JP2020028272A - Determination system, determination device, determination method, and computer program - Google Patents

Abstract

To predict a proper harvest timing of farm products.SOLUTION: A determination system comprises: an environment information sensor which is installed on a culture place on which specific farm products are cultured and acquire environment information indicating an environment in the culture place; an imaging device installed in the culture place and imaging an image of the farm products; and a determination unit for, on the basis of the environment information and image information according to a growth period of the farm products of pieces of image information acquired from the images of the farm products, determining a residual integration value which is an integration value of a prescribed environment value to a proper harvesting of the farm products.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a technique for estimating a growth state of an agricultural product.

  Fruit and vegetables such as tomatoes have a complicated growth process. Therefore, it is difficult to accurately predict the growth state. Such problems are not limited to fruits and vegetables, but are common to all agricultural products.

  Techniques disclosed in Patent Documents 1 to 3 have been proposed as techniques for solving such a problem. Patent Literature 1 proposes a system that suppresses variations in the quality and termination of agricultural products. Patent Document 2 proposes a technique for estimating the end with high accuracy by using a satellite image or the like. Patent Literature 3 proposes a technique for predicting the amount of agricultural products satisfying a shipping standard based on the amount of agricultural products delivered from a producer.

JP-A-2006-049102 JP-A-2005-004909 JP-A-2006-118895

However, an appropriate harvest time is often delayed due to factors such as a change in weather just before the harvest time. For this reason, it was difficult to predict an appropriate harvest date for agricultural products.
In view of the circumstances described above, an object of the present invention is to provide a technology that enables prediction of more appropriate harvest timing of agricultural products.

  One embodiment of the present invention is installed in a cultivation place where a specific agricultural product is cultivated, an environment information sensor that acquires environment information indicating an environment in the cultivation place, and is installed in the cultivation place, and an image of the agricultural product is provided. Based on an imaging device for imaging, the environmental information, and image information corresponding to the growing time of the agricultural product among image information that is information obtained from the image of the agricultural product, a predetermined time until an appropriate harvest of the agricultural product. And a determination device for determining a remaining integrated value that is an integrated value of the environmental values.

  One embodiment of the present invention is an environmental information indicating an environment in a cultivation site where a specific agricultural product is cultivated, and image information corresponding to a growth time of the agricultural product among image information obtained from an image of the agricultural product. And a determination unit that determines a residual integrated value that is an integrated value of a predetermined environmental value until an appropriate harvest of the agricultural product based on the above.

  One embodiment of the present invention is the above-described determination device, further including the determination unit, the real environment information and the real image information that have been acquired before the harvest of the agricultural products actually harvested at appropriate timing, Based on the actual environment information or the actual value of the remaining integrated value from the time when the actual image information is acquired to the timing of the harvest, a result of a learning process performed for each of the agricultural products belonging to the same growth period is used. Thus, the remaining integrated value is determined.

  One embodiment of the present invention is a step in which an environment information sensor installed in a cultivation place where a specific agricultural product is cultivated acquires environmental information indicating an environment in the cultivation place, and an imaging device installed in the cultivation place The image of the agricultural product, and, based on the environmental information, image information according to the growth time of the agricultural product of the image information that is information obtained from the image of the agricultural product, based on the agricultural product, Determining a remaining integrated value that is an integrated value of a predetermined environmental value until an appropriate harvest.

  One embodiment of the present invention is an environmental information indicating an environment in a cultivation site where a specific agricultural product is cultivated, and image information corresponding to a growth time of the agricultural product among image information obtained from an image of the agricultural product. A determination step of determining a remaining integrated value that is an integrated value of a predetermined environmental value until an appropriate harvest of the agricultural product based on the above.

  One embodiment of the present invention is a computer program for causing a computer to function as the above determination system.

  One embodiment of the present invention is a computer program for causing a computer to function as the above-described determination device.

  According to the present invention, it is possible to predict more appropriate harvest timing of agricultural products.

