Field management method, field management system, and program

Abstract

To provide a technique for acquiring the accuracy of light source information and calculating more accurate growth indices by using an image of crops in a field where a reference plate is installed.SOLUTION: A field management method includes: an image acquisition step of acquiring an image of crops cultivated in a field and a reference plate installed in the field; a first calculation step of calculating the accuracy of the reference plate; a second calculation step of calculating the accuracy of each pixel in the image; an interpolated value calculation step of calculating a reference plate interpolated value, which is an interpolated value of pixel values in regions of the image different from the reference plate; a reflectance calculation step of calculating reflectance as a ratio of the pixel value of the image to the reference plate interpolated value; a growth index calculation step of calculating a growth index; and an image display step of displaying, on a display device, the growth index calculated in the growth index calculation step and the accuracy of each pixel in the image obtained in the second calculation step.SELECTED DRAWING: Figure 11

Description

Technical Field

[0001] The present disclosure relates to a field management method, a field management system, and a program.

Background Art

[0002] Conventionally, from the perspective of informatization of fields, there is known a field management system that detects information on crops in a field and predicts and grasps the growth status of the crops from the detected information. Patent Document 1 discloses a technique for calculating a growth index from the reflected light of a crop with respect to a light source as a means for detecting information on the crop.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When receiving a light source outdoors, it may occur that accurate light source information cannot be obtained due to the influence of disturbances such as obstacles. Thus, the growth index of a crop calculated from light source information with uncertain accuracy may have a possibility of a decrease in accuracy.

Means for Solving the Problems

[0005] The present disclosure can be realized in the following forms.

[0006] (1) According to the first aspect of the present disclosure, a field management method is provided. This field management method includes an image acquisition step of acquiring an image of a crop cultivated in a field and a reference plate installed in the field, a first calculation step of calculating the accuracy of the reference plate using the pixel values of the reference plate in the image acquired in the image acquisition step, a second calculation step of calculating the accuracy of each pixel in the image using the accuracy of the reference plate acquired in the first calculation step, an interpolation value calculation step of calculating a reference plate interpolation value that is an interpolation value of pixel values in a region different from the reference plate in the image using the pixel values of the reference plate in the image acquired in the image acquisition step, a reflectance calculation step of calculating a reflectance that is a ratio of the pixel values of the image to the reference plate interpolation value using the reference plate interpolation value calculated in the interpolation value calculation step, a growth index calculation step of calculating a growth index using the reflectance calculated in the reflectance calculation step, and an image display step of displaying the growth index calculated in the growth index calculation step and the accuracy of each pixel in the image acquired in the second calculation step on a display device. (2) According to the second aspect of the present disclosure, a field management apparatus is provided. This field management apparatus includes an image acquisition unit that acquires an image of a crop cultivated in a field and a reference plate installed in the field, a first calculation unit that calculates the accuracy of the reference plate using the pixel values of the reference plate in the image acquired by the image acquisition unit, a second calculation unit that calculates the accuracy of each pixel in the image using the accuracy of the reference plate acquired by the first calculation unit, an interpolation value calculation unit that calculates a reference plate interpolation value that is an interpolation value of pixel values in a region different from the reference plate in the image using the pixel values of the reference plate in the image acquired by the image acquisition unit, a reflectance calculation unit that calculates a reflectance that is a ratio of the pixel values of the image to the reference plate interpolation value using the reference plate interpolation value calculated by the interpolation value calculation unit, a growth index calculation unit that calculates a growth index using the reflectance calculated by the reflectance calculation unit, and an image display unit that displays the growth index calculated by the growth index calculation unit and the accuracy of each pixel in the image acquired by the second calculation unit on a display device. (3) According to the third aspect of the present disclosure, a computer program is provided. This computer program includes an image acquisition function for acquiring images of crops cultivated in a field and a reference plate installed in the field, a first calculation function for calculating the accuracy of the reference plate using the pixel values of the reference plate in the images acquired by the image acquisition function, a second calculation function for calculating the accuracy of each pixel in the images using the accuracy of the reference plate acquired by the first calculation function, an interpolation value calculation function for calculating an interpolation value of the reference plate, which is an interpolation value of pixel values in a region different from the reference plate in the images, using the pixel values of the reference plate in the images acquired by the image acquisition function, a reflectance calculation function for calculating the reflectance, which is the ratio of the pixel values of the images to the interpolation value of the reference plate, using the interpolation value of the reference plate calculated by the interpolation value calculation function, a growth index calculation function for calculating a growth index using the reflectance calculated by the reflectance calculation function, and an image display function for displaying the growth index calculated by the growth index calculation function and the accuracy of each pixel in the images acquired by the second calculation function on a display device, and causing a computer to execute them.

Brief Description of Drawings

[0007]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Embodiments for Carrying Out the Invention

[0008] A. First Embodiment: FIG. 1 is a diagram showing the configuration of the farm management system 10 in the first embodiment. The farm management system 10 includes a farm 50, an imaging device 100, and a farm management device 200.

