Early identification method and device for rice planting

Abstract

The invention discloses a rice planting early recognition method and device. The method comprises the following steps: on the basis of a current potential sub-meter image of a monitored area, carrying out cultivated land parcel identification on the monitored area, and obtaining cultivated land parcel information corresponding to the monitored area, so as to assist rice planting identification by utilizing a cultivated land range and overcome the interference of a permanent water body on rice field extraction; determining a first time period according to the rice phenological information corresponding to the monitoring area, and performing rice feature extraction based on the time sequence radar image of the monitoring area in the first time period to obtain a rice field feature map corresponding to the monitoring area; and performing decision fusion processing on the cultivated land parcel information and the paddy field feature map to obtain a paddy identification result of the monitored area, thereby effectively distinguishing cultivated land and paddy distribution, realizing paddy early identification, and timely, quickly and accurately providing paddy planting early data for agricultural development.

Description

Technical Field

[0001] This application relates to the field of agricultural monitoring, and specifically relates to a method, device, electronic device, and medium for early identification of rice planting. Background Technique

[0002] Rice is one of the most important food crops in the world, and nearly half of the world's population takes rice as the main food. Timely and accurately monitoring the rice planting situation is of great significance in agricultural production management. Traditional monitoring of rice planting distribution relies on manual on-site surveys, with low timeliness and accuracy. In recent years, with the continuous development of satellite remote sensing technology, its advantages such as large coverage area, macroscopic monitoring, and short revisit cycle have been widely applied in the business of agricultural information monitoring.

[0003] However, in the current research on rice planting distribution extraction, generally, multi-temporal remote sensing data throughout the year or remote sensing images of the entire growth period of rice are used for rice planting distribution extraction, and the planting distribution results are obtained at the end of the rice growth period or the second year. This extraction mode cannot monitor the initial stage after rice transplanting, with poor timeliness and unable to meet the actual business requirements. Summary of the Invention

[0004] Therefore, this application provides a method and device for early identification of rice planting to solve the problems of poor timeliness of rice planting monitoring and inability to meet the actual application requirements in the prior art due to the inability of existing rice planting monitoring methods to monitor the initial stage after rice transplanting.

[0005] To achieve the above object, the first aspect of this application provides a method for early identification of rice planting, and the method includes: based on the current sub-meter image of the monitoring area, identifying the cultivated land plots in the monitoring area to obtain the cultivated land plot information corresponding to the monitoring area; determining the first time period according to the rice phenological information corresponding to the monitoring area; based on the time-series radar image of the monitoring area within the first time period, extracting rice features to obtain the rice field feature map corresponding to the monitoring area; performing decision fusion processing on the cultivated land plot information and the rice field feature map to obtain the rice identification result of the monitoring area.

[0006] According to the first aspect, the identifying the cultivated land plots in the monitoring area based on the current sub-meter image of the monitoring area to obtain the cultivated land plot information corresponding to the monitoring area includes: based on the cultivated land extraction algorithm and the current sub-meter image, identifying the cultivated land plots in the monitoring area to obtain the cultivated land plot information corresponding to the monitoring area; wherein, the cultivated land plot information at least includes the location information and distribution of the cultivated land.

[0007] According to the first aspect, or any implementation manner of the above first aspect, based on the time-series radar images of the monitoring area within the first time period, rice feature extraction is performed to obtain a rice paddy feature map corresponding to the monitoring area, including: performing minimum value synthesis processing on the time-series radar images of the monitoring area within the first time period to obtain a rice paddy feature map corresponding to the monitoring area.

[0008] According to the first aspect, or any implementation manner of the above first aspect, decision fusion processing is performed on the cultivated land plot information and the rice paddy feature map to obtain a rice recognition result for the monitoring area, including: performing decision fusion on the cultivated land plot information and the rice paddy feature map to obtain a fused image; determining the pixel mean value of each cultivated land plot in the fused image to obtain a plot image carrying the pixel mean value; performing threshold segmentation on the plot image based on a threshold segmentation algorithm, and determining the plot image with a pixel mean value less than the first threshold as the rice area in the monitoring area.

