Intelligent seeding operation terminal platform based on visual perception

Abstract

The invention relates to the field of image recognition, in particular to an intelligent seeding operation terminal platform based on visual perception, which performs dynamic evolution analysis on a farmland geographical image according to the soil moisture content of a farmland, calculates the soil moisture content characteristic of each seeding area, and calibrates each seeding area as a first type area or a second type area; carrying out soil moisture content airspace analysis according to the landform elements of the second-class region, and determining an effective seeding track of the second-class region; comparing the geographical distribution images of the first-class region and the second-class region with a visual perception image generated by the seeder, and determining whether the seeder enters the first-class region or the second-class region; and visually identifying the deviation between the actual seeding track and the effective seeding track in the second type of region so as to adjust the seed reseeding in the second type of region. Visual perception from a global range to a local range of a farmland can be performed to guide seeding operation, the seeding operation efficiency is improved, and the overall germination rate of the farmland is ensured.

Description

Technical Field

[0001] The present invention relates to the field of image recognition, and in particular to a terminal platform for intelligent seeding operations based on visual perception. Background Art

[0002] Spring plowing mainly involves sowing seeds on farmland. The timing of sowing directly affects the germination rate of seeds. Once the appropriate sowing time is missed, it will directly affect the growth trend and yield of crops, and may lead to poor harvest or total crop failure. In order to determine the appropriate time for sowing, the weather during the spring plowing period can be predicted, mainly for accurate predictions of temperature and rainfall. Studies have found that the soil moisture of farmland is an important indicator for judging whether the timing of sowing is appropriate. When the soil moisture is at a high level, the seeds after sowing can obtain the heat and water required for germination in the soil in a timely and sufficient manner, which is conducive to improving the germination rate of seeds. By monitoring the soil moisture of farmland, a reliable reference basis can be provided for sowing operations.

[0003] Existing seeding operations all judge whether the current time is suitable for seeding based on the soil moisture of the entire farmland. However, considering the large area of ​​farmland in the planting area, the seeding time of the entire farmland may be delayed due to insufficient soil moisture in local areas. If the global scope of the farmland is uniformly seeded without optimizing the seeding operations in the areas with insufficient soil moisture, it will be impossible to make up for the low germination rate of seeds in the local areas with insufficient soil moisture. How to visually perceive the global scope of the farmland to achieve differentiated identification of soil moisture and visually perceive the local scope of the farmland to adjust seed placement is of great significance for saving the workload of seeding operations, improving the efficiency of seeding operations, and ensuring the overall germination rate of the farmland. Summary of the invention

[0004] In order to avoid uniform seeding operations on the entire farmland, which leads to low seed germination rate in the local area of ​​insufficient soil moisture in the farmland, it is necessary to perform visual perception on the global range of the farmland to realize differentiated identification of soil moisture and perform visual perception on the local range of the farmland to realize seed placement adjustment, so as to realize visual perception-guided seeding operations from the global range to the local range of the farmland. The present invention provides a terminal platform for intelligent seeding operations based on visual perception, and the terminal platform includes the following modules: The soil moisture evolution analysis module is used to dynamically analyze the evolution of the farmland geographic image according to the soil moisture of the farmland and calculate the soil moisture characteristics of each sowing area; A region marking module, for marking each sowing region as a first type of region or a second type of region according to the soil moisture characteristics, and visually identifying geomorphic elements of the second type of region; A trajectory determination module, configured to perform a spatial analysis of soil moisture conditions in the second type of area according to the geomorphic elements, and determine an effective sowing trajectory for the second type of area; An image comparison module is used to generate a geographical distribution image of all first-category areas and second-category areas, and compare it with the visual perception image generated by the seed drill to determine whether the seed drill enters the first-category area or the second-category area; A trajectory deviation identification module, used for visually identifying the deviation between the actual sowing trajectory of the sowing machine and the effective sowing trajectory when the sowing machine enters the second type of area; An adjustment module is used to adjust the seeding machine's seed reseeding in the second type of area according to the deviation.

[0005] Preferably, before the soil moisture evolution analysis module performs dynamic evolution analysis on the farmland geographic image according to the soil moisture of the farmland, it includes: Thermal infrared visual recognition is performed on the entire farmland at several time points to obtain the surface temperature and soil moisture content of the entire farmland at several time points; wherein the several time points at least include daytime time points and evening time points on several dates; The surface temperature and soil moisture content at each time point are inverted and calculated to obtain the soil moisture conditions of the farmland at each time point.

[0006] Preferably, the soil moisture evolution analysis module performs a dynamic evolution analysis on the farmland geographic image according to the soil moisture of the farmland, and calculates the soil moisture characteristics of each sowing area, specifically: Mapping the soil moisture condition of the farmland at each time point to a farmland geographic image divided with sowing area boundaries, and performing soil moisture condition edge sharpening processing on all sowing areas in the farmland geographic image; A dynamic time evolution analysis of the soil moisture conditions of each sowing area in the farmland geographic image at all time points is performed, and the soil moisture characteristics of each sowing area in the corresponding time interval at all time points are calculated; wherein the soil moisture characteristics include the soil moisture fluctuation changes of each sowing area in the time interval.