[0009] The farm 50 has at least one or more reference plates R. In this embodiment, the farm 50 has four reference plates R. The four reference plates R are installed at equal intervals with a certain distance a therebetween. The four reference plates R are respectively arranged at the corners of a rectangle. The reference plate R is a square white plate. Here, the reference plate R has the characteristic of diffusely reflecting all wavelengths included in the incident light. Therefore, the reference plate R may be achromatic or may be another color such as gray. Also, the reference plate R is not limited to a square plate shape and may be other shapes such as a sphere or a polyhedron. In this embodiment, the reference plate R is installed to obtain accurate light source information.

[0010] The imaging device 100 images the farm 50 including the reference plate R. In this embodiment, the imaging device 100 is a color camera. Also, the imaging device 100 is installed on a high platform and performs fixed-point shooting. The imaging device 100 repeatedly performs imaging at regular intervals. For example, the imaging device 100 performs imaging for three days every hour. Note that the imaging conditions are not limited to the above. The imaging device 100 may be other cameras such as an omnidirectional camera or a spectroscopic camera. Also, the farm 50 may be imaged from above using the imaging device 100 installed on a drone or the like.

[0011] The field management device 200 is a device for managing the field 50. In the present embodiment, the field management device 200 is a server. The field management device 200 predicts and grasps the growth status of crops in the field 50 by using the image of the field 50 captured by the imaging device 100.

[0012] FIG. 2 is a diagram showing the configuration of the field management device 200. The field management device 200 includes a processor 202 and a memory 205. The processor 202 and the memory 205 are connected so as to be communicable bidirectionally via an internal bus 207. A program PG1 to be executed by the processor 202 is stored in the memory 205.

[0013] By executing the program PG1, the processor 202 functions as an image acquisition unit 210, a first calculation unit 220, a second calculation unit 230, an interpolation value calculation unit 240, a reflectance calculation unit 250, a growth index calculation unit 260, and an image display unit 270.

[0014] The image acquisition unit 210 acquires an image of the crops cultivated in the field 50 shown in FIG. 1 and the reference plate R installed in the field 50. The first calculation unit 220 calculates the accuracy of the reference plate R by using the pixel values of the reference plate R in the image acquired by the image acquisition unit 210. The second calculation unit 230 calculates the accuracy of each pixel in the image by using the accuracy of the reference plate R acquired by the first calculation unit 220. The interpolation value calculation unit 240 calculates a reference plate interpolation value, which is an interpolation value of the pixel values of the region different from the reference plate R in the image, by using the pixel values of the reference plate R in the image acquired by the image acquisition unit 210. The reflectance calculation unit 250 calculates a reflectance, which is the ratio of the pixel values of the image to the reference plate interpolation value, by using the reference plate interpolation value calculated by the interpolation value calculation unit 240. The growth index calculation unit 260 calculates a growth index by using the reflectance calculated by the reflectance calculation unit 250. The image display unit 270 displays the growth index calculated by the growth index calculation unit 260 and the accuracy of each pixel in the image acquired by the second calculation unit 230 on a display device. Details of each functional unit of the processor 202 will be described later.

[0015] Figure 3 is a flowchart showing a field management method using the field management apparatus 200. In step S10, the image acquisition unit 210 acquires an image of the agricultural crops cultivated in the field 50 shown in FIG. 1 and the reference plate R installed in the field 50, and stores it in the memory 205 of the field management apparatus 200 shown in FIG. 2. In the present embodiment, the image acquisition unit 210 acquires an image captured by the imaging device 100 shown in FIG. 1. Here, the image acquisition unit 210 may acquire an image via wire or wireless.

[0016] Figure 4 is a diagram schematically showing an example of an image acquired by the image acquisition unit 210. In the present embodiment, the image P1 is a color image having three values of R, G, and B for each pixel. Note that the sections divided by the grid represent pixels. Also, any pixel in the image P1 can be represented by a coordinate system (x, y). In the present embodiment, since the image acquisition unit 210 has acquired an image of the field 50 shown in FIG. 1, four reference plates R1 to R4 are shown in the image P1 shown in FIG. 4. Note that the four reference plates R1 to R4 each include nine pixels.

[0017] In step S20 shown in FIG. 3, the first calculation unit 220 calculates the accuracy of the reference plate R using the pixel values of the reference plate R in the image acquired by the image acquisition unit 210. In the present embodiment, the first calculation unit 220 calculates the accuracy of the reference plate R using the variance of the pixel values of the reference plate R in the image. The details of the method by which the first calculation unit 220 calculates the accuracy of the reference plate R will be described later.