FIG. 1 is a schematic block diagram illustrating a system configuration of a determination system 200 according to the present invention. FIG. 3 is a schematic block diagram illustrating a functional configuration example of a determination device 60. It is a figure showing the concept of a residual integrated value. It is a figure showing the example of classification information. It is a figure which shows the outline of an integrated value. 9 is a flowchart illustrating a specific example of a flow of a learning process of the determination device 60. 6 is a sequence chart showing a specific example of a flow of a determination process of a determination system 200.

Hereinafter, a specific configuration example of the present invention will be described with reference to the drawings.
FIG. 1 is a schematic block diagram showing the system configuration of the determination system 200 of the present invention. The determination system 200 is a system that determines an appropriate harvest timing of an agricultural product to be determined.

  First, a network configuration regarding the determination system 200 will be described. The determination system 200 includes a plurality of environment information sensors 10, a plurality of imaging devices 20, a control device 30, a log data storage device 40, a terminal device 50, and a determination device 60. The plurality of environment information sensors 10 and the plurality of imaging devices 20 are communicably connected to the control device 30, respectively. Communication performed by the plurality of environment information sensors 10 and the plurality of imaging devices 20 and the control device 30 may be realized by wireless communication or may be realized by wired communication. The control device 30 and the log data storage device 40 are communicably connected. The control device 30, the terminal device 50, and the determination device 60 are communicably connected via a network 80. The network 80 is configured using a communication network such as the Internet or a public line communication network. The determination device 60 is communicably connected to the weather forecast information providing device 70 via the network 80.

Next, each device related to the determination system 200 will be described.
The plurality of environment information sensors 10 and the plurality of imaging devices 20 are installed in the cultivation site 100 to be determined. In the cultivation place 100, one or more kinds of specific agricultural products are cultivated. For example, in the cultivation place 100, fruit and vegetables such as tomatoes and eggplants are cultivated. In this case, the determination device 60 of the determination system 200 determines an appropriate harvest timing of fruits and vegetables such as tomatoes and eggplants cultivated in the cultivation site 100.

  The environment information sensor 10 acquires specific information on the environment of the cultivation site 100 (hereinafter, referred to as “environmental information”). The environment information sensor 10 acquires, for example, one or more of values such as temperature, humidity, precipitation, sunshine time, and airflow in the cultivation site 100. As the environmental information sensor 10, one type of sensor may be installed in the cultivation site 100, or a plurality of types of sensors may be installed in the cultivation site 100. The environment information sensor 10 may be fixedly installed at a predetermined position, or may be installed movably. Each environment information sensor 10 transmits data indicating the acquired environment information to the control device 30. The data indicating the environment information transmitted from the environment information sensor 10 may be directly transmitted to the control device 30 by wireless communication or wired communication, or may be transmitted to the control device 30 via a relay device (not shown). Good.

  The imaging device 20 photographs the agricultural product to be determined cultivated in the cultivation site 100. The imaging device 20 may be configured to image the agricultural product from a predetermined imaging position in a predetermined imaging direction with a predetermined imaging parameter (angle of view, magnification, etc.). The imaging device 20 may be fixedly installed at a predetermined position and a predetermined direction, may be installed at a predetermined position so that the imaging direction can be changed, or may be movably installed. . For example, the imaging device 20 may be configured to move in the cultivation place 100 by being fixed to a moving body that moves along a predetermined guide, or may be configured to be cultivated by being fixed to a flying body such as a drone. It may be configured to move within the place 100. The imaging device 20 transmits data of an image obtained by shooting (hereinafter, referred to as a “shot image”) to the control device 30. The imaging device 20 may transmit the identification information of the own device in association with the data of the captured image. The captured image data transmitted from the imaging device 20 may be directly transmitted to the control device 30 by wireless communication or wired communication, or may be transmitted to the control device 30 via a relay device (not shown).

