JP5724762B2 - Maturity level determination program, maturity level determination device, and maturity level determination method - Google Patents

Description

  The present invention relates to a maturity determination program, a maturity determination device, and a maturity determination method.

  Conventionally, pollen maturity is determined in order to predict pollen scattering time. The maturity of pollen is determined, for example, by comparing a change in hue according to the maturity of pollen with past data. For example, “last year's date” having the closest color to the current pollen color is used as the maturity of the pollen. As a method for determining the maturity of pollen, for example, the method described below is performed.

  For example, there is a method of performing visual discrimination in a field survey. In this method, for example, a person who conducts an investigation directly in an area to be investigated determines the maturity of pollen by comparing the current pollen color with the past pollen color.

  In addition, for example, there is a method using an accumulated temperature value. In this method, for example, daily temperatures after pollen maturation starts are accumulated for each area to be investigated. And the maturity degree of the present pollen is determined by comparing with the past cumulative value.

  For example, there is a method using remote sensing. In this method, for example, a tree or forest to be investigated is photographed with a digital camera, and R value, G value, and B value are separated from the photographed image data. Then, each separated value is accumulated every day after the start of pollen maturity, and the current maturity of pollen is determined by comparing with the past accumulated value.

Yamagata University, Faculty of Engineering, Information Technology Office, Takanori Nakajima, “Research Report on Scientific Research Expenses 2005 (Encouragement Research 17921011), Research on Hazard Map of Cedar Pollen Spattering by Remote Sensing Image Analysis”, [online], [2011 Search August 5], Internet <URL: http://tech-staff.yz.yamagata-u.ac.jp/kakenhi/H17Nakajima.pdf>

  However, in the above prior art, pollen maturity cannot be determined accurately and simply.

  For example, in the method of visual discrimination in the field survey, it was necessary for the person conducting the survey to go directly to the area to be surveyed, so it was not possible to easily determine the maturity of pollen. In addition, for example, because there is an individual difference for each tree to be surveyed or for each male flower with pollen, an error in selecting the survey target occurs, and the maturity of pollen could not be accurately determined. .

  In addition, for example, in the method using the accumulated value of the temperature, it is necessary to measure the temperature of the area to be investigated every day, and therefore the pollen maturity cannot be easily determined. Further, for example, when the area to be investigated is in the mountains, a deviation from the temperature measured by the weather station is likely to occur, and the deviation may be increased due to accumulation. For this reason, this method cannot accurately determine the maturity of pollen.

  In addition, for example, in the method using remote sensing, it is necessary to photograph trees and forests to be investigated every day, so that the pollen maturity cannot be easily determined. In addition, for example, when rain or snow falls, the R value, G value, and B value separated from the image data are different from the values on a sunny day, so that the maturity of pollen can be accurately determined. could not.

  The disclosed technology has been made in view of the above, and an object thereof is to provide a maturity determination program, a maturity determination device, and a maturity determination method that can accurately and easily determine the maturity of pollen. And

  In one aspect, the disclosed program is a storage unit that stores, for each pollen maturity, spectrum data acquired by photographing an airborne flower to be processed and reference data based on spectrum data indicating the maturity of pollen. A computer is caused to execute a process of collating with the stored reference data. Further, the disclosed program causes the computer to execute a process of determining the maturity level of the pollen to be processed based on the collation result.

  According to one aspect of the technology disclosed in the present application, there is an effect that the maturity of pollen can be accurately and easily determined.

FIG. 1 is a block diagram illustrating a functional configuration of the maturity determination apparatus according to the first embodiment. FIG. 2 is a diagram illustrating an example of the HSD. FIG. 3 is a diagram illustrating an example of spectrum data included in the HSD. FIG. 4 is a diagram illustrating an example of spectrum data included in the HSD. FIG. 5 is a diagram for explaining a time-series database. FIG. 6 is a diagram for explaining the collation result. FIG. 7 is a diagram for explaining a process for obtaining a predicted pollen start date. FIG. 8 is a diagram for explaining processing for obtaining a predicted pollen start date. FIG. 9 is a flowchart illustrating the processing procedure of the maturity determination apparatus according to the first embodiment. FIG. 10 is a diagram for explaining the effect of the maturity determination device. FIG. 11 is a diagram for explaining the singular points included in the spectrum data. FIG. 12 is a diagram for explaining a time series database. FIG. 13 is a diagram for explaining the processing of the collation unit. FIG. 14 is a diagram illustrating an example of a computer that executes a maturity determination program.

  Hereinafter, embodiments of a maturity determination program, a maturity determination device, and a maturity determination method disclosed in the present application will be described in detail with reference to the drawings. Note that the present invention is not limited to the embodiments. Each embodiment can be appropriately combined within a range in which processing contents do not contradict each other.

  An example of a functional configuration of the maturity determination device according to the first embodiment will be described. FIG. 1 is a block diagram illustrating a functional configuration of the maturity determination apparatus according to the first embodiment. As illustrated in FIG. 1, the maturity determination apparatus 100 includes a storage unit 110 and a control unit 120. The maturity determination apparatus 100 is connected to an input apparatus 101 and an output apparatus 102. The maturity determination apparatus 100 corresponds to, for example, a personal computer.