[0007] Preferably, the region marking module marks each sowing region as a first type of region or a second type of region according to the soil moisture characteristics, specifically: According to the soil moisture fluctuation changes of each sowing area in the corresponding time interval at all time points included in the soil moisture characteristics, the cumulative time length of each sowing area in a stable soil moisture state is estimated; wherein the stable soil moisture state refers to a state in which the difference between the average soil moisture of the sowing area and the benchmark soil moisture is within a preset range; If the accumulated time length is greater than or equal to the preset time length threshold, the sowing area is marked as the first type of area; if the accumulated time length is less than the preset time length threshold, the sowing area is marked as the second type of area.

[0008] Preferably, the region demarcation module visually identifies geomorphic elements of the first type of region and the second type of region, specifically: According to the boundaries of the second type of areas, the remote sensing images of the global scope of the farmland are identified to obtain the geomorphic elements of the second type of areas; wherein the geomorphic elements include the surface contour elements of the second type of areas.

[0009] Preferably, the trajectory determination module performs a spatial analysis of soil moisture conditions on the second type of area according to the geomorphic elements to determine an effective sowing trajectory for the second type of area, specifically: According to the surface contour elements of the second type of area included in the landform elements, the soil moisture of the second type of area is mapped on the surface space to obtain a soil moisture distribution map of the second type of area; Calculating the soil moisture distribution space vector of the gridded soil moisture matrix of the soil moisture distribution map, performing cluster analysis on the soil moisture distribution space vector, and determining the grid area with sufficient moisture in the second type of area; According to the position of the grid area with sufficient soil moisture, an effective sowing trajectory for the second type of area is determined.

[0010] Preferably, the image comparison module generates geographical distribution images of all first-category areas and second-category areas, and compares them with the visual perception images generated by the planter to determine whether the planter enters the first-category area or the second-category area, specifically: Generate a geographical distribution image of all the first-category areas and the second-category areas according to the geographical boundary positioning data of the first-category areas and the second-category areas; wherein the geographical distribution image identifies the respective boundaries of the first-category areas and the second-category areas; The visual perception GIS image generated locally by the seeder is compared with the geographic distribution image in the same spatial coordinate system to determine the relative position relationship between the seeder and the boundaries of the first and second types of areas during operation, thereby determining whether the seeder enters the first or second type of area.

[0011] Preferably, the track deviation identification module is used to visually identify the deviation between the actual sowing track of the sowing machine and the effective sowing track when the sowing machine enters the second type of area, specifically: When the seeder enters the second type of area during operation, collecting images of seed clusters that have been placed in the second type of area; Performing background separation and seed contour recognition on the seed cluster image to determine the spatial distribution positions of the germination points of all the seeds that have been placed; Performing continuous fitting processing on the spatial distribution positions of the germination points of the seeds to obtain an actual sowing trajectory; The actual sowing trajectory is spatially compared with the effective sowing trajectory to determine the deviation between the two; wherein the deviation includes a distance deviation and an azimuth deviation between the actual sowing trajectory and the effective sowing trajectory.

[0012] Preferably, the adjustment module is used to adjust the seeding machine to re-sow seeds in the second type of area according to the deviation, specifically: According to the distance deviation and azimuth deviation between the actual sowing trajectory and the effective sowing trajectory included in the deviation, estimating the seed placement blank range between the actual sowing trajectory and the effective sowing trajectory; The seed supplementation density of the seeder in the seed placement blank range is adjusted according to the seed placement blank range and the soil moisture conditions along the effective sowing trajectory.

[0013] Compared with the prior art, the present invention has the following beneficial effects: Visual perception of the entire farmland can be used to identify the differentiated soil moisture conditions, and visual perception of the local area of ​​the farmland can be used to adjust the seed placement. Visual perception of the farmland from the global to the local area can be used to guide the sowing operation, improve the efficiency of the sowing operation and ensure the overall germination rate of the farmland. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them: Figure 1 It is a structural schematic diagram of a terminal platform for intelligent seeding operations based on visual perception provided by the present invention.

[0015] Figure 2 It is the soil moisture distribution of the farmland geographic image of the present invention.

[0016] Figure 3 This is the distribution of the first type of area and the second type of area in the farmland of the present invention.

[0017] Figure 4 It is a schematic diagram for determining the effective seeding trajectory of the present invention.

[0018] Figure 5 It is a schematic diagram for determining the actual sowing trajectory of the present invention.

[0019] Figure 6 It is a schematic diagram of the deviation between the effective sowing trajectory of the present invention and the actual sowing trajectory. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings. It is understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only the parts related to the present invention rather than all structures are shown in the accompanying drawings. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0021] The terms "include" and "have" and any variations thereof in the present invention are intended to cover non-exclusive inclusions. For example, a process, product or device comprising a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, products or devices.

