Parcel boundary data positioning system and method based on intelligent perception

Abstract

The invention discloses a plot boundary data positioning system and method based on intelligent perception, and relates to the technical field of agricultural machinery operation localization. GPS position data of agricultural machinery operation is gridded, a plot is divided into grid units of a certain size, and each position point is mapped to the corresponding grid unit according to the longitude and latitude of the position point; according to the method, continuous geographic position information is converted into discrete grid data, the data structure is effectively simplified, the generated boundary trajectory is accurate, error data such as secondary boundary point trajectory does not exist, the boundary of a geometric figure of normal operation can be well distinguished, the missing area and the area without operation can be screened out, the calculation efficiency is high, and the calculation cost is low. The boundary data of one land parcel is calculated at a millisecond level and is improved by one order of magnitude compared with a traditional method, and geometric figure boundaries, displayed on the map, of the operation track are clear and visible and do not intersect with one another.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural machinery operation positioning, and in particular to a land boundary data positioning system and method based on intelligent perception. Background Art

[0002] Currently, the display of agricultural machinery operation data usually relies on the collected GPS trajectory data. This data contains the location information of the operator when working in the field. The location information is recorded through two-dimensional coordinates of longitude and latitude, and forms a trajectory over time. When displaying this trajectory information, the system needs to load all the field operation data of the day. However, this data information contains a large number of location points and the data volume is huge. The browser will become slow when loading and rendering the data, affecting the user experience.

[0003] In the existing scheme, in order to solve the problem of loading and rendering efficiency caused by excessive data volume, a scheme is adopted to reduce the data volume by extracting the data of the boundary points of the plot. The goal of this scheme is to only display the boundary of the operation plot to reduce the data loading volume. The steps of the scheme include: first traversing all trajectory points and obtaining the location information of each point one by one; for each trajectory point, calculating the neighborhood distance between it and all other points and counting the number of points in the neighborhood; considering the points whose number of points in the neighborhood is less than a preset threshold as boundary points, extracting them, and classifying these points as boundary points;

[0004] However, this solution is computationally complex and time-consuming. It requires a large number of calculations for all trajectory points, and the calculation time is usually in seconds. In addition, the setting of the neighborhood distance and the number of points in the neighborhood requires a lot of experiments to determine, which increases the complexity of the system. Due to errors in the calculation process, some non-real boundary points (sub-boundary points) may be mistaken for boundary points, resulting in inaccurate boundary identification. When there are areas where operations are omitted or areas where operations are not required in the plot, the solution is prone to errors, resulting in failure of boundary identification. At the same time, when the boundary points calculated by this method are connected to form geometric figures on the map, intersections or other abnormalities may occur, resulting in failure of plot rendering, which directly affects the visualization of the operation information. Therefore, there is an urgent need for a plot boundary data positioning system and method based on intelligent perception to solve such problems. Summary of the invention

[0005] In view of the above existing problems, the present invention is proposed.

[0006] Therefore, the present invention provides a land boundary data positioning system and method based on intelligent perception to solve the problem that agricultural machinery operation data becomes slow when loading and rendering data during the browser display stage, affecting the user experience.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] On the one hand, the present invention provides a land boundary data positioning system based on intelligent perception, which includes an operation land data source acquisition module, a data conversion module, a boundary search module, a data mapping module, and a data induction module, wherein:

[0009] The module for acquiring data source of the working plot is used to acquire the data set of the agricultural machinery working alone in the field, including GPS longitude and latitude information;

[0010] Data conversion module, which creates binary grid data based on GPS longitude and latitude data for use by the boundary search module;

[0011] A boundary search module searches for the mathematical boundary position coordinates of the binary grid data obtained in the data conversion module;

[0012] The data mapping module maps the location coordinates obtained in the boundary search module with the operation plot data one by one;

[0013] Data summarization module, which collects and summarizes the data of all mapping relationships into a data set.

