processing on the at least one second restored image to determine a drought area and a non-drought area of ​​the at least one second restored image;

[0027] Determine second ratio information between the sum of the areas of the dry regions of the at least one second restored image and the sum of the areas of the entire regions of the at least one second restored image;

[0028] determining a target drought level according to the second ratio information;

[0029] The water supply to the designated pumping station is scheduled according to the target drought level.

[0030] In some embodiments, scheduling the water supply of the designated pumping station according to the target drought level includes:

[0031] Obtaining water level information of a second fore pool of the designated pumping station collected by a third photoelectric liquid level sensor, and water level information of a second rear pool of the designated pumping station collected by a fourth photoelectric liquid level sensor;

[0032] determining a total water supply flow rate of the designated pump station according to the target drought level and a second water level difference value obtained by subtracting the second rear pool water level information from the second front pool water level information;

[0033] According to the second water level difference and the total water supply flow, the operation of at least one fully adjustable angle water pump in the designated pumping station is controlled.

[0034] In some embodiments, before acquiring a plurality of initial images respectively photographed for multiple farmland areas, the method further includes:

[0035] Obtain R flow rates and R lifts of each water pump at each of a plurality of angles in at least one fully adjustable angle water pump in the designated pumping station; R is an integer greater than or equal to 3;

[0036] Fitting the R flow rates and the R lifts at each angle to obtain a preset corresponding relationship between the flow rate and the lift at each angle;

[0037] The step of controlling the operation of at least one fully adjustable angle water pump in the designated pumping station according to the second water level difference and the total water supply flow rate comprises:

[0038] Determine, according to the second water level difference and the preset corresponding relationship, a target flow rate corresponding to the second water level difference at each angle;

[0039] According to the target flow rate at each angle, determining a target corresponding relationship between the angle and the target flow rate;

[0040] According to the target corresponding relationship and the total water supply flow, the operation of at least one fully adjustable angle water pump in the designated pumping station is controlled.

[0041] In some embodiments, controlling the operation of at least one fully adjustable angle water pump in the designated pumping station according to the target corresponding relationship and the total water supply flow rate includes:

[0042] According to the second water level difference, a target water pump model is selected from a plurality of water pump signals corresponding to the designated pump station, and S available water pumps of the target water pump model are obtained from at least one fully adjustable angle water pump in the designated pump station; S is an integer greater than or equal to 1;

[0043] Dividing the total water supply flow rate by S to obtain an expected operating flow rate of each of the S available water pumps;

[0044] When the expected operating flow rate is less than or equal to the maximum operating flow rate of the pumping water pump of the target water pump model, determining the operating flow rate of each of the S available pumping water pumps to be the expected operating flow rate;

[0045] Determining target angles of the S available water pumps according to the target corresponding relationship corresponding to the target water pump model and the expected operating flow rate;

[0046] Control the S available water pumps to operate at the target angle.

[0047] In some embodiments, controlling the operation of at least one fully adjustable angle water pump in the designated pumping station according to the target corresponding relationship and the total water supply flow rate includes:

[0048] According to the second water level difference, a target water pump model is selected from a plurality of water pump signals corresponding to the designated pump station, and S available water pumps of the target water pump model are obtained from at least one fully adjustable angle water pump in the designated pump station; S is an integer greater than or equal to 1;

[0049] Dividing the total water supply flow rate by S to obtain the expected operating flow rate of each of the S available water pumps;

[0050] In the case where the expected operating flow rate is greater than the maximum operating flow rate of the pumping water pump of the target water pump model, determining the operating flow rate of each of the S available pumping water pumps to be the maximum operating flow rate;

[0051] Determining the predetermined angles of the S available water pumps according to the target corresponding relationship corresponding to the target water pump model and the maximum operating flow rate;

[0052] Controlling the S available water pumps to operate at the predetermined angle;

[0053] Determine T candidate water pumps according to the residual flow obtained by subtracting the total operating flow of the S available water pumps from the total water supply flow of the designated pumping station; wherein the total operating flow of the S available water pumps is the result of multiplying S by the maximum operating flow;

[0054] Determining the designated angles of the T candidate water pumps according to the target corresponding relationship corresponding to the models of the candidate water pumps and the remaining flow rate;

[0055] The T optional water pumps are controlled to operate at the specified angles.

