PLANT EVALUATION DEVICE, PLANT EVALUATION METHOD, AND PROGRAM

Abstract

To provide a plant evaluation device, a plant evaluation method, and a program which enhance convenience of a user when evaluating a leaf area index LAI while accurately evaluating the leaf area index.SOLUTION: A plant evaluation device 10 includes: a dividing unit 11 which divides an object plant image obtained by photographing an object plant into a plurality of areas on the basis previously set setting information; an estimation unit 12 which estimates a leaf area index for each of the divided areas; and a calculation unit 13 which calculates a leaf area index of a whole object plant on the basis the leaf area indexes estimated for the respective divided areas.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a plant evaluation device, a plant evaluation method, and a program for evaluating a plant. [Background technology]

[0002] Patent Document 1 discloses a method for evaluating the tree production capacity of an isolated tree or multiple trees spaced apart from one another. According to the method of Patent Document 1, first, a semi-ellipsoid model is determined, which is an upwardly convex semi-ellipsoid with the trunk of one tree as its axis and the tree height and the average crown radius as its two diameters.

[0003] Next, an optical tree structure measuring device is placed near the ground a specified distance away from the main trunk with the incident optical axis facing vertically upward relative to the horizontal plane, and light is incident at multiple zenith angles to be measured by the optical tree structure measuring device, and the intensity of light that passes through the leaves is measured.

[0004] Next, an optical tree structure measuring device is placed in a position where light from the sky is not blocked so that the incident optical axis faces vertically upward relative to the horizontal plane, and the optical tree structure measuring device measures the intensity of light that does not pass through the leaves at multiple zenith angles to be measured.

[0005] Next, the gap index at a plurality of zenith angles is calculated using the intensity of light that is incident at a plurality of zenith angles and passes through the leaves and the intensity of light that does not pass through the leaves.

[0006] Next, the optical path length that the incident light passes from the point of incidence on the semi-ellipsoid surface of the semi-ellipsoid model to the optical tree structure measurement device and the crown volume for each of the multiple zenith angles to be measured are calculated based on the semi-ellipsoid model.

[0007] Next, the amount of light attenuation corresponding to each zenith angle is calculated from the gap index at multiple zenith angles and the optical path length corresponding to multiple zenith angles. After that, the leaf area density is calculated from the amount of light attenuation, and the total leaf area LA (=LAD x V) of the tree body is calculated from the leaf area density LAD and the crown volume V. [Prior art documents] [Patent documents]

[0008] [Patent Document 1] Patent No. 5034052 Summary of the Invention [Problem to be solved by the invention]

[0009] However, the method of Patent Document 1 uses a plant canopy analyzer (PCA: LAI-2000 manufactured by LI-COR, USA), which results in an expensive device configuration. Therefore, the method of Patent Document 1 discloses a method of capturing an image of a target plant using an inexpensive device configuration equipped with a fisheye lens instead of the plant canopy analyzer.

[0010] However, although Patent Document 1 discloses a method for estimating the total leaf area LA of a tree using an image of a target plant captured by an imaging device equipped with a fisheye lens, it does not disclose a method for estimating the leaf area index LAI.

[0011] Therefore, there is a need to develop technology that can accurately estimate the leaf area index (LAI) even with an inexpensive configuration that uses an imaging device equipped with a fisheye lens, and that further improves user convenience when estimating the leaf area index (LAI).

[0012] In one aspect, an object of the present invention is to provide a plant evaluation device, a plant evaluation method, and a program that improve the convenience of users when estimating a leaf area index (LAI) and accurately estimate the leaf area index (LAI). [Means for solving the problem]

[0013] In order to achieve the above object, a plant evaluation device according to one aspect includes: A division unit that divides a target plant image into a plurality of regions based on preset setting information; An estimation unit that estimates a leaf area index for each of the divided regions; A calculation unit that calculates a leaf area index of the entire target plant based on the leaf area index estimated for each of the divided regions; The present invention is characterized by having the following.

[0014] In order to achieve the above object, a plant evaluation method in one aspect includes: A division step of dividing a target plant image into a plurality of regions based on preset setting information; An estimation step of estimating a leaf area index for each of the divided regions; A calculation step of calculating a leaf area index of the entire target plant based on the leaf area index estimated for each of the divided regions; The present invention is characterized by having the following.

[0015] Furthermore, in order to achieve the above object, the program in one aspect comprises: On the computer, Dividing a target plant image into a plurality of regions based on preset setting information; Estimating a leaf area index for each of the divided regions; Calculating the leaf area index of the entire target plant based on the leaf area index estimated for each of the divided regions. The present invention is characterized by including instructions. Effect of the Invention

[0016] As one aspect, it is possible to improve the convenience for users when estimating the leaf area index and to estimate the leaf area index (LAI) with high accuracy. [Brief description of the drawings]

[0017] [Figure 1] FIG. 1 is a diagram for explaining an example of a plant evaluating device. [Diagram 2] FIG. 2 is a diagram for explaining the plant evaluation device in detail. [Diagram 3]FIG. 3 is a diagram for explaining imaging of a target plant. [Figure 4] FIG. 4 is a diagram showing an example of an image captured using a wide-angle lens. [Diagram 5] FIG. 5 is a diagram for explaining division of a target plant image using a zenith circle. [Figure 6] FIG. 6 is a diagram for explaining division of a target plant image using a zenith circle and an azimuth direction. [Figure 7] FIG. 7 is a diagram for explaining the relationship between the divided regions and the void index. [Figure 8] FIG. 8 is a diagram for explaining the relationship between the divided regions and the leaf area index. [Figure 9] FIG. 9 is a diagram for explaining the selection of the divided regions. [Figure 10] FIG. 10 is a diagram for explaining an example of the operation of the plant evaluating device. [Figure 11] FIG. 11 is a diagram showing the results of evaluation of the leaf area index. [Figure 12] FIG. 12 is a diagram for explaining an example of a computer that realizes the plant evaluating device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0018] (Embodiment) Hereinafter, an embodiment of the present invention will be described with reference to the drawings. In the drawings described below, elements having the same or corresponding functions are denoted by the same reference numerals, and repeated description thereof may be omitted.