[0018] In step S30, the second calculation unit 230 calculates the accuracy of each pixel in the image using the accuracy of the reference plate R acquired by the first calculation unit 220. The details of the method by which the second calculation unit 230 calculates the accuracy of each pixel in the image will be described later. Also, in the following description, steps S20 and S30 may be collectively referred to as the "accuracy calculation step".

[0019] FIG. 5 is a flowchart showing the first calculation step and the second calculation step. FIG. 6 is a diagram for explaining the accuracy of the reference plate R.

[0020] In step S210 shown in FIG. 5, the first calculation unit 220 sets an initial value of the accuracy of the reference plate R. In the present embodiment, the first calculation unit 220 sets an initial value of the accuracy for each of the four reference plates R1 to R4. Here, the first calculation unit 220 does not set the initial value of the accuracy for all the pixels constituting the reference plate R, but sets the initial value of the accuracy, which is a unique value, for one reference plate R. That is, the first calculation unit 220 sets the initial value of the accuracy of the reference plate R1 to "I1", the initial value of the accuracy of the reference plate R2 to "I2", the initial value of the accuracy of the reference plate 3 to "I3", and the initial value of the accuracy of the reference plate R4 to "I4". In the present embodiment, the accuracy is a real number between 0.0 and 1.0, and the initial values I1 to I4 are each "1.0". The first calculation unit 220 sets the initial value of the accuracy for each of the four reference plates R1 to R4 in the image P1 shown in FIG. 4.

[0021] In step S220 shown in FIG. 5, the first calculation unit 220 calculates the variance of the pixel values of the reference plate R in the image. FIG. 6 shows the pixel values of the four reference plates R1 to R4. In the present embodiment, the pixel value refers to the value of the G component in the color image P1 shown in FIG. 4. Note that the pixel value may be the value of the R component or the B component instead of the value of the G component. Also, it may be the average value or the median value of the pixel values in a plurality of channels among R, G, and B. In the present embodiment, among the four reference plates R1 to R4, for the reference plates R1, R3, and R4, all the pixel values of the G component constituting each of the reference plates R1, R3, and R4 are "10". On the other hand, for the reference plate R2, some of the pixel values constituting the reference plate R2 are "3" and the rest are "10". Usually, it is assumed that the pixel values constituting the reference plate R are approximately the same. In contrast, for example, when an object is reflected between the reference plate R and the imaging device 100 such as a plant covering the reference plate R, or when dirt adheres to the reference plate R, some of the pixel values become lower compared to the surrounding pixel values as in the reference plate R2. Therefore, it is assumed that the reference plates R1, R3, and R4 are imaged without being affected by disturbances such as obstacles, while it can be seen that the reference plate R2 may be affected by disturbances. Here, as described above, the first calculation unit 220 calculates the variance of the pixel values for each of the reference plates R1 to R4 in the image. When the number of pixels constituting each of the reference plates R1 to R4 is n, the variance for each of the reference plates R1 to R4 is calculated using, for example, the following formula (1).

Equation

[0022] When the first calculation unit 220 calculates the variance of the pixel values of the reference plate R using Equation (1), the reference plate R2 that may be affected by disturbances is calculated to have a larger variance value compared to the reference plates R1, R3, and R4 that are not affected by disturbances. In the present disclosure, a reference plate R with a variance value less than a certain value, which is assumed not to be affected by disturbances, is denoted as a "normal" reference plate R, and a reference plate R with a variance value greater than or equal to the certain value, which is assumed to be affected by disturbances, may be denoted as an "abnormal" reference plate R. Also, in the following figures, the reference plates R1, R3, and R4 will be described as normal reference plates R, and the reference plate R2 will be described as an abnormal reference plate R.

[0023] In step S230 shown in FIG. 5, the first calculation unit 220 determines whether the variance calculated in step S220 is greater than or equal to a predetermined value. If the variance is greater than or equal to the predetermined value, the process proceeds to step S240. If the variance is less than the predetermined value, the process proceeds to step S245. In step S240, the first calculation unit 220 changes the accuracy of the reference plate R. More specifically, the first calculation unit 220 decreases the accuracy of the reference plate R. For example, the first calculation unit 220 may decrease the accuracy of the reference plate R from the initial value of "1.0" to "0.0", or may change the value by which it is decreased according to the variance value. For example, if the variance value is greater than or equal to a predetermined value A, the accuracy is decreased from the initial value of "1.0" by "0.2", and if the variance value is greater than B which is larger than A, the accuracy is decreased from the initial value of "1.0" by "0.4", and so on.

[0024] In step S245, the first calculation unit 220 maintains the initial value without changing the accuracy of the reference plate R. In the present embodiment, the first calculation unit 220 maintains the accuracy of the reference plate R at the initial value of "1.0".

[0025] In step S210 described above, the first calculation unit 220 sets the initial values of all the reference plates R1 to R4. In contrast, in steps S220 to S245, the first calculation unit 220 processes each of the reference plates R1 to R4 in order. In the following description, steps S220 to S245 are collectively referred to as "accuracy change processing".