[0056] In a second aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the pump station scheduling method based on image recognition of farmland disaster conditions as described above are implemented.

[0057] In a third aspect, an embodiment of the present application provides a non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the pump station scheduling method based on image recognition of farmland disaster conditions as described in any of the above items are implemented.

[0058] The pump station scheduling method, equipment and medium for image recognition of farmland disaster conditions provided in the embodiments of the present application determine the target waterlogging level based on the first ratio information between the area sum of the waterlogged area and the area sum of the entire area, and schedule the drainage of the target pump station according to the target waterlogging level. When the target waterlogging level indicates that the disaster is more serious, the drainage flow rate can be increased. When the target waterlogging level indicates that the disaster is less serious, the drainage flow rate can be appropriately reduced. This enables the drainage flow rate to be accurately controlled, thereby improving the accuracy of drainage scheduling for the target pump station. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the following is a brief introduction to the drawings required for use in the embodiments or the related technical descriptions. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0060] Figure 1 A schematic flow chart of a method for dispatching a pump station based on image recognition of farmland disaster conditions provided in an embodiment of the present application;

[0061] Figure 2 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are 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.

[0063] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0064] Figure 1 A schematic flow chart of a method for dispatching a pump station based on image recognition of farmland disaster conditions provided in an embodiment of the present application, the method being applied to an electronic device or a processor, such as Figure 1 As shown, the method includes:

[0065] S101, acquiring a plurality of initial images respectively obtained by photographing a plurality of farmland areas, and performing image definition restoration processing on the plurality of initial images respectively to obtain a plurality of restored images.

[0066] The electronic device in the embodiments of the present application can be any device with data processing capabilities, such as a server, a server cluster, a control device, a visitor machine, a server, a mobile phone, a tablet computer, a laptop computer, a PDA, a personal digital assistant, a portable media player, a smart speaker, a navigation device, a wearable device, a smart bracelet or a desktop computer, etc.

[0067] S102: using a classification network model to perform category recognition on each of the multiple repaired images to obtain category information of the multiple repaired images.

[0068] By performing image clarity restoration processing on the multiple initial images respectively, it is possible to reduce the situation in which the clarity of the images captured is low due to the harsh working environment of the camera used to photograph the farmland and the heavy dust on the camera surface, thereby causing inaccurate image classification. Therefore, the embodiment of the present application can improve the accuracy of image classification.

[0069] Exemplarily, the classification network model may include a convolutional neural network model, a recurrent neural network model, a long short-term memory network model, or a transformer model, etc.

[0070] S103: When the category information of the plurality of restored images are all normal categories, output prompt information; the prompt information is used to indicate that there is no need to perform water supply and drainage processing of the pump station.

[0071] In some embodiments, when there is at least one first restored image whose category information among the category information of the multiple restored images is a waterlogging category, designated information is output, and the designated information is used to indicate that waterlogging has occurred in the farmland area corresponding to the at least one first restored image.

[0072] In some embodiments, when there is at least one second restored image whose category information is drought category among the category information of the multiple restored images, target information is output, and the target information is used to indicate that the farmland area corresponding to the at least one second restored image is drought.

[0073] In other embodiments, when there is at least one second restored image whose category information is drought category among the category information of the multiple restored images, the water supply of the designated pumping station is scheduled so that the designated pumping station can supply water to the farmland area corresponding to the at least one second restored image.

[0074] S104: When there is at least one first restored image whose category information is a waterlogging category among the category information of the plurality of restored images, determine at least one first shooting position information corresponding to the at least one first restored image.

[0075] In some embodiments, the shooting location information may include identification information of the farmland area. In other embodiments, the shooting location information may include longitude and latitude information of the farmland area. In still other embodiments, the shooting location information may include longitude and latitude information of a camera used to shoot the farmland area.

[0076] S105. Determine a target pumping station corresponding to the at least one first shooting location information according to the at least one first shooting location information.

[0077] In some embodiments, the electronic device may store a target mapping relationship between the shooting location information and a drainage pumping station. For example, a drainage pumping station may drain one or more farmland areas. The target pumping station may be determined based on the target mapping relationship and at least one first shooting location information.