[0022] 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 invention. The appearance of the phrase in various places 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.

[0023] See also Figure 1 As shown, the present invention provides a terminal platform for intelligent seeding operations based on visual perception, and the terminal platform includes the following modules: The soil moisture evolution analysis module is used to dynamically analyze the evolution of the farmland geographic image according to the soil moisture of the farmland and calculate the soil moisture characteristics of each sowing area; A region marking module is used to mark each sowing area as a first-class area or a second-class area according to soil moisture characteristics, and visually identify geomorphic elements of the second-class area; A trajectory determination module is used to perform a spatial analysis of soil moisture conditions in the second type of area according to geomorphic elements, and determine an effective sowing trajectory for the second type of area; An image comparison module is used to generate geographical distribution images of all first-category areas and second-category areas, and compare them with the visual perception images generated by the seed drill to determine whether the seed drill enters the first-category area or the second-category area; A trajectory deviation recognition module is used to visually recognize the deviation between the actual sowing trajectory of the seeder and the effective sowing trajectory when the seeder enters the second type of area; The adjustment module is used for adjusting the seeding machine to re-sow seeds in the second type of area according to the deviation.

[0024] During the sowing process, accurate prediction of the soil moisture of the farmland plays a decisive role in whether the seeds can germinate normally after sowing; insufficient soil moisture will cause the seeds to not obtain sufficient heat and water in the soil and cannot germinate in the appropriate time. Once the seeds are delayed in germination or cannot germinate, it will affect the crop yield; considering that the soil moisture will change on different dates and in the morning and evening time periods of the same date, too large differences in soil moisture changes are not conducive to seed germination and growth. For this reason, it is necessary to dynamically evolve and distinguish the soil moisture of the farmland at the farmland geographic image level according to the global range of the farmland, obtain the soil moisture characteristics of the sowing area such as the seed placement pit in the farmland, and accurately distinguish and judge whether each sowing area has sufficient moisture to meet the seed germination.

[0025] Considering the vast area of ​​farmland, the soil moisture conditions in different sowing areas in the farmland may vary greatly. For example, the soil moisture in some sowing areas is sufficient, and sowing according to the conventional seed placement mode can ensure that the seeds in these sowing areas have a high germination rate; the soil moisture in other sowing areas is insufficient. If sowing according to the conventional seed placement mode, some seeds will not be able to obtain sufficient heat and water to germinate, which will affect the germination rate. At this time, it is necessary to improve the seed placement status under the original conventional seed placement mode. To this end, it is necessary to mark each sowing area as a first-class area with sufficient moisture or a second-class area without sufficient moisture according to the moisture characteristics, so that only the second-class area can be adjusted for sowing in the future, and the first-class area can maintain the original conventional seed placement mode, taking into account the sowing efficiency of the global area of ​​the farmland and the sowing optimization of the local area of ​​the farmland.

[0026] For the second type of areas without sufficient soil moisture, there are large differences in the distribution of soil moisture inside. For example, the soil moisture in some directions in the second type of areas is sufficient, and the ranges along these directions can provide relatively more heat and water for the seeds. If the seeds are placed along the ranges along these directions, the seeds can have a high germination rate. However, if the seeds are placed outside the ranges along these directions, the seed germination rate will be seriously reduced. It can be seen that the ranges along these directions in the second type of areas form effective sowing trajectories, which can provide spatial position references for the subsequent optimization of the sowing range of the second type of areas, so that the seed placement is as consistent as possible with the effective sowing trajectory.

[0027] Considering the difference in soil moisture distribution between the first and second types of areas, in the actual sowing process, it is only necessary to optimize the sowing operation for the second type of area, and only need to maintain the original conventional seed placement mode for the first type of area. In order to accurately and timely implement the sowing operation change when switching from the first type of area to the second type of area, it is necessary to determine whether the seeder is currently located in the first type of area or the second type of area, so that the seeder can adjust the sowing mode in time. For this purpose, the geographic distribution images of all the first and second types of areas are generated and compared with the visual perception images generated by the seeder. Through visual perception recognition, it is possible to accurately locate whether the seeder is in the first type of area or the second type of area, and timely and accurately achieve optimized sowing of the second type of area.

[0028] During the sowing operation on farmland, the seeder will sow in a conventional seed placement mode in all first-category areas and all second-category areas, that is, the sowing operation will be carried out according to the preset conventional seed placement spatial density and placement direction. Taking into account the insufficient soil moisture in the second-category areas, the seed germination rate in the second-category areas cannot be guaranteed by sowing solely relying on the above-mentioned conventional seed placement mode. It is necessary to further implement optimized sowing on the basis of the above-mentioned conventional seed placement mode sowing. The purpose of implementing optimized sowing in the second-category areas is to enable seeds to be placed along a range consistent with the effective sowing trajectory. For this reason, when the seeder enters the second-category area, it visually identifies the actual sowing trajectory formed after the seeder implements the above-mentioned conventional seed placement mode sowing, and compares the actual sowing trajectory with the effective sowing trajectory to determine the deviation between the two, so as to provide a reference for the subsequent further optimization of sowing in the second-category areas.