  The control device 30 is configured using an information processing device such as a personal computer or a PLC (Programmable Logic Controller). The control device 30 receives environment information data from the environment information sensor 10. The control device 30 records the received environmental information data in the log data storage device 40 in association with the date and time information. The recorded date and time information may be the date and time information when the environment information data was acquired by the environment information sensor 10, the date and time information when the environment information data was received by the control device 30, or the log data. The date and time information recorded in the storage device 40 may be used. The control device 30 receives data of a captured image from the imaging device 20. The control device 30 records the received captured image data in the log data storage device 40 in association with date and time information. The recorded date and time information may be the date and time information at which the captured image data was obtained by the imaging device 20, the date and time information at which the captured image data was received by the control device 30, or the log data storage. The date and time information recorded in the device 40 may be used.

  The log data storage device 40 is configured using a storage device such as a magnetic hard disk device or a semiconductor storage device. The log data storage device 40 stores a log of data obtained by the environment information sensor 10 and the imaging device 20 installed in the cultivation site 100.

  The terminal device 50 is a device having an information processing function such as a personal computer, a server, a smartphone, a tablet, a smart speaker, and a television receiver. The terminal device 50 is used by a user such as a manager or a manager of the cultivation site 100, for example. The terminal device 50 receives information about the harvest time of the agricultural product from the determination device 60 via the network 80. The terminal device 50 outputs the received information to the user in a predetermined manner. For example, the terminal device 50 may output information about the harvest time of the produce by displaying an image on a display, or may output information about the harvest time of the produce by voice.

  The determination device 60 is configured using an information processing device such as a personal computer or a server device. FIG. 2 is a schematic block diagram illustrating an example of a functional configuration of the determination device 60. The determination device 60 includes a communication unit 61, a log storage unit 62, a learning information storage unit 63, a classification information storage unit 64, a learning result storage unit 65, and a control unit 66.

  The communication unit 61 is configured using a communication interface. The communication unit 61 performs data communication with another device via the network 80. For example, the communication unit 61 receives data from the control device 30. For example, the communication unit 61 transmits data indicating the determination result to the terminal device 50.

  The log storage unit 62 is configured using a storage device such as a magnetic hard disk device or a semiconductor storage device. The log storage unit 62 stores environment information and a log of a captured image. The log storage unit 62 stores, for example, a record in which date and time information and environment information are associated with each other. The log storage unit 62 further stores, for example, a record in which date and time information is associated with a captured image.

  The learning information storage unit 63 is configured using a storage device such as a magnetic hard disk device or a semiconductor storage device. The learning information storage unit 63 stores learning information. The learning information is data used when the learning unit 663 of the control unit 66 performs the learning process. The learning information includes, for example, evaluation information indicating whether or not the harvest timing was appropriate for the agricultural products already harvested in the cultivation plant 100, and a captured image of each agricultural product captured before the harvest (hereinafter, ““ Real image information), real image information indicating environment information acquired before harvesting, and remaining integration at the timing when the data of the real individual image or the real environment information is acquired. Information indicating the actual value of the value may be associated information. The real image information may be, for example, information indicating the color of the agricultural product shown in the real individual image, or information indicating the size of the agricultural product on the real individual image.

  Learning information, for example, for agricultural products that have already been harvested at appropriate timing in the cultivation plant 100, real image information obtained from real individual images taken before harvest, real environment information obtained before harvest, Information indicating the actual value of the remaining integrated value at the timing when the data of the real individual image or the real environment information is acquired may be the information associated with the actual integrated image. The remaining integrated value indicates an integrated value of specific environmental information values from that day to the optimal harvest timing. The learning information may be further associated with the weather forecast information at the time when each real environment information or real individual image is obtained. The weather forecast information is information indicating a weather forecast for an area including the cultivation site 100. The weather forecast information is information indicating forecast values such as weather, temperature, humidity, and atmospheric pressure after the target date.