[0014] Furthermore, in the data summarization module, the data set is the boundary data information of the agricultural machinery operation plot.

[0015] On the other hand, the present invention provides a method for locating land boundary data based on intelligent perception, comprising:

[0016] Step S1, extracting source data of the agricultural machinery operation plot, and forming a data source set C arranged in chronological order based on the source data (obtaining the operation plot data source);

[0017] Step S2, calculation grid (data conversion);

[0018] Step S3, find the boundary (call OpenCV function to find the data boundary);

[0019] Step S4, obtaining boundary data (boundary data and source data mapping),

[0020] Step S5, generating a boundary data set (obtaining a land parcel boundary data set).

[0021] Furthermore, in step S1, the extracted source data only includes land operations, but does not include road driving source data, and each source data includes: longitude, latitude and time information.

[0022] Furthermore, in step S2, the grid calculation method is:

[0023] Traverse the data source set C and calculate the following values ​​based on all longitude and latitude data:

[0024] Minimum longitude min_long, maximum longitude max_long, minimum latitude min_lat, maximum latitude max_lat;

[0025] Set the step size and calculate the number of grids:

[0026] Among them, long_grid_num and lat_grid_num represent the number of grid cells in longitude and latitude respectively;

[0027] Initialize a two-dimensional array:

[0028] Initialize a binary grid data two-dimensional array array with a size of long_grid_num rows and lat_grid_num columns, with an initial value of 0;

[0029] Similarly, initialize a two-dimensional array array_msg with a size of long_grid_num rows and lat_grid_num columns, and the initial value is also 0;

[0030] Traverse the set C, obtain the longitude and latitude information of each data, and calculate the grid index.

[0031] Furthermore, in step S2, the set C is traversed to obtain the longitude and latitude information of each data, and the grid index is calculated as follows:

[0032] Among them, long_x and lat_y represent the grid indexes of longitude and latitude information respectively. According to the calculated indexes long_x and lat_y, array[long_x][lat_y] is set to 1, and array_msg[long_x][lat_y] is set to the corresponding data information. Here, array[long_x][lat_y] represents a grid cell determined by the longitude index long_x and the latitude index lat_y in the grid. The value of the grid cell is set to 1, indicating that there is a valid block operation data at this location, and array_msg[long_x][lat_y] stores the data information in the corresponding grid cell of array[long_x][lat_y]. Specifically, it saves detailed data information associated with the longitude and latitude of the location, including time, speed or other information related to agricultural machinery operations.

[0033] Furthermore, in step S3, the boundary search method is: passing the two-dimensional array array as a parameter into the OpenCV boundary search function findContours to obtain the boundary point data cluster C2.

[0034] Furthermore, in step S3, the boundary points are determined according to the positions with values ​​of 1 in the array.

[0035] Furthermore, in step S4, the boundary data is obtained by obtaining the data information data at the corresponding position in array_msg according to the index information of the element in C2.

[0036] Furthermore, in step S5, the boundary data set is generated by recording each piece of data into a set, and the set is the boundary data set of the agricultural machinery operation plot.

[0037] The beneficial effects of the present invention are:

[0038] The present invention generates an accurate boundary trajectory without error data such as secondary boundary point trajectory, can well distinguish the boundaries of geometric figures of normal operation, and can screen out missed areas or areas that do not require operation. The calculation efficiency is high, and the boundary data of a plot of land is calculated in milliseconds, which is an order of magnitude higher than the traditional method. The boundaries of geometric figures displayed on the map of the operation trajectory are clearer and more visible without intersections.

[0039] The present invention performs grid processing on the GPS location data of agricultural machinery operations, divides the plots into grid units of a certain size, maps each location point to the corresponding grid unit according to its longitude and latitude, converts continuous geographical location information into discrete grid data, and effectively simplifies the data structure. At the same time, in each grid unit, if there is an operation data point, the value of the unit is set to 1, otherwise it is set to 0. Through the binarization operation, the complex trajectory data is simplified into a binary matrix, which indicates which areas have operation data and which areas do not, thereby reducing data complexity.