[0029] In the process of further optimizing the sowing process in the second type of area, it is necessary to ensure that the seeds for supplementary sowing are as consistent as possible with the effective sowing trajectory of the second type of area. To this end, the operable area range of the supplementary sowing seeds is determined based on the deviation between the actual sowing trajectory and the effective sowing trajectory of the second type of area, thereby ensuring that the seeds for supplementary sowing fall within the range consistent with the effective sowing trajectory to the maximum extent and do not overlap with the actual sowing trajectory.

[0030] Furthermore, before the soil moisture evolution analysis module performs dynamic evolution analysis on the farmland geographic image according to the soil moisture of the farmland, it includes: Thermal infrared visual recognition is performed on the entire farmland at several time points to obtain the surface temperature and soil moisture content of the entire farmland at several time points; wherein the several time points at least include daytime time points and evening time points on several dates; The surface temperature and soil moisture content at each time point are inverted and calculated to obtain the soil moisture conditions of the farmland at each time point.

[0031] Soil moisture is an important parameter indicator reflecting the state of soil, and it has important reference significance for agricultural operations such as sowing. Soil moisture is related to soil surface temperature and soil moisture content. By monitoring and analyzing soil surface temperature data and soil moisture content data, a linear regression relationship between soil surface temperature and soil moisture content is established, and then the above linear regression relationship is transformed by an inversion algorithm to obtain soil moisture.

[0032] Considering the vast area of ​​farmland, if the distributed sampling method is used to collect soil surface temperature data and soil moisture content at several locations in the farmland, the obtained soil surface temperature data and soil moisture content data cannot fully and accurately reflect the actual surface temperature and soil moisture status of the entire farmland, resulting in large errors in the inverted soil moisture conditions and reducing the credibility of the soil moisture conditions. To this end, remote sensing thermal infrared images of the entire farmland can be collected and analyzed, and thermal infrared visual recognition can be performed on the entire farmland to obtain the surface temperature and soil moisture content of the entire farmland. Considering that the soil surface temperature and soil moisture content are affected by the external environment, for example, during the day, the external environment temperature and humidity are high, and the soil surface temperature and soil moisture content are also high; during the night, the external environment temperature and humidity are low, and the soil surface temperature and soil moisture content are also low. In this way, the soil moisture conditions of the same farmland on different dates and in the morning and evening time periods of the same date will fluctuate. For example Figure 2 As shown in the figure, (a) is the soil moisture distribution of the farmland at a certain time point (such as 13:00) during the daytime of a certain date, and (b) is the soil moisture distribution of the farmland at a certain time point (such as 21:00) during the night of a certain date. By comparing (a) and (b), it can be found that there are large differences in the soil moisture distribution of the same farmland at different time points on the same date. If the calculation of the global soil moisture distribution of the farmland is based only on a single time point on a certain date, it will not be able to accurately reflect the fluctuation of the global soil moisture distribution of the farmland, thereby affecting the accuracy of the subsequent distinction between the first and second types of areas within the global scope of the farmland. To this end, thermal infrared visual identification was carried out on the entire farmland at several time points, and the surface temperature and soil moisture content of the entire farmland at daytime and evening time points on several dates were obtained. The surface temperature and soil moisture content at each time point were inverted and calculated to obtain the soil moisture distribution of the entire farmland at each time point. The soil moisture of the entire farmland was examined from the time domain change level, providing a basis for the subsequent determination of the moisture stability characteristics of all sowing areas in the farmland.

[0033] Furthermore, the soil moisture evolution analysis module dynamically analyzes the farmland geographic image according to the soil moisture of the farmland, and calculates the soil moisture characteristics of each sowing area, specifically: Mapping the soil moisture conditions of the farmland at each time point to the farmland geographic image divided with the sowing area boundaries, and performing soil moisture edge sharpening processing on all sowing areas in the farmland geographic image; The soil moisture content of each sowing area in the farmland geographic image at all time points is dynamically analyzed over time, and the soil moisture content characteristics of each sowing area in the corresponding time interval at all time points are calculated; the soil moisture content characteristics include the soil moisture fluctuation changes of each sowing area in the time interval.

[0034] After sowing in farmland, seeds rely on the heat and moisture in the soil to germinate. If the soil cannot provide heat and moisture to the seeds continuously and stably, the health and germination of the seeds cannot be guaranteed. Considering that it takes some time from sowing to seed germination, if the soil moisture changes greatly during this period, the seeds cannot obtain sufficient heat and moisture continuously and stably and will not germinate normally. Before sowing, the farmland will be plowed and a large number of seed placement pits and other sowing areas will be formed on the farmland. There are differences in the fluctuation of soil moisture in each sowing area; for example, the fluctuation of soil moisture in some sowing areas is small, and it can remain relatively stable for a long time, so that it can continuously and stably provide heat and moisture to the seeds; the fluctuation of soil moisture in other sowing areas is large, and it cannot remain relatively stable for a long time, so it cannot continuously and stably provide heat and moisture to the seeds.