  FIG. 3 is a diagram illustrating the concept of the remaining integrated value. In the example of FIG. 3, the environment information represented by the remaining integrated value is a temperature value. When the temperatures of the day (eg, maximum temperature, average temperature, minimum temperature, etc.) are integrated for each day, a value integrated from a certain reference date to an optimal harvest timing is referred to as a residual integrated value. In the example of FIG. 3, the remaining integrated value is 0 degree on the day of harvest, which is the optimal timing. The fact that the remaining integrated value is 0 degrees indicates the optimal timing for harvesting. When the remaining integrated value is 40 degrees, the timing at which the temperature reaches 40 degrees when the temperature is integrated every day from that day is the optimal harvest timing. Therefore, when the remaining integrated value is 40 degrees and the temperature of the day is 40 degrees, it indicates that the next day is the optimal harvest timing. If the remaining integrated value is 40 degrees and the temperatures of the current day and the next day (one day later) are 20 degrees, respectively, it indicates that two days later is the optimal harvest timing. FIG. 3 shows such an example. Even if the remaining integrated value is 40 degrees, if the air temperature is 10 degrees every day after that day, it indicates that four days later is the optimal harvest timing. It should be noted that, based on the value of the remaining integrated value, the harvester may appropriately change the harvest timing to a more suitable one. For example, the harvest timing may be changed according to circumstances such as whether the sale is performed immediately after the harvest or whether the product is transported to a remote location and then sold.

  The correspondence between each remaining integrated value and the number of days until harvesting shown in FIG. 3 is only one specific example. Even if the remaining integrated value is the same, the number of days until the optimal harvest changes depending on the value of the temperature after that day.

  Returning to the description of FIG. The learning information stored in the learning information storage unit 63 is given to the determination device 60 in advance by a predetermined means. For example, the learning information may be given by recording the learning information recorded on a storage medium such as a USB memory or a CD-ROM in the learning information storage unit 63. For example, the learning information may be provided to the learning information storage unit 63 of the determining device 60 by transmitting the learning information to the determining device 60 from another information processing device. For example, with respect to the log information stored in the log storage unit 62, evaluation information indicating whether or not the user's harvest timing was appropriate, and an actual individual image extracted from the captured image recorded as the log information And the actual value of the actual environment information or the actual value of the remaining integrated value corresponding to the actual individual image calculated based on the actual harvesting timing, thereby generating learning information, and the learning information storage unit. 63 may be provided.

  The classification information storage unit 64 is configured using a storage device such as a magnetic hard disk device or a semiconductor storage device. The classification information storage unit 64 stores the classification information. The classification information is information used to classify each captured image as an image at any time (hereinafter referred to as “growth time”) from the flowering time to a date suitable for harvesting. In addition, the classification information may further include information indicating which learning result is used when performing the determination process using the captured image at the time of each classification result.

  FIG. 4 is a diagram illustrating a specific example of the classification information. The classification information illustrated in FIG. 4 includes a plurality of records having three values of a classification identifier, a classification condition, and a use model. The classification identifier indicates a group identifier in the classification result. The classification condition indicates a condition for classification into the group indicated by the classification identifier. The usage model indicates the type of the feature amount used for the learning process and the determination process of the image classified into the group indicated by the classification identifier.

  For example, the record described in the first row has values of “A”, “H> 25”, and “R / G” as a classification identifier, a classification condition, and a use model, respectively. H indicates the average value of the hues of the captured image. R indicates the average value of the R component of the image. G indicates the average value of the G component of the image. When the average value of the hues of all the pixels of the captured image is larger than 25, this record is classified into the group of the identifier A, and the determination process is performed on the captured image classified into the group of the identifier A. In this case, it is shown that the learning result obtained by the learning process using the R / G value of the actual individual image as the feature value is used. It should be noted that the group of identifiers A is classified with the intention of being agricultural products from immediately before harvest to four days before harvest.