[0009] According to the first aspect, or any implementation manner of the above first aspect, the first time period includes: a fixed duration before the rice transplanting period to a fixed duration after the rice transplanting period.

[0010] According to the first aspect, or any implementation manner of the above first aspect, the method further includes: verifying the accuracy of the rice recognition result based on the historical rice planting data corresponding to the monitoring area.

[0011] A second aspect of the present application provides a rice planting early recognition device, which includes: a cultivated land recognition module, based on the current sub-meter image of the monitoring area, performing cultivated land plot recognition on the monitoring area to obtain cultivated land plot information corresponding to the monitoring area; a data selection module, determining a first time period according to the rice phenological information corresponding to the monitoring area; a feature extraction module, based on the time-series radar images of the monitoring area within the first time period, performing rice feature extraction to obtain a rice paddy feature map corresponding to the monitoring area; a fusion recognition module, performing decision fusion processing on the cultivated land plot information and the rice paddy feature map to obtain a rice recognition result for the monitoring area.

[0012] A third aspect of the present application provides an electronic device, which includes: one or more processors; a storage device, on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method of any item in the first aspect; one or more I / O interfaces, connected between the processor and the memory, configured to implement information interaction between the processor and the memory.

[0013] A fourth aspect of the present application provides a computer-readable medium, on which a computer program is stored, and when the program is executed by a processor, it implements the method of any item in the above first aspect.

[0014] The present application has the following advantages: In a rice planting early recognition method provided by an embodiment of the present application, based on the current sub-meter image of the monitoring area, the cultivated land plots in the monitoring area are recognized to obtain the cultivated land plot information corresponding to the monitoring area, so as to use the cultivated land range to assist in rice planting recognition and overcome the interference of permanent water bodies on paddy field extraction; then, according to the rice phenological information corresponding to the monitoring area, the first time period is determined, and based on the temporal radar image of the monitoring area within the first time period, rice feature extraction is performed to obtain the rice field feature map corresponding to the monitoring area; finally, decision fusion processing is performed on the cultivated land plot information and the rice field feature map to obtain the rice recognition result of the monitoring area, thereby effectively distinguishing the distribution of cultivated land and rice, realizing early rice recognition, and providing timely, rapid, and accurate early rice planting data for agricultural development. Description of the Drawings

[0015] The drawings are used to provide a further understanding of the present application and constitute a part of the specification. They are used to explain the present application together with the following specific embodiments, but do not constitute a limitation to the present application.

[0016] Figure 1 It is a schematic flowchart of a rice planting early recognition method provided by an embodiment of the present application; Figure 2 It is a schematic diagram of the distribution of cultivated land plots in a monitoring area provided by an embodiment of the present application; Figure 3 It is a schematic diagram of the backscattering value distribution in a monitoring area provided by an embodiment of the present application; Figure 4 It is a schematic flowchart of another rice planting early recognition method provided by an embodiment of the present application; Figure 5 It is a schematic diagram of the rice distribution in a monitoring area provided by an embodiment of the present application; Figure 6 It is a schematic structural diagram of a rice planting early recognition device provided by an embodiment of the present application; Figure 7 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed Description of the Embodiments

[0017] To enable those skilled in the art to better understand the technical solutions of the present disclosure, the following describes exemplary embodiments of the present disclosure with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to assist in understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for clarity and conciseness, the description below omits the description of well-known functions and structures.

[0018] In the case of no conflict, the embodiments of the present disclosure and the features in the embodiments may be combined with each other.

[0019] As used in this application, the term "and / or" includes any and all combinations of one or more related listed items.

[0020] The terms used in this application are only used to describe specific embodiments and are not intended to limit this application. As used in this application, the singular forms "a" and "the" are also intended to include the plural forms unless the context clearly indicates otherwise.

[0021] When the terms "comprising" and / or "made of" are used in this application, it is specified that there are features, wholes, steps, operations, elements and / or components, but it does not exclude the existence or addition of one or more other features, wholes, steps, operations, elements, components and / or their groups.

