A method and related device for identifying ridge break points of strip crops

Abstract

The present invention discloses a method for identifying the breakpoints of strip crops, including obtaining a spliced ​​spectral orthophoto; calculating the spectral characteristic index corresponding to each pixel in the spectral orthophoto; binarizing each pixel in the spectral orthophoto according to the spectral characteristic index to obtain a preliminary classification result; removing weeds in the preliminary classification result to obtain a result to be used; extracting a target ridge line of the result to be used; and identifying the breakpoints of crops according to the target ridge line. The breakpoints of crops can be identified by using spectral orthophotos and effectively utilizing the spectral characteristics of crops, which can provide effective support for precise positioning and greatly improve robustness. The use of spectral orthophotos has richer crop characteristics, which can greatly improve the monitoring accuracy, thereby accurately identifying the breakpoints of strip crops. The present invention also provides a device, equipment, and storage medium, which also have the above-mentioned beneficial effects.

Description

Technical Field

[0001] The present invention relates to the field of precision agriculture technology, and in particular to a method for identifying ridge break points of strip crops, a device for identifying ridge break points of strip crops, equipment for identifying ridge break points of strip crops, and a computer-readable storage medium. Background Art

[0002] Precision agriculture, a novel agricultural production management concept facilitated by the rapid development of information technology and artificial intelligence, provides precise management of agricultural production, including location-based crop management and variable inputs tailored to actual needs. Remote sensing monitoring technology is a key technology for acquiring field information in precision agriculture, providing information on the crop growth environment, growth status, and spatial variation within a specific farmland. Remote sensing is a comprehensive Earth observation technology with advantages such as macroscopic, cost-effective, and timely.

[0003] When determining the position of crop ridges or identifying the breakpoints of crop strips, existing technologies for identifying crop strips have low robustness, making it difficult to accurately identify breakpoints using drones. Therefore, finding a technical solution that can accurately identify breakpoints in crop strips is an urgent problem for those skilled in the art. Summary of the Invention

[0004] The object of the present invention is to provide a method for identifying the breakpoints of strip crops, which can accurately identify the breakpoints of strip crops; another object of the present invention is to provide a device for identifying the breakpoints of strip crops, a device for identifying the breakpoints of strip crops and a computer-readable storage medium, which can accurately identify the breakpoints of strip crops.

[0005] In order to solve the above technical problems, the present invention provides a method for identifying ridge break points of strip crops, comprising:

[0006] Obtain stitched spectral orthoimages;

[0007] Calculating the spectral characteristic index corresponding to each pixel in the spectral orthoimage;

[0008] Binarizing each pixel in the spectral orthophoto according to the spectral characteristic index to obtain a preliminary classification result;

[0009] Eliminating weeds from the initial classification results to obtain results to be used;

[0010] Extracting the target ridge line of the result to be used;

[0011] The crop ridge break points are identified according to the target ridge line.

[0012] Optionally, binarizing each pixel in the spectral orthoimage according to the spectral characteristic index to obtain a preliminary classification result includes:

[0013] The minimum threshold to the maximum threshold of the spectral characteristic index is used as the value range of the initial classification standard, and each pixel in the spectral orthophoto is binarized according to the initial classification standard to obtain the initial classification result.

[0014] Optionally, calculating the spectral characteristic index corresponding to each pixel in the spectral orthoimage includes:

[0015] Calculate the EVI index and GpId index corresponding to each pixel in the spectral orthoimage; the GpId index is the ratio of the near-infrared band reflectivity to the green band reflectivity multiplied by the red band reflectivity multiplied by the red edge band reflectivity.

[0016] Optionally, the minimum threshold to the maximum threshold of the spectral characteristic index is used as the value range of the preliminary classification standard, and each pixel in the spectral orthophoto is binarized according to the preliminary classification standard to obtain the preliminary classification result including:

[0017] The minimum threshold value of the EVI index to the maximum threshold value of the EVI index are used as the value range of the first preliminary classification standard, and the minimum threshold value of the GpId index to the maximum threshold value of the GpId index are used as the value range of the second preliminary classification standard;

[0018] When the EVI index of the pixel is within the value range of the first preliminary classification standard, and the GpId index is within the value range of the second preliminary classification standard, setting the value of the pixel to the first pixel value;

[0019] When the EVI index of the pixel is not within the value range of the first preliminary classification standard, or the GpId index is not within the value range of the second preliminary classification standard, the value of the pixel is set to the second pixel value to obtain a preliminary classification result.

