CN107220647A - Crop location of the core method and system under a kind of blade crossing condition - Google Patents

Abstract

The present invention provides a method and system for locating the center point of a crop under the condition of leaves crossing. The method includes: acquiring a grayscale image and a binary image of the target crop based on the original grayscale image of the target crop; Degree image and binary image to obtain the coordinates of the center point of the target crop. The solution of the present invention has the following beneficial effects: the interference of crossing leaves of crops can be effectively eliminated, and the accuracy and speed of positioning the center point of crops can be improved.

Description

A method and system for locating the center point of crops under the condition of leaves crossing

technical field

The present invention relates to the technical field of automatic identification and positioning of crops, and more particularly, to a method and system for locating the center point of crops under the condition of leaves crossing.

Background technique

The crop automatic identification and positioning technology based on machine vision can quickly obtain the distribution of crops, provide reference for mechanized management of crops in the field, help reduce labor intensity, and improve work efficiency and precision. The automatic identification and location of crops can usually be realized by collecting two-dimensional color images or three-dimensional position information of crops. The two-dimensional color image is obtained by a color camera, which contains the color information of the crop, and has flexible application and low cost of use; the three-dimensional position data needs to be obtained by a depth camera, a stereo camera or a laser sensor, which can generate point cloud data of the crop, and the cost is relatively high. The amount of calculation data is large. Therefore, crop identification and positioning based on color images has always been a research hotspot.

The method of crop identification and location based on color images is to use color cameras to obtain image information of crops, and through image analysis and processing, crops are extracted and their center points are located. Generally, the green information of the crop is used to segment the crop from the complex background, extract the outline of the crop and the connected area, and then calculate the centroid of the connected area to obtain the center point of the crop. However, when this method detects crops with irregular shapes, the location of the crop center point is prone to deviation.

In the prior art, for the extracted target crops, firstly, the crop row to be tested is determined through the histogram statistics of the pixel rows, and then the histogram statistics of the pixel columns are performed on the crop row to be tested to determine the center point of the crop. This method can overcome the crop shape The impact of irregularities on positioning, but when crop leaves cross, it will cause the failure of crop center point positioning. Crop images are usually skeletonized when leaves cross. In the skeleton of the image, there will be an end point at the end position of the leaf, and there will be an intersection point at the intersection of the leaf and the center point of the crop. Retrieve the end point and intersection point in the skeleton, and classify and logically judge the intersection point, so as to realize the The location of the crop center point, but this method has a large amount of calculation and low accuracy.

Contents of the invention

In order to overcome the above problems or at least partly solve the above problems, the present invention provides a method and system for locating the center point of crops under the condition of leaves crossing.

According to one aspect of the present invention, a kind of crop center point location method under the condition of crossing leaves is proposed, comprising:

Step 1, based on the original grayscale image of the target crop, obtain the grayscale image and binary image of the target crop;

Step 2, based on the grayscale image and the binary image of the target crop, the coordinates of the center point of the target crop are obtained.

Further, said step 1 further includes:

S11. Obtain a binary image of the original grayscale image of the target crop based on the original grayscale image of the target crop;

S12, performing morphological denoising processing on the binary image of the original grayscale image of the target crop, and determining an image interest area of the target crop;

S13. Based on the ROI of the image of the target crop, acquire a binary image of the ROI of the image of the target crop.

Further, said step 2 further includes:

S21. Fusing the original grayscale image of the target crop with the binary image of the image region of interest of the target crop to obtain a grayscale image of the image region of interest of the target crop;

S22. Obtain the minimum value point of the grayscale image of the image region of interest of the target crop; obtain the minimum value point in the grayscale image of the image region of interest of the target crop with a difference from surrounding pixel points greater than a threshold;

S23, based on the grayscale image of the image region of interest of the target crop and the minimum point obtained in S22, using the watershed algorithm to obtain the coordinates of the center point of the target crop.

Further, before the step 1, it also includes:

The initial image of the target crop is subjected to grayscale processing, and the grayscale processing includes the following steps,

I _gray (i,j)=G(i,j)*1.262-R(i,j)*0.884-B(i,j)*0.311,

Where i and j are the row and column coordinates of the pixel, and G(i,j), R(i,j) and B(i,j) are the grayscales of the G, R and B color components of the pixel at image (i,j) respectively value, Igray(i,j) is the gray value of the pixel at (i,j) in the transformed image.