[0019] [Device configuration] First, the configuration of a plant evaluation device 10 in this embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram for explaining an example of a plant evaluation device.

[0020] The plant evaluation device 10 shown in Fig. 1 is a device for easily and accurately estimating a leaf area index. As shown in Fig. 1, the plant evaluation device 10 has a division unit 11, an estimation unit 12, and a calculation unit 13.

[0021] The division unit 11 divides the target plant image into a plurality of regions based on preset setting information. The estimation unit 12 estimates the leaf area index (LAI) of each divided region. j (j represents a divided region). The calculation unit 13 estimates the leaf area index LAI estimated for each divided region. j Based on this, the leaf area index (LAI) of the entire target plant is calculated.

[0022] In this way, in this embodiment, a target plant image captured with an inexpensive device configuration (for example, an image captured with a wide-angle lens attached to a smartphone camera) is divided, and the leaf area index LAI is calculated for each divided region. j and estimate the leaf area index (LAI) j is used to estimate the leaf area index (LAI) of the entire target plant.

[0023] This improves the convenience for users when estimating the leaf area index of an isolated plant or multiple plants spaced apart, and enables the leaf area index (LAI) to be estimated with high accuracy.

[0024] [System Configuration] Next, the configuration of the plant evaluation device 10 in this embodiment will be described in more detail with reference to Fig. 2. Fig. 2 is a diagram for explaining the plant evaluation device in detail.

[0025] As shown in FIG. 2, the plant evaluation device 10 in this embodiment has an imaging section 20, a wide-angle lens 21, a display section 22, an input section 23, and a control section 30.

[0026] The plant evaluation device 10 is an information processing device such as a mobile terminal equipped with a programmable device such as a CPU (Central Processing Unit) or an FPGA (Field-Programmable Gate Array), or both. Examples of the mobile terminal include a smartphone, tablet, and personal computer equipped with an imaging device such as a camera.

[0027] The imaging unit 20 is an imaging device such as a camera that is provided in advance in the plant evaluation device 10. Specifically, the imaging unit 20 outputs an image of the target plant to the image information acquisition unit 14. In the example of Fig. 2, the imaging unit 20 is provided in the plant evaluation device 10, but it may be provided separately from the plant evaluation device 10. In that case, the imaging unit 20 transmits the image to the plant evaluation device 10 using communication such as wired or wireless communication.

[0028] The wide-angle lens 21 is a lens that can be attached to the imaging unit 20. Specifically, the wide-angle lens 21 is attached to the imaging unit 20. However, the wide-angle lens 21 also includes a fisheye lens. Note that, although the wide-angle lens 21 is attached to the imaging unit 20 in the example of FIG. 2, the wide-angle lens 21 does not necessarily have to be attached to the imaging unit 20.

[0029] Fig. 3 is a diagram for explaining the imaging of a target plant. In the example of Fig. 3, a plant evaluation device 10 equipped with a wide-angle lens 21 is placed horizontally under a target plant to image the entire target plant. Fig. 4 is a diagram showing an example of an image captured using the wide-angle lens.

[0030] The display unit 22 acquires display information such as a user interface that has been converted into a displayable format by the display information generating unit 18, and outputs a generated image based on the display information. The display unit 22 is, for example, an image display device using liquid crystal or organic EL (Electro Luminescence). In addition to the display unit 22, an audio output unit such as a speaker may be provided. In the example of FIG. 2, the display unit 22 is provided in the plant evaluation device 10, but it may be provided separately from the plant evaluation device 10.

[0031] The input unit 23 outputs input information input by a user to the input information acquisition unit 19 using a user interface displayed on the display unit 22 or the like. The input unit 23 is, for example, a touch panel type input device integrated with the display unit 22. In the example of Fig. 2, the input unit 23 is provided in the plant evaluation device 10, but it may be provided separately from the plant evaluation device 10. In that case, the input unit 23 may be an input device such as a keyboard or a mouse pointer.

[0032] The control unit will now be described. The control unit 30 has an image information acquisition unit 14, a setting unit 15, a division unit 11, a void index calculation unit 16, an estimation unit 12, a selection unit 17, a calculation unit 13, a display information generation unit 18, an input information acquisition unit 19, a model generation unit 24, a memory unit 25, etc.

[0033] The control unit 30 is provided in the plant evaluation device 10, but may be provided in the server computer. In that case, the target plant image is transmitted to the server computer via a network. Also, the display information generated by the display information generation unit 18 of the server computer is transmitted to the display unit 22 of the plant evaluation device 10 via the network. Furthermore, the input information input by the user using the input unit 23 is transmitted to the input information acquisition unit 19 of the server computer via the network.

[0034] The image information acquisition unit 14 acquires a target plant image obtained by capturing an image of the target plant. Specifically, the image information acquisition unit 14 acquires an image of the target plant from the imaging unit 20. Then, the image information acquisition unit 14 outputs the acquired target plant image to the storage unit 25 or the like.