[0020] Optionally, removing weeds from the initial classification results to obtain results to be used includes:

[0021] Perform edge detection and line detection on the initial classification results to obtain the average angle of the plot;

[0022] generating a fringe marker matrix according to the average angle of the plot;

[0023] Calculating an area matrix based on the stripe marking matrix and the initial classification result;

[0024] Stripes corresponding to values ​​in the area matrix that are smaller than the area threshold are removed to obtain a result to be used.

[0025] Optionally, extracting the target ridge line of the result to be used includes:

[0026] Calculate the minimum circumscribed convex polygon for each connected domain in the result and record the node coordinates;

[0027] Calculating the distance between each node in the connected domain and the other nodes in the connected domain according to the node coordinates;

[0028] When the distance is less than the distance threshold and the slope of the line between the two nodes is within the allowable error range, connecting the two nodes;

[0029] Generate a connected domain label matrix based on the newly added connection lines.

[0030] Optionally, identifying the crop ridge break point according to the target ridge line includes:

[0031] Grayscale morphological operation is performed on the connected domain marker matrix to obtain the center point and area of ​​the broken ridge point.

[0032] The present invention also provides a device for identifying ridge break points of strip crops, comprising:

[0033] Acquisition module, used to obtain the spliced ​​spectral orthoimage;

[0034] A characteristic index module is used to calculate the spectral characteristic index corresponding to each pixel in the spectral orthoimage;

[0035] A preliminary classification result module is used to binarize each pixel in the spectral orthophoto according to the spectral characteristic index to obtain a preliminary classification result;

[0036] a weed removal module, configured to remove weeds from the initial classification results to obtain results to be used;

[0037] An extraction module, used for extracting the target ridge line of the result to be used;

[0038] The identification module is used to identify the crop ridge break points according to the target ridge line.

[0039] The present invention also provides a device for identifying ridge break points of ridge crops, comprising:

[0040] memory for storing computer programs;

[0041] A processor is used to execute the computer program to implement the steps of the method for identifying ridge break points of strip crops as described in any one of the above.

[0042] The present invention also provides a computer-readable storage medium, in which a computer program is stored. The computer program is executed by a processor to implement the steps of the method for identifying the break point of strip crops as described in any one of the above items.

[0043] The present invention provides a method for identifying ridge break points of strip crops, comprising obtaining a spliced ​​spectral orthoimage; calculating a spectral characteristic index corresponding to each pixel in the spectral orthoimage; binarizing each pixel in the spectral orthoimage according to the spectral characteristic index to obtain a preliminary classification result; removing weeds from the preliminary classification result to obtain a result to be used; extracting a target ridge line from the result to be used; and identifying the crop ridge break points according to the target ridge line.

[0044] Using spectral orthophotos to identify crop breakpoints effectively utilizes crop spectral characteristics, providing effective support for precise positioning and greatly improving robustness. Using spectral orthophotos, which provide richer crop characteristics, can greatly improve monitoring accuracy and accurately identify breakpoints in strip crops.

[0045] The present invention also provides a device for identifying the break point of strip crops, a device for identifying the break point of strip crops, and a computer-readable storage medium, which also have the above-mentioned beneficial effects and will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. 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 paying any creative work.

[0047] Figure 1 A flow chart of a method for identifying ridge break points of strip crops provided by an embodiment of the present invention;

[0048] Figure 2 A flowchart of a specific method for identifying ridge break points of strip crops provided by an embodiment of the present invention;

[0049] Figure 3 A structural block diagram of a device for identifying ridge break points of ridge crops provided by an embodiment of the present invention;

[0050] Figure 4 This is a structural block diagram of a device for identifying ridge break points of strip crops provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The core of this invention is to provide a method for identifying the breakpoints of crop strips. In the prior art, when it is necessary to determine the position of crop ridges or identify the breakpoints of crop strips, the robustness of identifying crop strips in the prior art is low, making it impossible to accurately identify crop strips using drones.