Further, said S12 further includes:

Based on the original grayscale image of the target crop, the conversion threshold for obtaining the binary image of the original grayscale image of the target crop is obtained by using the maximum inter-class variance method.

Further, said S12 further includes:

Using the morphological opening operation to remove the interference of weed noise in the binary image of the original grayscale image of the target crop;

Horizontally project the pixel values of the binary image of the original grayscale image of the target crop after denoising to obtain a projection curve with the pixel row coordinates as the abscissa; divide the projection curve into two parts with the intermediate pixel behavior, and find each The coordinates of the pixel row corresponding to the position of the minimum value of the curve, and the area between two pixel rows is the image interest area of the target crop.

Further, said S22 further includes:

Calculate the minimum value point and the maximum value point in the eight neighbors in the grayscale image of the image interest area of the target crop, and calculate the average value of the minimum value point and the maximum value point, the difference between the two, As a threshold, keep the minimum value points whose drop from the surrounding pixels is greater than the threshold value, and obtain the final local minimum value.

Further, said S23 further includes:

Using the minimum value point obtained in S22 to carry out foreground marking on the grayscale image of the image interest area of the target crop; using the watershed algorithm to use the marked grayscale image as an input image to obtain the central area of the target crop;

Based on the central area of the target crop, add and sum the x-coordinates and y-coordinates of the pixels in the central area, and count the number of pixels in the central area, the ratio of the x-coordinate sum, y-coordinate sum to the number of pixel points That is, the coordinates of the final crop center point.

According to another aspect of the present invention, there is provided a crop center point positioning system under leaf crossing conditions, comprising:

The obtaining module is used to obtain the grayscale image and the binary image of the target crop based on the original grayscale image of the target crop;

The positioning module is used to obtain the coordinates of the center point of the target crop based on the grayscale image and the binary image of the target crop.

According to yet another aspect of the present invention, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions cause the computer to perform any one of the above-mentioned the method described.

The present application proposes a method and system for locating the center point of crops under the condition of intersecting leaves. The scheme of the invention has the following beneficial effects: it can effectively eliminate the interference of intersecting leaves of crops, and improve the accuracy and speed of locating the center point of crops.

Description of drawings

1 is a schematic diagram of the overall flow of a method for locating the center point of a crop under the condition of crossing leaves according to an embodiment of the present invention;

2 is a schematic flow diagram of a method for locating the center point of a crop under the condition of crossing leaves according to an embodiment of the present invention;

3 is a schematic diagram of an original grayscale image of a target crop according to a method for locating the center point of a crop under the condition of crossing leaves according to an embodiment of the present invention;

4 is a schematic diagram of an original binary image of a target crop according to a method for locating the center point of a crop under the condition of crossing leaves according to an embodiment of the present invention;

5 is a schematic diagram of a binary image horizontal projection of the original grayscale image of the target crop in a method for locating the center point of the crop under the leaf crossing condition according to an embodiment of the present invention;

6 is a schematic diagram of the interest area of the target corn image in a method for locating the center point of corn under the condition of crossing leaves according to an embodiment of the present invention;

7 is a schematic diagram of the original grayscale image of the target corn in a method for locating the center point of the corn under the condition of crossing leaves according to an embodiment of the present invention;

Fig. 8 is a schematic diagram of a binary image of the target corn in a method for locating the center point of corn under the condition of crossing leaves according to an embodiment of the present invention.

9 is a schematic diagram of the minimum value region of the original grayscale image of the target corn in a method for locating the center point of the corn under the leaf crossing condition according to an embodiment of the present invention;

Fig. 10 is a schematic diagram of the crop center area obtained by segmentation processing using the watershed algorithm in a method for locating the center point of corn under the condition of crossing leaves according to an embodiment of the present invention;

11 is a schematic diagram of the coordinates of the corn center point obtained by using the watershed algorithm in a method for locating the center point of corn under the condition of crossing leaves according to an embodiment of the present invention;

12 is a schematic diagram of the overall framework of a corn center point positioning system under the condition of crossing leaves according to an embodiment of the present invention;

Fig. 13 is a schematic structural frame diagram of a device for a method for locating the center point of corn under the condition of crossing leaves according to an embodiment of the present invention.

detailed description

The specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

As shown in FIG. 1 , in a specific embodiment of the present invention, it shows a schematic diagram of the overall flow of a method for locating the center point of a crop under the condition of leaves crossing. Generally, it includes: Step 1, based on the original grayscale image of the target crop, obtain the grayscale image and binary image of the target crop; Step 2, based on the grayscale image and binary image of the target crop, obtain the Center point coordinates.