[0078] In some embodiments, the target pump station may include one pump station. In other embodiments, the target pump station may include multiple pump stations.

[0079] S106: Perform image segmentation processing on the at least one first restored image to determine a waterlogged area and a non-waterlogged area of ​​the at least one first restored image.

[0080] In some embodiments, an image segmentation model may be used to perform image segmentation processing on the at least one first repaired image to determine the waterlogged area and the non-waterlogged area of ​​the at least one first repaired image. Exemplarily, the image segmentation model may include one of the following: Segment Anything Model (SAM), DINOv2, Mask2Former, Swin Transformer, SegFormer, MaxViT, HRNet, U-Net, Global Context Network (GC-Net), an evolution of any of the foregoing models, etc.

[0081] Exemplarily, when there is no accumulated water in a first restored image, it is determined that there is no waterlogging area in the first restored image.

[0082] S107: Determine first ratio information between the sum of the areas of the waterlogged areas of the at least one first restored image and the sum of the areas of the entire areas of the at least one first restored image.

[0083] Exemplarily, at least one first restored image includes image 1, image 2 and image 3, the area of ​​the waterlogged area in image 1 is A, the area of ​​the waterlogged area in image 2 is B, the area of ​​the waterlogged area in image 3 is 0, and the area of ​​each image in image 1, image 2 and image 3 is A, then the first ratio information is (A+B) / 3A.

[0084] S108. Determine a target waterlogging level according to the first ratio information.

[0085] In some embodiments, the electronic device may store a mapping relationship between the ratio information range and different waterlogging levels, and determine the target waterlogging level based on the mapping relationship and the first ratio information.

[0086] Exemplarily, different waterlogging levels may be predefined. Exemplarily, the smaller the value of the waterlogging level, the more serious the disaster situation under the waterlogging level.

[0087] S109. Dispatching drainage of the target pump station according to the target flood level.

[0088] The pump station scheduling method for farmland disaster conditions based on image recognition provided in the embodiment of the present application determines the target waterlogging level based on the first ratio information between the area sum of the waterlogged area and the area sum of the entire area, and schedules the drainage of the target pump station based on the target waterlogging level. Thus, when the target waterlogging level indicates that the disaster is more serious, the drainage flow rate can be increased; when the target waterlogging level indicates that the disaster is less serious, the drainage flow rate can be appropriately reduced, thereby enabling the drainage flow rate to be accurately controlled and improving the accuracy of the drainage scheduling of the target pump station.

[0089] In some embodiments, the acquiring of multiple initial images obtained by photographing multiple farmland areas respectively includes:

[0090] Obtain Y original images captured by Y cameras associated with each farmland area in the multiple farmland areas; Y is an integer greater than or equal to 2;

[0091] Splicing the Y original images of each farmland area to obtain a spliced ​​image of each farmland area;

[0092] A downsampling network model is used to downsample the stitched image of each farmland area to obtain an initial image of each farmland area.

[0093] In some embodiments, different cameras among the Y cameras associated with each farmland area may respectively photograph different sub-areas in each farmland area, and the sub-areas photographed by different cameras may not overlap or may partially overlap.

[0094] In some implementations, computer vision may be used to stitch the Y original images of each farmland area.

[0095] In some embodiments, the size of the initial image is the input size of the classification network model.

[0096] In some embodiments, the scheduling of drainage of the target pump station according to the target flooding level includes:

[0097] Acquire the water level information of the first fore pool of the target pump station collected by the first photoelectric liquid level sensor, and the water level information of the first rear pool of the target pump station collected by the second photoelectric liquid level sensor;

[0098] Determine the total drainage flow of the pump of the target pump station according to the target flooding level and a first water level difference value of the first front pool water level information minus the first back pool water level information;

[0099] According to the total drainage flow of the water pumps, the operation of M drainage water pumps in the target pumping station is controlled; M is an integer greater than or equal to 2.