[0035] In order to accurately determine whether each sowing area in the farmland can continuously and stably provide heat and water to the seeds, it is necessary to identify and analyze the changes in soil moisture on the global farmland geographic image; specifically, the soil moisture of the farmland at each time point is mapped to the farmland geographic image divided by the sowing area boundaries and the soil moisture edges are sharpened to enhance the soil moisture resolution of different sowing areas on the farmland geographic image; then, the dynamic time evolution analysis of the soil moisture of each sowing area in the farmland geographic image at all time points is performed, and the soil moisture fluctuation changes of each sowing area in the corresponding time interval at all time points are calculated to achieve accurate characterization of the magnitude of soil moisture changes in each sowing area.

[0036] Furthermore, the region calibration module calibrates each sowing area as a first-category area or a second-category area according to soil moisture characteristics, specifically: According to the fluctuation of soil moisture in each sowing area at all time points in the corresponding time interval, the cumulative length of time that each sowing area is in a stable soil moisture state is estimated; wherein the stable soil moisture state refers to a state in which the difference between the average soil moisture in the sowing area and the benchmark soil moisture is within a preset range; If the accumulated time length is greater than or equal to the preset time length threshold, the sowing area is marked as the first type of area; if the accumulated time length is less than the preset time length threshold, the sowing area is marked as the second type of area.

[0037] When the soil moisture conditions in the sowing area of ​​the farmland always maintain a relatively stable state within the corresponding time period, and the soil moisture fluctuations are small, it indicates that the above-mentioned sowing area can continuously and stably provide heat and water for the seeds; when the soil moisture conditions in the sowing area of ​​the farmland cannot maintain a stable state within the corresponding time period, and the soil moisture fluctuations are large, it indicates that the above-mentioned sowing area cannot continuously and stably provide heat and water for the seeds. According to the above analysis, for some sowing areas with sufficient and stable soil moisture conditions, it is only necessary to sow according to the conventional seed placement mode to ensure that the seeds in these sowing areas have a high germination rate; for some sowing areas with unstable soil moisture conditions, if sowing is carried out according to the conventional seed placement mode, some seeds will not be able to obtain sufficient heat and water to germinate, affecting the germination rate. At this time, it is necessary to improve the seed placement status under the original conventional seed placement mode.

[0038] In order to implement zoning operations for seeding operations in farmland, it is necessary to distinguish and calibrate all seeding areas in the farmland. Specifically, based on the fluctuations in soil moisture in each seeding area within the corresponding time interval at all time points, estimate the cumulative length of time that each seeding area is in a stable soil moisture state. The longer the cumulative length of time that the seeding area is in a stable soil moisture state, the more the seeding area can continuously and stably provide heat and moisture to the seeds. Then, a threshold comparison is performed on the cumulative length of time that the seeding area is in a stable soil moisture state, and each seeding area is calibrated as a first-class area or a second-class area. Figure 3 As shown, corresponding to all the sowing areas in the farmland, the sowing areas corresponding to the red boxes belong to the first category, and the sowing areas corresponding to the green boxes belong to the second category. Through the above method, each sowing area is marked as the first category area with sufficient moisture or the second category area without sufficient moisture, so that subsequent sowing adjustments are only made to the second category area, and the second category area can maintain the original conventional seed placement mode, taking into account the sowing efficiency of the global area of ​​the farmland and the sowing optimization of the local area of ​​the farmland.

[0039] Furthermore, the region calibration module visually identifies the geomorphic elements of the first type of region and the second type of region, specifically: According to the boundaries of the second type of areas, the remote sensing images of the global scope of the farmland are identified to obtain the geomorphic elements of the second type of areas; wherein the geomorphic elements include the surface contour elements of the second type of areas.

[0040] The second type of area in the farmland does not have sufficient moisture, and the seeds placed in the second type of area cannot obtain heat and moisture from the soil in the second type of area in a continuous and stable manner. In order to improve the germination rate of seeds in the second type of area, it is necessary to optimize the seed placement and sowing in the second type of area so that the seeds can obtain as much heat and moisture as possible from the second type of area to ensure the survival and germination rate of the seeds. Considering that there are spatial differences in soil moisture within the second type of area, that is, the soil moisture in some intervals of the second type of area is larger and the soil moisture in other intervals is smaller, the remote sensing image of the global range of the farmland is identified according to the boundary of the second type of area, and the surface contour elements of the second type of area are obtained, which can comprehensively characterize the surface contour shape of the second type of area and provide a basis for the subsequent refinement and determination of the soil moisture distribution in the second type of area.