[0052] The present invention provides a method for identifying ridge-break points of strip crops, comprising obtaining a spliced ​​spectral orthoimage; calculating a spectral characteristic index corresponding to each pixel in the spectral orthoimage; binarizing each pixel in the spectral orthoimage according to the spectral characteristic index to obtain a preliminary classification result; removing weeds from the preliminary classification result to obtain a result to be used; extracting a target ridge line from the result to be used; and identifying the crop ridge-break points according to the target ridge line.

[0053] Using spectral orthophotos to identify crop breakpoints effectively utilizes crop spectral characteristics, providing effective support for precise positioning and greatly improving robustness. Using spectral orthophotos, which provide richer crop characteristics, can greatly improve monitoring accuracy and accurately identify breakpoints in strip crops.

[0054] In order to enable those skilled in the art to better understand the present invention, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0055] Please refer to Figure 1 , Figure 1 This is a flow chart of a method for identifying ridge break points of strip crops provided by an embodiment of the present invention.

[0056] See also Figure 1 In an embodiment of the present invention, a method for identifying ridge break points of strip crops includes:

[0057] S101: Obtain the stitched spectral orthoimage.

[0058] In this step, a spectral orthophoto is acquired. This spectral orthophoto is typically formed by registering and stitching multiple spectral orthophoto images. Specifically, this spectral orthophoto can be acquired by remotely sensing the crop rows in the target area. Accordingly, in embodiments of the present invention, this spectral orthophoto can be acquired using drones equipped with spectral sensors, using drone spectral remote sensing monitoring. Methods for acquiring this data include, but are not limited to, multispectral and hyperspectral detection methods.

[0059] Specifically, in this embodiment of the present invention, the value of each pixel in the spectral orthoimage is the radiometrically corrected spectral reflectance of the ground object. This spectral reflectance allows accurate determination of the position of each crop row in subsequent steps. Of course, other spectral parameters can also be used as the value of each pixel in the spectral orthoimage in this embodiment of the present invention, and this is not specifically limited here.

[0060] S102: Calculate the spectral characteristic index corresponding to each pixel in the spectral orthoimage.

[0061] In this step, the spectral characteristic index corresponding to each pixel will be calculated based on the pixel value of each pixel in the above-mentioned spectral orthophoto. The specific selection of the spectral characteristic index will be introduced in detail in the following embodiments of the invention and will not be described in detail here. In an embodiment of the present invention, the spectral characteristic index can quantitatively characterize the measurement result of the position of the corresponding pixel. The spectral characteristic index usually needs to include a vegetation index so as to determine the position of the ridge crops in the subsequent steps. In an embodiment of the present invention, the spectral characteristic index, such as the crop spectral characteristics, is effectively utilized to provide effective support for subsequent precise positioning, greatly improving the robustness of the algorithm.

[0062] S103: Binarize each pixel in the spectral orthophoto according to the spectral characteristic index to obtain an initial classification result.

[0063] In this step, each pixel in the spectral orthoimage is binarized according to the above spectral characteristic index, so as to determine the outline of the strip crops in the spectral orthoimage according to the spectral characteristic index.

[0064] Specifically, in this step, the minimum threshold to the maximum threshold of the spectral characteristic index is used as the value range of the preliminary classification standard, and each pixel in the spectral orthophoto is binarized according to the preliminary classification standard to obtain the preliminary classification result. That is, in this step, the corresponding upper and lower thresholds, i.e., the minimum threshold and the maximum threshold, are first set for each of the above-mentioned spectral characteristic indices, and then the range from the minimum threshold to the maximum threshold is used as the value range of the preliminary classification standard, and then each pixel in the spectral orthophoto is binarized according to the preliminary classification standard. Specifically, when the spectral characteristic index corresponding to the pixel is within the value range of the preliminary classification standard, its value is set to 1; when the spectral characteristic index corresponding to the pixel is not within the value range of the preliminary classification standard, its value is set to 0, thereby realizing the binarization of the spectral orthophoto and obtaining the preliminary classification result.

[0065] S104: Weeds are removed from the initial classification results to obtain results to be used.

[0066] In this step, weeds are further removed from the initial classification results to obtain the results to be used, thereby preventing weeds from affecting the distribution morphology of the strip crops. The specific details will be described in detail in the following invention embodiments and will not be repeated here.