[0026] In step S250, the first calculation unit 220 determines whether or not the above-described accuracy change processing has been completed for all the reference plates R1 to R4. If the accuracy change processing has been completed for all the reference plates R1 to R4, the process proceeds to step S310. If there is one or more reference plates R for which the accuracy change processing has not been performed, the process returns to step S220. Then, the first calculation unit 220 performs the accuracy change processing on the reference plates R for which the accuracy change processing has not been performed in order. The first calculation unit 220 repeats the accuracy change processing until the accuracy change processing has been completed for all the reference plates R1 to R4.

[0027] In step S310, the second calculation unit 230 calculates the accuracy of each pixel in the image using the accuracy of the reference plate R acquired by the first calculation unit 220.

[0028] FIG. 7 is a diagram for explaining the second calculation step. In the present embodiment, the second calculation unit 230 calculates the product of the accuracy of the reference plate R and the attenuation rate Ci at each pixel as the accuracy at the pixel g1(x1, y1) to be estimated. When there are a plurality of reference plates R, the average value of the accuracies obtained from each of the reference plates R1 to R4 is adopted. In the present embodiment, the accuracy is attenuated according to the distance between the pixel g1(x1, y1) to be estimated and the coordinates of the reference plate R. Specifically, it is assumed that the attenuation rate Ci follows a general Gaussian function. For example, if the reference plate number is i and the distance between the center coordinates of the reference plate and the coordinates to be estimated is r i then the attenuation rate Ci is calculated using the following formula (2). Note that the distance r i is a value greater than "0".

Equation

[0029] As shown in the image P3, in this embodiment, the accuracies of the four reference plates R1, R2, R3, and R4 are set to A1, A2, A3, and A4, respectively. Also, the distance from the pixel g1(x1, y1) to the reference plate R1 is r1, the distance to the reference plate R2 is r2, the distance to the reference plate R3 is r3, and the distance to the reference plate R4 is r4. At this time, the attenuation rates C1, C2, C3, and C4 are calculated based on the distances r1, r2, r3, and r4 using the above-described formula (2). Therefore, the accuracy E at the estimated coordinates (x, y1) can be expressed using the following formula (3).

Equation

[0030] In this embodiment, the second calculation unit 230 calculates the accuracy E of each of all the pixels constituting the image P3. Note that when there are a plurality of reference plates R, the second calculation unit 230 does not necessarily have to adopt the average value of the accuracies E obtained from each of the reference plates R1 to R4. For example, the accuracy E calculated using the reference plate R with the highest accuracy E may be adopted. Also, the maximum value or the median value of the accuracies E obtained from each of the reference plates R1 to R4 may be adopted.

[0031] In step S40 shown in FIG. 3, the interpolation value calculation unit 240 calculates a reference plate interpolation value, which is an interpolation value of pixel values in a region different from the reference plate R in the image, using the pixel values of the reference plate R in the image acquired by the image acquisition unit 210. In the present embodiment, accurate light source information can be obtained at the position where the reference plate R is installed, while accurate light source information cannot be obtained at the position where the reference plate R is not installed. However, when a large number of reference plates R are installed in the farm field 50, it becomes difficult to obtain information about the crops in the farm field 50 because the reference plates R become obstacles. For this reason, in the present embodiment, a reference plate interpolation value, which is an estimated value of the light source information in the section where the reference plate R is not installed, is calculated using the pixel values of the reference plate R. The interpolation value calculation step includes a step of dividing the image into an interpolation section, which is a section including the reference plate R, and an extrapolation section, which is a section other than the interpolation section in the image. The interpolation value calculation step also includes a step of calculating an interpolation value, which is a reference plate interpolation value in the interpolation section, and an extrapolation value, which is a reference plate interpolation value in the extrapolation section, and a step of assigning the interpolation value to the pixels in the interpolation section and assigning the extrapolation value to the pixels in the extrapolation section.

[0032] FIG. 8 is a flowchart showing the interpolation value calculation step in step S40. FIG. 9 is a diagram for explaining the interpolation section and the extrapolation section.

[0033] In step S410 shown in FIG. 8, the interpolation value calculation unit 240 determines the interpolation section and the extrapolation section. The interpolation section is a section including the reference plate. The extrapolation section is a section other than the interpolation section in the image. The interpolation section is the inner range of the convex hull including a plurality of reference plates R1 to R4. As shown in FIG. 9, in the present embodiment, the interpolation section F1 is the section of the region surrounded by a square including the four reference plates R1 to R4 in the image P4. The extrapolation section F2 is a section other than the interpolation section F1.

[0034] In step S420 shown in FIG. 8, the interpolation value calculation unit 240 calculates an interpolation value. Note that the interpolation value is the reference plate interpolation value in the interpolation section F1 shown in FIG. 9. In the present embodiment, the interpolation value calculation unit 240 calculates the interpolation value using linear interpolation based on the distance between the pixel of the interpolation section F1 to which the interpolation value is assigned and the reference plate R in the image, and the pixel value of the reference plate R.