[0041] Furthermore, the trajectory determination module performs a spatial analysis of soil moisture conditions in the second type of area according to the geomorphic elements, and determines an effective sowing trajectory for the second type of area, specifically: According to the surface contour elements of the second type of area included in the geomorphic elements, the soil moisture conditions of the second type of area are mapped on the surface space to obtain a soil moisture distribution map of the second type of area; Calculate the soil moisture distribution space vector of the gridded soil moisture matrix of the soil moisture distribution map, perform cluster analysis on the soil moisture distribution space vector, and determine the grid area with sufficient soil moisture in the second type of area; According to the location of the grid area with sufficient soil moisture, the effective sowing trajectory of the second type of area is determined.

[0042] The soil moisture conditions within the second type of area also show an uneven distribution trend, and there are differences in soil moisture conditions in different intervals. In order to accurately determine the locations within the second type of area that can provide more heat and water, the surface contour elements of the second type of area and the soil moisture conditions of the second type of area are first mapped to the surface space of the same coordinate system to obtain a soil moisture distribution map of the second type of area. The above soil moisture distribution map represents the distribution of soil moisture conditions on the global surface of the second type of area.

[0043] After dividing the above soil moisture distribution map into equally spaced grids, a gridded moisture matrix is ​​obtained. The spatial gradient simulation calculation of the moisture size is performed on the gridded moisture matrix to obtain the moisture distribution space vector; then a neural network model cluster analysis is performed on all moisture distribution space vectors to determine the grid areas with sufficient moisture in the second category of areas; wherein, the grid areas with sufficient moisture refer to the grid cluster areas in the second category of areas where the moisture is greater than the preset moisture threshold and are adjacent in spatial distribution. Finally, according to the location of the grid areas with sufficient moisture, a continuous simulation of the spatial distribution of the grid areas is performed to determine the effective sowing trajectory for the second category of areas. Figure 4As shown, the second type of area is divided into multiple grid spaces at equal intervals, and each grid space has a corresponding moisture content, wherein the moisture content of the white grid space is smaller (for example, less than the preset moisture content threshold), and the moisture content of the gray grid space is larger (for example, greater than or equal to the preset moisture content threshold). By performing moisture distribution spatial vector and cluster analysis on all grid spaces in the second type of area, several effective sowing trajectories in the second type of area are obtained; it can be considered that each effective sowing trajectory and its adjacent range in the second type of area can provide more and more continuous heat mixed moisture supply for seeds compared with other spatial ranges, and provide a spatial position reference for the subsequent optimization of the sowing range of the second type of area, so as to make the seed placement as consistent as possible with the effective sowing trajectory.

[0044] Furthermore, the image comparison module generates geographical distribution images of all first-category areas and second-category areas, and compares them with the visual perception images generated by the planter to determine whether the planter enters the first-category area or the second-category area, specifically: Generate a geographical distribution image of all the first-category areas and the second-category areas according to the geographical boundary positioning data of the first-category areas and the second-category areas; wherein the geographical distribution image identifies the respective boundaries of the first-category areas and the second-category areas; The visual perception GIS image generated locally by the seeder is compared with the geographic distribution image in the same spatial coordinate system to determine the relative position relationship between the seeder and the boundaries of the first and second types of areas during operation, thereby determining whether the seeder enters the first or second type of area.

[0045] All the first-class and second-class areas in the farmland each have fixed geographical boundaries. Through the above analysis, it can be seen that the first-class and second-class areas have different sowing operation requirements due to different soil moisture conditions. For the first-class area, it is only necessary to sow according to the conventional seed placement mode to ensure that the seeds inside have a high germination rate; for the second-class area, if the sowing is carried out according to the conventional seed placement mode, some seeds will not be able to obtain sufficient heat and water to germinate, which will affect the germination rate. At this time, on the basis of implementing the sowing operation for the second-class area according to the conventional seed placement mode, it is also necessary to implement additional improved and optimized sowing operations. In order for the seeder to perform differentiated sowing operations for the first-class and second-class areas, it is necessary to first determine the type of area where the seeder is currently located. Specifically, based on the geographic boundary positioning data of the first and second categories of areas, a geographic distribution image with the boundaries of the first and second categories of areas is generated; then the visual perception GIS image generated locally by the built-in GIS device during the operation of the seeder is compared with the geographic distribution image in the same spatial coordinate system to determine the relative distance and relative azimuth between the seeder itself and the boundaries of the first and second categories of areas during the operation, thereby determining whether the seeder enters the first or second category of areas. When the seeder enters the first category of areas, the seeder is controlled to sow according to the conventional seed placement mode; when the seeder enters the second category of areas, the seeder is controlled to sow according to the conventional seed placement mode, and then the optimized and improved sowing operation is implemented.