[0040] The present invention converts the data of the entire plot into a form similar to an image after completing the gridding and binarization processing, and then uses the findContours function in OpenCV to quickly find the boundary contour in the binary image. The findContours algorithm can efficiently identify the boundary of the area with a value of 1 in the grid, determine the external boundary of the agricultural machinery operation plot, and omit the process of screening boundary points by calculating the neighborhood distance, and directly use the boundary recognition technology to provide a clear boundary recognition effect.

[0041] The present invention maps the grid unit index corresponding to the boundary point data obtained by the findContours algorithm with the original GPS data, thereby extracting the detailed information of each boundary point, making the relationship between the boundary data and the original operation data correspond, retaining the position of the boundary point, and also retaining the operation information related to it, and then summarizing and arranging the mapped boundary point information to generate a complete plot boundary data set, which is used to display the boundary of the operation plot, and does not have the rendering failure problem caused by calculation errors or complex plot shapes in traditional methods.

[0042] The present invention greatly reduces the computational burden during data processing and boundary search. Gridding and binarization processing make the data structure simpler. The application of image processing algorithms makes boundary search faster and more accurate, shortening the calculation time of land plot boundaries to milliseconds, significantly improving the computational efficiency of the system. Furthermore, due to the direct use of mature algorithms in image processing, the error of boundary recognition is reduced. It performs well when there are omissions in operations or complex shapes in land plots, and can accurately extract the real boundary to avoid misjudgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0044] Figure 1 Provides information data maps of field operations for existing programs;

[0045] Figure 2 It is an information data map of the field operation of the present invention;

[0046] Figure 3 It is a flow chart of the method for locating the land parcel boundary data of the present invention;

[0047] Figure 4 This is a framework diagram of the land parcel boundary data positioning system of the present invention. DETAILED DESCRIPTION

[0048] 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.

[0049] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0050] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0051] Example 1, reference Figure 1 , Figure 2 and Figure 4 This embodiment provides a land parcel boundary data positioning system based on intelligent perception, including:

[0052] The module for acquiring data source of the working plot obtains the data set of the agricultural machinery working alone in the field, and the data includes GPS longitude and latitude information.

[0053] Data conversion module, which creates binary grid data based on GPS longitude and latitude data for use by the boundary search module;

[0054] A boundary search module searches for the mathematical boundary position coordinates of the binary grid data obtained in the data conversion module;

[0055] The data mapping module maps the location coordinates obtained in the boundary search module with the operation plot data one by one;

[0056] The data summarization module collects and summarizes all the mapping data into a data set, which is the boundary data information of the agricultural machinery operation plot.

[0057] Example 2, reference Figure 1 , Figure 2 and Figure 3 This embodiment provides a method for locating land boundary data based on intelligent perception, comprising the following steps:

[0058] Step S1, extracting source data of the agricultural machinery operation plot, and forming a data source set C (obtaining the operation plot data source) arranged in chronological order based on the source data; the extracted source data only includes the plot operation, and does not include the road driving source data, and each source data includes: longitude, latitude and time information;

[0059] Step S2, calculation grid (data conversion);

[0060] Traverse the data source set C and calculate the following values ​​based on all longitude and latitude data:

[0061] Minimum longitude min_long, maximum longitude max_long, minimum latitude min_lat, maximum latitude max_lat;

[0062] Set the step size and calculate the number of grids:

[0063] Among them, long_grid_num and lat_grid_num represent the number of grid cells in longitude and latitude respectively;

[0064] Initialize a two-dimensional array:

[0065] Initialize a binary grid data two-dimensional array array with a size of long_grid_num rows and lat_grid_num columns, with an initial value of 0;