  The input device 101 receives input of various information. For example, the input device 101 receives spectrum data acquired by photographing an airborne flower to be processed, and sends the received spectrum data to the receiving unit 121 described later. For example, the input device 101 receives an input of an instruction to start processing by the user, and sends the input of the received instruction to the reception unit 121. For example, the input device 101 corresponds to a keyboard, a mouse, a medium reading device, or various sensors such as a thermometer, a hygrometer, and a hyperspectral sensor.

  The output device 102 outputs various information. For example, the output device 102 outputs the maturity level of pollen determined by the determination unit 123 described later. For example, the output device 102 corresponds to a display, a monitor, or the like.

  The storage unit 110 includes an HSD (Hyper-Spectral Data) 111 and a time series database 112. The storage unit 110 corresponds to, for example, a semiconductor memory device such as a random access memory (RAM), a read only memory (ROM), and a flash memory, and a storage device such as a hard disk or an optical disk.

  The HSD 111 is data having a three-dimensional configuration that includes two-dimensional elements as an image and elements as spectrum data. For example, the HSD 111 has spectral data including wavelength information and light intensity or reflectance information for each pixel of the image. For example, the HSD 111 is captured by a hyperspectral sensor. The HSD 111 is also called hyperspectral data.

  FIG. 2 is a diagram illustrating an example of the HSD. FIG. 2 shows, as an example, an HSD 111 obtained by photographing a forest in which cedar, which is an airborne flower to be measured, is vegetated, using a hyperspectral sensor mounted on an aircraft. As shown in FIG. 2, the HSD 111 includes, for example, a pixel 2a. The pixel 2a has, for example, spectral data corresponding to mature cedar pollen. In addition, although the case where HSD111 image | photographed with the hyperspectral sensor mounted in the aircraft was demonstrated here, this invention is not limited to this. For example, the HSD 111 may be taken by a hyperspectral sensor mounted on an artificial satellite or a vehicle traveling on the ground, or may be taken by a human hand. For example, the HSD 111 may be acquired from an external storage device that stores the HSD 111 taken in the past.

  The spectral data of the HSD will be described with reference to FIGS. 3 and 4 are diagrams illustrating an example of spectrum data included in the HSD. FIG. 3 shows a case where spectral intensity is used, and FIG. 4 shows a case where relative reflectance is used. This relative reflectance is a value obtained by removing the spectral component of the light source from the spectral intensity. 3 and 4, the horizontal axis indicates the wavelength, and the vertical axis indicates the spectral intensity or the relative reflectance. 3 and 4 show a case where the image is taken with a hyperspectral sensor having a measurement wavelength range of 400 nm to 900 nm. The degree of pollen maturation tends to appear in the visible light region from 400 nm to 700 nm in this measurement wavelength region. In particular, cedar pollen maturation tends to appear in the region from 550 nm to 650 nm containing a yellow component. Further, the measurement wavelength range of the hyperspectral sensor used for photographing is not limited to 400 nm to 900 nm. For example, the measurement wavelength range of the hyperspectral sensor may be appropriately selected according to the type of wind medium flower to be measured. As spectrum data, spectrum intensity may be used, and relative reflectance may be used. Hereinafter, a case where relative reflectance is used will be described. For example, the pixel 2a of the HSD 111 shown in FIG. 2 has the spectral data shown in FIG.

  The time-series database 112 stores reference data based on spectral data indicating pollen maturity for each pollen maturity. For example, the time-series database 112 stores spectrum data corresponding to past dates from when pollen is immature to when pollen is scattered for each corresponding past date. FIG. 5 is a diagram for explaining a time-series database. As illustrated in FIG. 5, the time series database 112 stores, for example, pollen spectrum data corresponding to the date of last year for each corresponding date. The time series database 112 is an example of reference data. The spectrum data stored in the time series database 112 is an example of spectrum data for verification.

  For example, the time-series database 112 is generated by daily recording of pollen spectrum data from pollen immaturity to pollen scattering. It should be noted that the spectral data acquired during rainy weather or snowing is different from the spectral data during sunny weather, so it is desirable to use the spectral data during sunny weather. In addition, when desirable spectrum data cannot be recorded due to rain or snowfall, it may be estimated from spectrum data recorded on another date. For example, an intermediate value of spectrum data corresponding to dates before and after a date that cannot be recorded may be used.

  The control unit 120 includes a reception unit 121, a verification unit 122, and a determination unit 123. The function of the control unit 120 can be realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA). Further, the function of the control unit 120 can be realized, for example, by a CPU (Central Processing Unit) executing a predetermined program.

  The receiving unit 121 receives various types of information. For example, the accepting unit 121 accepts spectrum data acquired by photographing an airborne flower to be processed. For example, the reception unit 121 receives the HSD 111 from the input device 101 and stores the received HSD 111 in the storage unit 110. For example, the reception unit 121 receives an instruction to start processing by the user from the input device 101, and sends the received instruction to the verification unit 122.

  The collation unit 122 collates the spectrum data acquired by photographing the wind medium flower to be processed with the time-series database 112. For example, when the collation unit 122 receives an instruction to start processing from the reception unit 121, the verification unit 122 selects one pixel included in the HSD 111 in which pollen to be processed is captured. The collation unit 122 collates the spectrum data of the selected pixel with the spectrum data of the time series database 112.