[0022] The embodiments of this application can be described with reference to the plan view and / or sectional view by means of the ideal schematic diagrams of this application. Therefore, the example illustrations can be modified according to the manufacturing technology and / or tolerance.

[0023] Unless otherwise defined, the meanings of all terms (including technical and scientific terms) used in this application are the same as those commonly understood by those of ordinary skill in the art. It will also be understood that terms such as those defined in common dictionaries should be interpreted as having a meaning consistent with their meaning in the relevant art and the context of this application, and will not be interpreted as having an idealized or overly formal meaning unless this application clearly defines so.

[0024] Rice is one of the most important food crops in the world, and nearly half of the world's population takes rice as the main food. Timely and accurately monitoring the rice planting situation is of great significance in agricultural production management. The traditional monitoring of rice planting distribution relies on manual field surveys, with low timeliness and accuracy. In recent years, with the continuous development of satellite remote sensing technology, its advantages such as large coverage area, macro monitoring, and short revisit cycle have been widely applied to the business of agricultural information monitoring.

[0025] However, in the current research on rice planting distribution extraction, generally, multi-temporal remote sensing data throughout the year or remote sensing images of the entire growth period of rice are used for rice planting distribution extraction, and the planting distribution results are obtained at the end of the rice growth period or the following year. This extraction mode cannot monitor the initial stage after rice transplanting, with poor timeliness and unable to meet the actual business needs. For example, in the field of agricultural insurance, it is necessary to monitor the rice planting distribution in the initial stage after rice transplanting to assist in the underwriting inspection work of rice planting insurance.

[0026] To this end, the present application provides a method for early identification of rice planting, which extracts cultivated land plots using high-resolution sub-meter images, then uses dual-polarization radar data to distinguish paddy fields during the field flooding period from other ground objects, obtains a paddy field feature map, and performs decision fusion and threshold segmentation on the paddy field feature map and the cultivated land plot data to obtain the identification result of the early stage of rice planting. This method can overcome the limitation of difficult visible light imaging in cloudy and rainy areas, does not require field collection of rice samples, is simple, easy to operate, and has high accuracy, effectively solving the limitation of using satellite remote sensing images for early rice identification, and can provide timely, rapid, and accurate early rice planting data for relevant departments.

[0027] In the embodiment of the present application, in order to monitor rice planting in the study area (monitoring area), basic data of the study area can be collected in advance. Such basic data includes, for example, the study area range data, the phenological information of rice, and the historical rice planting data of the statistical yearbook for consecutive years (such as 5 years or 7 years).

[0028] Among them, the study area range data is the regional range vector of the area where rice planting distribution needs to be monitored (the regional range vector of the monitoring area), and the phenological period information of rice is the rice phenological calendar of the monitoring area, including the time period when the transplanting period of rice is located, etc. The transplanting period of this rice (commonly known as the "rice transplanting period") refers to the stage of transplanting the cultivated rice seedlings from the seedbed to the paddy field.

[0029] The method for early identification of rice planting provided by the embodiment of the present application is applied to an electronic device. As Figure 1 shown, this rice planting monitoring method includes: step S101 - step S104.

[0030] Among them, in step S101, based on the current sub-meter image of the monitoring area, the cultivated land plots in the monitoring area are identified to obtain the cultivated land plot information corresponding to the monitoring area.

[0031] In the embodiment of the present application, this current sub-meter image can select the sub-meter base map product on the Four-dimensional Cloud Service Platform Four-dimensional Earth. This product is updated once a year in the Chinese range, with a spatial resolution of 0.8 meters, and the spatial resolution of multiple cities is 0.5 meters.

[0032] The cultivated land plot information is in raster form, and this cultivated land plot information includes at least the location information and distribution of the cultivated land.

[0033] In a possible implementation manner provided by the embodiment of the present application, the electronic device identifies the cultivated land plots in the monitoring area based on the current sub-meter image of the monitoring area to obtain the cultivated land plot information corresponding to the monitoring area, including: identifying the cultivated land plots in the monitoring area based on the cultivated land extraction algorithm and the current sub-meter image of the monitoring area to obtain the cultivated land plot information corresponding to the monitoring area.