  For example, the record described in the second row has values of “B”, “H ≦ 25”, and “R / G + integrated value” as a classification identifier, a classification condition, and a use model, respectively. The integrated value indicates the integrated value of the value of the specific environmental information from the time of flowering until the day when the image was taken. The integrated value may be, for example, an integrated value of the temperature between the time of flowering and the day on which the image was taken. FIG. 5 is a diagram showing an outline of the integrated value. FIG. 5 shows an example in which the integrated value is the integrated value of the temperature. On the day of flowering, the integrated value is 0 ° C. Thereafter, as the day elapses, the integrated value increases. The second record in FIG. 4 indicates that when the average value of the hues of all the pixels of the captured image is equal to or less than 25, the record is classified into the group of the identifier B, and the photographed image is classified into the group of the identifier B. When the determination process is performed on the image, the learning obtained by the learning process using a combination of the R / G value of the real individual image and the integrated value at the time when the real individual image was captured is used as a feature amount. The results are used. It should be noted that the group of identifiers B is classified with the intention of being agricultural products before 5 days before harvest.

The average value of the hue is shown as a specific example of the classification condition, but other conditions may be used as long as the image can be classified at any time between the flowering time and a date suitable for harvesting. May be used.
Although only the R / G, the R / G, and the integrated value are used as the feature amounts of the use model, the learning process may be performed using other feature amounts. For example, the average value of the hue (H above) may be used as the feature amount, or a combination of H and the integrated value may be used as the feature amount.

  The learning result storage unit 65 is configured using a storage device such as a magnetic hard disk device or a semiconductor storage device. The learning result storage unit 65 stores information indicating the learning result obtained by the learning process of the learning unit 663 of the control unit 66. As will be described later, the learning unit 663 performs a learning process for each group that is the result of classification by the classification unit 662. Therefore, the learning result storage unit 65 stores information indicating the learning result for each group. For example, the learning result storage unit 65 stores a learning result belonging to group A and a learning result belonging to group B, respectively. The learning result stored by the learning result storage unit 65 is used by the determination unit 665.

  The control unit 66 is configured using a processor such as a CPU (Central Processing Unit) and a memory connected by a bus. The control unit 66 functions as a log control unit 661, a classification unit 662, a learning unit 663, a detection unit 664, a determination unit 665, and an information providing unit 666 by the processor executing the program.

  Note that all or a part of the log control unit 661, the classifying unit 662, the learning unit 663, the detecting unit 664, the determining unit 665, and the information providing unit 666, which are realized by the processor executing the program, are provided by an ASIC (Application Specific Integrated Integrated Circuit). Circuits, PLDs (Programmable Logic Devices), FPGAs (Field Programmable Gate Arrays), and other hardware may be used. The program may be recorded on a computer-readable recording medium. The computer-readable recording medium is, for example, a portable medium such as a flexible disk, a magneto-optical disk, a ROM, a CD-ROM, a semiconductor storage device (for example, SSD: Solid State Drive), a hard disk or a semiconductor storage built in a computer system. It is a storage device such as a device. The program may be transmitted via a telecommunication line.

  The log control unit 661 receives environmental information and data of a captured image from the control device 30. The log control unit 661 records the received data as a log in the log storage unit 62 in association with date and time information.

  The classifying unit 662 classifies the actual individual image used for the learning process and the individual image used for the determination process in an image at any time between the flowering time and a date suitable for harvesting. The classification unit 662 performs a classification process based on the classification condition of the classification information stored in the classification information storage unit 64. The classification unit 662 classifies the image into any one of a group of a classification identifier A and a group of a classification identifier B, for example.

  The learning unit 663 uses, for each classified group, only the feature amount defined in the use model of the learning information belonging to the group among the learning information stored in the learning information storage unit 63. To do machine learning. The learning unit 663 obtains a learning result for obtaining a value of a remaining integrated value up to an optimal harvest among a plurality of values included in the learning information. For the learning unit 663, for example, a machine learning technique for generating or updating a classifier by supervised learning is applied. Specific examples of the machine learning technology include SVM (Support Vector Machine) and DL (Deep Learning). When performing the learning process using, for example, real individual images belonging to group A, the learning unit 663 uses R / G of each real individual image as a feature amount. When performing the learning process using, for example, real individual images belonging to group B, the learning unit 663 uses a combination of R / G and an integrated value of each real individual image as a feature amount.