[0035] The storage unit 25 is a memory that stores various information handled by the plant evaluation device 10. In the example of Fig. 2, the storage unit 24 is provided in the plant evaluation device 10, but it may be provided separately from the plant evaluation device 10. In that case, the storage unit 24 may be a storage device such as a database or a server computer.

[0036] The setting unit 15 performs settings used to estimate the leaf area index. Specifically, first, the setting unit 15 acquires setting information input by a user via the input unit 23 and the input information acquisition unit 19, using a user interface displayed on the screen of the display unit 22. Next, the setting unit 15 stores the acquired setting information in the storage unit 25 or the like.

[0037] The setting information will be described. The setting information is information used for dividing the target plant image in the dividing unit 11, and information used for estimating the leaf area index in the estimating unit 12 and the calculating unit 13. The setting information used for dividing the target plant image includes, for example, information on the diagonal angle of view of the imaging unit 20 (diagonal angle of view information), information on whether the wide-angle lens 21 is attached (wide-angle lens presence / absence information), information on the angle of view of the wide-angle lens 21 (wide-angle lens angle of view information), information on whether vignetting correction is performed (wide-angle lens vignetting correction presence / absence information), information used for setting divided areas (divided area calculation information), and the like.

[0038] For example, in the case where a smartphone is used as the plant evaluation device 10 for estimating the leaf area index, the diagonal angle of view information is information regarding the diagonal angle of view of the camera (imaging unit 20) provided on the smartphone. If the diagonal angle of view is stored in advance in the smartphone, the user does not need to input the diagonal angle of view information using a user interface. Furthermore, even if the diagonal angle of view information is not stored, if the smartphone stores information such as the size and focal length of the imaging sensor mounted on the camera, the diagonal angle of view may be calculated using this information.

[0039] The wide-angle lens presence / absence information is information indicating whether or not a wide-angle lens 21 is attached to the imaging unit 20. The wide-angle lens angle of view information is information indicating the angle of view of the wide-angle lens 21 attached to the imaging unit 20. The wide-angle lens vignetting correction presence / absence information is information indicating whether or not correction is performed to stretch the peripheral parts of an image so that vignetting (black edges on the peripheral parts of an image) is not captured.

[0040] The divided area calculation information is information for setting the size of the divided area of ​​the target plant image. When the target plant image is divided using multiple zenith angle circles, the divided area calculation information has information regarding the zenith angle of each zenith angle circle. Specifically, the divided area calculation information has information for calculating the diameter of each zenith angle circle on the image in order to divide the target plant image into multiple zenith angle circles based on equally spaced incidence angles. The divided area calculation information is information used to calculate the diameter of the zenith angle circle and set the divided area according to the settings of wide-angle lens presence / absence information, wide-angle lens angle of view information, and wide-angle lens vignetting correction presence / absence information.

[0041] Furthermore, for example, when a target plant image is divided using multiple zenith angle circles and multiple azimuth directions, the divided region information includes information on the zenith angle of each zenith angle circle and information on the azimuth direction. The information on the azimuth direction among the divided region information includes information such as the number of azimuth divisions for dividing the multiple zenith angle circles of the target plant image into multiple azimuth directions at equally spaced azimuth angles.

[0042] Fig. 5 is a diagram for explaining the division of a target plant image using zenith angle circles. The zenith angle circles are concentric circles that divide the target plant image into regions at equally spaced zenith angles, with the zenith angle of 0 degrees at the time the target plant image was captured as the center of the image. The example in Fig. 5 shows the division of the target plant image into five regions using five zenith angle circles Z1 to Z5.

[0043] For example, if the target plant image is divided into areas each with a zenith angle of 15°, the areas are R1 represented by the zenith angle circle Z1-center (area with a zenith angle of 0° or more and less than 15°), R2 represented by the zenith angle circle Z2-Z1 (area with a zenith angle of 15° or more and less than 30°), R3 represented by the zenith angle circle Z3-Z2 (area with a zenith angle of 30° or more and less than 45°), R4 represented by the zenith angle circle Z4-Z3 (area with a zenith angle of 45° or more and less than 60°), and R5 represented by the zenith angle circle Z5-Z4 (area with a zenith angle of 60° or more and less than 75°).

[0044] The zenith angle θ i Possible angles are 7.5°, 22.5°, 37.5°, 52.5°, and 67.5°.

[0045] Fig. 6 is a diagram for explaining the division of a target plant image using zenith circle and azimuth direction. In the example of Fig. 6, the target plant image is divided into 50 regions using five zenith circle Z1 to Z5 and ten azimuth directions D1 to D10. However, the target plant image may be divided by a method other than the above-mentioned method.

[0046] In addition, the setting information used to estimate the leaf area index includes gap threshold information representing a threshold value for detecting gaps between leaves in the target plant image, minimum porosity information representing the minimum value to be used instead of a porosity of 0 when there are no gaps between leaves in the divided area, and weighting information for each zenith angle circle for correcting zenith angle circles whose diameters are not equally spaced due to differences in the diagonal angle of view of the imaging unit 20 or the angle of view of the wide-angle lens 21 to the area of ​​equally spaced zenith angle circles.

[0047] The division unit 11 divides the target plant image into a plurality of regions. Specifically, first, the division unit 11 acquires division region calculation information from the storage unit 25. Next, the division unit 11 sets the division regions as shown in FIG. 6 based on the division region calculation information. Next, the division unit 11 stores the division regions in the storage unit 25.