[0100] In some other embodiments, the scheduling of drainage of the target pump station according to the target flooding level includes:

[0101] Acquire a first forepool image and a first rear pool image obtained by photographing the forepool and the rear pool of the target pump station respectively;

[0102] Performing water level analysis on the first forepool image and the first backpool image to obtain a first forepool water level and a first backpool water level of the target pump station;

[0103] Determine the total drainage flow of the pump of the target pump station according to the target flooding level and a first water level difference value of the first front pool water level information minus the first back pool water level information;

[0104] According to the total drainage flow of the water pumps, the operation of M drainage water pumps in the target pumping station is controlled; M is an integer greater than or equal to 2.

[0105] In some embodiments, the first front pool image and the first rear pool image are used to determine the first front pool water level and the first rear pool water level as follows: the closest distances of multiple corner points of the front pool edge of the target pumping station in the first front pool image to the water surface are respectively determined as multiple first distances; the first real distance between the front pool edge of the target pumping station and the water surface is determined based on the average value of the multiple first distances; the first front pool water level is determined based on the first real distance and the actual height from the front pool edge to the front pool bottom of the target pumping station; the closest distances of multiple corner points of the rear pool edge of the target pumping station in the first rear pool image to the water surface are respectively determined as multiple second distances; the second real distance between the rear pool edge of the target pumping station and the water surface is determined based on the average value of the multiple second distances; the first rear pool water level is determined based on the second real distance and the actual height from the rear pool edge to the rear pool bottom of the target pumping station.

[0106] There is an intersection line between the pool edge and the pool wall, and the corner point is the point formed by the intersection of the intersection lines. Multiple corner points of the pool edge are located in the plane where the pool edge is located, and also in the plane where the pool wall is located.

[0107] In some embodiments, the first real distance is determined based on the average of the plurality of first distances and the position of the camera relative to the target pump station fore pool. In some embodiments, the second real distance is determined based on the average of the plurality of second distances and the position of the camera relative to the target pump station back pool.

[0108] In some embodiments, the electronic device may store a mapping relationship between waterlogging level, water level difference and flow, and thereby determine the total drainage flow of the pump of the target pump station according to the mapping relationship, the target waterlogging level and the first water level difference.

[0109] In some embodiments, the method further comprises:

[0110] When the category information of at least one second restored image in the category information of the plurality of restored images is a drought category, obtaining at least one second shooting position information corresponding to the at least one second restored image;

[0111] Determining, according to the at least one second shooting location information, a designated pumping station corresponding to the at least one second shooting location information;

[0112] Performing image segmentation processing on the at least one second restored image to determine a drought area and a non-drought area of ​​the at least one second restored image;

[0113] Determine second ratio information between the sum of the areas of the dry regions of the at least one second restored image and the sum of the areas of the entire regions of the at least one second restored image;

[0114] determining a target drought level according to the second ratio information;

[0115] The water supply to the designated pumping station is scheduled according to the target drought level.

[0116] In some embodiments, the electronic device may store a specified mapping relationship between the shooting location information and the pumping station. For example, a pumping station may provide the pumped water to one or more farmland areas. The specified pumping station is determined based on the specified mapping relationship and at least one second shooting location information.

[0117] In some embodiments, the designated pump station may include one pump station. In other embodiments, the designated pump station may include multiple pump stations.

[0118] In some implementations, an image segmentation model may be used to perform image segmentation processing on the at least one second restoration image to determine a drought region and a non-drought region of the at least one second restoration image.

[0119] In other embodiments, drought areas may be identified based on at least one of information such as leaf color, leaf status, and land color of crops in the image.

[0120] In some embodiments, scheduling the water supply of the designated pumping station according to the target drought level includes:

[0121] Obtaining water level information of a second fore pool of the designated pumping station collected by a third photoelectric liquid level sensor, and water level information of a second rear pool of the designated pumping station collected by a fourth photoelectric liquid level sensor;

[0122] determining a total water supply flow rate of the designated pump station according to the target drought level and a second water level difference value obtained by subtracting the second rear pool water level information from the second front pool water level information;

[0123] The operation of at least one fully adjustable angle water pump in the designated pumping station is controlled according to the second water level difference and the total water supply flow.

[0124] In some embodiments, the electronic device may store a mapping relationship between drought level, water level difference and flow, so as to determine the total water supply flow of a designated pump station according to the mapping relationship, the target drought level and the second water level difference.