[0034] Among them, the cultivated land extraction algorithm is the AI cultivated land recognition algorithm.

[0035] As Figure 2 shown, an embodiment of the present application provides a schematic diagram of the distribution of cultivated land plots in a monitoring area. Among them, the area framed by the circle 201 is the monitoring area, and the area covered by the grid is the cultivated land plot, such as the cultivated land plot 202. It should be noted that the distribution of the cultivated land plots in this monitoring area is only for illustrative purposes. In actual applications, the shape of the cultivated land plot may be irregular.

[0036] In the embodiment of the present application, the information of the cultivated land plots in the monitoring area is first determined to facilitate the exclusion of the interference of permanent water bodies on the extraction of paddy fields in the subsequent rice recognition process. After determining the information of the cultivated land plots in the monitoring area, the rice characteristics of the monitoring area need to be extracted. This process can be referred to the following steps S102 - step S103.

[0037] In step S102, according to the rice phenological information corresponding to the monitoring area, the first time period is determined.

[0038] In the embodiment of the present application, according to the pre - obtained rice phenological information of the monitoring area, the rice transplanting period is determined, and the period from a fixed duration before the rice transplanting period to a fixed duration after the rice transplanting period is used as the first time period. For example, the period from one week before the rice transplanting period to one week after the rice transplanting period is used as the first time period. Taking the rice transplanting period from April 10th to April 20th as an example, the first time period is from April 3rd to April 27th.

[0039] It should be noted that in the embodiment of the present application, the early stage of rice planting refers to the initial stage after rice transplanting, that is, from the start of the rice transplanting period to one week after the rice transplanting period. Taking the rice transplanting period from April 10th to April 20th as an example, the early stage of rice planting is from April 10th to April 27th.

[0040] In step S103, based on the time - series radar images of the monitoring area within the first time period, rice feature extraction is performed to obtain the rice field feature map corresponding to the monitoring area.

[0041] Among them, the time - series radar images can adopt the time - series Sentinel - 1 L1 Ground Range Detected (GRD) products before and after the rice transplanting period, and the polarization mode is the polarization mode of vertical transmission (V) and horizontal reception (H) (VH polarization).

[0042] In a possible implementation provided by the embodiments of the present application, the electronic device extracts rice characteristics based on the time-series radar images of the monitoring area in the first time period, and obtains the rice paddy characteristic map corresponding to the monitoring area (the above step S103), including: performing minimum value composition processing on the time-series radar images of the monitoring area in the first time period to obtain the rice paddy characteristic map corresponding to the monitoring area.

[0043] Among them, minimum value composition processing is a commonly used data processing method in remote sensing time-series analysis. Its core is to compare pixel by pixel (pixel element) the image data of multiple time phases in the same area, select the minimum value, and finally generate a composite image. The specific process is as follows: Data selection: Obtain multiple GRD radar images of the same area at different time points; Pixel-by-pixel comparison: Traverse the backscattering values (radar reflection intensities) corresponding to each pixel point in all time phases, and select the minimum value of the backscattering value of the pixel point in the entire time series as the final value of the pixel in the composite image; Generate composite image: Combine the minimum values of the backscattering values of all pixels into a new image.

[0044] It should be noted that in the initial stage after rice transplanting (which can also be called the flooded field period), the rice plants do not cover the water surface, and the rice paddy has a lower backscattering compared to other ground objects, showing dark features on the radar image. According to the inconsistent tones of the rice paddy and other ground objects on the radar image in the initial stage after rice transplanting, the ground object features corresponding to different tones are judged, and then the remote sensing interpretation mark of the rice paddy in the initial stage after rice transplanting of the time-series GRD product is constructed. In order to maximize the tonal difference between the flooded field rice paddy and other ground objects, in the embodiments of the present application, minimum value composition processing is performed on the time-series GRD product to obtain the minimum value composite image map.