In another specific embodiment of the present invention, a method for locating the center point of a crop under the condition of crossing leaves, the step 1 further includes: S11, based on the original grayscale image of the target crop, obtaining the original grayscale image of the target crop Binary image; S12, perform morphological denoising processing on the binary image of the original grayscale image of the target crop, and determine the image interest area of the target crop; S13, obtain the image interest area based on the target crop image The binary image of the ROI of the target crop image.

In another specific embodiment of the present invention, a method for locating the center point of a crop under the condition of crossing leaves, the step 2 further includes:

S21. Fusing the original grayscale image of the target crop with the binary image of the image region of interest of the target crop to obtain a grayscale image of the image region of interest of the target crop;

S22. Obtain the minimum value point of the grayscale image of the image region of interest of the target crop; obtain the minimum value point in the grayscale image of the image region of interest of the target crop with a difference from surrounding pixel points greater than a threshold;

S23, based on the grayscale image of the image region of interest of the target crop and the minimum point obtained in S22, using the watershed algorithm to obtain the coordinates of the center point of the target crop.

In another specific embodiment of the present invention, a method for locating the center point of crops under the condition of leaves crossing, the step 1 also includes:

The initial image of the target crop is subjected to grayscale processing, and the grayscale processing includes the following steps,

I _gray (i,j)=G(i,j)*1.262-R(i,j)*0.884-B(i,j)*0.311,

Where i and j are the row and column coordinates of the pixel, and G(i,j), R(i,j) and B(i,j) are the grayscales of the G, R and B color components of the pixel at image (i,j) respectively value, Igray(i,j) is the gray value of the pixel at (i,j) in the converted image.

In another specific embodiment of the present invention, a method for locating the center point of a crop under the condition of crossing leaves, the S12 further includes:

Using the morphological opening operation to remove the interference of weed noise in the binary image of the original grayscale image of the target crop;

Horizontally project the pixel values of the binary image of the original grayscale image of the target crop after denoising to obtain a projection curve with the pixel row coordinates as the abscissa; divide the projection curve into two parts with the intermediate pixel behavior, and find each The coordinates of the pixel row corresponding to the position of the minimum value of the curve, and the area between two pixel rows is the image interest area of the target crop.

In another specific embodiment of the present invention, a method for locating the center point of a crop under the condition of crossing leaves, the S22 further includes:

Calculate the minimum value point and the maximum value point in the eight neighbors in the grayscale image of the image interest area of the target crop, and calculate the average value of the minimum value point and the maximum value point, the difference between the two, As a threshold, keep the minimum value points whose drop from the surrounding pixels is greater than the threshold value, and obtain the final local minimum value.

In another specific embodiment of the present invention, a method for locating the center point of a crop under the condition of crossing leaves, said S23 further includes:

Using the minimum value point obtained in S22 to carry out foreground marking on the grayscale image of the image interest area of the target crop; using the watershed algorithm to use the marked grayscale image as an input image to obtain the central area of the target crop;

Based on the central area of the target crop, add and sum the x-coordinates and y-coordinates of the pixels in the central area, and count the number of pixels in the central area, the ratio of the x-coordinate sum, y-coordinate sum to the number of pixel points That is, the coordinates of the final crop center point.

FIG. 2 is a schematic flowchart of a method for locating the center point of a crop under the condition of crossing leaves according to an embodiment of the present invention. This specific embodiment provides a method for locating the center point of a crop in the case of leaves crossing. The method fully considers the influence of factors such as weeds and crossing leaves on the location of the crop center point, and improves the speed and accuracy of the location of the crop center point. The method specifically includes the following steps.

Adjust the height and angle of the installed camera so that the camera shoots the crop row vertically to ensure that the crop row in the collected image is approximately parallel to the horizontal direction, and the crop to be tested is located in the middle of the image, and the crop row where it is located is called a specific crop row.

The image is converted as follows:

I _gray (i,j)=G(i,j)*1.262-R(i,j)*0.884-B(i,j)*0.311,

Where i and j are the row and column coordinates of the pixel, and G(i,j), R(i,j) and B(i,j) are the grayscales of the G, R and B color components of the pixel at image (i,j) respectively value, Igray(i,j) is the gray value of the pixel at (i,j) in the transformed image.