[0125] In some other embodiments, scheduling the water supply of the designated pumping station according to the target drought level includes:

[0126] When the category information of at least one second restored image in the category information of the plurality of restored images is a drought category, obtaining at least one second shooting position information corresponding to the at least one second restored image;

[0127] Determining, according to the at least one second shooting location information, a designated pumping station corresponding to the at least one second shooting location information;

[0128] Acquire a second fore pool image and a second rear pool image obtained by photographing the fore pool and the rear pool of the designated pump station respectively;

[0129] Performing water level analysis on the second fore pool image and the second back pool image to obtain the second fore pool water level and the second back pool water level of the designated pump station;

[0130] The operation of at least one fully adjustable angle water pump in the designated pumping station is controlled according to a second water level difference value obtained by subtracting the second rear pool water level from the second front pool water level, and according to the total water supply flow.

[0131] In some embodiments, the second front pool image and the second back pool image are used to determine the second front pool water level and the second back pool water level as follows: the closest distances of the multiple corner points of the front pool edge of the designated pumping station in the second front pool image to the water surface are respectively determined as multiple third distances; the third real distance between the front pool edge of the designated pumping station and the water surface is determined based on the average value of the multiple third distances; the second front pool water level is determined based on the third real distance and the actual height from the front pool edge to the front pool bottom of the designated pumping station; the closest distances of the multiple corner points of the back pool edge of the designated pumping station in the second back pool image to the water surface are respectively determined as multiple fourth distances; the fourth real distance between the back pool edge of the designated pumping station and the water surface is determined based on the average value of the multiple fourth distances; the second back pool water level is determined based on the fourth real distance and the actual height from the back pool edge to the back pool bottom of the designated pumping station.

[0132] In some embodiments, the third real distance is determined based on the average of the plurality of third distances and the position of the camera relative to the designated pump station fore pool. In some embodiments, the fourth real distance is determined based on the average of the plurality of fourth distances and the position of the camera relative to the designated pump station back pool.

[0133] In some embodiments, before acquiring a plurality of initial images respectively photographed for multiple farmland areas, the method further includes:

[0134] Obtain R flow rates and R lifts of each water pump at each of a plurality of angles in at least one fully adjustable angle water pump in the designated pumping station; R is an integer greater than or equal to 3;

[0135] Fitting the R flow rates and the R lifts at each angle to obtain a preset corresponding relationship between the flow rate and the lift at each angle;

[0136] The step of controlling the operation of at least one fully adjustable angle water pump in the designated pumping station according to the second water level difference and the total water supply flow rate comprises:

[0137] Determine, according to the second water level difference and the preset corresponding relationship, a target flow rate corresponding to the second water level difference at each angle;

[0138] According to the target flow rate at each angle, determining a target corresponding relationship between the angle and the target flow rate;

[0139] According to the target corresponding relationship and the total water supply flow, the operation of at least one fully adjustable angle water pump in the designated pumping station is controlled.

[0140] In some implementations, different water pump types have different preset correspondences, and different water pump types have different target correspondences.

[0141] In some embodiments, controlling the operation of at least one fully adjustable angle water pump in the designated pumping station according to the target corresponding relationship and the total water supply flow rate includes:

[0142] According to the second water level difference, a target water pump model is selected from a plurality of water pump signals corresponding to the designated pump station, and S available water pumps of the target water pump model are obtained from at least one fully adjustable angle water pump in the designated pump station; S is an integer greater than or equal to 1;

[0143] Dividing the total water supply flow rate by S to obtain the expected operating flow rate of each of the S available water pumps;

[0144] When the expected operating flow rate is less than or equal to the maximum operating flow rate of the pumping water pump of the target water pump model, determining the operating flow rate of each of the S available pumping water pumps to be the expected operating flow rate;

[0145] Determining target angles of the S available water pumps according to the target corresponding relationship corresponding to the target water pump model and the expected operating flow rate;

[0146] Control the S available water pumps to operate at the target angle.

[0147] In some implementations, there is at least one pump of a pump model in the designated pump station, and the head of the pump of the target pump model at the highest efficiency is closest to the second water level difference.

[0148] In some implementations, the electronic device may store a mapping relationship between the flow range and the number of water pumps of the target water pump model, and determine S available water pumps based on the mapping relationship and the total water supply flow.