  For example, the matching unit 122 performs spectrum data matching using the cosine distance of the vector. For example, the collation part 122 calculates | requires the reference vector eHS based on spectrum data, as described in Unexamined-Japanese-Patent No. 2009-39280. For example, the matching unit 122 obtains the reference vector eHS1 from the spectrum data of the selected pixel, and obtains the reference vector eHS2 from the spectrum data in the time series database 112. The matching unit 122 calculates the cosine distance cos θ using the following formula (1). Since eHS1 and eHS2 are unit vectors having a magnitude of 1, the closer the cosine distance cos θ is to 1, the closer the collation unit 122 has the spectral data of the selected pixel, the spectral data of the time series database 112, and Are determined to be similar.

  For example, the collation unit 122 collates the spectrum data of the selected pixel with the spectrum data in the time series database 112. The collation unit 122 associates the date of last year of the spectrum data most similar to the spectrum data of the selected pixel with the selected pixel. The collation unit 122 associates the date of last year with the other pixels in the same manner. As described above, the matching unit 122 associates the date of last year of the most similar spectrum data with each pixel included in the HSD 111 in which the pollen to be processed is captured. This method is also referred to as a Spectral Angle Mapper method.

  FIG. 6 is a diagram for explaining the collation result. The upper part of FIG. 6 shows the spectrum data of the time series database 112 and the corresponding last date. 6 shows images 6a to 6c in which pixels similar to the past date are mapped in the HSD 111 shown in FIG. 2 as actually measured data. That is, the pixel shown in the image 6a is similar to January 18 last year, the pixel shown in the image 6b is similar to January 19 last year, and the pixel shown in the image 6c is similar to January 20 last year Respectively. For example, as illustrated in FIG. 6, the collation unit 122 outputs data in which pixels similar to the past date are mapped to each pixel of the HSD 111 as a collation result. Although the case where the data mapped by the collation unit 122 is output as the collation result has been described here, the present invention is not limited to this. For example, the matching unit 122 may output data in which similar past dates are associated with the coordinates of each pixel of the HSD 111 as a matching result.

  The determination unit 123 determines the maturity of the pollen to be processed based on the collation result by the collation unit 122. For example, the determination unit 123 determines the past date having the largest number of pixels as the maturity level of the pollen to be processed among the past dates included in the collation result received from the collation unit 122. For example, when the date with the largest number of pixels among the past dates included in the matching result shown in FIG. 6 is January 19, the determination unit 123 sets January 19 as the pollen to be processed. Judge as maturity. Note that the determination method by the determination unit 123 is not limited to this method. For example, the determination unit 123 may determine the earliest date as the maturity level of the pollen to be processed among past dates in which a predetermined number or more of pixels exist in the collation result. For example, a case will be described in which the past date in which the number of pixels is greater than or equal to a predetermined number in the collation result illustrated in FIG. 6 is January 18, January 19, and January 20. In this case, the determination unit 123 determines January 18 as the maturity of the pollen to be processed.

  Further, for example, the determination unit 123, based on the maturity level of the pollen to be processed, predicts the start date of pollen scattering indicating the date on which pollen scattering starts, and indicates the predicted date of end of pollen scattering indicating the date on which pollen scattering ends. And ask. For example, the determination unit 123 subtracts the past date corresponding to the maturity of the pollen to be processed from the date on which pollen scattering started in the past, and adds the subtraction result to the date on which the pollen to be processed is captured. By doing so, the date when the pollen to be processed starts to be scattered is calculated.

  FIG. 7 is a diagram for explaining a process for obtaining a predicted pollen start date. In the example shown in FIG. 7, a case where the maturity of pollen photographed on January 17 as an actual measurement value corresponds to January 19 of last year stored in the time series database 112 will be described. In the example illustrated in FIG. 7, the time series database 112 stores the fact that the start date of pollen scattering last year was January 24th. In the example illustrated in FIG. 7, the determination unit 123 calculates (24 days−19 days) +17 days = 22 days as the pollen scattering start predicted date. In this way, the determination unit 123 can calculate the predicted pollen start date only by measuring one actual measurement value. In addition, the process in which the determination part 123 calculates a pollen scattering end predicted date is the same as the process which calculates a pollen scattering start predicted date.

  FIG. 8 is a diagram for explaining processing for obtaining a predicted pollen start date. In the example shown in FIG. 8, the case where the maturity level of pollen photographed on January 13 and January 17 as an actual measurement value is determined will be described. FIG. 8 shows a case where the maturity of pollen photographed on January 13 corresponds to January 14 last year, and the maturity of pollen photographed on January 17 corresponds to January 19 last year. Show. Further, the example shown in FIG. 8 shows a case where the time series database 112 stores that the pollen start date of last year was January 24th. In the example illustrated in FIG. 8, the determination unit 123 calculates 13 days + (24 days−14 days) × (17 days−13 days) / (19 days−14 days) = 21 days as the pollen scattering start prediction date. . As described above, the determination unit 123 can accurately calculate the pollen scattering start predicted date by measuring two actual measurement values. Here, the case where the actual measurement values are measured at two points has been described, but the present invention is not limited to this. For example, by measuring three or more actual measurement values, the pollen scattering start predicted date can be calculated more accurately. This is because the tendency of pollen maturity for the year can be grasped by comparing measured values on a plurality of dates with the time-series database 112. Moreover, the process which the determination part 123 calculates a pollen scattering end prediction date is the same as the process which calculates a pollen scattering start prediction date.