[0066] Similarly, initialize a two-dimensional array array_msg with a size of long_grid_num rows and lat_grid_num columns, and the initial value is also 0;

[0067] Traverse the collection C, obtain the longitude and latitude information of each data, and calculate the grid index:

[0068] Among them, long_x and lat_y represent the grid index of longitude and latitude information respectively. According to the calculated indexes long_x and lat_y, array[long_x][lat_y] is set to 1, and array_msg[long_x][lat_y] is set to the corresponding data information. Here, array[long_x][lat_y] represents a grid cell determined by the longitude index long_x and the latitude index lat_y in the grid. The value of the grid cell is set to 1, indicating that there is a valid block operation data at the location, and array_msg[long_x][lat_y] stores the data information in the grid cell corresponding to array[long_x][lat_y]. Specifically, detailed data information associated with the longitude and latitude of the location is saved, including time, speed or other information related to agricultural machinery operation;

[0069] Specifically, by gridding and binarizing GPS data, continuous location information is mapped into simple grid cells, which simplifies the data structure and effectively reduces the computational complexity. Compared with the traditional point-by-point calculation method, gridding processing greatly shortens the data processing time and eliminates the system performance bottleneck that may be caused by excessive data volume.

[0070] Step S3, find the boundary (call OpenCV function to find data boundary); pass the two-dimensional array array as a parameter to OpenCV's boundary search function findContours to obtain the boundary point data cluster C2;

[0071] In step S3, the boundary point is determined according to the position with a value of 1 in the array;

[0072] Specifically, the gridded data is used as input, and the findContours function is used to quickly and accurately extract the boundary points of the plot, which improves the accuracy of boundary recognition. It also overcomes the problem of inaccurate identification of secondary boundary points in traditional methods and avoids misjudging irrelevant points as boundary points.

[0073] Step S4, obtaining boundary data (boundary data and source data mapping), and obtaining data information data at the corresponding position in array_msg according to the index information of the element in C2;

[0074] Specifically, when there are areas where operations are missed or where no operations are required in the plot, the system can automatically identify and exclude these areas so that the generated boundary data only contains the actual operation areas. The boundary recognition is more intelligent, which enhances the robustness of the system and enables mechanical equipment to effectively avoid potential collision risks in various complex operating environments.

[0075] Step S5, generating a boundary data set (obtaining a plot boundary data set); recording each data item in the set, which is the boundary data set of the agricultural machinery operation plot;

[0076] Specifically, the boundary calculation time is shortened from seconds in traditional methods to milliseconds, significantly improving the overall performance of the system and quickly responding to user needs.

[0077] Figure 1 This is the information data of a driver who went to work in the field on a certain day. On the left side of the picture is the driver's basic information data and the number of acres of field work on that day. On the right side of the picture is a satellite map of the driver's working area. The red and green points on the map represent the driver's location information during the operation on a certain day, including two-dimensional coordinates of longitude and latitude. The continuous position points in time constitute the driver's driving trajectory on that day. The red trajectory represents the driver's trajectory while driving, and the green trajectory represents the driver's trajectory while working in the field. When displaying the operation information to the customer, the browser needs to load the trajectory data containing all the driver's field operation information on that day. Too much location data will cause the browser to load and render slowly, affecting the customer experience.

[0078] Figure 2The geometric figures of the working plots obtained according to the algorithm of this patent, the green figures are the plots where the operator is working in the field, and the yellow figures are the areas that are missed or do not need to be worked during field operations; it can be seen that the boundary trajectory generated by the scheme of the present invention is accurate, there is no error data such as secondary boundary point trajectory, the boundaries of the geometric figures of normal operations can be well distinguished, and the missed areas or areas that do not need to be worked can be screened out, the calculation efficiency is high, and the boundary data of a plot is calculated in milliseconds, which is an order of magnitude higher than the traditional one. The boundaries of the geometric figures displayed on the map of the working trajectory are clearer and more visible, and there is no intersection.