  The detection unit 664 detects an image of an individual agricultural product to be processed from the captured image. For example, when the agricultural product to be processed is a tomato, and the photographed image includes ten cultivated tomatoes, the detection unit 664 detects each of the ten tomatoes. The detecting unit 664 extracts an image of each detected tomato (hereinafter, referred to as an “individual image”). The detection unit 664 determines the position of the agricultural product in the extracted cultivation site 100 based on the identification information of the imaging device associated with the captured image. The detection unit 664 outputs each of the extracted individual images to the classification unit 662 and the determination unit 665 as an image to be processed.

  The determination unit 665 acquires the current environment information from the log control unit 661. In addition, the determination unit 665 acquires, from the detection unit 664, an individual image in which an individual agricultural product to be subjected to the determination processing is captured, and a classification result of the individual image by the classification unit 662. The determination unit 665 acquires, from the individual image, a feature amount defined as a use model according to the classification result as image information. The determination unit 665 is photographed as an individual image based on the acquired environment information and image information and the learning result corresponding to the group of the classification result among the learning results stored in the learning result storage unit 65. The remaining integrated value of agricultural products is determined. The determination unit 665 may use the weather forecast information in the determination process in addition to the environment information and the image information. In this case, a learning process needs to be performed so that the determination process is performed based on the weather forecast information. The weather forecast information may be acquired from the weather forecast information providing device 70 via the network 80, for example. The weather forecast information providing device 70 is, for example, a server installed by the Meteorological Agency or a specific corporation or individual, and is a device that provides weather forecast information.

  The information providing unit 666 generates provided information including information indicating a result of the determination by the determining unit 665. For example, the provided information includes the individual image that has been subjected to the determination process, the remaining integrated value indicating the result of the determination process performed by the determination unit 665 on the individual image, and the cultivation site 100 of the agricultural product photographed in the individual image. And information indicating a location.

  FIG. 6 is a sequence chart showing a specific example of the flow of the learning process of the determination device 60. First, the classification unit 662 classifies the learning information stored in the learning information storage unit 63 into each group based on the classification condition of the classification information (step S101). The learning unit 663 acquires a feature amount defined in the use model of the classification information for each group, and performs a learning process (step S102). The learning unit 663 records the learning result obtained for each group in the learning result storage unit 65 (Step S103). With the above processing, the learning processing by the determination device 60 ends.

  FIG. 7 is a sequence chart showing a specific example of the flow of the determination process of the determination system 200. Each environment information sensor 10 acquires environment information at a predetermined timing and transmits the acquired environment information to the control device 30 (step S201). Each imaging device 20 performs imaging at a predetermined timing, and transmits a captured image to the control device 30 (Step S202).

  The control device 30 records the environment information received from the environment information sensor 10 and the captured image received from the imaging device 20 in the log data storage device 40 (Step S203). Then, the control device 30 transmits the environment information received from the environment information sensor 10 and the captured image received from the imaging device 20 to the determination device 60 (Step S204).

  The log control unit 661 of the determination device 60 receives the environment information and the captured image from the control device 30. The log control unit 661 records the received environment information and the captured image as a log in the log storage unit 62 in association with the time information (step S205). The detection unit 664 detects an agricultural product that is captured as a subject in the newly acquired captured image (Step S206). The detection unit 664 assigns a label to the detected image (individual image) of each agricultural product (step S207). The classification unit 662 classifies the labeled individual images into groups (step S208). The determination unit 665 stores the received environment information, image information (feature amount) obtained according to the group of the classification result regarding the image information of the agricultural product to be determined, and the learning information storage unit 63. The remaining integrated value of the agricultural product to be determined is determined based on the learning result corresponding to the group of the classification result among the learning results (step S209). The information providing unit 666 generates provided information including a result of the determination process (Step S210). The information providing unit 666 transmits the provided information to the terminal device 50 associated with the cultivation site 100 subjected to the determination processing (Step S211). The terminal device 50 outputs the received provided information to the user.