  For example, the determination unit 123 determines the amount of pollen scattering based on the maturity of the pollen to be processed. For example, the determination unit 123 determines the spectral intensity at the pollen wavelength included in the spectral data corresponding to the maturity of the pollen to be processed with respect to the spectral intensity at the wavelength of the pollen included in the spectral data for matching corresponding to the maturity of the pollen. The ratio of spectral intensity is calculated. The determination unit 123 calculates the amount of scattering when the pollen to be processed is scattered by multiplying the calculated ratio by the calculated amount of scattering.

  For example, the case where the amount of pollen scattered last year was 3000 per square centimeter will be described. Further, a case will be described where the maturity of pollen photographed on January 17 as an actual measurement value corresponds to January 19 last year. Also, the case where the relative reflectance at 600 nm of the spectrum data taken on January 17 is 0.22 and the relative reflectance at 600 nm of the spectrum data corresponding to January 19 of last year is 0.2 will be described. To do. In this case, the predicted amount of pollen scattering is 3000 × 0.22 / 0.2 = 3300 per square centimeter. In addition, although it calculated here that the wavelength of pollen is 600 nm, this invention is not limited to this. For example, the wavelength of pollen may be appropriately selected according to the plant species. Alternatively, the pollen wavelength range may be selected, the ratio calculated using the integral value of the spectrum data within the selected range, and the pollen scattering amount predicted.

  Next, a processing procedure of the maturity determination apparatus 100 according to the first embodiment will be described. FIG. 9 is a flowchart illustrating the processing procedure of the maturity determination apparatus according to the first embodiment. The process shown in FIG. 9 is executed at predetermined time intervals, for example, while power is supplied from the power source to the illustrated devices.

  As illustrated in FIG. 9, when the receiving unit 121 receives an instruction to start processing from the input device 101 (Yes in step S <b> 101), the matching unit 122 includes one pixel included in the HSD 111 in which pollen to be processed is captured. Select (step S102).

  The collation unit 122 collates the spectrum data of the selected pixel with the spectrum data of the time series database 112 (step S103). For example, the matching unit 122 associates the date of last year of the spectrum data most similar to the spectrum data included in the selected pixel with the selected pixel.

  The collation unit 122 repeatedly executes the processes of step S102 and step S103 until all the pixels included in the HSD 111 in which the pollen to be processed has been photographed are selected (No in step S104).

  When all the pixels are selected (Yes at Step S104), the determination unit 123 determines the maturity level of the pollen to be processed based on the collation result by the collation unit 122 (Step S105).

  Next, the effect of the maturity determination apparatus 100 according to the first embodiment will be described. The maturity determination apparatus 100 stores, for each maturity of the pollen to be processed, the spectrum data acquired by photographing the airborne flower to be processed and the reference data based on the spectrum data indicating the maturity of the pollen. Is compared with the reference data stored in. The maturity determination apparatus 100 determines the maturity of pollen to be processed based on the collation result. For this reason, the maturity determination apparatus 100 can determine the maturity of pollen accurately and easily. Moreover, the maturity determination apparatus 100 can determine the pollen scattering start prediction date, the pollen scattering end prediction date, and the pollen scattering amount accurately and simply based on the determined pollen maturity.

  For example, the maturity determination apparatus 100 photographs an airborne flower to be processed using a hyperspectral sensor. For this reason, the maturity determination apparatus 100 can easily determine the maturity of pollen without the person who conducts the survey going directly to the area to be investigated. For example, as shown in FIG. 10, the maturity determination apparatus 100 can easily determine the maturity of pollen over a wide range by performing remote sensing using a hyperspectral sensor mounted on an artificial satellite. FIG. 10 is a diagram for explaining the effect of the maturity determination device.

  In addition, for example, the maturity determination apparatus 100 compares the reference data for each pixel included in the HSD 111 and determines the maturity of pollen. For this reason, the maturity determination apparatus 100 can reduce the influence by the individual difference for every tree used as investigation object, or every male flower, and can determine the maturity of pollen correctly.

  For example, the maturity determination apparatus 100 determines the maturity of pollen based on the pollen HSD 111 photographed as a processing target. For this reason, the maturity determination apparatus 100 can easily determine the maturity of pollen without photographing pollen every day. Moreover, since the maturity determination apparatus 100 does not need to photograph pollen every day and accumulate data, it is possible to reduce the influence of deviation and accurately determine the maturity of pollen.

  A maturity determination apparatus 100 according to the second embodiment will be described. In the first embodiment, the case where spectral data is collated using a vector cosine distance has been described. However, spectral data may be collated using a plurality of singular points included in the spectral data. Thus, in the second embodiment, a case will be described in which spectrum data is collated using a plurality of singular points included in spectrum data.