[0048] The setting of the divided regions will now be described. The division unit 11 uses the setting information set in the storage unit 25 to select a zenith angle circle diameter calculation model corresponding to the setting information from the storage unit 25. Then, the division unit 11 inputs the diagonal angle of view, etc., into the selected zenith angle circle diameter calculation model to calculate the diameter of the zenith angle circle.

[0049] The zenith circle diameter calculation model included in the divided area calculation information is a model created by experiments and simulations, and is stored in the storage unit 25 in advance.

[0050] Specifically, the division unit 11 first sets a zenith angle circle for dividing the target plant image based on the diameter of each calculated zenith angle circle, as shown in Fig. 5. Next, the division unit 11 further sets an orientation for dividing the target plant image based on information such as the number of orientation divisions, as shown in Fig. 6. Thereafter, the division unit 11 stores these settings in the storage unit 25.

[0051] As a method for setting the divided regions, all the divided regions may be set to the same area, or the divided regions located on the outer side of the divided regions shown in FIG. 6 may be further divided.

[0052] The void index calculation unit 16 calculates a void index for each divided region of the target plant image. The void index is an index that represents the ratio of the light intensity that reaches the lower part of the plant community to the light intensity at the upper part of the plant community. The void index is, for example, a ratio that represents how many pixels that indicate voids between leaves are included in the image of the divided region.

[0053] Specifically, first, the gap index calculation unit 16 acquires an image corresponding to the divided region. Next, the gap index calculation unit 16 calculates the inter-leaf gap area of ​​the image of each divided region. For example, the gap index calculation unit 16 converts the image of the divided region into a binarized (black and white) image based on the gap threshold indicated by the above-mentioned gap threshold information, detects white pixels in the binarized divided region, and calculates the number of pixels as the inter-leaf gap area. The inter-leaf gap area may be calculated using the color tone of the leaves.

[0054] Next, the void index calculation unit 16 calculates the void ratio for each divided region using the formula shown in Equation 1.

[0055] (Number 1) Po j = WA j / RA j Po j :Divided area j Void Index W.A. j :Divided area j Interleaf gap area RA j :Divided area j Total area of

[0056] In this way, the void index Po j However, the calculation of the void index is not limited to the above-mentioned method.

[0057] After that, the gap index calculation unit 16 associates the divided regions with the gap index Po and stores them in the storage unit 25. FIG. 7 is a diagram for explaining the relationship between the divided regions and the gap index. In the example of FIG. 7, the gap index Po is calculated for the 50 divided regions shown in FIG. j are associated and stored.

[0058] The estimation unit 12 estimates the leaf area index (LAI) for each divided region. j Specifically, the estimation unit 12 first estimates the void index Po j (j represents the division region).

[0059] Next, the estimation unit 12 estimates the optical path length ratio (1 / cos(θ)) estimated from the zenith angle corresponding to the divided region for the image of the divided region. i ) is calculated.

[0060] In addition, the estimation unit 12 estimates the zenith angle θ i Weighting coefficients (ω(θ i ) is obtained from the storage unit 25.

[0061] The weighting coefficients are associated with each zenith angle and stored in the storage unit 25. Although the ratio of the projected areas of the zenith angle circle differs depending on the angle of view of the wide-angle lens 21, by adopting the ratio of the projected areas of the zenith angle circle by equidistant projection as the weighting coefficient, it is possible to obtain results equivalent to those by equidistant projection. Also, each weighting coefficient is a value (ω(θ i ) / n).

[0062] Next, the estimation unit 12 calculates the leaf area index LAI for each divided region using the formula shown in Equation 2. j The formula 2 is used to estimate the void index Po j When is 0, it is indefinite, so the minimum value indicated by the minimum porosity information is used to calculate the leaf area index LAI. j so that it does not become indefinite.

[0063] (Number 2) LAI j = -2 × ln(Po j ) × (ω(θ i ) / n) / (1 / cos(θ i )) LAI j : Leaf area index of the divided area Po j :Porosity of the divided area θ i : Zenith angle circle area i Central zenith angle of i (radians) 1 / cos(θ i): Optical path length ratio estimated from zenith angle i ω(θ i ) : Zenith angle circle area i Weighting factor for converting to an equidistant projection in n: Number of azimuth divisions (D1, D2, D3, D4, D5, D6, D7, D8, D9, D10 in Figure 6) i : Each zenith angle circle area (Z1, Z2, Z3, Z4, Z5 in Figures 5 and 6) j : represents each divided region

[0064] Next, the estimation unit 12 associates the divided regions with the leaf area index and stores them in the storage unit 25. Fig. 8 is a diagram for explaining the relationship between the divided regions and the leaf area index. However, the calculation of the leaf area index is not limited to the above-mentioned method.

[0065] The selection unit 17 selects a segmented region to be subjected to the estimation of the leaf area index or a segmented region to be excluded according to the crown shape for which the leaf area evaluation of the target plant image is performed. The segmented region to be subjected to the estimation of the leaf area index is, for example, a segmented region corresponding to the crown of the target plant, a trunk or a branch with a crown behind it, etc. The segmented region to be excluded from the estimation of the leaf area index is, for example, a segmented region corresponding to a tree in the background, a trunk without a crown behind it, the sky, a photographer, etc.

[0066] The divided area to be estimated is selected by displaying the target plant image and the divided area superimposed on the display unit 22, and allowing the user to specify the divided area to be estimated or the divided area to be excluded from the estimation target using the input unit 23. When selecting the divided area, the leaf area index estimated for each divided area may also be displayed. The leaf area index is displayed to provide an indicator to the user and guide the selection.