[0079] 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. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A land boundary data positioning system based on intelligent perception, comprising: The operation plot data source acquisition module, data conversion module, boundary search module, data mapping module and data induction module are characterized in that: The operation plot data source acquisition module acquires a data set of agricultural machinery operating alone in the field, the data including GPS longitude and latitude information; The data conversion module creates binary grid data based on GPS longitude and latitude data for use by the boundary search module; The boundary search module searches for the mathematical boundary position coordinates of the binary grid data obtained in the data conversion module; The data mapping module maps the position coordinates obtained in the boundary search module with the operation plot data one by one; The data summarization module collects and summarizes the data of all mapping relationships into a data set.

2. The land boundary data positioning system based on intelligent perception according to claim 1, characterized in that: In the data summarization module, the data set is the boundary data information of the agricultural machinery operation plot.

3. A method for locating land boundary data based on intelligent perception, characterized in that: A land boundary data positioning system based on intelligent perception according to any one of claims 1 to 2 comprises the following steps: Step S1, extracting source data of the agricultural machinery operation plot, and forming a data source set C arranged in chronological order based on the source data; Step S2, calculating the grid; Step S3, finding the boundary; Step S4, obtaining boundary data; Step S5, generating a boundary data set.

4. The method for locating land boundary data based on intelligent perception according to claim 3, characterized in that: In step S1, the extracted source data only includes land operations, and does not include road driving source data. Each source data includes: longitude, latitude and time information.

5. The method for locating land boundary data based on intelligent perception according to claim 4, characterized in that: In step S2, the grid calculation method is: Traverse the data source set C and calculate the following values ​​based on all longitude and latitude data: Minimum longitude min_long, maximum longitude max_long, minimum latitude min_lat, maximum latitude max_lat; Set the step size and calculate the number of grids: Among them, long_grid_num and lat_grid_num represent the number of grid cells in longitude and latitude respectively; Initialize a two-dimensional array: Initialize a binary grid data two-dimensional array array with a size of long_grid_num rows and lat_grid_num columns, with an initial value of 0; Similarly, initialize a two-dimensional array array_msg with a size of long_grid_num rows and lat_grid_num columns, and the initial value is also 0; Traverse the set C, obtain the longitude and latitude information of each data, and calculate the grid index.

6. A method for locating land boundary data based on intelligent perception as claimed in claim 5, characterized in that: In step S2, the set C is traversed to obtain the longitude and latitude information of each data, and the grid index is calculated as follows: Among them, long_x and lat_y represent the grid indexes of longitude and latitude information respectively. According to the calculated indexes long_x and lat_y, array[long_x][lat_y] is set to 1, and array_msg[long_x][lat_y] is set to the corresponding data information. Here, array[long_x][lat_y] represents a grid cell determined by the longitude index long_x and the latitude index lat_y in the grid. The value of the grid cell is set to 1, indicating that there is a valid block job data at this location, and array_msg[long_x][lat_y] stores the data information in the grid cell corresponding to array[long_x][lat_y].

7. The method for locating land boundary data based on intelligent perception according to claim 6, characterized in that: In step S3, the boundary search method is: passing the two-dimensional array array as a parameter into the OpenCV boundary search function findContours to obtain the boundary point data cluster C2.

8. The method for locating land boundary data based on intelligent perception according to claim 7, characterized in that: In step S3, the boundary points are determined according to the positions with values ​​of 1 in the array.

9. The method for locating land boundary data based on intelligent perception according to claim 8, characterized in that: In step S4, the boundary data is obtained in the following manner: according to the index information of the element in C2, the data information data of the corresponding position in array_msg is obtained.

10. The method for locating land boundary data based on intelligent perception according to claim 9, characterized in that: In step S5, the boundary data set is generated by recording each piece of data into a set, and the set is the boundary data set of the agricultural machinery operation plot.

Images