  According to the determination system 200 configured as described above, the remaining integrated value is determined as information indicating an appropriate timing of harvest for the agricultural products cultivated in the cultivation site 100. The value of the remaining integrated value itself is less likely to be affected by changes in weather after the timing at which the determination is made. In other words, although the date, which is a timing suitable for harvesting, changes according to the actual temperature and the like after the timing at which the determination is made, the remaining integrated value itself at the timing at which the determination is made is uniquely determined. By providing such a residual integrated value to the user as information indicating an appropriate harvest timing, it becomes possible for the user to more accurately determine a more suitable harvest timing.

  Such a determination system 200 is particularly effective for a type of agricultural product in which the integrated value of environmental information from a predetermined event (for example, flowering) to an optimal harvest timing of the agricultural product is constant. Such agricultural products include, for example, fruits and vegetables such as tomatoes. In FIG. 3 described above, the temperature has been described as a specific example of the remaining integrated value, but the remaining integrated value does not necessarily need to be an integrated value related to the temperature. For example, it may be an integrated value of sunshine hours.

  In particular, in the determination system 200, in the determination processing for obtaining the remaining integrated value, image information (feature amount) corresponding to the classification result of the individual image obtained at that time and learning performed using the image information. The learning result of the processing is used. The classification result is information indicating at which time between the flowering time and the date suitable for harvesting the image is. Therefore, the determination is made using different characteristic amounts depending on the timing of the agricultural crop to be determined between the flowering time and the date suitable for harvesting. In other words, depending on the timing of the crop to be determined between the flowering time and the date suitable for harvesting, the remaining amount can be more accurately determined using the feature values and learning results suitable for that time. The integrated value can be determined.

  In the determination system 200, the remaining integrated value is determined based not only on the environment information but also on the image information of the individual image. Therefore, it is possible to determine the remaining integrated value more accurately than when the remaining integrated value is determined based only on the environment information.

(Modification)
Any means may be adopted as means for causing the environment information to reach the determination device 60 from each environment information sensor 10. In the above description, the environment information is transmitted from each environment information sensor 10 to the determination device 60 via the control device 30. For example, the environment information is transmitted from each environment information sensor 10 to the determination device 60 without passing through the control device 30. May be done. Further, for example, one or more of the environmental information sensors 10 collect environmental information from the other environmental information sensors 10 and collectively transmit one or a plurality of environmental information to the control device 30 or the determination device 60. Is also good. The same applies to the imaging device 20.

  The determination device 60 does not necessarily need to be configured as one device. For example, the determination device 60 may be configured using a plurality of information processing devices. The plurality of information processing devices constituting the determination device 60 may be communicably connected via a communication path such as the network 80, and may be configured as a system such as a cluster machine or a cloud.

  The determination device 60 may be configured as a device or a system that does not include the learning unit 663. In this case, the process performed by the learning unit 663 described above may be executed by another device or system as a learning device. In this case, the determination device including the determination unit 665 acquires the data of the learning result from the learning device and performs the determination process.

  A storage battery or a charger may be connected to the environment information sensor 10. With this configuration, it is possible to reduce restrictions on the installation location of the environmental information sensor 10. For example, it is possible to install the environmental information sensor 10 even in a place where electricity does not pass. In addition, a device that generates power using natural energy may be connected to the environment information sensor 10. For example, a generator such as a solar panel or a wind power generator may be connected. The environment information sensor 10 may operate based on the electric power generated by the device that performs such power generation.

  The determination unit 665 and the learning result storage unit 65 may be provided in the control device 30. With this configuration, it is possible to more quickly determine the remaining integrated value of agricultural products in each individual image.

  The learning unit 663 may perform the learning process for each set of a plurality of pieces of learning information. For example, the learning unit 663 may perform a learning process based on learning information prepared in advance for each type or variety of agricultural products. In this case, the learning result storage unit 65 stores the learning results obtained for each type or each type for each group of the classification results. The determination unit 665 selects an optimal learning result to be used in accordance with the type and variety of the agricultural product shown in the individual image to be processed, and performs residual integration using the selected optimal learning result. Determine the value. With this configuration, it is possible to determine the remaining integrated value with higher accuracy. The set of a plurality of pieces of learning information is not limited to the above-described patterns (for each type and each type). For example, a plurality of sets of learning information may be used according to the cultivation method (house hydroponic, house soil cultivation, alley, etc.), the season (spring, summer, autumn and winter).