[0067] The selection unit 17 may input the target plant image to a model generated by machine learning, which will be described later, and select a segmented area to be estimated or a segmented area to be excluded. The model is generated by using the model generation unit 24, for example.

[0068] Furthermore, the divided area selected using the model or the excluded divided area may be displayed on the display unit 22, and the user may use the input unit 23 to change the selection or exclusion of the divided area.

[0069] Fig. 9 is a diagram for explaining the selection of divided regions. In the example of Fig. 9, it is shown that the region corresponding to the cell marked with "1" is selected as the target for estimating the LAI. Also, it is shown that the region corresponding to the cell marked with "0" is excluded from the target for estimating the LAI.

[0070] In this way, it is possible to select the regions to be estimated or excluded from the multiple regions, so that it is possible to estimate the leaf area index according to the crown shape. Furthermore, it is no longer necessary to measure the tree height and crown radius to model the crown shape, as in the conventional method, which improves user convenience.

[0071] In the learning phase, the model generation unit 24 performs machine learning using past target plant images and selection results of divided regions (divided regions selected as targets for estimating LAI or divided regions excluded from the targets for estimation) to generate a model for estimating divided regions to be used as targets for estimating LAI or divided regions to be excluded. The model is stored in the storage unit 24, for example.

[0072] The calculation unit 13 calculates the leaf area index LAI estimated for each divided area. j Specifically, the calculation unit 13 first calculates the leaf area index LAI of the entire target plant based on the leaf area index LAI corresponding to the selected divided area. j Next, the calculation unit 13 obtains the leaf area index LAI of the divided region. j Calculate the sum of.

[0073] In addition, the calculation unit 13 calculates the weighting coefficient (ω(θ i Next, the calculation unit 13 obtains the weighting coefficient (ω(θ i ) / n) total Calculate.

[0074] Next, the calculation unit 13 calculates the leaf area index LAI of the divided region. j The sum of LAI total The weighting coefficient (ω(θ i ) / n) total Divide by this to calculate the Leaf Area Index (LAI) for the entire selected crown shape.

[0075] Specifically, the calculation unit 13 calculates the leaf area index LAI of the entire estimation target using the formula shown in Equation 3.

[0076] (Number 3) LAI = LAI total / ω total LAI total : Leaf area index (LAI) of the selected divided area j ) ω total : Weighting coefficient of the selected divided region (ω(θ i ) / n)

[0077] Next, the calculation unit 13 stores the leaf area index LAI in the memory unit 24.

[0078] The display information generating unit 18 generates display information for displaying, for example, a user interface, a target plant image, a display of divided regions as shown in Fig. 5 and Fig. 6, a display showing a divided region to be estimated or excluded, a leaf area index LAI, etc. Then, the display information converted into a format that can be displayed on the display unit 22 is output.

[0079] [Device operation] Next, the operation of the plant evaluation device in the embodiment will be described with reference to Fig. 10. Fig. 10 is a diagram for explaining an example of the operation of the plant evaluation device. In the following description, Figs. 1 to 9 will be referred to as appropriate. Also, in the embodiment, the plant evaluation method is carried out by operating the plant evaluation device. Therefore, the description of the plant evaluation method in the embodiment will be replaced with the description of the operation of the plant evaluation device below.

[0080] As shown in FIG. 10, first, the setting unit 15 sets information used for dividing a target plant image into regions and information used for estimating a leaf area index (step A1).

[0081] Specifically, in step A1, first, the setting unit 15 acquires setting information input by a user via the input unit 23 and the input information acquisition unit 19, using a user interface displayed on the screen of the display unit 22. Next, in step A1, the setting unit 15 stores the acquired setting information in the storage unit 25 or the like.

[0082] Next, the image information acquisition unit 14 acquires a target plant image obtained by capturing an image of the target plant (step A2). Specifically, in step A2, the image information acquisition unit 14 first acquires an image obtained by capturing an image of the target plant from the imaging unit 20. Then, in step A2, the image information acquisition unit 14 outputs the acquired target plant image to the storage unit 25 or the like.

[0083] Next, the division unit 11 divides the target plant image into a plurality of regions (step A3). Specifically, in step A3, first, the division unit 11 acquires division region calculation information from the storage unit 25. Then, in step A3, the division unit 11 sets division regions as shown in FIG. 6 based on the division region calculation information. Then, in step A3, the division unit 11 stores the division regions in the storage unit 25.

[0084] Next, the gap index calculation unit 16 calculates a gap index for each divided region of the target plant image (step A4). Specifically, in step A4, the gap index calculation unit 16 first acquires an image corresponding to the divided region. Then, in step A4, the gap index calculation unit 16 calculates the inter-leaf gap area of ​​the image of each divided region.

[0085] For example, the gap index calculation unit 16 converts the image of the divided region into a binary (black and white) image based on the gap threshold value indicated by the above-mentioned gap threshold information, detects white pixels in the binarized divided region, and calculates the number of pixels as the interleaf gap area. The interleaf gap area may also be calculated using the color tone of the leaves.

[0086] Next, in step A4, the void index calculation unit 16 calculates the total area RA j and interleaf gap area WA j Using the above, the void index Po j (=WA j / RA j In this way, the void index Po j However, the calculation of the void index is not limited to the above-mentioned method.

[0087] Then, in step A4, the void index calculation unit 16 calculates the divided area and the void index Po j 6. The gap index Po and the gap index P are stored in the storage unit 25 in association with each other. FIG. 7 is a diagram for explaining the relationship between the divided regions and the gap index. In the example of FIG. 7, the gap index Po and the gap index P are stored in the 50 divided regions shown in FIG. j are associated and stored.