[0035] FIG. 10 is a diagram for explaining a method of calculating an interpolation value. Here, four reference plates R1 to R4 are used to calculate the interpolation value of an arbitrary pixel g2(x2, y2) in the interpolation section F1. In the present embodiment, the interpolation value calculation unit 240 calculates the average value of the pixel values for each of the four reference plates R1 to R4. As shown in FIG. 6, in the present embodiment, since all nine pixel values constituting the reference plate R1 are "10", the average value is "10". Similarly, the average values of the reference plates R3 and R4 are also "10". On the other hand, among the nine pixel values constituting the reference plate R2, five are "10" and the remaining four are "3". Therefore, the average value of the pixel values of the reference plate R2 is "6.9". Here, let the distance from the pixel g2(x2, y2) to the reference plate R1 be r5, the distance to the reference plate R2 be r6, the distance to the reference plate R3 be r7, and the distance to the reference plate R4 be r8. In the present embodiment, the interpolation value calculation unit 240 calculates the interpolation value using linear interpolation based on the distances r5, r6, r7, r8 from the pixel g2(x2, y2) to the reference plates R1 to R4 and the average values of the pixel values of the four reference plates R1 to 4. Further, the interpolation value calculation unit 240 assigns the calculated interpolation value to the corresponding pixel g2(x2, y2). The interpolation value calculation unit 240 calculates the interpolation values of all the pixels in the region of the interpolation section F1 excluding the reference plates R1 to R4. Note that the method by which the interpolation value calculation unit 240 calculates the interpolation value is not limited to the linear interpolation described above.

[0036] In step S430 shown in FIG. 8, the interpolation value calculation unit 240 calculates an extrapolation value. Note that the extrapolation value is the reference plate interpolation value in the extrapolation section F2 shown in FIG. 9. The interpolation value calculation unit 240 calculates, as the extrapolation value, the interpolation value at the pixel of the interpolation section F1 that is closest to the pixel of the extrapolation section F2 to which the extrapolation value is assigned.

[0037] The method for calculating the extrapolated value will be described with reference to FIG. 9. In the present embodiment, as described above, the interpolation value calculation unit 240 calculates, as the extrapolated value, the interpolation value at the pixel of the interpolation section F1 that is closest to the pixel of the extrapolation section F2 to which the extrapolated value is assigned. For example, the extrapolated value assigned to pixel g3(9,1) is the interpolation value at pixel g4(9,3), which is the pixel of the interpolation section F1 closest to pixel g3(9,1). Note that the extrapolated value may be calculated as the pixel value at the pixel constituting the reference plate R. For example, the extrapolated value assigned to pixel g5(2,2) is the interpolation value at pixel g6(3,3), which is the pixel of the interpolation section F1 closest to pixel g5(2,2). That is, the interpolation value calculation unit 240 calculates the pixel value at pixel g6(3,3) in the reference plate R1 as the extrapolated value of pixel g5(2,2). Note that the interpolation value calculation unit 240 calculates the extrapolated values for all the pixels constituting the extrapolation section F2. Further, the interpolation value calculation unit 240 assigns the calculated extrapolated values to the corresponding pixels.

[0038] In step S50 shown in FIG. 3, the reflectance calculation unit 250 calculates the reflectance, which is the ratio of the pixel value of the image to the reference plate interpolation value, using the reference plate interpolation value calculated by the interpolation value calculation unit 240. The reflectance is usually represented as the ratio of the reflected light to the incident light. In the present embodiment, the above-described reference plate interpolation value is regarded as the incident light, and the pixel value of the G component in the image is regarded as the reflected light. That is, the reflectance G´(x,y) is the value obtained by dividing the pixel value of the G component at pixel (x,y) by the reference plate interpolation value at pixel (x,y). Note that the reflectance calculation unit 250 also calculates the reflectance R´, which is the value obtained by dividing the pixel value of the R component by the reference plate interpolation value, and the reflectance B´, which is the value obtained by dividing the pixel value of the B component by the reference plate interpolation value. Further, the reflectance calculation unit 250 calculates the reflectances G´, R´, and B´ for all the pixels constituting the image.

[0039] In step S60 shown in FIG. 3, the growth index calculation unit 260 calculates the growth index using the reflectance calculated by the reflectance calculation unit 250.

[0040] In the present embodiment, the growth index calculation unit 260 calculates the growth index N using, for example, the green-red vegetation index represented by the following formula (4).

Equation

[0041] In step S70 shown in FIG. 3, the image display unit 270 displays the growth index calculated by the growth index calculation unit 260 and the accuracy of each pixel in the image acquired by the second calculation unit 230 on the display device.