  In the above-described embodiment, an example has been described in which a suitable feature amount (use model) is known for each group of the classification results. However, it may not be known which feature amount is suitable for each group of the classification results. In this case, before the learning process is performed, the value of the use model of the classification information need not be recorded. In this case, the learning unit 663 may perform the learning process as described below. The learning unit 663 performs a learning process for each of a plurality of use model candidates defined in advance for each group. That is, a learning result is obtained for each combination of a group and a usage model. The determination unit 665 performs a determination process using the learning information and each learning result. At this time, the learning information used for the learning process may be used for the determination process, or the learning information not used for the learning process (prepared for the determination process) may be used for the determination process. You may. The learning unit 663 compares, for each group, the obtained determination result with the actual value of the remaining integrated value of the learning information, and selects the learning result with the smallest difference. The learning unit 663 records the usage model used for the selected learning result as the value of the usage model in the classification information storage unit 64, and records the selected learning result in the learning result storage unit 65. With this configuration, a suitable use model is automatically selected even if it is unknown which model is optimal for each group.

  As described above, the embodiments of the present invention have been described in detail with reference to the drawings. However, the specific configuration is not limited to the embodiments and includes a design and the like within a range not departing from the gist of the present invention.

Reference Signs List 100 cultivation plant, 200 judgment system, 10 environmental information sensor, 20 imaging device, 30 control device, 40 log data storage device, 50 terminal device, 60 judgment device, 61 communication unit, 62 communication unit Log storage unit, 63: learning information storage unit, 64: classification information storage unit, 65: learning result storage unit, 66: control unit, 661: log control unit, 662: classification unit, 663: learning unit, 664 ... detection Section, 665 ... determination section, 666 ... information providing section

Claims (7)

An environment information sensor that is installed in a cultivation place where a specific agricultural product is cultivated and acquires environment information indicating an environment in the cultivation place,
An imaging device that is installed in the cultivation place and captures an image of the agricultural product,
Based on the environmental information and image information corresponding to the growth time of the agricultural product among image information that is information obtained from the image of the agricultural product, an integrated value of a predetermined environmental value until an appropriate harvest of the agricultural product A determination device for determining a remaining integrated value that is
A judgment system comprising:   Based on environmental information indicating an environment in a cultivation place where a specific agricultural product is cultivated, and image information corresponding to the growing time of the agricultural product among image information that is information obtained from an image of the agricultural product, A determination unit that determines a residual integrated value that is an integrated value of a predetermined environmental value until an appropriate harvest of the target.   Further, the determination unit may be configured to obtain the real environment information, the real image information, and the real environment information or the real environment information or the real image information that have been obtained before the harvest of the agricultural products actually harvested at appropriate timing. 3. The remaining integrated value is determined by using a result of a learning process performed for each of the agricultural products belonging to the same growth period, based on the actual value of the remaining integrated value up to the timing. Determination device. An environment information sensor installed in a cultivation place where a specific agricultural product is cultivated, and acquiring environmental information indicating an environment in the cultivation place,
An imaging device installed in the cultivation site, imaging an image of the agricultural product,
Based on the environmental information and image information corresponding to the growth time of the agricultural product among image information that is information obtained from the image of the agricultural product, an integrated value of a predetermined environmental value until an appropriate harvest of the agricultural product Determining the remaining integrated value.   Based on environmental information indicating an environment in a cultivation place where a specific agricultural product is cultivated, and image information corresponding to the growing time of the agricultural product among image information that is information obtained from an image of the agricultural product, A determining step of determining a residual integrated value that is an integrated value of a predetermined environmental value until an appropriate harvest of the above.   A computer program for causing a computer to function as the determination system according to claim 1.   A computer program for causing a computer to function as the determination device according to claim 2.

Images