[0088] Next, the estimation unit 12 calculates the leaf area index LAI for each divided region. i Specifically, in step A5, the estimation unit 12 first estimates the void index Po j Get the.

[0089] Next, in step A5, the estimation unit 12 estimates the optical path length ratio (1 / cos(θ i In step A5, the estimation unit 12 calculates the zenith angle θ i Weighting coefficient (ω(θ i ) is obtained from the storage unit 25.

[0090] Next, in step A5, the estimation unit 12 calculates a leaf area index (LAI) for each divided region using the formula shown in Equation 2. j Then, in step A5, the estimation unit 12 stores the divided regions and the leaf area index in the storage unit 25 in association with each other.

[0091] Next, the selection unit 17 selects a segmented region to be subjected to leaf area index estimation or a segmented region to be excluded according to the crown shape for which the leaf area evaluation of the target plant image is performed (step A6). The segmented region to be subjected to leaf area index estimation is, for example, a segmented region corresponding to the crown of the target plant, a trunk or branch with a crown behind it, etc. The segmented region to be excluded from the subject of leaf area index estimation is, for example, a segmented region corresponding to a tree in the background of the target plant, a trunk or branch without a crown behind it, the sky, the photographer, etc.

[0092] The divided area to be estimated is selected by displaying the target plant image and the divided area in an overlapping manner on the display unit 22, and allowing the user to specify the divided area to be estimated or the divided area to be excluded using the input unit 23. When selecting the divided area, the leaf area index estimated for each divided area may also be displayed.

[0093] The selection unit 17 may input a target plant image and select a segmented area to be estimated or a segmented area to be excluded using a model generated by the model generation unit 24. Furthermore, the display unit 22 may display the segmented area selected using the model or the segmented area excluded, and the user may use the input unit 23 to change the selection or exclusion of the segmented area.

[0094] In this way, it is possible to select the regions to be estimated or excluded from the multiple regions, so that it is possible to estimate the leaf area index according to the crown shape. Furthermore, it is no longer necessary to measure the tree height and crown radius to model the crown shape as in the conventional method, which improves user convenience.

[0095] Next, the calculation unit 13 calculates the leaf area index LAI estimated for each divided region. jBased on the above, the calculation unit 13 calculates the leaf area index LAI of the entire target plant (step A7). j Next, in step A7, the calculation unit 13 obtains the leaf area index LAI of the selected divided region. j Calculate the sum of.

[0096] In step A7, the calculation unit 13 calculates the weighting coefficient (ω(θ i Next, in step A7, the calculation unit 13 obtains the weighting coefficient (ω(θ i ) / n) total Calculate.

[0097] Next, in step A7, the calculation unit 13 calculates the leaf area index LAI of the selected divided region. j The sum of LAI total The weighting coefficient (ω(θ j ) / n) to calculate the Leaf Area Index LAI of the entire selected crown shape portion. Next, in step A7, the calculation unit 13 stores the Leaf Area Index LAI in the storage unit 25.

[0098] Next, the display information generating unit 18 generates display information for displaying, for example, a user interface, a target plant image, a display of divided regions as shown in Fig. 5 and Fig. 6, a display showing the estimated target or excluded divided regions, a leaf area index LAI, etc. (Step A8). After that, in Step A8, the display information converted into a format that can be displayed on the display unit 22 is output.

[0099] [Effects of this embodiment] In fruit tree cultivation, in order to prevent the fruit from becoming too large and to obtain a stable harvest, pruning is carried out to remove unnecessary branches so that the tree has an appropriate leaf area according to the condition of the crown of the tree. However, pruning work depends on the skill of the worker, and workers with low skill levels have difficulty pruning appropriately.

[0100] Therefore, clarifying the LAI is an effective method for pruning. However, in the method using PCA described above, the tree height is measured for each target tree, and the crown radius in all four directions is measured to obtain the average crown radius. Furthermore, the PCA must be installed at a position a specified distance away from the main trunk for each of the multiple trees to perform the above measurements, which places a heavy burden on the worker.

[0101] However, according to the present embodiment, a target plant image captured with an inexpensive device configuration (for example, an image captured with a wide-angle lens attached to a smartphone camera) is divided, and the leaf area index LAI is calculated for each divided region. j The leaf area index (LAI) of the selected divided area is calculated based on the shape of the tree crown. j can be used to estimate the leaf area index (LAI) of the entire target plant.

[0102] This eliminates the need to measure tree height and crown radius to define a crown shape model, improving user convenience when estimating the leaf area index. Furthermore, the leaf area index (LAI) can be estimated with high accuracy.

[0103] In addition, the average crown radius [m] and the average leaf area [cm 2 By measuring the leaf area index (LAI), the total leaf area and the total number of leaves, which are indicators of plant productivity, can be calculated using the estimated leaf area index (LAI). The total leaf area can be calculated using the formula shown in Equation 4. The total number of leaves can be calculated using the formula shown in Equation 5.

[0104] (Number 4) Total leaf area [cm 2 ] = Leaf area index (LAI) × (average crown radius [m] 2 ×π)×10000

[0105] (Number 5) Total number of leaves = Total leaf area [cm 2 ] / average leaf area [cm 2 ]

[0106] Next, we will explain the results of estimating the leaf area index for 10 citrus trees. The target plant images used for the estimation were taken at six points, each at a distance of 30cm, 40cm, 50cm, 60cm, 70cm, and 80cm from the center of the trunk. In addition, the leaf area index was measured in order to compare with the estimated leaf area index.