[0042] FIG. 11 shows the image displayed by the image display unit 270. In the present embodiment, the image display unit 270 superimposes and displays the growth index and the accuracy of each pixel in the image. In the image P5, the value of the growth index is displayed for each pixel. In the present embodiment, as described above, the green-red vegetation index is used as the growth index, and the larger the value, the higher the activity of the agricultural crop. Note that the value of the growth index is between -1 and 1. In the image P5, in addition to the growth index, the accuracy of each pixel in the image is indicated using hatching. Here, the higher the density of the hatching, the lower the accuracy of each pixel. In the present embodiment, since the reference plate R2 among the reference plates R1 to R4 is abnormal, the pixels around the reference plate R2 have low accuracy. Note that the accuracy of each pixel can also be expressed using color. For example, pixels with low accuracy are displayed in red, and pixels with high accuracy are displayed in blue, etc. Further, the accuracy of each pixel may be expressed using the shade of color. For example, among the red pixels with low accuracy, those with even lower accuracy are displayed in dark red, etc. According to this form, among the growth indices displayed in the image P5, it is possible to distinguish between the region with high accuracy and the region with low accuracy. For example, the growth indices at the pixel g7(6,12) and the pixel g8(15,1) are both low with a value of "-0.5". On the other hand, the accuracy of the pixels is high at the pixel g7(6,12) and low at the pixel g8(15,1). Therefore, at the pixel g7(6,12), since the actual activity of the agricultural crop is low, the growth index is calculated to be low. On the other hand, at the pixel g8(15,1), it can be seen that there is a high possibility that the activity of the agricultural crop has not been correctly evaluated because the accuracy of the pixel is low. Further, the image display unit 270 may superimpose and display the image of the field 50 in addition to the growth index and the accuracy of each pixel in the image. Thereby, in addition to the growth index of the agricultural crop for each region of the field 50, the accuracy of the growth index can also be obtained at the same time.

[0043] In the above-described first embodiment, the farm management device 200 acquires an image of the farm 50 including the reference plate R, and calculates the accuracy of each pixel in the image using the pixel values of the reference plate R. Thereby, the accuracy of the light source information in the entire image can be obtained. Further, the farm management device 200 calculates a reference plate interpolation value, which is an interpolation value of the pixel values, using the pixel values of the reference plate R, and calculates a growth index using the reference plate interpolation value. Thereby, since the growth index is calculated using the light source information taking into account the influence of disturbances, a more accurate growth index can be obtained.

[0044] B. Other forms: (B1) In the above-described first embodiment, the imaging device 100 has imaged the farm 50. In contrast, the imaging device 100 does not necessarily have to image the farm 50. The imaging device 100 may image the inside of a house cultivation environment or the like other than the farm 50. Further, the imaging device 100 may acquire other images for which a reflectance image of the object is required.

[0045] (B2) In the above-described first embodiment, the interpolation value calculation unit 240 has calculated the interpolation value by linear interpolation using the average value of the pixel values in each of the reference plates R1 to R4 and the distance from each of the reference plates R1 to R4 to the estimated pixel g2(x2, y2). In contrast, when calculating the interpolation value, the interpolation value calculation unit 240 does not necessarily have to use the average value of the pixel values in each of the reference plates R1 to R4 and the distance from each of the reference plates R1 to R4 to the estimated pixel g2(x2, y2). The interpolation value calculation unit 240 may calculate the interpolation value by linear interpolation using the representative value of the pixel values in each of the reference plates R1 to R4 and the distance from the representative value of each of the reference plates R1 to R4 to the estimated pixel g2(x2, y2).

[0046] C. Other forms: The present disclosure is not limited to the above-described embodiments, and can be implemented in various configurations without departing from the gist thereof. For example, the technical features of the embodiments corresponding to the technical features in each form described in the summary of the invention can be appropriately replaced or combined in order to solve part or all of the above-described problems, or to achieve part or all of the above-described effects. Further, if the technical feature is not described as essential in this specification, it can be appropriately deleted.

[0047] (1) According to the first aspect of the present disclosure, a field management method is provided. This field management method includes an image acquisition step of acquiring an image of a crop cultivated in a field and a reference plate installed in the field, a first calculation step of calculating the accuracy of the reference plate using the pixel value of the reference plate in the image acquired in the image acquisition step, a second calculation step of calculating the accuracy of each pixel in the image using the accuracy of the reference plate acquired in the first calculation step, an interpolation value calculation step of calculating a reference plate interpolation value that is an interpolation value of pixel values in a region different from the reference plate in the image using the pixel value of the reference plate in the image acquired in the image acquisition step, a reflectance calculation step of calculating a reflectance that is a ratio of the pixel value of the image to the reference plate interpolation value using the reference plate interpolation value calculated in the interpolation value calculation step, a growth index calculation step of calculating a growth index using the reflectance calculated in the reflectance calculation step, and an image display step of displaying the growth index calculated in the growth index calculation step and the accuracy of each pixel in the image acquired in the second calculation step on a display device. According to this aspect, the accuracy of light source information in the entire image can be obtained. Further, since the growth index is calculated using the light source information taking into account the influence of disturbances, a more accurate growth index can be obtained.