[0149] In some embodiments, controlling the operation of at least one fully adjustable angle water pump in the designated pumping station according to the target corresponding relationship and the total water supply flow rate includes:

[0150] According to the second water level difference, a target water pump model is selected from a plurality of water pump signals corresponding to the designated pump station, and S available water pumps of the target water pump model are obtained from at least one fully adjustable angle water pump in the designated pump station; S is an integer greater than or equal to 1;

[0151] Dividing the total water supply flow rate by S to obtain the expected operating flow rate of each of the S available water pumps;

[0152] In the case where the expected operating flow rate is greater than the maximum operating flow rate of the pumping water pump of the target water pump model, determining the operating flow rate of each of the S available pumping water pumps to be the maximum operating flow rate;

[0153] Determining the predetermined angles of the S available water pumps according to the target corresponding relationship corresponding to the target water pump model and the maximum operating flow rate;

[0154] Controlling the S available water pumps to operate at the predetermined angle;

[0155] Determine T candidate water pumps according to the residual flow obtained by subtracting the total operating flow of the S available water pumps from the total water supply flow of the designated pumping station; wherein the total operating flow of the S available water pumps is the result of multiplying S by the maximum operating flow;

[0156] Determining the designated angles of the T candidate water pumps according to the target corresponding relationship corresponding to the models of the candidate water pumps and the remaining flow rate;

[0157] The T optional water pumps are controlled to operate at the specified angles.

[0158] Exemplarily, a mapping relationship between a flow range and the number of candidate water pumps may be stored in the electronic device, and T candidate water pumps may be determined according to the mapping relationship and the remaining flow rate.

[0159] In some implementations, the T alternative water pumps may be water pumps of the same model.

[0160] Figure 2 An example of a schematic diagram of an electronic device structure is shown in FIG. Figure 2 As shown, the electronic device may include: a processor 201, a communications interface 202, a memory 203 and a communication bus 204, wherein the processor 201, the communications interface 202 and the memory 203 communicate with each other via the communication bus 204. The processor 201 may call the logic instructions in the memory 203 to execute the following method:

[0161] Acquire a plurality of initial images obtained by photographing multiple farmland areas respectively, and perform image definition restoration processing on the plurality of initial images respectively to obtain a plurality of restored images;

[0162] Using a classification network model, performing category recognition on each of the multiple repaired images to obtain category information of the multiple repaired images;

[0163] When the category information of the plurality of repaired images are all normal categories, outputting prompt information; the prompt information is used to indicate that no water supply and drainage treatment of the pump station is required;

[0164] In a case where the category information of at least one first restored image among the category information of the plurality of restored images is a waterlogging category, determining at least one first shooting position information corresponding to the at least one first restored image;

[0165] Determining a target pumping station corresponding to the at least one first shooting position information according to the at least one first shooting position information;

[0166] Performing image segmentation processing on the at least one first restored image to determine a waterlogged area and a non-waterlogged area of ​​the at least one first restored image;

[0167] Determine first ratio information between the sum of the areas of the waterlogged areas of the at least one first restored image and the sum of the areas of the entire areas of the at least one first restored image;

[0168] Determining a target waterlogging level according to the first ratio information;

[0169] The drainage of the target pump station is scheduled according to the target flood level.

[0170] It can be understood that the processor 201 of the electronic device can also execute the other steps mentioned in the embodiment of the present application, which will not be described one by one here.

[0171] Illustratively, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of a pump station scheduling method based on image recognition of farmland disaster conditions as described in any embodiment of the present application are implemented.

[0172] This embodiment also provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described in the above embodiments are implemented. For example, it includes:

[0173] Acquire a plurality of initial images obtained by photographing multiple farmland areas respectively, and perform image definition restoration processing on the plurality of initial images respectively to obtain a plurality of restored images;

[0174] Using a classification network model, performing category recognition on each of the multiple repaired images to obtain category information of the multiple repaired images;

[0175] When the category information of the plurality of repaired images are all normal categories, outputting prompt information; the prompt information is used to indicate that no water supply and drainage treatment of the pump station is required;

[0176] In a case where the category information of at least one first restored image among the category information of the plurality of restored images is a waterlogging category, determining at least one first shooting position information corresponding to the at least one first restored image;

[0177] Determining a target pumping station corresponding to the at least one first shooting position information according to the at least one first shooting position information;

[0178] Performing image segmentation processing on the at least one first restored image to determine a waterlogged area and a non-waterlogged area of ​​the at least one first restored image;

[0179] Determine first ratio information between the sum of the areas of the waterlogged areas of the at least one first restored image and the sum of the areas of the entire areas of the at least one first restored image;

[0180] Determining a target waterlogging level according to the first ratio information;

[0181] The drainage of the target pump station is scheduled according to the target flood level.