  Here, singular points included in the spectrum data will be described. FIG. 11 is a diagram for explaining the singular points included in the spectrum data. FIG. 11 shows an example of spectrum data using the spectrum intensity. The singular points included in the spectrum data are, for example, the maximum point and the minimum point of the spectrum data. In the example illustrated in FIG. 11, the maturity determination apparatus 100 performs spectral data matching using the singular points A to E. A singular point is also referred to as a feature point.

  An example of a functional configuration of the maturity determination apparatus 100 according to the second embodiment will be described. The functional configuration of the maturity determination apparatus 100 according to the second embodiment is basically the same as the functional configuration of the maturity determination apparatus 100 illustrated in FIG. 1, and only differences will be described.

  The time series database 112 stores, as reference data, a combination including one or a plurality of feature amounts calculated from a plurality of singularity values included in spectrum data indicating pollen maturity, and stores the data for each maturity of pollen. .

  FIG. 12 is a diagram for explaining a time series database. As shown in FIG. 12, the time-series database 112 stores past dates and numerical values derived from singular points included in spectrum data photographed on the corresponding day in association with each other. For example, the time series database 112 stores α, β, γ, and δ as numerical values derived from singular points. α is calculated using the following equation (2). β is calculated using the following equation (3). γ is calculated using the following equation (4). δ is calculated using the following equation (5). In the following formulas (2) to (5), A represents the spectral intensity at the singular point A in FIG. 11, B represents the spectral intensity at the singular point B, and C represents the spectral intensity at the singular point C. , D represents the spectral intensity at the singular point D, and E represents the spectral intensity at the singular point E. Moreover, this numerical value is an example of a feature amount.

α = C / A (2)
β = (C−B) / (A−B) (3)
γ = (A / B) / (A / C) (4)
δ = {(C−B) / (C−D)} / {(C−D) / (C−E)} (5)

  Since the above formulas (2) to (5) are used to determine the ratio of the spectral intensity of the singular points, the influence of the imaging conditions hardly appears. In addition, the formula for obtaining the numerical value is not limited to the above formulas (2) to (5), and a person who uses the maturity determination apparatus 100 may appropriately set it.

  As illustrated in FIG. 12, the time series database 112 includes, for example, a past date “2009.12.1”, α “OO”, β “ΔΔΔ”, and γ “xxx”. , Δ “□□□” are stored in association with each other. In other words, the time-series database 112 has α = OO, β = ΔΔΔ, γ = XXX, and numerical values derived from singular points included in the spectrum data acquired on December 1, 2009. , Δ = □□□ is stored. The time series database 112 stores numerical values in the same manner for other dates.

  The matching unit 122 calculates one or a plurality of feature amounts from the values of a plurality of singular points included in the spectrum data of each pixel included in an image acquired by photographing pollen to be processed with a hyperspectral sensor. . The collation unit 122 collates the calculated one or more feature quantities with one or more feature quantities included in the combination of feature quantities stored in the time series database 112.

  For example, when the collation unit 122 receives an instruction to start processing from the reception unit 121, the verification unit 122 selects one pixel included in the HSD 111 in which pollen to be processed is captured. The collation unit 122 collates the spectrum data of the selected pixel with the spectrum data of the time series database 112.

  For example, the matching unit 122 performs spectrum data matching using a plurality of singular points included in the spectrum data. As a method for detecting this singular point, for example, a method using a zero cross point where a differential coefficient of spectrum data changes from positive to negative or from negative to positive, a method of detecting a singular point by performing pattern matching, and the like are used.

  FIG. 13 is a diagram for explaining the processing of the collation unit. As illustrated in FIG. 13, the matching unit 122 applies a plurality of singular points included in the spectrum data of the selected pixel to the above formulas (2) to (5), and α, β, γ, and δ are calculated. Calculate each. The matching unit 122 compares the calculated α, β, γ, and δ with α, β, γ, and δ in the time series database 112, respectively. For example, the collation unit 122 sets the past date when the error range of the numerical values of α, β, γ, and δ is within ± 5% as the collation result of the selected pixel. In addition, when there are a plurality of past dates in which the error of each numerical value is within ± 5%, the collating unit 122 specifies the only past date by narrowing the error range. Further, when there is no past date in which the error of each numerical value is within ± 5%, the collating unit 122 specifies the only past date by widening the error range. In this manner, the collation unit 122 outputs data in which similar past dates are associated with each pixel of the HSD 111 as a collation result.

  As described above, the maturity determination apparatus 100 according to the second embodiment collates spectrum data using a plurality of singular points included in the spectrum data. For this reason, since the maturity determination apparatus 100 does not need to store spectrum data in the time series database 112, the storage capacity required for the time series database 112 can be reduced.

  Although the embodiments of the present invention have been described so far, the present invention may be implemented in other embodiments besides the above-described embodiments. Therefore, other embodiments will be described below.

  For example, in the above-described first and second embodiments, the case where each pixel included in the HSD 111 obtained by photographing the airborne flower to be processed is compared with the time series database 112 has been described, but the present invention is not limited to this. Absent. For example, the collation unit 122 may collate the pixels included in the HSD 111 obtained by photographing the airborne flower to be processed, and collate with the time-series database 112 for the pixels having the most similar pixels.