[0067] S105: Extract the target ridge line of the result to be used.

[0068] S106: Identify crop ridge break points according to the target ridge line.

[0069] In the embodiment of the present invention, the target ridge line is further determined based on the result to be used generated in S104, and the crop break point is further identified. The specific content will be described in detail in the following embodiment of the invention and will not be repeated here.

[0070] A method for identifying ridge break points of strip crops provided by an embodiment of the present invention includes obtaining a spliced ​​spectral orthoimage; calculating a spectral characteristic index corresponding to each pixel in the spectral orthoimage; binarizing each pixel in the spectral orthoimage according to the spectral characteristic index to obtain a preliminary classification result; removing weeds from the preliminary classification result to obtain a result to be used; extracting a target ridge line from the result to be used; and identifying the crop ridge break points based on the target ridge line.

[0071] Using spectral orthophotos to identify crop breakpoints effectively utilizes crop spectral characteristics, providing effective support for precise positioning and greatly improving robustness. Using spectral orthophotos, which provide richer crop characteristics, can greatly improve monitoring accuracy and accurately identify breakpoints in strip crops.

[0072] The specific contents of the method for identifying ridge break points of strip crops provided by the present invention will be described in detail in the following invention embodiments.

[0073] Please refer to Figure 2 , Figure 2 The present invention provides a flow chart of a specific method for identifying ridge break points of strip crops.

[0074] See also Figure 2 In an embodiment of the present invention, a method for identifying ridge break points of strip crops includes:

[0075] S201: Obtain the stitched spectral orthophoto.

[0076] This step is basically the same as S101 in the above-mentioned embodiment of the invention. Please refer to the above-mentioned embodiment of the invention for details, and will not be described again here.

[0077] S202: Calculate the EVI index and GpId index corresponding to each pixel in the spectral orthoimage.

[0078] In the embodiment of the present invention, the GpId index is the ratio of the near-infrared band reflectivity to the green band reflectivity multiplied by the red band reflectivity multiplied by the red edge band reflectivity. The above-mentioned EVI index is the enhanced vegetation index. In the embodiment of the present invention, the calculation formula of the EVI index is:

[0079]

[0080] The calculation formula of GpId index is:

[0081]

[0082] Among them, blue represents the blue band reflectivity; green represents the green band reflectivity; red represents the red band reflectivity; rededge represents the red edge band reflectivity; nir represents the near-infrared band reflectivity. Of course, other spectral characteristic indices can also be used in the embodiment of the present invention, and it is not limited to the use of only the above-mentioned EVI index and GpId index. Through the above-mentioned EVI index and GpId index, it can be accurately identified in subsequent steps whether the object corresponding to the pixel point belongs to the strip crop to be monitored. It should be noted that in the embodiment of the present invention, the EVI index and GpId index of each pixel are usually specifically calculated.

[0083] S203: The minimum threshold value of the EVI index to the maximum threshold value of the EVI index are used as the value range of the first preliminary classification standard, and the minimum threshold value of the GpId index to the maximum threshold value of the GpId index are used as the value range of the second preliminary classification standard.

[0084] In an embodiment of the present invention, the EVI and GpId indices are used simultaneously to binarize the spectral orthoimage. Specifically, in this step, the range from the minimum threshold of the EVI index to the maximum threshold of the EVI index is used as the value range of the first preliminary classification criterion, and the range from the minimum threshold of the GpId index to the maximum threshold of the GpId index is used as the value range of the second preliminary classification criterion, thereby determining two classification criteria. Of course, the maximum and minimum thresholds are generally user-adjustable.

[0085] S204: When the EVI index of the pixel is within the value range of the first preliminary classification standard and the GpId index is within the value range of the second preliminary classification standard, the value of the pixel is set to the first pixel value.

[0086] In this step, when the EVI index of a pixel is within the value range of the above-mentioned first preliminary classification standard, and the GpId index of the pixel is within the value range of the second preliminary classification standard, the value of the pixel will be set to the first pixel value, usually the value of the pixel is set to 1.

[0087] S205: When the EVI index of the pixel is not within the value range of the first preliminary classification standard, or the GpId index is not within the value range of the second preliminary classification standard, the pixel value is set to the second pixel value to obtain a preliminary classification result.