In the binary image, white pixels (with a gray value of 1) are crops, and black pixels (with a gray value of 0) are backgrounds. The binary image is morphologically opened with square structural elements to remove the tiny white area noise in the binary image.

According to the binary image obtained by the denoising process, the region of interest is determined according to the following method: horizontally project the pixel gray value of the binary image, obtain the projection curve with the pixel row coordinate as the abscissa, and use the middle pixel row Midrow as the boundary to project The curve is divided into two parts, each curve has a minimum value min1, min2, each minimum value may correspond to one or more pixel row coordinates, record the pixel row coordinates closest to the middle pixel row Midrow as Rowmin1, Rowmin2, determine Rowmin1 and Rowmin2 The area in between is the region of interest.

Calculate the area of each connected region in the region of interest of the binary image, retain the region with the largest area, and obtain a binary image containing the crop to be tested.

The binary image containing the crop to be tested and the grayscale image are fused according to the following method to extract a new grayscale image Inew: Detect the coordinates (i, j) of the white pixel point containing the binary image of the crop to be tested, and the white pixel point The gray value of is the corresponding gray value Igray(i,j) in the gray image, and the gray value at the black pixel is set to 0.

The center area of the crop is the new leaf. In the grayscale image Inew, the grayscale value of this area is higher than that of the surrounding mature leaves, and the pixel grayscale value has a large drop. By detecting the grayscale value in the eight neighborhoods of the pixel in the grayscale image Minimum value to determine the central area of the crop. However, there are usually a large number of local minimum points in the grayscale image, which is easy to cause false detection. Apply the following formula to perform the extended minimum operation on it, and perform blanking processing on the minimum point in the image whose gray value difference with the neighboring pixels is smaller than the threshold h, and obtain the local minimum value:

BW1=EM(Inew,h),

Among them, BW1 represents the grayscale image obtained by the extended minimum operation, which marks the minimum value of the image; EM represents the extended minimum operation; h represents the drop threshold. The drop threshold is obtained by calculating the difference between the average value of the maximum point and the average value of the minimum point in the image.

Apply the following formula to perform a morphologically enforced minimum operation on the image to mark the image minimum and eliminate all other minimum values outside the specified area:

BW2 = Imposemin(Inew, BW1),

Among them, BW2 represents the grayscale image after marking, and Imposemin represents the minimum operation of morphological enforcement.

Taking the marked image BW2 as the input image, the watershed algorithm is used to segment the image to obtain the central area of the crop.

Calculate the center of mass coordinates of the crop center area according to the following method, and locate the crop center point. Firstly, the center area of the obtained crop is extracted to obtain the binary image of the center area, the white pixels (gray value 1) are the center area, and the black pixels (gray value 0) are the background. Scan and count the white pixels of the binary image in the central area to obtain the number N of pixels in the central area, and add and sum the pixel row coordinates x of all white pixels to obtain X, and add and sum the pixel column coordinates y To get Y, calculate the center of mass coordinates (Xcenter, Ycenter) of the crop center area according to the following formula,

Among them, ceil represents the rounding operation, and the coordinates of the center point of the crop in the original image are (Xcenter+Rowmin1, Ycenter).

Yet another specific embodiment of the present invention provides a method for locating the center point of a crop under the condition of leaves crossing. Taking the corn image as an example, under natural conditions, the rapid positioning of the center point of the corn is realized.

In the image originally collected in this embodiment, the middle row of crops is approximately horizontal, and this row of crops is a specific crop row, and the corn to be tested is located in the middle of the specific crop row.

Fig. 3 is a schematic diagram of the original grayscale image of the target corn according to the embodiment of the present invention. The collected image is converted to grayscale, and the maximum between-class variance method is used to calculate the grayscale threshold value of 138, and the grayscale image is converted into a binary image. As shown in Figure 4, the white pixels (with a grayscale value of 1) are plants (corn or weed), black pixels (gray value 0) are the background.