[0045] Among them, on the minimum value composite image map, the pixel values of the flooded field rice paddy are lower and the tone is darker; the pixel values of other ground objects are slightly higher and the tone is brighter. In the embodiments of the present application, the minimum value composite image is used as the rice paddy characteristic map for subsequent early rice identification.

[0046] As Figure 3 shown, the embodiments of the present application provide a schematic diagram of the backscattering value distribution of the monitoring area. Among them, the area framed by the circle 301 is the monitoring area, and the black-covered area is the area with a low backscattering value (which can be considered as a rice paddy in this rice paddy characteristic map), such as area 302. It should be noted that the backscattering value distribution of this monitoring area is only for illustrative purposes, and in actual applications, the shape of the area with a low backscattering value may be irregular.

[0047] It is understandable that the main rice-producing areas are mostly in the cloudy and rainy southern regions, where optical remote sensing imaging is difficult and the available effective images are few. In addition, in the initial stage of rice transplanting, its characteristics are not obvious, and it is difficult to monitor and analyze rice planting based on visible light. In the embodiments of the present application, dual-polarization radar data is used to distinguish paddy fields during the field flooding period from other ground objects, and a paddy field feature map is obtained, which can effectively identify the rice distribution in the later stage.

[0048] In step S104, decision fusion processing is performed on the cultivated land parcel information and the paddy field feature map to obtain the rice recognition result of the monitoring area.

[0049] Among them, the rice recognition result of the monitoring area is a raster image, which contains information such as the location and distribution of rice planting.

[0050] In a possible implementation manner provided by the embodiments of the present application, as Figure 4 shown, performing decision fusion processing on the cultivated land parcel information and the paddy field feature map to obtain the rice recognition result of the monitoring area (the above step S104) includes: the following steps S401 - step S403.

[0051] Step S401: Perform decision fusion on the cultivated land parcel information and the paddy field feature map to obtain a fused image.

[0052] Step S402: Determine the pixel mean value of each cultivated land parcel in the fused image to obtain a parcel image carrying the pixel mean value.

[0053] Among them, the pixel mean value is the average of the gray values or color values of all pixel points. In an 8-bit gray image, the pixel value range is from 0 (pure black) to 255 (pure white). The pixel values in the dark area are close to 0, and those in the bright area are close to 255. For example, the pixel values in the dark area may be concentrated between 0 - 50, while those in the bright area may be between 200 - 255. If a certain area is darker, its pixel values are generally lower, and the calculated mean value is naturally smaller. For example, the mean value of four dark pixels (10, 20, 30, 40) is 25, which is much lower than the mean value of the bright area.

[0054] Step S403: Perform threshold segmentation on the parcel image based on the threshold segmentation algorithm, and determine the parcel image with a pixel mean value less than the first threshold as the rice area in the monitoring area.

[0055] Among them, the first threshold is a threshold for screening out relatively small pixel mean values, and this first threshold can be set according to the actual application situation, for example, set to 50.

[0056] In this embodiment, the electronic device uses the cultivated land range to assist in the early identification of rice planting. That is, by performing decision fusion processing on the cultivated land parcel information and the paddy field feature map, the interference of permanent water bodies on paddy field extraction can be overcome, and the rice recognition result of the monitoring area can be obtained.

[0057] In the embodiment itself, the rice recognition result of the monitoring area can be reflected as a schematic diagram of rice distribution. For example Figure 5 As shown, the embodiment of the present application provides a schematic diagram of rice distribution in a monitoring area. Among them, the area framed by the circle 501 is the monitoring area, and the area covered by the black dot pattern is the rice planting area, such as the rice planting area 505. It should be noted that the rice distribution in this monitoring area is only for illustrative purposes. In actual applications, the shape of this rice distribution area may be irregular.

[0058] In the embodiment of the present application, the early rice planting recognition method further includes: determining the accuracy of the rice recognition result based on the historical rice planting data corresponding to the monitoring area.