[0088] In this step, when the EVI index of a pixel is not within the value range of the above-mentioned first preliminary classification standard, or the GpId index of the pixel is not within the value range of the second preliminary classification standard, the value of the pixel will be set to the second pixel value, usually the value of the pixel will be set to 0, thereby achieving binarization and obtaining the preliminary classification result.

[0089] Specifically, after binarizing the spectral orthoimage through S204 to S205, a binarization result I can be obtained. fcI ; After that usually need to I fc′ Perform morphological operations to obtain the initial classification result I fc .

[0090] S206: Perform edge detection and line detection on the initial classification results in sequence to obtain the average angle of the plot.

[0091] In this step, the above-mentioned initial classification results I fc Perform Sobel edge detection, then Hough line detection to obtain a line angle matrix. This line angle matrix is ​​then filtered and averaged to obtain the average angle ang of the plot. For details on Sobel edge detection and Hough line detection, please refer to the existing art and will not be elaborated here.

[0092] S207: Generate a stripe marking matrix according to the average angle of the plot.

[0093] In this step, a stripe marking matrix I needs to be generated label The stripe marking matrix has the same size as the above spectral orthophoto. The stripe direction of the stripe marking matrix is ​​the average angle ang of the plot. Each stripe i in the stripe marking matrix label ∈I label , the size of its stripes is (m*n); while the size of the spectral orthophoto is (M*N).

[0094] S208: Calculate the area matrix based on the stripe marking matrix and the initial classification result.

[0095] In this step, the area matrix count_num is calculated according to the following formula:

[0096] I fl =I fc *I label ;

[0097] In this step, we need to calculate the fl ∈I fl The area of ​​​​I fl The area matrix count_num.

[0098] S209: Remove the stripes corresponding to the values ​​smaller than the area threshold in the area matrix to obtain the result to be used.

[0099] In this step, when the value of the stripe in the area matrix count_num is less than e, the pixels in the stripe can be considered as weeds and set to 0, that is, the stripes corresponding to the values ​​less than the area threshold in the area matrix are eliminated, and finally I is obtained. flA ; where e is the area threshold.

[0100] After that, you can flA Binarization is I flAB , the I flAB It is the result after weed removal, i.e. the result to be used. It should be noted that the above weed removal process is usually achieved by automatically dividing the calculation area according to the drawn polygons through software, and calling the above weed removal algorithm for each area in turn to achieve weed removal.

[0101] S210: Calculate the minimum circumscribed convex polygon for each connected domain in the result to be used and record the node coordinates.

[0102] In this step, the above I flAB For each connected domain in , calculate the minimum circumscribed convex polygon and record the node coordinates so as to identify the broken ridge points in the subsequent steps.

[0103] S211: Calculate the distance between each node in the connected domain and the other nodes in the connected domain according to the node coordinates.

[0104] In this step, the distances between the nodes in each connected domain and the nodes in other connected domains need to be calculated in sequence. Specifically, the distances are calculated based on the node coordinates recorded in S210 above.

[0105] S212: When the distance is less than the distance threshold and the slope of the line between the two nodes is within the allowable error range, connect the two nodes.

[0106] In this step, if the distance is less than the distance threshold f and the distance between the two nodes is less than the distance threshold f Two nodes are connected if the distance is within the permissible tan(ang) error range, that is, when the distance is less than the distance threshold and the slope of the line connecting the two nodes is within the permissible error range. The distance threshold f is used to limit the maximum length of the breakpoint identification; (u, v) represents two nodes that do not belong to the same connected domain, i.e., connected nodes.

[0107] It should be noted that in the embodiment of the present invention, by fully considering the influence of the planting direction on the algorithm in the above S207 and this step, in special scenarios such as vineyards, a recognition algorithm with higher accuracy can be created, so as to accurately calculate the identification of the ridge break points in subsequent steps.

[0108] S213: Generate a connected domain label matrix based on the newly added connection lines.

[0109] In this step, I flAB All newly added links in the matrix generate a connected component label matrix I line .

[0110] S214: Perform grayscale morphological operations on the connected component marker matrix to obtain the center point and area of ​​the broken ridge point.