[0048] (2) In the above aspect, in the image display step, the growth index and the accuracy of each pixel in the image may be superimposed and displayed on the display device. According to this embodiment, for each pixel in the image, the accuracy and the growth index can be superimposed and displayed.

[0049] (3) In the above embodiment, the first calculation step may calculate the accuracy of the reference plate using the variance of the pixel values of the reference plate in the image. According to this embodiment, by using the variance of the pixel values of the reference plate, the accuracy of the reference plate can be calculated.

[0050] (4) In the above embodiment, the interpolation value calculation step may include a step of dividing the image into an interpolation section that is a section including the reference plate and an extrapolation section that is a section other than the interpolation section in the image, a step of calculating an interpolation value that is the reference plate interpolation value in the interpolation section and an extrapolation value that is the reference plate interpolation value in the extrapolation section, and a step of assigning the interpolation value to the pixels in the interpolation section and assigning the extrapolation value to the pixels in the extrapolation section. According to this embodiment, by dividing the image into an interpolation section and an extrapolation section, an interpolation value that is the reference plate interpolation value in the interpolation section and an extrapolation value that is the reference plate interpolation value in the extrapolation section can be calculated.

[0051] (5) In the above embodiment, the interpolation value calculation step may calculate the interpolation value using linear interpolation based on the distance between the pixels in the interpolation section to which the interpolation value is assigned and the reference plate in the image and the pixel values of the reference plate. According to this embodiment, in the interpolation value calculation step, the interpolation value can be calculated.

[0052] (6) In the above embodiment, the interpolation value calculation step may calculate, as the extrapolation value, the interpolation value at the pixel in the interpolation section that is closest to the pixel in the extrapolation section to which the extrapolation value is assigned. According to this embodiment, in the interpolation value calculation step, the extrapolation value can be calculated.

[0053] (7) In the above aspect, in the image display step, the growth index, the accuracy of each pixel in the image, and the image may be superimposed and displayed. According to this aspect, the growth index, the accuracy of each pixel in the image, and the image of the agricultural crop can be superimposed and displayed.

[0054] (8) According to the second aspect of the present disclosure, a field management device is provided. The field management device includes an image acquisition unit that acquires an image of an agricultural crop cultivated in a field and a reference plate installed in the field, a first calculation unit that calculates the accuracy of the reference plate using the pixel value of the reference plate in the image acquired by the image acquisition unit, a second calculation unit that calculates the accuracy of each pixel in the image using the accuracy of the reference plate acquired by the first calculation unit, an interpolation value calculation unit that calculates a reference plate interpolation value that is an interpolation value of the pixel value of a region different from the reference plate in the image using the pixel value of the reference plate in the image acquired by the image acquisition unit, a reflectance calculation unit that calculates a reflectance that is a ratio of the pixel value of the image to the reference plate interpolation value using the reference plate interpolation value calculated by the interpolation value calculation unit, a growth index calculation unit that calculates a growth index using the reflectance calculated by the reflectance calculation unit, and an image display unit that displays the growth index calculated by the growth index calculation unit and the accuracy of each pixel in the image acquired by the second calculation unit on a display device. According to this aspect, the field management device can acquire the accuracy of the light source information in the entire image. Further, since the field management device calculates the growth index using the light source information considering the influence of disturbances, a more accurate growth index can be acquired.

[0055] (9) According to the third aspect of the present disclosure, a computer program is provided. This computer program includes an image acquisition function for acquiring images of crops cultivated in a field and a reference plate installed in the field, a first calculation function for calculating the accuracy of the reference plate using the pixel values of the reference plate in the images acquired by the image acquisition function, a second calculation function for calculating the accuracy of each pixel in the images using the accuracy of the reference plate acquired by the first calculation function, an interpolation value calculation function for calculating an interpolation value of the reference plate, which is an interpolation value of pixel values in a region different from the reference plate in the images, using the pixel values of the reference plate in the images acquired by the image acquisition function, a reflectance calculation function for calculating a reflectance, which is a ratio of the pixel values of the images to the interpolation value of the reference plate, using the interpolation value of the reference plate calculated by the interpolation value calculation function, a growth index calculation function for calculating a growth index using the reflectance calculated by the reflectance calculation function, and an image display function for displaying the growth index calculated by the growth index calculation function and the accuracy of each pixel in the images acquired by the second calculation function on a display device, and causing a computer to execute them. According to this aspect, the accuracy of light source information in the entire image can be obtained. Further, since the growth index is calculated using the light source information considering the influence of disturbances, a more accurate growth index can be obtained.