  In addition, among the processes described in the first and second embodiments, all or part of the processes described as being automatically performed can be manually performed, or have been described as being manually performed. All or a part of the processing can be automatically performed by a known method. For example, the process of the maturity determination apparatus 100 has been described as being manually started when the reception unit 121 receives an instruction to start the process by the user, but is not limited thereto. . For example, the process of the maturity determination apparatus 100 may be automatically started when the receiving unit 121 receives the HSD 111 to be processed. In addition, the processing procedures, control procedures, specific names, and information including various data and parameters shown in the above-described document and drawings can be arbitrarily changed unless otherwise specified. For example, the time series database 112 illustrated in FIG. 12 may store numerical values obtained by other calculation methods.

  Each component of the maturity determination apparatus 100 shown in FIG. 1 is functionally conceptual and does not necessarily need to be physically configured as illustrated. That is, the specific form of the distribution / integration of the maturity determination apparatus 100 is not limited to the illustrated one, and all or a part of the maturity determination apparatus 100 may be functional or physical in arbitrary units according to various loads or usage conditions. Can be distributed and integrated. For example, the server is provided with any or all of the functions of the collation unit 122, the determination unit 123, and the time series database 112 illustrated in FIG. 1, and the server and the maturity determination device 100 cooperate with each other to generate pollen. You may determine the maturity level.

  Moreover, the maturity determination apparatus 100 can also be realized by installing each function of the maturity determination apparatus 100 in a known information processing apparatus. The known information processing apparatus corresponds to a device such as a personal computer, a workstation, a mobile phone, a PHS (Personal Handy-phone System) terminal, a mobile communication terminal, or a PDA (Personal Digital Assistant).

  FIG. 14 is a diagram illustrating an example of a computer that executes a maturity determination program. As illustrated in FIG. 14, the computer 300 includes a CPU 301 that executes various arithmetic processes, an input device 302 that receives data input from a user, and a monitor 303. The computer 300 also includes a medium reading device 304 that reads a program or the like from a storage medium, an interface device 305 for connecting to another device, and a wireless communication device 306 for connecting to another device wirelessly. The computer 300 also includes a RAM (Random Access Memory) 307 that temporarily stores various types of information and a hard disk device 308. Each device 301 to 308 is connected to a bus 309.

  The hard disk device 308 stores a maturity determination program having the same functions as the processing units of the collation unit 122 and the determination unit 123 illustrated in FIG. Alternatively, the disk device 308 stores various data for realizing the maturity determination program.

  The CPU 301 reads each program stored in the hard disk device 308, develops it in the RAM 307, and performs various processes. In addition, these programs can cause the computer to function as the collation unit 122 and the determination unit 123 illustrated in FIG.

  Note that the maturity determination program is not necessarily stored in the hard disk device 308. For example, the computer 300 may read and execute a program stored in a computer-readable recording medium. As the computer-readable recording medium, for example, a portable recording medium such as a CD-ROM, a DVD disk, and a USB memory, a semiconductor memory such as a flash memory, a hard disk drive, and the like are supported. Further, the program may be stored in a device connected to a public line, the Internet, a LAN (Local Area Network), a WAN (Wide Area Network), etc., and the computer 300 may read and execute the program therefrom. good.

  The following supplementary notes are further disclosed with respect to the embodiments including the above examples.

(Supplementary note 1)
The spectrum data acquired by photographing the airborne flower to be processed is compared with the reference data stored in the storage unit that stores the reference data based on the spectrum data indicating the maturity of the pollen for each maturity of the pollen. And
A maturity determination program for executing a process of determining a maturity level of pollen to be processed based on a matching result obtained by the matching process.

(Additional remark 2) The process to collate collates the spectrum data for every pixel contained in the image acquired by photographing the pollen used as the processing object with a hyperspectral sensor, and the reference data,
The maturity determination program according to appendix 1, wherein the determining process determines the maturity level of the pollen to be processed based on a matching result for each pixel by the matching process.

(Additional remark 3) The said determination process subtracts the past date corresponding to the maturity degree of the said pollen to be processed from the date when the scattering of pollen started in the past, and the pollen to be processed captures the subtraction result. The maturity determination program according to appendix 1 or 2, wherein a date on which scattering of the pollen to be processed starts is calculated by adding the date to the processed date.

(Additional remark 4) The said determination process subtracts the past date corresponding to the maturity degree of the said pollen to be processed from the date when the scattering of the pollen ended in the past, and the pollen to be processed captures the subtraction result. The maturity determination program according to any one of appendices 1 to 3, wherein a date when the scattering of the pollen to be processed ends is calculated by adding to the calculated date.

(Supplementary Note 5) In the storage unit, spectral data for verification, which is spectral data indicating pollen maturity, is stored as the reference data for each maturity of the pollen,
The process of collating collates the spectral data of each pixel included in the image acquired by photographing the pollen to be processed with a hyperspectral sensor and the spectral data for verification stored in the storage unit. The maturity determination program according to any one of appendices 1 to 4, characterized in that:

(Additional remark 6) The amount of scattering for collation which is the amount of scattering when pollen corresponding to the spectrum data for verification is scattered is stored in the storage unit,
The determination process calculates a ratio of the spectral intensity at the pollen wavelength included in the spectral data corresponding to the maturity of the pollen to be processed with respect to the spectral intensity at the pollen wavelength included in the verification spectral data. The maturity determination program according to appendix 5, wherein the amount of scattering when the pollen to be processed is scattered is calculated by multiplying the calculated amount of scattering by the calculated ratio.