[0059] Among them, the historical rice planting data corresponding to the monitoring area can be the historical rice planting data in the statistical yearbooks of the statistical bureau for consecutive years (such as 5 years or 7 years).

[0060] In this embodiment, the electronic device counts the rice planting area according to administrative regions (such as city - county - township), and compares it with the collected historical rice planting area data, so as to verify the accuracy of rice recognition.

[0061] In this embodiment, when the accuracy of the rice recognition result is relatively large (for example, the accuracy is greater than 90%), the early rice recognition result can be mapped according to administrative region division (such as city - county - township) to make a series of thematic maps for rice monitoring. It can also monitor the growth trend of rice based on this rice recognition result, which is convenient for providing real - time data for precision agriculture in the follow - up.

[0062] In an early rice planting recognition method provided by an embodiment of the present application, the electronic device first identifies the cultivated land plots in the monitoring area based on the current sub - meter image of the monitoring area, obtains the cultivated land plot information corresponding to the monitoring area, so as to use the cultivated land range to assist in rice planting recognition and overcome the interference of permanent water bodies on paddy field extraction; then determines the first time period according to the rice phenological information corresponding to the monitoring area, and performs rice feature extraction based on the time - series radar image of the monitoring area within this first time period to obtain the rice field feature map corresponding to the monitoring area; finally, performs decision - level fusion processing on the cultivated land plot information and the rice field feature map to obtain the rice recognition result of the monitoring area, so as to effectively distinguish the cultivated land and the rice distribution, realize early rice recognition, and provide timely, fast, and accurate early rice planting data for agricultural development.

[0063] The rice planting early identification method provided by the embodiments of the present application has the following advantages: First, compared with traditional rice planting monitoring methods, this method makes full use of multi-source satellite remote sensing data and image processing technology, without the need for on-site manual investigation, and has a fast extraction speed, fundamentally solving the problems of complex work, low efficiency, and low accuracy in traditional rice planting monitoring.

[0064] Second, compared with other multi-source satellite image rice planting monitoring technologies, this method fully analyzes the unique scattering characteristics of paddy fields in radar images, fundamentally solving the problem of confusion between paddy fields and permanent water bodies, and uses cultivated land plot auxiliary analysis to achieve early identification of rice planting.

[0065] This method has application value in multiple scenarios. For example, it can play a role in scenarios such as agricultural management, agricultural insurance, agricultural production, and precision agriculture.

[0066] Agricultural management. In this early identification of rice, the rice planting area can be quickly obtained within a short time after rice transplanting, which can provide data support for researchers in the monitoring area to accurately understand the rice planting situation in a timely manner.

[0067] Agricultural insurance. Currently, major insurance companies have introduced satellite remote sensing technology to empower the insurance underwriting work. However, in actual business, the rice underwriting inspection time node has not reached the optimal growth period of rice, so the exploration of rice early identification technology is particularly important.

[0068] Agricultural production. By early identifying the rice planting situation, agricultural producers can timely master the growth situation of rice, reasonably arrange farming activities, and improve agricultural production efficiency.

[0069] Precision agriculture. Timely and accurate crop planting distribution data can provide real-time data for precision agriculture. For example, subsequent growth monitoring can be carried out based on crop varieties, and the growth monitoring data is more referenceable.

[0070] The step division of the above various methods is only for clear description. When implemented, they can be combined into one step or some steps can be split into multiple steps. As long as the same logical relationship is included, it is within the protection scope of the present application; adding insignificant modifications to the algorithm or process or introducing insignificant designs, but not changing the core design of its algorithm and process, are within the protection scope of this application.

[0071] In the second aspect, the embodiments of the present application provide a rice planting early identification device based on multi-source data. As Figure 6 shown, the rice planting early identification device includes: a cultivated land identification module 61, a data selection module 62, a feature extraction module 63, and a fusion identification module 64.

[0072] The cultivated land recognition module 61 recognizes the cultivated land plots in the monitoring area based on the current sub-meter image of the monitoring area, and obtains the cultivated land plot information corresponding to the monitoring area; The data selection module 62 determines the first time period according to the rice phenological information corresponding to the monitoring area.