[0107] Fig. 11 shows the evaluation results of the leaf area index. Fig. 11 shows the comparison results between the leaf area index estimated from the target plant image and the leaf area index obtained by actual measurement.

[0108] The relationship between the leaf area index estimated from the target plant images and the leaf area index measured showed a high correlation (r = 0.861-0.939) within the distance range of 30-60 cm from the center of the trunk. Furthermore, a relatively high correlation (r = 0.798-0.818) was also observed within the distance range of 70-80 cm from the center of the trunk.

[0109] Since the leaf area index estimation results can be obtained with a high correlation without strictly specifying the distance from the center of the trunk as the shooting position for the target plant image, the leaf area index is estimated accurately while improving user convenience.

[0110] [program] The program in the embodiment of the present invention may be a program that causes a computer to execute steps A1 to A8 shown in Fig. 10. By installing and executing this program in a computer, the plant evaluation device and plant evaluation method in the present embodiment can be realized. In this case, the processor of the computer functions as an image information acquisition unit 14, a setting unit 15, a division unit 11, a void index calculation unit 16, an estimation unit 12, a selection unit 17, a calculation unit 13, a display information generation unit 18, an input information acquisition unit 19, and a model generation unit 24, and performs processing.

[0111] The program in this embodiment may be executed by a computer system constructed by a plurality of computers. In this case, for example, each computer may function as any one of the image information acquisition unit 14, the setting unit 15, the division unit 11, the void index calculation unit 16, the estimation unit 12, the selection unit 17, the calculation unit 13, the display information generation unit 18, the input information acquisition unit 19, and the model generation unit 24.

[0112] [Physical configuration] Here, a computer that realizes the plant evaluation device by executing a program in the embodiment will be described with reference to Fig. 12. Fig. 12 is a diagram for explaining an example of a computer that realizes the plant evaluation device.

[0113] 12, the computer 110 includes a CPU (Central Processing Unit) 111, a main memory 112, a storage device 113, an input interface 114, a display controller 115, a data reader / writer 116, and a communication interface 117. These components are connected to each other via a bus 121 so as to be able to communicate data with each other. Note that the computer 110 may include a GPU (Graphics Processing Unit) or an FPGA (Field-Programmable Gate Array) in addition to the CPU 111 or instead of the CPU 111.

[0114] The CPU 111 loads the programs (codes) in this embodiment stored in the storage device 113 into the main memory 112 and executes them in a predetermined order to perform various calculations. The main memory 112 is typically a volatile storage device such as a dynamic random access memory (DRAM). The programs in this embodiment are provided in a state stored in a computer-readable recording medium 120. The programs in this embodiment may be distributed on the Internet connected via the communication interface 117. The recording medium 120 is a non-volatile recording medium.

[0115] Specific examples of the storage device 113 include a hard disk drive and a semiconductor storage device such as a flash memory. The input interface 114 mediates data transmission between the CPU 111 and input devices 118 such as a keyboard and a mouse. The display controller 115 is connected to a display device 119 and controls the display on the display device 119.

[0116] Data reader / writer 116 mediates data transmission between CPU 111 and recording medium 120, reads programs from recording medium 120, and writes processing results in computer 110 to recording medium 120. Communication interface 117 mediates data transmission between CPU 111 and other computers.

[0117] Specific examples of recording medium 120 include general-purpose semiconductor storage devices such as CF (Compact Flash (registered trademark)) and SD (Secure Digital), magnetic recording media such as a flexible disk, or optical recording media such as a CD-ROM (Compact Disk Read Only Memory).

[0118] The plant evaluation device 10 in this embodiment can be realized by using hardware corresponding to each part, instead of a computer with a program installed. Furthermore, the plant evaluation device 10 may be partially realized by a program and the remaining part by hardware.

[0119] [Note] The following supplementary notes are further disclosed regarding the above-described embodiments. A part or all of the above-described embodiments can be expressed by (Supplementary Note 1) to (Supplementary Note 15) described below, but are not limited to the following descriptions.

[0120] (Appendix 1) A division unit that divides a target plant image into a plurality of regions based on preset setting information; An estimation unit that estimates a leaf area index for each of the divided regions; A calculation unit that calculates a leaf area index of the entire target plant based on the leaf area index estimated for each of the divided regions; A plant evaluation device having the following:

[0121] (Appendix 2) 2. A plant evaluation device according to claim 1, The dividing unit divides the target plant image into a plurality of regions based on a plurality of zenith circles and / or a plurality of azimuth directions that are set in advance. Plant evaluation equipment.

[0122] (Appendix 3) The plant evaluation device according to claim 1 or 2, a selection unit for selecting a region to be estimated for the leaf area index or a region to be excluded from the estimation target; A plant evaluation device having the following:

[0123] (Appendix 4) 4. A plant evaluation device according to claim 3, The calculation unit calculates the leaf area index of the entire target plant based on the leaf area index of the selected region. Plant evaluation equipment.

[0124] (Appendix 5) 5. A plant evaluation device according to claim 4, A model generation unit that performs machine learning using the past selection results of the region of the leaf area index to generate a model for estimating a region to be estimated or excluded from the leaf area index, The selection unit uses the model to select an area to be estimated or excluded from the estimation of the leaf area index. Plant evaluation equipment.