5 is a schematic diagram of the horizontal projection of the binary image of the original grayscale image of the target corn in a method for locating the center point of the corn under the condition of crossing leaves according to an embodiment of the present invention. 6 is a schematic diagram of the ROI of the target corn image in a method for locating the center point of corn under the condition of crossing leaves according to an embodiment of the present invention. First, in this embodiment, a square structural element with a pixel size of 4 pixels is selected to perform an opening operation on the binary image to eliminate the small white area of the binary image; then, the denoised binary image is horizontally projected, Obtain the projection curve; divide the projection curve into two parts with the middle pixel line Midrow as the boundary, Midrow=360 in the present embodiment; determine the minimum value min1, min2 and the corresponding pixel row coordinates of each curve, select the distance from the middle pixel row The nearest pixel row coordinates of Midrow are Rowmin1 and Rowmin2. In this embodiment, min1=0, min2=0, the corresponding pixel row coordinates are Rowmin1=299, Rowmin2=631, then the area between Rowmin1 and Rowmin2 is determined to be the interest of the image Area.

Fig. 7 is a schematic diagram of the original grayscale image of the target corn in a method for locating the center point of the corn under the condition of crossing leaves according to an embodiment of the present invention. Fig. 8 is a schematic diagram of a binary image of the target corn in a method for locating the center point of corn under the condition of crossing leaves according to an embodiment of the present invention. The area of each area in the area of interest is counted. The corn to be tested is located in the area of interest. Since it intersects with other leaves, its area is the largest. Keep the area with the largest area and remove the interference of scattered leaves. In this embodiment, the area where the corn to be tested is located is 23048 square meters. Detect the white pixel point containing the binary image of the corn to be tested, its coordinates are (i, j), and the gray value of the white pixel point in the new gray image Inew is that of the gray image (i, j) in Figure 3 value. The gray value of the black pixels in the corn area to be tested in the new gray image Inew is 0.

9 is a schematic diagram of the minimum value region of the original grayscale image of the target corn in a method for locating the center point of corn under the condition of leaf crossing according to an embodiment of the present invention; it is to perform an extended minimum operation on the grayscale image Inew of the embodiment The obtained BW1, the gray value near the corn center point of BW1 is higher than the surrounding pixels. In this embodiment, the average value of the minimum value point is 147.09, the average value of the maximum value point is 150.47, and the drop threshold h is set to 3.38 to eliminate the minimum value in the micro region.

Fig. 10 is a schematic diagram of a crop center area obtained by segmentation processing using a watershed algorithm in a method for locating a center point of corn under the condition of crossing leaves according to an embodiment of the present invention. The gray-scale image Inew of the embodiment is marked by the morphological forced minimum operation, and the marked image is used as the input image, and the image is segmented by using the watershed algorithm to obtain the central area of the embodiment, as shown in FIG. 10 .

11 is a schematic diagram of the coordinates of the corn center point obtained by using the watershed algorithm in a method for locating the center point of corn under the cross-leaf condition according to an embodiment of the present invention.

The shape of the corn center area obtained in Figure 10 is irregular, and the centroid of this area is calculated as the center point of the corn. Scanning statistics are performed on the pixels in the central area, and the centroid coordinates are calculated according to formula (4). In this embodiment, the pixel point N=557 in the central area, the sum of the x coordinates of the pixels X=89017, the sum of the y coordinates Y=152204, and the centroid coordinates (160,270) are obtained, then the coordinates of the center point of the corn are (459,270), The results are shown in Figure 11 with cross marks.

As shown in FIG. 12 , in another specific embodiment of the present invention, it shows a schematic diagram of the overall framework of a crop center point positioning system under the condition of leaves crossing. On the whole, it includes: acquisition module A1, used to acquire the grayscale image and binary image of the target crop based on the original grayscale image of the target crop; positioning module A2, used to obtain the grayscale image and binary image of the target crop Image, get the coordinates of the center point of the target crop.

In another specific embodiment of the present invention, a system for locating the center point of a crop under the condition of crossing leaves, the acquisition module is further configured to: based on the original grayscale image of the target crop, obtain a binary image of the original grayscale image of the target crop value image; perform morphological denoising processing on the binary image of the original grayscale image of the target crop to determine the image interest area of the target crop; based on the image interest area of the target crop, obtain the image interest area of the target crop Binary image of the region.

In another specific embodiment of the present invention, a crop center point positioning system under the condition of crossing leaves, the positioning module is also used for:

S21. Fusing the original grayscale image of the target crop with the binary image of the image region of interest of the target crop to obtain a grayscale image of the image region of interest of the target crop;

S22. Obtain the minimum value point of the grayscale image of the image region of interest of the target crop; obtain the minimum value point in the grayscale image of the image region of interest of the target crop with a difference from surrounding pixel points greater than a threshold;

S23, based on the grayscale image of the image region of interest of the target crop and the minimum point obtained in S22, using the watershed algorithm to obtain the coordinates of the center point of the target crop.