(Supplementary note 7) In the storage unit, a combination including one or a plurality of feature amounts calculated from a plurality of feature point values included in spectrum data indicating pollen maturity is used as the reference data as the pollen maturity Remembered every time,
In the process of collating, one or a plurality of feature amounts are obtained from the values of a plurality of feature points included in spectrum data of each pixel included in an image obtained by photographing pollen to be processed with a hyperspectral sensor. The one or more feature amounts calculated and the one or more feature amounts included in the combination stored for each maturity of the pollen in the storage unit are collated The maturity determination program according to any one of 1 to 6.

(Additional remark 8) The memory | storage part which memorize | stores the reference data based on the spectrum data which show the maturity degree of pollen for every maturity degree of the said pollen,
A collation unit that collates spectral data acquired by photographing an airborne flower to be processed and the reference data stored in the storage unit;
A maturity determination apparatus comprising: a determination unit that determines a maturity level of pollen to be processed based on a result of verification by the verification unit.

(Additional remark 9) The said collation part collates the spectrum data for every pixel contained in the image acquired by image | photographing the pollen used as the said process target with a hyperspectral sensor, and the said reference data,
The maturity determination apparatus according to appendix 8, wherein the determination unit determines the maturity level of the pollen to be processed based on a matching result for each pixel by the matching process.

(Additional remark 10) The said determination part subtracts the past date corresponding to the maturity degree of the said pollen to be processed from the date when the scattering of pollen started in the past, and the pollen to be processed is photographed as the subtraction result. The maturity determination apparatus according to appendix 8 or 9, wherein a date on which scattering of the pollen to be processed starts is calculated by adding to the date.

(Additional remark 11) The said determination part subtracts the past date corresponding to the maturity degree of the said pollen to be processed from the date when the scattering of pollen ended in the past, and the pollen to be processed is photographed as the subtraction result. The maturity determination device according to any one of appendices 8 to 10, wherein the date when the pollen to be processed ends is calculated by adding to the date.

(Supplementary Note 12) In the storage unit, spectral data for verification, which is spectral data indicating pollen maturity, is stored as the reference data for each maturity of the pollen,
The collation unit collates spectral data of each pixel included in an image acquired by photographing the pollen to be processed with a hyperspectral sensor and the spectral data for verification stored in the storage unit. The maturity determination apparatus according to any one of supplementary notes 8 to 11, characterized by:

(Additional remark 13) The amount of scattering for collation which is the amount of scattering when pollen corresponding to the spectrum data for verification is scattered is stored in the storage unit,
The determination unit calculates a ratio of the spectral intensity at the wavelength of pollen included in the spectral data corresponding to the maturity of the pollen to be processed with respect to the spectral intensity at the wavelength of pollen included in the spectral data for verification, The maturity determination apparatus according to appendix 12, wherein the amount of scattering when the pollen to be processed is scattered is calculated by multiplying the calculated amount of scattering by the calculated ratio.

(Supplementary note 14) In the storage unit, a combination including one or a plurality of feature amounts calculated from values of a plurality of feature points included in spectrum data indicating pollen maturity is used as the reference data for the maturity of the pollen Remembered every time,
The collation unit calculates one or a plurality of feature amounts from values of a plurality of feature points included in spectrum data of each pixel included in an image acquired by photographing pollen to be processed with a hyperspectral sensor. The calculated one or more feature amounts are collated with one or more feature amounts included in the combination stored for each maturity of the pollen in the storage unit. The maturity determination apparatus as described in any one of -13.

(Supplementary Note 15) A maturity determination method executed by a computer,
The spectrum data acquired by photographing the airborne flower to be processed is compared with the reference data stored in the storage unit that stores the reference data based on the spectrum data indicating the maturity of the pollen for each maturity of the pollen. And
A maturity level determination method, wherein the maturity level of the pollen to be processed is determined based on a verification result of the verification process.

(Additional remark 16) The process to collate collates the spectrum data for every pixel contained in the image acquired by photographing the pollen used as the processing object with a hyperspectral sensor, and the reference data,
The maturity determination method according to appendix 15, wherein the determining process determines the maturity level of the pollen to be processed based on a matching result for each pixel by the matching process.

(Additional remark 17) The said determination process subtracts the past date corresponding to the maturity degree of the said pollen to be processed from the date when the scattering of pollen started in the past, and the pollen to be processed captures the subtraction result. The maturity determination method according to Supplementary Note 15 or 16, wherein a date on which scattering of the pollen to be processed starts is calculated by adding to the processed date.

(Additional remark 18) The determination process subtracts the past date corresponding to the maturity of the pollen to be processed from the date on which pollen scattering ended in the past, and the pollen to be processed captures the subtraction result. The maturity determination method according to any one of appendices 15 to 17, wherein a date on which the pollen to be processed ends is calculated by adding to the date that has been processed.