[0111] In this step, the connected domain labeling matrix I line Perform grayscale morphological operations and record the position and area of ​​each connected domain. Usually, the position and area of ​​each connected domain are recorded in R point In the process, the center point and area of ​​the ridge breaking point are used to realize the identification of the crop ridge breaking point.

[0112] The present invention provides a method for identifying ridge breakpoints in strip crops. This method takes into account practical limitations in monitoring scenarios, such as the presence of numerous weeds, gradual changes in ridge orientation within the same plot, and the presence of other vegetation adjacent to the plot. By adding and optimizing a weed detection algorithm and a weakly dependent Hough line detection algorithm, the accuracy of automatic ridge break identification is improved. Spectral remote sensing methods are used to enrich the acquired information with crop characteristics, and the spectral vegetation index can significantly improve monitoring accuracy. Furthermore, the aforementioned process has a low reliance on features such as shape, thus relaxing restrictions on flight altitude and improving the efficiency of field data acquisition.

[0113] The following is an introduction to a device for identifying ridge-break points of strip crops provided by an embodiment of the present invention. The device for identifying ridge-break points of strip crops described below and the method for identifying ridge-break points of strip crops described above can be referenced to each other.

[0114] Please refer to Figure 3 , Figure 3 This is a structural block diagram of a device for identifying ridge break points of ridge crops provided by an embodiment of the present invention. Figure 3 The device for identifying the break point of a ridge crop may include:

[0115] The acquisition module 100 is used to acquire the spliced ​​spectral orthoimage.

[0116] The characteristic index module 200 is used to calculate the spectral characteristic index corresponding to each pixel in the spectral orthoimage.

[0117] The initial classification result module 300 is used to binarize each pixel in the spectral orthoimage according to the spectral characteristic index to obtain an initial classification result.

[0118] The weed removal module 400 is used to remove weeds from the initial classification results to obtain results to be used.

[0119] The extraction module 500 is used to extract the target ridge line of the result to be used.

[0120] The identification module 600 is used to identify the crop ridge break point according to the target ridge line.

[0121] Preferably, in the embodiment of the present invention, the preliminary classification result module 300 is specifically used to:

[0122] The minimum threshold to the maximum threshold of the spectral characteristic index is used as the value range of the initial classification standard, and each pixel in the spectral orthophoto is binarized according to the initial classification standard to obtain the initial classification result.

[0123] Preferably, in the embodiment of the present invention, the characteristic index module 200 is specifically configured to:

[0124] Calculate the EVI index and GpId index corresponding to each pixel in the spectral orthoimage; the GpId index is the ratio of the near-infrared band reflectivity to the green band reflectivity multiplied by the red band reflectivity multiplied by the red edge band reflectivity.

[0125] Preferably, in this embodiment of the present invention, the preliminary classification result module 300 includes:

[0126] The range determination unit is used to use the minimum threshold value of the EVI index to the maximum threshold value of the EVI index as the value range of the first preliminary classification standard, and use the minimum threshold value of the GpId index to the maximum threshold value of the GpId index as the value range of the second preliminary classification standard.

[0127] The first pixel value unit is configured to set the value of the pixel to a first pixel value when the EVI index of the pixel is within the value range of the first preliminary classification standard and the GpId index is within the value range of the second preliminary classification standard.

[0128] The second pixel value unit is used to set the value of the pixel to the second pixel value to obtain the initial classification result when the EVI index of the pixel is not within the value range of the first initial classification standard, or the GpId index is not within the value range of the second initial classification standard.

[0129] Preferably, in the embodiment of the present invention, the weed removal module 400 includes:

[0130] The angle unit is used to perform edge detection and line detection on the initial classification results in sequence to obtain the average angle of the plot.

[0131] The stripe mark matrix unit is used to generate a stripe mark matrix according to the average angle of the land parcel.

[0132] An area matrix unit is used to calculate an area matrix according to the stripe mark matrix and the initial classification result.

[0133] The elimination unit is used to eliminate the stripes corresponding to the values ​​smaller than the area threshold in the area matrix to obtain the result to be used.

[0134] Preferably, in this embodiment of the present invention, the extraction module 500 includes:

[0135] The node recording unit is used to calculate the minimum circumscribed convex polygon for each connected domain in the result to be used and record the node coordinates.