[0056] The present disclosure can be realized in various forms, and in addition to the above aspects, it can be realized in the form of a non-transitory recording medium recording a computer program or the like.

Explanation of Reference Numerals

[0057] 10... Field management system, 50... Field, 100... Imaging device, 200... Field management device, 202... Processor, 205... Memory, 207... Internal bus, 210... Image acquisition unit, 220... First calculation unit, 230... Second calculation unit, 240... Interpolation value calculation unit, 250... Reflectance calculation unit, 260... Growth index calculation unit, 270... Image display unit, F1... Interpolation interval, F2... Extrapolation interval, R... Reference plate

Claims

1. A field management method, comprising: an image acquisition step of acquiring an image of a crop cultivated in a field and a reference board installed in the field; a first calculation step of calculating the accuracy of the reference board using the pixel values of the reference board in the image acquired in the image acquisition step; a second calculation step of calculating the accuracy of each pixel in the image using the accuracy of the reference board acquired in the first calculation step; an interpolation value calculation step of calculating a reference board interpolation value, which is an interpolation value of pixel values in a region different from the reference board in the image, using the pixel values of the reference board in the image acquired in the image acquisition step; a reflectance calculation step of calculating a reflectance, which is a ratio of the pixel value of the image to the reference board interpolation value, using the reference board interpolation value calculated in the interpolation value calculation step; a growth index calculation step of calculating a growth index using the reflectance calculated in the reflectance calculation step; an image display step of displaying, on a display device, the growth index calculated in the growth index calculation step and the accuracy of each pixel in the image acquired in the second calculation step. A field management method.

2. The field management method according to claim 1, wherein in the image display step, the growth index and the accuracy of each pixel in the image are superimposed and displayed on the display device.

3. The field management method according to claim 1, wherein in the first calculation step, the accuracy of the reference board is calculated using the variance of the pixel values of the reference board in the image.

4. The field management method according to claim 1, wherein the interpolation value calculation step includes a step of dividing the image into an interpolation section, which is a section including the reference board, and an extrapolation section, which is a section other than the interpolation section in the image; a step of calculating an interpolation value, which is the reference board interpolation value in the interpolation section, and an extrapolation value, which is the reference board interpolation value in the extrapolation section; a step of assigning the interpolation value to the pixels in the interpolation section and assigning the extrapolation value to the pixels in the extrapolation section.

5. The field management method according to claim 4, wherein in the interpolation value calculation step, the interpolation value is calculated using linear interpolation based on the distance between the pixels in the interpolation section to which the interpolation value is assigned and the reference board in the image and the pixel values of the reference board.

6. The field management method according to claim 4, wherein in the interpolation value calculation step, for the pixels in the extrapolation section to which the extrapolation value is assigned, the interpolation value at the pixel in the interpolation section that is closest is calculated as the extrapolation value, the field management method.

7. The field management method according to claim 1, wherein in the image display step, the growth index, the accuracy of each pixel in the image, and the image are superimposed and displayed, the field management method.

8. A field management device, comprising an image acquisition unit that acquires an image of a crop cultivated in a field and a reference board installed in the field; a first calculation unit that calculates the accuracy of the reference board using the pixel values of the reference board in the image acquired by the image acquisition unit; a second calculation unit that calculates the accuracy of each pixel in the image using the accuracy of the reference board acquired by the first calculation unit; an interpolation value calculation unit that calculates a reference board interpolation value, which is an interpolation value of pixel values in a region of the image different from the reference board, using the pixel values of the reference board in the image acquired by the image acquisition unit; a reflectance calculation unit that calculates a reflectance, which is a ratio of the pixel value of the image to the reference board interpolation value, using the reference board interpolation value calculated by the interpolation value calculation unit; a growth index calculation unit that calculates a growth index using the reflectance calculated by the reflectance calculation unit; and an image display unit that displays the growth index calculated by the growth index calculation unit and the accuracy of each pixel in the image acquired by the second calculation unit on a display device. Field management device.

9. A computer program, comprising an image acquisition function that acquires an image of a crop cultivated in a field and a reference board installed in the field; a first calculation function that calculates the accuracy of the reference board using the pixel values of the reference board in the image acquired by the image acquisition function; a second calculation function that calculates the accuracy of each pixel in the image using the accuracy of the reference board acquired by the first calculation function; an interpolation value calculation function that calculates a reference board interpolation value, which is an interpolation value of pixel values in a region of the image different from the reference board, using the pixel values of the reference board in the image acquired by the image acquisition function; a reflectance calculation function that calculates a reflectance, which is a ratio of the pixel value of the image to the reference board interpolation value, using the reference board interpolation value calculated by the interpolation value calculation function; A growth index calculation function that calculates a growth index using the reflectance calculated by the reflectance calculation function; An image display function that displays, on a display device, the growth index calculated by the growth index calculation function and the accuracy of each pixel in the image acquired by the second calculation function; A computer program for causing a computer to execute the above.

Images