[0182] To summarize, the pump station scheduling method, equipment and medium for image recognition of farmland disaster conditions provided in the embodiments of the present application determine the target waterlogging level based on the first ratio information between the area sum of the waterlogged area and the area sum of the entire area, and schedule the drainage of the target pump station according to the target waterlogging level. When the target waterlogging level indicates that the disaster is more serious, the drainage flow rate can be increased. When the target waterlogging level indicates that the disaster is less serious, the drainage flow rate can be appropriately reduced. This enables the drainage flow rate to be accurately controlled, thereby improving the accuracy of drainage scheduling for the target pump station.

[0183] All the above-mentioned implementation modes provided in this application can be combined with each other if they do not conflict with each other.

[0184] The method embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0185] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution can essentially or in other words, the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc., including a number of instructions for an electronic device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0186] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for dispatching pump stations based on image recognition of farmland disaster conditions, characterized in that: include: Acquire a plurality of initial images obtained by photographing multiple farmland areas respectively, and perform image definition restoration processing on the plurality of initial images respectively to obtain a plurality of restored images; Using a classification network model, performing category recognition on each of the multiple repaired images to obtain category information of the multiple repaired images; When the category information of the plurality of restored images are all normal categories, outputting prompt information; The prompt information is used to indicate that there is no need to perform water supply and drainage treatment at the pump station; In a case where the category information of at least one first restored image among the category information of the plurality of restored images is a waterlogging category, determining at least one first shooting position information corresponding to the at least one first restored image; Determining a target pumping station corresponding to the at least one first shooting position information according to the at least one first shooting position information; Performing image segmentation processing on the at least one first restored image to determine a waterlogged area and a non-waterlogged area of ​​the at least one first restored image; Determine first ratio information between the sum of the areas of the waterlogged areas of the at least one first restored image and the sum of the areas of the entire areas of the at least one first restored image; Determining a target waterlogging level according to the first ratio information; The drainage of the target pump station is scheduled according to the target flood level.

2. The pump station dispatching method according to claim 1, characterized in that: The obtaining of a plurality of initial images obtained by photographing multiple farmland areas respectively includes: Obtain Y original images captured by Y cameras associated with each farmland area in the multiple farmland areas; Y is an integer greater than or equal to 2; Splicing the Y original images of each farmland area to obtain a spliced ​​image of each farmland area; A downsampling network model is used to downsample the stitched image of each farmland area to obtain an initial image of each farmland area.

3. The pump station dispatching method according to claim 1, characterized in that: The step of scheduling drainage of the target pump station according to the target flood level includes: Acquire the water level information of the first fore pool of the target pump station collected by the first photoelectric liquid level sensor, and the water level information of the first rear pool of the target pump station collected by the second photoelectric liquid level sensor; Determine the total drainage flow of the pump of the target pump station according to the target flooding level and a first water level difference value of the first front pool water level information minus the first back pool water level information; According to the total drainage flow of the water pumps, the operation of M drainage water pumps in the target pumping station is controlled; M is an integer greater than or equal to 2.

4. The pump station dispatching method according to claim 1, characterized in that: The method further comprises: When the category information of at least one second restored image in the category information of the plurality of restored images is a drought category, obtaining at least one second shooting position information corresponding to the at least one second restored image; Determining, according to the at least one second shooting location information, a designated pumping station corresponding to the at least one second shooting location information; Performing image segmentation processing on the at least one second restored image to determine a drought area and a non-drought area of ​​the at least one second restored image; Determine second ratio information between the sum of the areas of the dry regions of the at least one second restored image and the sum of the areas of the entire regions of the at least one second restored image; determining a target drought level according to the second ratio information; The water supply to the designated pumping station is scheduled according to the target drought level.