[0136] A distance calculation unit, configured to calculate the distance between a node in each connected domain and the other nodes in the connected domain according to the node coordinates;

[0137] The node connection unit is used to connect two nodes when the distance is less than a distance threshold and the slope of the connection line between the two nodes is within an allowable error range.

[0138] The connected domain labeling matrix unit is used to generate a connected domain labeling matrix according to the newly added connection lines.

[0139] Preferably, in the embodiment of the present invention, the identification module 600 is specifically configured to:

[0140] Grayscale morphological operation is performed on the connected domain marker matrix to obtain the center point and area of ​​the broken ridge point.

[0141] The strip crop break point identification device of this embodiment is used to implement the aforementioned strip crop break point identification method. Therefore, the specific implementation method of the strip crop break point identification device can be seen in the embodiment part of the strip crop break point identification method in the previous text. For example, the acquisition module 100, the feature index module 200, the initial classification result module 300, the weed removal module 400, the extraction module 500, and the identification module 600 are respectively used to implement steps S101 to S106 in the above-mentioned strip crop break point identification method. Therefore, its specific implementation method can refer to the description of the corresponding each part embodiment, and will not be repeated here.

[0142] The following is an introduction to a strip crop break point identification device provided by an embodiment of the present invention. The strip crop break point identification device described below and the strip crop break point identification method and strip crop break point identification device described above can be referenced to each other.

[0143] Please refer to Figure 4 , Figure 4 This is a structural block diagram of a device for identifying ridge break points of strip crops provided by an embodiment of the present invention.

[0144] Reference Figure 4 The device for identifying crop break points in a ridge may include a processor 11 and a memory 12.

[0145] The memory 12 is used to store computer programs; the processor 11 is used to implement the specific content of the method for identifying ridge break points of strip crops described in the above-mentioned embodiment of the invention when executing the computer program.

[0146] The processor 11 in the ridge-break point identification device of this embodiment is used to install the ridge-break point identification device described in the above-mentioned invention embodiments. The processor 11, in combination with the memory 12, can implement the ridge-break point identification method described in any of the above-mentioned invention embodiments. Therefore, the specific implementation of the ridge-break point identification device can be found in the embodiment section of the ridge-break point identification method described above. The specific implementation of the ridge-break point identification device can be found in the description of the corresponding embodiment section of the ridge-break point identification method. The specific implementation of the ridge-break point identification device can be found in the description of the corresponding embodiment section, and will not be repeated here.

[0147] The present invention also provides a computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements the method for identifying ridge break points in a row crop described in any of the aforementioned embodiments. The remaining details can be referenced to the prior art and will not be further described here.

[0148] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from the other embodiments. Reference can be made to the descriptions of the identical or similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and the relevant parts can be referred to the descriptions of the methods.

[0149] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0150] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0151] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0152] The above is a detailed introduction to a method for identifying ridge break points of strip crops, a device for identifying ridge break points of strip crops, a device for identifying ridge break points of strip crops, and a computer-readable storage medium provided by the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core concept. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of the present invention, several improvements and modifications can be made to the present invention, and these improvements and modifications also fall within the scope of protection of the claims of the present invention.

Claims

1. A method for identifying the break point of a ridge crop, characterized in that: include: Obtain stitched spectral orthoimages; Calculating the spectral characteristic index corresponding to each pixel in the spectral orthoimage; The spectral characteristic index can quantitatively characterize the measurement result of the position of the corresponding pixel to determine the position of the strip crop; Binarizing each pixel in the spectral orthophoto according to the spectral characteristic index to obtain a preliminary classification result; wherein, when the binarization of the spectral orthophoto is realized, the outline of the ridge crop in the spectral orthophoto is determined according to the spectral characteristic index to obtain a preliminary classification result; Eliminating weeds in the initial classification results to obtain results to be used; Extracting the target ridge line of the result to be used; Identify crop ridge break points according to the target ridge line; Wherein, calculating the spectral characteristic index corresponding to each pixel in the spectral orthophoto includes: The EVI index and the GpId index corresponding to each pixel in the spectral orthophoto are calculated; the GpId index is the ratio of the near-infrared band reflectivity to the green band reflectivity multiplied by the red band reflectivity multiplied by the red edge band reflectivity.