[0073] The feature extraction module 63 extracts rice features based on the temporal radar image of the monitoring area within the first time period, and obtains the rice paddy feature map corresponding to the monitoring area.

[0074] The fusion recognition module 64 performs decision fusion processing on the cultivated land plot information and the rice paddy feature map to obtain the rice recognition result of the monitoring area.

[0075] In the embodiment of the present application, the fusion recognition module further includes: a first sub-module, a second sub-module, and a third sub-module. Among them, the first sub-module is used to perform decision fusion on the cultivated land plot information and the rice paddy feature map to obtain a fused image; the second sub-module is used to determine the pixel mean value of each cultivated land plot in the fused image to obtain a plot image carrying the pixel mean value; the third sub-module is used to perform threshold segmentation on the plot image based on the threshold segmentation algorithm, and determine the plot image with a pixel mean value less than the first threshold as the rice area in the monitoring area.

[0076] In the rice planting early recognition device provided by the embodiment of the present application, the cultivated land recognition module is used to recognize the cultivated land plots in the monitoring area based on the current sub-meter image of the monitoring area, and obtain the cultivated land plot information corresponding to the monitoring area, so as to use the cultivated land range to assist rice planting recognition and overcome the interference of permanent water bodies on paddy field extraction; the data selection module is used to determine the first time period according to the rice phenological information corresponding to the monitoring area, and the feature extraction module is used to extract rice features based on the temporal radar image of the monitoring area within the first time period, and obtain the rice paddy feature map corresponding to the monitoring area; the fusion recognition module is used to perform decision fusion processing on the cultivated land plot information and the rice paddy feature map to obtain the rice recognition result of the monitoring area, so as to effectively distinguish the distribution of cultivated land and rice, realize early rice recognition, and provide timely, fast, and accurate early rice planting data for agricultural development.

[0077] It should be clear that the present application is not limited to the specific configurations and processes described and illustrated in the above embodiments. For the convenience and brevity of description, the detailed descriptions of known methods are omitted here, and the specific working processes of the systems, modules, and units described above can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0078] Figure 7 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. See Figure 7, the electronic device includes: one or more processors 701; a memory 702 storing one or more programs, which when executed by the one or more processors, cause the one or more processors to implement the early rice planting recognition method of any one of the above; one or more I / O interfaces 703 connected between the processor and the memory and configured to enable information interaction between the processor and the memory.

[0079] Among them, the processor 701 is a device with data processing capabilities, including but not limited to a central processing unit (CPU), etc.; the memory 702 is a device with data storage capabilities, including but not limited to a random access memory (RAM, more specifically such as SDRAM, DDR, etc.), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory (FLASH); the I / O interface (read / write interface) 703 is connected between the processor 701 and the memory 702 and can enable information interaction between the processor 701 and the memory 702, including but not limited to a data bus (Bus), etc.

[0080] In some embodiments, the processor 701, the memory 702, and the I / O interface 703 are interconnected through a bus and further connected to other components of the computing device.

[0081] This embodiment also provides a computer-readable medium storing a computer program, which when executed by a processor, implements the early rice planting recognition method provided in this embodiment. To avoid repeated description, the specific steps of the early rice planting recognition method are not elaborated here.

[0082] Those of ordinary skill in the art can understand that all or some of the steps in the above-invented method, and the functional modules / units in the system and device, can be implemented as software, firmware, hardware, and their appropriate combinations. In the hardware implementation, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component can have multiple functions, or one function or step can be executed by several physical components in cooperation. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or can be implemented as hardware, or can be implemented as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include a computer storage medium (or non-transitory medium) and a communication medium (or transitory medium). As is well known to those of ordinary skill in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data. Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile discs (DVD) or other optical disc storage, magnetic cartridges, tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, as is well known to those of ordinary skill in the art, a communication medium typically contains computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and can include any information delivery medium.

[0083] It should be noted that in this article, the term "including", "comprising", or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article, or device including a series of elements not only includes those elements but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article, or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article, or device including that element.