5. The pump station dispatching method according to claim 4, characterized in that: The step of scheduling the water supply of the designated pumping station according to the target drought level includes: Obtaining water level information of a second fore pool of the designated pumping station collected by a third photoelectric liquid level sensor, and water level information of a second rear pool of the designated pumping station collected by a fourth photoelectric liquid level sensor; determining a total water supply flow rate of the designated pump station according to the target drought level and a second water level difference value obtained by subtracting the second rear pool water level information from the second front pool water level information; According to the second water level difference and the total water supply flow, the operation of at least one fully adjustable angle water pump in the designated pumping station is controlled.

6. The pump station dispatching method according to claim 5, characterized in that: Before acquiring a plurality of initial images respectively obtained by photographing multiple farmland areas, the method further includes: Obtain R flow rates and R lifts of each water pump at each of a plurality of angles in at least one fully adjustable angle water pump in the designated pumping station; R is an integer greater than or equal to 3; Fitting the R flow rates and the R lifts at each angle to obtain a preset corresponding relationship between the flow rate and the lift at each angle; The step of controlling the operation of at least one fully adjustable angle water pump in the designated pumping station according to the second water level difference and the total water supply flow rate comprises: Determine, according to the second water level difference and the preset corresponding relationship, a target flow rate corresponding to the second water level difference at each angle; According to the target flow rate at each angle, determining a target corresponding relationship between the angle and the target flow rate; According to the target corresponding relationship and the total water supply flow, the operation of at least one fully adjustable angle water pump in the designated pumping station is controlled.

7. The pump station dispatching method according to claim 6, characterized in that: The step of controlling the operation of at least one fully adjustable angle water pump in the designated pumping station according to the target corresponding relationship and the total water supply flow rate includes: According to the second water level difference, a target water pump model is selected from a plurality of water pump signals corresponding to the designated pump station, and S available water pumps of the target water pump model are obtained from at least one fully adjustable angle water pump in the designated pump station; S is an integer greater than or equal to 1; Dividing the total water supply flow rate by S to obtain the expected operating flow rate of each of the S available water pumps; When the expected operating flow rate is less than or equal to the maximum operating flow rate of the pumping water pump of the target water pump model, determining the operating flow rate of each of the S available pumping water pumps to be the expected operating flow rate; Determining target angles of the S available water pumps according to the target corresponding relationship corresponding to the target water pump model and the expected operating flow rate; Control the S available water pumps to operate at the target angle.

8. The pump station dispatching method according to claim 6, characterized in that: The step of controlling the operation of at least one fully adjustable angle water pump in the designated pumping station according to the target corresponding relationship and the total water supply flow rate includes: According to the second water level difference, a target water pump model is selected from a plurality of water pump signals corresponding to the designated pump station, and S available water pumps of the target water pump model are obtained from at least one fully adjustable angle water pump in the designated pump station; S is an integer greater than or equal to 1; Dividing the total water supply flow rate by S to obtain the expected operating flow rate of each of the S available water pumps; In the case where the expected operating flow rate is greater than the maximum operating flow rate of the pumping water pump of the target water pump model, determining the operating flow rate of each of the S available pumping water pumps to be the maximum operating flow rate; Determining the predetermined angles of the S available water pumps according to the target corresponding relationship corresponding to the target water pump model and the maximum operating flow rate; Controlling the S available water pumps to operate at the predetermined angle; Determine T candidate water pumps according to the residual flow obtained by subtracting the total operating flow of the S available water pumps from the total water supply flow of the designated pumping station; wherein the total operating flow of the S available water pumps is the result of multiplying S by the maximum operating flow; Determining the designated angles of the T candidate water pumps according to the target corresponding relationship corresponding to the models of the candidate water pumps and the remaining flow rate; The T optional water pumps are controlled to operate at the specified angles.

9. An electronic 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 pump station scheduling method based on image recognition of farmland disaster conditions as described in any one of claims 1 to 8 are implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the pump station scheduling method based on image recognition of farmland disaster conditions as described in any one of claims 1 to 8 are implemented.

Images