[0046] Furthermore, the trajectory deviation recognition module is used to visually identify the deviation between the actual sowing trajectory of the sowing machine and the effective sowing trajectory when the sowing machine enters the second type of area, specifically: When the seeder enters the second type of area during operation, an image of the seed cluster that has been placed in the second type of area is collected; Perform background separation and seed outline recognition on the seed cluster image to determine the spatial distribution of the germination points of all the seeds that have been released; The spatial distribution position of the germination point of the seeds is continuously fitted to obtain the actual sowing trajectory; The actual sowing trajectory is spatially compared with the effective sowing trajectory to determine the deviation between the two; wherein the deviation includes the distance deviation and azimuth deviation between the actual sowing trajectory and the effective sowing trajectory.

[0047] After entering the second type of area, the seeder will first sow according to the conventional seed placement mode. A certain number of seeds will be placed in the second type of area, and these seeds are distributed inside the second type of area. Seed germination is the formation of young sprouts in a specific area on the surface of the seed, and the distribution position of the bud points on the surface of the seed is relatively fixed. The distribution position of the bud points of the same type of crop seeds depends on the seed type. The moisture content of the space around the seed bud point in the soil will affect the germination of the seeds. The higher the moisture content of the space around the seed bud point, the easier it is to promote the germination of the bud point. The greater the distance between the seed bud point and the soil with higher moisture content, the more difficult it is to obtain sufficient heat and moisture, which affects the germination of the seed bud point. In order to enable the seeds after reseeding in the second type of area to obtain sufficient heat and moisture from the soil, and to prevent the reseeded seeds from overlapping with the seeds sown initially in space, it is necessary to determine the spatial distribution position of the germination points of each seed sown initially, and then perform continuous fitting processing on the spatial distribution position of the germination points of all seeds to obtain the actual sowing trajectory. Figure 5 As shown in the figure, visual perception recognition can be performed after the initial sowing is completed in the second type of area to obtain the seed cluster image that has been placed in the second type of area, and then the background separation and seed contour recognition of the seed cluster image can be performed to obtain the spatial distribution position of the germination point, and finally the actual sowing trajectory can be fitted. Finally, the actual sowing trajectory is compared with the effective sowing trajectory to determine the deviation between the two, which provides a reference for further optimizing the sowing in the second type of area.

[0048] Furthermore, the adjustment module is used to adjust the seeding machine to re-sow seeds in the second type of area according to the deviation, specifically: According to the distance deviation and azimuth deviation between the actual sowing trajectory and the effective sowing trajectory included in the deviation, a seed placement blank range between the actual sowing trajectory and the effective sowing trajectory is estimated; According to the blank area for seed placement and the soil moisture conditions along the effective sowing trajectory, adjust the seed supplementation density of the seeder in the blank area for seed placement.

[0049] like Figure 6As shown, the actual sowing trajectory and the effective sowing trajectory are mapped to the same image space, and the pixel contours of the above two trajectories are recognized to obtain the distance deviation and azimuth deviation between the actual sowing trajectory and the effective sowing trajectory, so as to estimate the seed placement blank range between the actual sowing trajectory and the effective sowing trajectory; the above seed placement blank range can be, but is not limited to, the range where the number of seeds placed per unit area between the actual sowing trajectory and the effective sowing trajectory is less than the preset number threshold. Then, according to the seed placement blank range and the soil moisture along the effective sowing trajectory, the seed supplement placement density of the seeder in the seed placement blank range is adjusted, so that more seeds can be placed in the seed placement blank range and the position with higher soil moisture along the effective sowing trajectory, ensuring that the supplementary sowing seeds can obtain sufficient heat and moisture from the second type of area, and the seed germination rate in the second type of area is increased as much as possible.

[0050] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by adding a necessary general hardware platform, and of course can also be implemented by combining hardware and software. Based on such an understanding, the above technical solution can essentially or in other words be embodied in the form of a computer product, and the present invention can be implemented in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0051] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it, and other embodiments may also be used. Although the present invention has been described in detail with reference to the aforementioned embodiments, ordinary technicians in this field should understand that they can still modify the technical solutions recorded in the aforementioned embodiments, or replace some of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A terminal platform for intelligent seeding operations based on visual perception, characterized in that: The terminal platform includes the following modules: The soil moisture evolution analysis module is used to dynamically analyze the evolution of the farmland geographic image according to the soil moisture of the farmland and calculate the soil moisture characteristics of each sowing area; A region marking module, for marking each sowing region as a first type of region or a second type of region according to the soil moisture characteristics, and visually identifying geomorphic elements of the second type of region; A trajectory determination module, configured to perform a spatial analysis of soil moisture conditions in the second type of area according to the geomorphic elements, and determine an effective sowing trajectory for the second type of area; An image comparison module is used to generate a geographical distribution image of all first-category areas and second-category areas, and compare it with the visual perception image generated by the seed drill to determine whether the seed drill enters the first-category area or the second-category area; A trajectory deviation identification module, used for visually identifying the deviation between the actual sowing trajectory of the sowing machine and the effective sowing trajectory when the sowing machine enters the second type of area; An adjustment module is used to adjust the seeding machine's seed reseeding in the second type of area according to the deviation.