(Supplementary Note 19) In the storage unit, spectral data for verification, which is spectral data indicating pollen maturity, is stored as the reference data for each maturity of the pollen,
The process of collating collates the spectral data of each pixel included in the image acquired by photographing the pollen to be processed with a hyperspectral sensor and the spectral data for verification stored in the storage unit. The maturity determination method according to any one of supplementary notes 15 to 18, characterized in that:

(Additional remark 20) The amount of scattering for collation which is the amount of scattering when pollen corresponding to the spectrum data for verification is scattered is stored in the storage unit,
The determination process calculates a ratio of the spectral intensity at the pollen wavelength included in the spectral data corresponding to the maturity of the pollen to be processed with respect to the spectral intensity at the pollen wavelength included in the verification spectral data. The maturity determination method according to appendix 19, wherein the amount of scattering when the pollen to be processed is scattered is calculated by multiplying the calculated amount of scattering by the calculated ratio.

(Supplementary Note 21) In the storage unit, a combination including one or a plurality of feature amounts calculated from values of a plurality of feature points included in spectrum data indicating pollen maturity is used as the reference data. Remembered every time,
In the process of collating, one or a plurality of feature amounts are obtained from the values of a plurality of feature points included in spectrum data of each pixel included in an image obtained by photographing pollen to be processed with a hyperspectral sensor. The one or more feature amounts calculated and the one or more feature amounts included in the combination stored for each maturity of the pollen in the storage unit are collated The maturity determination method according to any one of 15 to 20.

DESCRIPTION OF SYMBOLS 100 Maturity determination apparatus 101 Input apparatus 102 Output apparatus 110 Storage part 112 Time series database 120 Control part 121 Reception part 122 Collation part 123 Determination part 300 Computer 301 CPU
302 Input Device 303 Monitor 304 Medium Reading Device 305 Interface Device 306 Wireless Communication Device 307 RAM
308 Hard disk device 309 Bus

Claims (9)

On the computer,
The spectrum data acquired by photographing the airborne flower to be processed is compared with the reference data stored in the storage unit that stores the reference data based on the spectrum data indicating the maturity of the pollen for each maturity of the pollen. And
A maturity determination program for executing a process of determining a maturity level of pollen to be processed based on a matching result obtained by the matching process. The process of collating collates spectral data for each pixel included in an image acquired by photographing the pollen to be processed with a hyperspectral sensor, and the reference data,
The maturity determination program according to claim 1, wherein the determining process determines the maturity level of the pollen to be processed based on a matching result for each pixel by the matching process.   In the determination process, a past date corresponding to the maturity of the pollen to be processed is subtracted from a date on which pollen scattering started in the past, and the subtraction result is set to the date on which the pollen to be processed is taken. The maturity determination program according to claim 1 or 2, wherein a date when scattering of the pollen to be processed starts is calculated by addition.   In the determination process, a past date corresponding to the maturity of the pollen to be processed is subtracted from the date on which pollen scattering ends in the past, and the subtraction result is set to the date on which the pollen to be processed is photographed. The maturity determination program according to any one of claims 1 to 3, wherein the date when the pollen to be processed ends is calculated by adding. In the storage unit, spectrum data for verification, which is spectrum data indicating pollen maturity, is stored as the reference data for each maturity of the pollen,
The process of collating collates the spectral data of each pixel included in the image acquired by photographing the pollen to be processed with a hyperspectral sensor and the spectral data for verification stored in the storage unit. The maturity determination program according to any one of claims 1 to 4, wherein: The storage unit stores a collation scattering amount that is a scattering amount when pollen corresponding to the verification spectrum data is scattered,
The determination process calculates a ratio of the spectral intensity at the pollen wavelength included in the spectral data corresponding to the maturity of the pollen to be processed with respect to the spectral intensity at the pollen wavelength included in the verification spectral data. The maturity determination program according to claim 5, wherein the amount of scattering when the pollen to be processed is scattered is calculated by multiplying the calculated amount of scattering by the calculated ratio. In the storage unit, a combination including one or a plurality of feature amounts calculated from values of a plurality of feature points included in spectrum data indicating pollen maturity is stored as the reference data for each maturity of the pollen. And
In the process of collating, one or a plurality of feature amounts are obtained from the values of a plurality of feature points included in spectrum data of each pixel included in an image obtained by photographing pollen to be processed with a hyperspectral sensor. The calculated one or more feature amounts are collated with one or more feature amounts included in the combination stored in the storage unit for each maturity of the pollen. Item 7. The maturity determination program according to any one of Items 1 to 6. A storage unit that stores reference data based on spectral data indicating pollen maturity for each pollen maturity;
A collation unit that collates spectral data acquired by photographing an airborne flower to be processed and the reference data stored in the storage unit;
A maturity determination apparatus comprising: a determination unit that determines a maturity level of pollen to be processed based on a result of verification by the verification unit. A maturity determination method executed by a computer,
The spectrum data acquired by photographing the airborne flower to be processed is compared with the reference data stored in the storage unit that stores the reference data based on the spectrum data indicating the maturity of the pollen for each maturity of the pollen. And
A maturity level determination method, wherein the maturity level of the pollen to be processed is determined based on a verification result of the verification process.