[0125] (Appendix 6) A division step of dividing a target plant image into a plurality of regions based on preset setting information; An estimation step of estimating a leaf area index for each of the divided regions; A calculation step of calculating a leaf area index of the entire target plant based on the leaf area index estimated for each of the divided regions; A plant evaluation method comprising the steps of:

[0126] (Appendix 7) 7. The plant evaluation method according to claim 6, In the dividing step, the target plant image is divided into a plurality of regions based on a plurality of zenith circles and / or a plurality of azimuth directions that are set in advance. Plant evaluation methods.

[0127] (Appendix 8) The plant evaluation method according to claim 6 or 7, A selection step of selecting an area to be estimated or an area to be excluded from the estimation target of the leaf area index; A plant evaluation method comprising the steps of:

[0128] (Appendix 9) 9. The plant evaluation method according to claim 8, The calculation step calculates a leaf area index of the entire target plant based on the leaf area index of the selected region. Plant evaluation methods.

[0129] (Appendix 10) 10. The plant evaluation method according to claim 9, A model generation step of performing machine learning using a past target plant image and a selection result of the region, and generating a model for estimating a region to be estimated or excluded from the LAI estimation; In the selection step, the model is used to select an area to be included in or excluded from the estimation of the leaf area index. Plant evaluation methods.

[0130] (Appendix 11) On the computer, A division step of dividing a target plant image into a plurality of regions based on preset setting information; An estimation step of estimating a leaf area index for each of the divided regions; A calculation step of calculating a leaf area index of the entire target plant based on the leaf area index estimated for each of the divided regions; A program that contains instructions to execute a program.

[0131] (Appendix 12) 12. The program of claim 11, In the dividing step, the target plant image is divided into a plurality of regions based on a plurality of zenith circles and / or a plurality of azimuth directions that are set in advance. program.

[0132] (Appendix 13) 13. The program according to claim 11 or 12, The program causes the computer to A selection step of selecting an area to be estimated or an area to be excluded from the estimation target of the leaf area index; The program further comprises instructions to execute the

[0133] (Appendix 14) 14. The program of claim 13, The calculation step calculates a leaf area index of the entire target plant based on the leaf area index of the selected region. program.

[0134] (Appendix 15) 15. The program of claim 14, The program causes the computer to The method further includes an instruction to execute a model generation step of performing machine learning using a past target plant image and a result of region selection, and generating a model for estimating a region to be estimated or excluded from the LAI estimation, In the selection step, the model is used to select an area to be included in or excluded from the estimation of the leaf area index. program.

[0135] Although the present invention has been described above with reference to the embodiment, the present invention is not limited to the above embodiment. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention. [Industrial Applicability]

[0136] As described above, according to the present invention, it is possible to improve the convenience of users when estimating the leaf area index of an isolated plant or a plurality of plants that exist at intervals, and to estimate the leaf area index LAI with high accuracy. The present invention is useful in fields where estimation of the leaf area index is required in plant evaluation. [Explanation of symbols]

[0137] 10 Plant evaluation device 11 Division 12 Estimation part 13 Calculation section 14 Image information acquisition section 15 Setting section 16 Porosity index calculation section 17 Selection section 18 Display information generation section 19 Input information acquisition section 20 Imaging unit 21 Wide-angle lens 22 Display section 23 Input section 24 Model Generation Unit 25 Memory section 30 Control section 110 Computer 111 CPU 112 Main memory 113 Storage device 114 Input Interface 115 Display Controller 116 Data Reader / Writer 117 Communication Interface 118 Input Devices 119 Display device 120 Recording media 121 Bus

Claims

1. A dividing means for dividing a target plant image into a plurality of regions based on preset setting information; An estimation means for estimating a leaf area index for each of the divided regions; A calculation means for calculating a leaf area index of the entire target plant based on the leaf area index estimated for each of the divided regions; A model generating means for performing machine learning by inputting a past target plant image and a selection result of an area, and generating a model for estimating an area to be estimated or excluded from the LAI estimation; A selection means for selecting an area to be estimated or an area to be excluded from the estimation target of the leaf area index using the model; A plant evaluation device having the following:

2. The plant evaluation device according to claim 1, The dividing means divides the target plant image into a plurality of regions based on a plurality of zenith circles and / or a plurality of azimuth directions that are set in advance. Plant evaluation equipment.

3. The plant evaluation device according to claim 2, The calculation means calculates the leaf area index of the entire target plant based on the leaf area index of the selected region. Plant evaluation equipment.

4. A computer comprising: Dividing a target plant image into a plurality of regions based on preset setting information; Estimating a leaf area index for each of the divided regions; Calculating a leaf area index of the entire target plant based on the leaf area index estimated for each of the divided regions; A machine learning is performed by inputting the past target plant image and the region selection result, and a model is generated for estimating the region to be estimated or excluded for the LAI estimation; Using the model, a region to be estimated or a region to be excluded from estimation of the LAI is selected. Plant evaluation methods.

5. The plant evaluation method according to claim 4, The computer, In the division, the target plant image is divided into a plurality of regions based on a plurality of zenith circles and / or a plurality of azimuth directions that are set in advance. Plant evaluation methods.

6. Dividing a target plant image into a plurality of regions based on preset setting information; Estimating a leaf area index for each of the divided regions; Calculating a leaf area index of the entire target plant based on the leaf area index estimated for each of the divided regions; A machine learning is performed by inputting the past target plant image and the region selection result, and a model is generated for estimating the region to be estimated or excluded for the LAI estimation; Using the model, a region to be estimated or a region to be excluded from estimation of the LAI is selected. A program that contains instructions that cause a computer to carry out a process.

7. The program according to claim 6, In the division, the target plant image is divided into a plurality of regions based on a plurality of zenith circles and / or a plurality of azimuth directions that are set in advance. program.

Images