2. The terminal platform according to claim 1, characterized in that: Before the soil moisture evolution analysis module performs dynamic evolution analysis on the farmland geographic image according to the soil moisture of the farmland, it includes: Thermal infrared visual recognition is performed on the entire farmland at several time points to obtain the surface temperature and soil moisture content of the entire farmland at several time points; wherein the several time points at least include daytime time points and evening time points on several dates; The surface temperature and soil moisture content at each time point are inverted and calculated to obtain the soil moisture conditions of the farmland at each time point.

3. The terminal platform according to claim 2, characterized in that: The soil moisture evolution analysis module dynamically analyzes the farmland geographic image according to the soil moisture of the farmland, and calculates the soil moisture characteristics of each sowing area, specifically: Mapping the soil moisture condition of the farmland at each time point to a farmland geographic image divided with sowing area boundaries, and performing soil moisture condition edge sharpening processing on all sowing areas in the farmland geographic image; A dynamic time evolution analysis of the soil moisture conditions of each sowing area in the farmland geographic image at all time points is performed, and the soil moisture characteristics of each sowing area in the corresponding time interval at all time points are calculated; wherein the soil moisture characteristics include the soil moisture fluctuation changes of each sowing area in the time interval.

4. The terminal platform according to claim 3, characterized in that: The region marking module marks each sowing region as a first type region or a second type region according to the soil moisture characteristics, specifically: According to the soil moisture fluctuation changes of each sowing area in the corresponding time interval at all time points included in the soil moisture characteristics, the cumulative time length of each sowing area in a stable soil moisture state is estimated; wherein the stable soil moisture state refers to a state in which the difference between the average soil moisture of the sowing area and the benchmark soil moisture is within a preset range; If the accumulated time length is greater than or equal to the preset time length threshold, the sowing area is marked as the first type of area; if the accumulated time length is less than the preset time length threshold, the sowing area is marked as the second type of area.

5. The terminal platform according to claim 1, characterized in that: The region demarcation module visually identifies the geomorphic elements of the first and second types of regions, specifically: According to the boundaries of the second type of areas, the remote sensing images of the global scope of the farmland are identified to obtain the geomorphic elements of the second type of areas; wherein the geomorphic elements include the surface contour elements of the second type of areas.

6. The terminal platform according to claim 1, characterized in that: The trajectory determination module performs a spatial analysis of the soil moisture condition of the second type of area according to the geomorphic elements to determine an effective sowing trajectory for the second type of area, specifically: According to the surface contour elements of the second type of area included in the landform elements, the soil moisture of the second type of area is mapped on the surface space to obtain a soil moisture distribution map of the second type of area; Calculating the soil moisture distribution space vector of the gridded soil moisture matrix of the soil moisture distribution map, performing cluster analysis on the soil moisture distribution space vector, and determining the grid area with sufficient moisture in the second type of area; According to the position of the grid area with sufficient soil moisture, an effective sowing trajectory for the second type of area is determined.

7. The terminal platform according to claim 1, characterized in that: The image comparison module generates geographical distribution images of all first-category areas and second-category areas, and compares them with the visual perception images generated by the planter to determine whether the planter enters the first-category area or the second-category area, specifically: Generate a geographical distribution image of all the first-category areas and the second-category areas according to the geographical boundary positioning data of the first-category areas and the second-category areas; wherein the geographical distribution image identifies the respective boundaries of the first-category areas and the second-category areas; The visual perception GIS image generated locally by the seeder is compared with the geographic distribution image in the same spatial coordinate system to determine the relative position relationship between the seeder and the boundaries of the first and second types of areas during operation, thereby determining whether the seeder enters the first or second type of area.

8. The terminal platform according to claim 1, characterized in that: The track deviation identification module is used to visually identify the deviation between the actual sowing track of the sowing machine and the effective sowing track when the sowing machine enters the second type of area, specifically: When the seeder enters the second type of area during operation, collecting images of seed clusters that have been placed in the second type of area; Performing background separation and seed contour recognition on the seed cluster image to determine the spatial distribution positions of the germination points of all the seeds that have been placed; Performing continuous fitting processing on the spatial distribution positions of the germination points of the seeds to obtain an actual sowing trajectory; The actual sowing trajectory is spatially compared with the effective sowing trajectory to determine the deviation between the two; wherein the deviation includes a distance deviation and an azimuth deviation between the actual sowing trajectory and the effective sowing trajectory.

9. The terminal platform according to claim 1, characterized in that: The adjustment module is used to adjust the seeding machine to re-sow seeds in the second type of area according to the deviation, specifically: According to the distance deviation and azimuth deviation between the actual sowing trajectory and the effective sowing trajectory included in the deviation, estimating the seed placement blank range between the actual sowing trajectory and the effective sowing trajectory; The seed supplementation density of the seeder in the seed placement blank range is adjusted according to the seed placement blank range and the soil moisture conditions along the effective sowing trajectory.

Images