In another specific embodiment of the present invention, a crop center point positioning system under leaf crossing conditions, the acquisition module is also used to grayscale the initial image of the target crop, and the grayscale processing includes the following step,

I _gray (i,j)=G(i,j)*1.262-R(i,j)*0.884-B(i,j)*0.311,

Where i and j are the row and column coordinates of the pixel, and G(i,j), R(i,j) and B(i,j) are the grayscales of the G, R and B color components of the pixel at image (i,j) respectively value, Igray(i,j) is the gray value of the pixel at (i,j) in the transformed image.

In another specific embodiment of the present invention, a crop center point positioning system under leaf crossing conditions, the acquisition module is also used to obtain a binary image of the original grayscale image of the target crop based on the original grayscale image of the target crop. The conversion threshold of the value image is obtained by the method of maximum between-class variance.

In another specific embodiment of the present invention, a crop center point positioning system under the condition of crossing leaves, the acquisition module is also used for:

Using the morphological opening operation to remove the interference of weed noise in the binary image of the original grayscale image of the target crop;

Horizontally project the pixel values of the binary image of the original grayscale image of the target crop after denoising to obtain a projection curve with the pixel row coordinates as the abscissa; divide the projection curve into two parts with the intermediate pixel behavior, and find each The coordinates of the pixel row corresponding to the position of the minimum value of the curve, and the area between two pixel rows is the image interest area of the target crop.

In another specific embodiment of the present invention, a crop center point positioning system under the condition of crossing leaves, the positioning module is also used for:

Calculate the minimum value point and the maximum value point in the eight neighbors in the grayscale image of the image interest area of the target crop, and calculate the average value of the minimum value point and the maximum value point, the difference between the two, As a threshold, keep the minimum value points whose drop from the surrounding pixels is greater than the threshold value, and obtain the final local minimum value.

In another specific embodiment of the present invention, a crop center point positioning system under the condition of crossing leaves, the positioning module is also used for:

Using the minimum value point obtained in S22 to carry out foreground marking on the grayscale image of the image interest area of the target crop; using the watershed algorithm to use the marked grayscale image as an input image to obtain the central area of the target crop;

Based on the central area of the target crop, add and sum the x-coordinates and y-coordinates of the pixels in the central area, and count the number of pixels in the central area, the ratio of the x-coordinate sum, y-coordinate sum to the number of pixel points That is, the coordinates of the final crop center point.

Fig. 13 shows a structural block diagram of equipment for a method for locating a crop center point under the condition of crossing leaves according to an embodiment of the present application.

Referring to Fig. 13, the equipment of the crop center point positioning method under the leaf crossing condition includes: a processor (processor) 1301, a memory (memory) 1302 and a bus 1303;

in,

The processor 1301 and the memory 1302 communicate with each other through the bus 1303;

The processor 1301 is used to call the program instructions in the memory 1302 to execute the methods provided by the above method embodiments, for example, including: step 1, based on the original grayscale image of the target crop, acquiring the grayscale of the target crop Image and binary image; step 2, based on the grayscale image and binary image of the target crop, obtain the coordinates of the center point of the target crop.

This embodiment discloses a computer program product, the computer program product includes a computer program stored on a non-transitory computer-readable storage medium, the computer program includes program instructions, and when the program instructions are executed by the computer, the computer The methods provided by the above method embodiments can be executed, for example, including: step 1, based on the original grayscale image of the target crop, acquiring the grayscale image and binary image of the target crop; step 2, based on the grayscale image of the target crop Image and binary image to obtain the coordinates of the center point of the target crop.

This embodiment provides a non-transitory computer-readable storage medium, the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions cause the computer to execute the methods provided in the above method embodiments, for example, including : Step 1, based on the original gray image of the target crop, obtain the gray image and binary image of the target crop; Step 2, based on the gray image and binary image of the target crop, obtain the coordinates of the center point of the target crop.

Those of ordinary skill in the art can understand that all or part of the steps for realizing the above-mentioned method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the It includes the steps of the above method embodiments; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other various media that can store program codes.

The above-described embodiments of the equipment and other embodiments of the crop center point positioning method under the condition of leaf crossing are only illustrative, and the units described as separate components may or may not be physically separated, and the components shown as units may be It may or may not be a physical unit, that is, it may be located in one place, or may be distributed to multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. It can be understood and implemented by those skilled in the art without any creative efforts.