2. The method according to claim 1, characterized in that Binarizing each pixel in the spectral orthophoto according to the spectral characteristic index to obtain the initial classification result includes: The minimum threshold to the maximum threshold of the spectral feature index is used as the value range of the initial classification standard, and each pixel in the spectral orthophoto is binarized according to the initial classification standard to obtain the initial classification result.

3. The method according to claim 1, characterized in that The minimum threshold to the maximum threshold of the spectral characteristic index is used as the value range of the initial classification standard, and each pixel in the spectral orthophoto is binarized according to the initial classification standard to obtain the initial classification results including: The minimum threshold value of the EVI index to the maximum threshold value of the EVI index are used as the value range of the first preliminary classification standard, and the minimum threshold value of the GpId index to the maximum threshold value of the GpId index are used as the value range of the second preliminary classification standard; When the EVI index of the pixel is within the value range of the first preliminary classification standard, and the GpId index is within the value range of the second preliminary classification standard, setting the value of the pixel to the first pixel value; When the EVI index of the pixel is not within the value range of the first preliminary classification standard, or the GpId index is not within the value range of the second preliminary classification standard, the value of the pixel is set to the second pixel value to obtain a preliminary classification result.

4. The method according to claim 1, characterized in that: The removing of weeds from the initial classification results to obtain the results to be used comprises: Perform edge detection and straight line detection on the initial classification results in turn to obtain an average angle of the plot; the average angle of the plot is the average angle of the plot obtained by filtering and averaging the straight line angle matrix obtained by the straight line detection; Generate a stripe mark matrix according to the average angle of the plot; the stripe mark matrix is ​​a matrix with the same size as the spectral orthophoto and a stripe direction of the average angle of the plot; The area matrix is ​​calculated based on the stripe marking matrix and the initial classification result; wherein, according to Calculate the area matrix count_num by calculating each stripe The area of The area matrix count_num; is the initial classification result, is the stripe marking matrix; The stripes corresponding to the values ​​in the area matrix that are smaller than the area threshold are removed to obtain the result to be used.

5. The method according to claim 1, characterized in that Extracting the target ridge line of the result to be used includes: Calculate the minimum circumscribed convex polygon for each connected domain in the result and record the node coordinates; Calculate the distance between each node in each connected domain and the other nodes in the connected domain according to the node coordinates; When the distance is less than the distance threshold and the slope of the line between the two nodes is within the allowable error range, the two nodes are connected; Generate a connected domain label matrix based on the newly added connection lines.

6. The method according to claim 5, characterized in that Identifying the crop ridge break point according to the target ridge line includes: Grayscale morphological operation is performed on the connected domain marker matrix to obtain the center point and area of ​​the broken ridge point.

7. A device for identifying the break point of a crop strip, characterized in that: include: An acquisition module is used to obtain the spliced ​​spectral orthophoto; A characteristic index module is used to calculate the spectral characteristic index corresponding to each pixel in the spectral orthophoto; the spectral characteristic index can quantitatively characterize the measurement result of the position of the corresponding pixel to determine the position of the strip crop; The initial classification result module is used to binarize each pixel in the spectral orthophoto according to the spectral characteristic index to obtain the initial classification result; wherein, when the binarization of the spectral orthophoto is realized, the outline of the strip crops in the spectral orthophoto is determined according to the spectral characteristic index to obtain the initial classification result; A weed removal module is used to remove weeds from the initial classification results to obtain results to be used; An extraction module, used for extracting the target ridge line of the result to be used; An identification module, used for identifying crop ridge break points according to the target ridge line; Among them, the characteristic index module is specifically used for: The EVI index and the GpId index corresponding to each pixel in the spectral orthophoto are calculated; the GpId index is the ratio of the near-infrared band reflectivity to the green band reflectivity multiplied by the red band reflectivity multiplied by the red edge band reflectivity.

8. A device for identifying the break point of ridge crops, characterized in that: include: Memory for storing computer programs; A processor is used to execute the computer program to implement the steps of the method for identifying the breaking points of crops in a ridge as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the method for identifying ridge break points of crops in strips of ridges as described in any one of claims 1 to 6.

Images