[0084] Those skilled in the art can understand that although some embodiments herein include certain features included in other embodiments rather than other features, the combination of features of different embodiments means that it is within the scope of this embodiment and forms different embodiments.

[0085] It is understandable that the above embodiments are merely exemplary embodiments adopted to illustrate the principle of the present application. However, the present application is not limited thereto. For those of ordinary skill in the art, various modifications and improvements can be made without departing from the spirit and essence of the present application, and these modifications and improvements are also regarded as the protection scope of the present application.

Claims

1. A method for early identification of rice planting, characterized in that: Methods include: Based on the current sub-meter image of the monitoring area, the cultivated land parcels in the monitoring area are identified to obtain the cultivated land parcel information corresponding to the monitoring area; wherein the cultivated land parcel information at least includes the location information and distribution of the cultivated land; Determine the first time period according to the rice phenological information corresponding to the monitoring area; Extract rice features based on the time-series radar images of the monitoring area within the first time period to obtain a rice field feature map corresponding to the monitoring area; The cultivated land plot information and rice field characteristic map are fused and processed to obtain the rice identification results in the monitored area.

2. The method according to claim 1, characterized in that The method of identifying cultivated land plots in the monitoring area based on the current sub-meter image of the monitoring area and obtaining cultivated land plot information corresponding to the monitoring area includes: Based on the cultivated land extraction algorithm and current sub-meter images, the cultivated land plots in the monitoring area are identified to obtain the cultivated land plot information corresponding to the monitoring area.

3. The method according to claim 1, characterized in that The step of extracting rice features based on the time-series radar images of the monitoring area within the first time period to obtain a rice field feature map corresponding to the monitoring area includes: The time-series radar images of the monitoring area within the first time period are processed by minimum value synthesis to obtain a rice field characteristic map corresponding to the monitoring area.

4. The method according to claim 3, characterized in that The cultivated land plot information and rice field feature map are processed for decision fusion to obtain the rice identification results in the monitoring area, including: Make decision fusion on cultivated land plot information and rice field feature map to obtain fused image; Determine the pixel mean of each cultivated land plot in the fused image to obtain a plot image carrying the pixel mean; The plot images are segmented based on the threshold segmentation algorithm, and the plot images with pixel mean values ​​less than the first threshold are determined as the rice areas in the monitoring area.

5. The method according to claim 3, characterized in that: The first time period includes: a fixed time period before the rice transplanting period to a fixed time period after the rice transplanting period.

6. The method according to claim 1, characterized in that The method further comprises: The accuracy of rice identification results is verified based on the historical rice planting data corresponding to the monitoring area.

7. A device for early identification of rice planting, characterized in that: The device includes: The cultivated land identification module identifies cultivated land plots in the monitored area based on the current sub-meter images of the monitored area and obtains the cultivated land plot information corresponding to the monitored area; The data selection module determines the first time period according to the rice phenological information corresponding to the monitoring area; A feature extraction module extracts rice features based on the time-series radar images of the monitoring area during the first time period to obtain a rice field feature map corresponding to the monitoring area; The fusion recognition module performs decision fusion processing on the cultivated land plot information and the rice field characteristic map to obtain the rice recognition results in the monitored area.

8. The device according to claim 7, characterized in that The fusion recognition module comprises: The first submodule is used to make a decision fusion of the cultivated land plot information and the rice field feature map to obtain a fused image; The second submodule is used to determine the pixel mean of each cultivated land plot in the fused image to obtain a plot image carrying the pixel mean; The third submodule is used to perform threshold segmentation on the plot image based on the threshold segmentation algorithm, and determine the plot image with a pixel mean value less than the first threshold as the rice area in the monitoring area.

9. An electronic device, characterized in that: include: one or more processors; A storage device having one or more programs stored thereon, wherein when the one or more programs are executed by one or more processors, the one or more processors implement the method according to any one of claims 1 to 6; One or more I / O interfaces are connected between the processor and the memory and are configured to implement information exchange between the processor and the memory.

10. A computer readable medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images