Through the above description of the implementations, those skilled in the art can clearly understand that each implementation can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the prior art can be embodied in the form of software products, and the computer software products can be stored in computer-readable storage media, such as ROM/RAM, magnetic discs, optical discs, etc., including several instructions to make a computer device (which may be a personal computer, server, or network device, etc.) execute the methods described in various embodiments or some parts of the embodiments.

Finally, the method of the present application is only a preferred embodiment, and is not intended to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims (10)

1. a crop center point location method under the crossing condition of leaves, it is characterized in that, comprising: Step 1, based on the original grayscale image of the target crop, obtain the grayscale image and binary image of the target crop; Step 2, based on the grayscale image and the binary image of the target crop, the coordinates of the center point of the target crop are obtained. 2. The method according to claim 1, wherein said step 1 further comprises: S11. Obtain a binary image of the original grayscale image of the target crop based on the original grayscale image of the target crop; S12, performing morphological denoising processing on the binary image of the original grayscale image of the target crop, and determining an image interest area of the target crop; S13. Based on the ROI of the image of the target crop, acquire a binary image of the ROI of the image of the target crop. 3. The method according to claim 2, wherein said step 2 further comprises: S21. Fusing the original grayscale image of the target crop with the binary image of the image region of interest of the target crop to obtain a grayscale image of the image region of interest of the target crop; S22. Obtain the minimum value point of the grayscale image of the image region of interest of the target crop; obtain the minimum value point in the grayscale image of the image region of interest of the target crop with a difference from surrounding pixel points greater than a threshold; S23, based on the grayscale image of the image region of interest of the target crop and the minimum point obtained in S22, using the watershed algorithm to obtain the coordinates of the center point of the target crop. 4. The method according to claim 1, characterized in that, before the step 1, it also comprises: The initial image of the target crop is subjected to grayscale processing, and the grayscale processing includes the following steps, I _gray (i,j)=G(i,j)*1.262-R(i,j)*0.884-B(i,j)*0.311, Where i and j are the row and column coordinates of the pixel, and G(i,j), R(i,j) and B(i,j) are the grayscales of the G, R and B color components of the pixel at image (i,j) respectively value, Igray(i,j) is the gray value of the pixel at (i,j) in the converted image. 5. The method according to claim 2, characterized in that, said S12 further comprises: Based on the original grayscale image of the target crop, the conversion threshold for obtaining the binary image of the original grayscale image of the target crop is obtained by using the maximum inter-class variance method. 6. The method according to claim 2, characterized in that, said S12 further comprises: Using the morphological opening operation to remove the interference of weed noise in the binary image of the original grayscale image of the target crop; Horizontally project the pixel values of the binary image of the original grayscale image of the target crop after denoising to obtain a projection curve with the pixel row coordinates as the abscissa; divide the projection curve into two parts with the intermediate pixel behavior, and find each The coordinates of the pixel row corresponding to the position of the minimum value of the curve, and the area between two pixel rows is the image interest area of the target crop. 7. The method according to claim 4, characterized in that, said S22 further comprises: Calculate the minimum value point and the maximum value point in the eight neighbors in the grayscale image of the image interest area of the target crop, and calculate the average value of the minimum value point and the maximum value point, the difference between the two, As a threshold, keep the minimum value points whose drop from the surrounding pixels is greater than the threshold value, and obtain the final local minimum value. 8. The method according to claim 7, characterized in that, said S23 further comprises: Using the minimum value point obtained in S22 to carry out foreground marking on the grayscale image of the image interest area of the target crop; using the watershed algorithm to use the marked grayscale image as an input image to obtain the central area of the target crop; Based on the central area of the target crop, add and sum the x-coordinates and y-coordinates of the pixels in the central area, and count the number of pixels in the central area, the ratio of the x-coordinate sum, y-coordinate sum to the number of pixel points That is, the coordinates of the final crop center point. 9. A crop center point positioning system under the condition of leaf crossing, characterized in that, comprising: The obtaining module is used to obtain the grayscale image and the binary image of the target crop based on the original grayscale image of the target crop; The positioning module is used to obtain the coordinates of the center point of the target crop based on the grayscale image and the binary image of the target crop. 10. A non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions cause the computer to execute the computer according to any one of claims 1 to 8. Methods.