JP7644665B2 - Field management method, field management system, and field management program - Google Patents

Description

The present invention relates to a farm field management method, a farm field management system, and a farm field management program.

In recent years, there has been research into analyzing cultivation management using information about work carried out in farm fields. In order to analyze cultivation management, the farm field where work is carried out may be registered in a system.

Patent Document 1 discloses a technology that identifies the shape of a field based on satellite photos taken from the sky and travel path data of a work implement traveling within the field.

JP 2020-101446 A

The technology described in Patent Document 1 requires travel path data of the working equipment traveling within the field, and when the travel path data is insufficient, the field cannot be detected. In addition, to identify the shape of the field, satellite photos are used that can detect and divide the area of each field. However, depending on the time when the satellite photos were taken, there are cases where the areas of multiple adjacent fields cannot be divided from the image captured in the satellite photos.

In view of the above situation, one of the objectives of the present disclosure is to reduce the amount of input operations of field information by users and to support the analysis of cultivation management by using images captured from the sky. Other objectives can be understood from the following description and explanation of the embodiment.

The means for solving the problems will be explained below using the numbers and symbols used in the description of the embodiment of the invention. These numbers and symbols are added in parentheses for reference purposes to show an example of the correspondence between the description of the claims and the description of the embodiment of the invention. Therefore, the description in parentheses should not be interpreted as limiting the scope of the claims.

A field management method according to one embodiment for achieving the above object includes detecting a contour (510) of an area (500) including the field (400) in a plurality of captured images taken from the air at different times of an area including at least the same plurality of fields (400). The field management method also includes detecting a field area of the field (400) surrounded by the contour (510) based on the contour (510) detected in the plurality of captured images.

A farm field management method according to one embodiment for achieving the above object includes detecting work performed in the farm field (400) based on changes in the farm field (400) in multiple captured images taken from the air over an area including at least the same multiple farm fields (400) at different times. The farm field management method also includes outputting work information representing the detected work.

The farm field management system (1000) according to one embodiment for achieving the above object includes a contour detection unit (150) and a farm field management unit (160). The contour detection unit (150) detects a contour (510) of an area (500) including the farm field (400) in a plurality of captured images taken from the air at different times of an area including at least the same plurality of farm fields (400). The farm field management unit (160) detects the farm field area of the farm field (400) surrounded by the contour (510) based on the contour (510) detected in the plurality of captured images.

The farm field management system (1000) according to one embodiment for achieving the above object includes a work detection unit (170) and an output unit (180). The work detection unit (170) detects work performed in the farm field (400) based on changes in the farm field (400) in a plurality of captured images taken from above an area including at least the same plurality of farm fields (400) at different times. The output unit (180) outputs work information representing the detected work.

In one embodiment of the field management program (300) for achieving the above object, the program causes the calculation device (120) to detect the contour (510) of an area (500) including the field (400) in a plurality of captured images taken from the air at different times of an area including at least the same plurality of fields (400). The field management program (300) also causes the calculation device (120) to detect the field area of the field (400) surrounded by the contour (510) based on the contour (510) detected in the plurality of captured images.

To achieve the above object, a field management program (300) according to one embodiment causes a computing device (120) to detect work performed in a field (400) based on changes in the field (400) in multiple captured images taken from the air over an area including at least the same multiple fields (400) at different times. The field management program (300) also causes the computing device (120) to output work information representing the detected work.

The above embodiment reduces the amount of input operations for field information by the user and can assist in the analysis of cultivation management.

FIG. 1 is a configuration diagram of a farm land management system according to an embodiment. FIG. 2 is a diagram for explaining an area imaged by an imaging device in one embodiment. FIG. 2 is a diagram illustrating an image captured by an imaging device in one embodiment. FIG. 2 is a diagram illustrating an image captured by an imaging device in one embodiment. 1 is a configuration diagram of a farm land management device according to an embodiment; FIG. 2 is a diagram illustrating functional blocks executed by a farm land management system according to an embodiment. FIG. 2 is a configuration diagram of a terminal according to an embodiment. 4 is a flowchart showing a process performed by a farm land management system in one embodiment.

(Embodiment 1)
A farm field management system 1000 according to this embodiment of the present invention will be described with reference to the drawings. In this embodiment, as shown in Fig. 1, the farm field management system 1000 includes a farm field management device 100 and a terminal 200. The farm field management device 100 is communicatively connected to the terminal 200 and an image acquisition device 50 via a network 20, for example the Internet.

2, the image acquisition device 50 acquires image information representing captured images of a plurality of fields 400 captured from the sky by an imaging device 60, for example, an artificial satellite. The imaging device 60 captures a plurality of images from the sky at different times of at least the same plurality of fields 400, for example, an area including a first field 400-1, a second field 400-2, a third field 400-3, and a fourth field 400-4 adjacent to a road. For example, as shown in FIGS. 3 and 4, the imaging device 60 captures an image of the field 400 from the sky at a time before the crops in the first area 500-1 including the first field 400-1 and the second field 400-2 are harvested and after the crops in the second area 500-2 including the third field 400-3 are harvested. Furthermore, the imaging device 60 captures images of the field 400 from the sky before the crops in the fourth area 500-4, which includes the first field 400-1, are harvested and after the crops in the fifth area 500-5, which includes the second field 400-2 and the third field 400-3, are harvested. The image acquisition device 50 acquires image information representing the multiple captured images captured by the imaging device 60 from the imaging device 60 and transmits the image information to the field management device 100 shown in FIG. 1.

The farm field management device 100 detects a farm field area that is an area of the farm field 400 based on a plurality of captured images acquired from the image acquisition device 50. For example, the farm field management device 100 detects a contour 510 of an area 500 that includes the farm field 400, and detects the farm field area of the farm field 400 based on the detected contour 510.

The farm field management device 100 also detects the work, such as planting and harvesting, that was carried out in the farm field 400 between the two captured images based on the multiple captured images taken at different times. For example, in the example shown in Figures 3 and 4, the farm field management device 100 detects that crops have been harvested in the second farm field 400-2.

In this way, the farm field management device 100 detects the field area of the field 400 and the work performed in the field 400 based on multiple captured images. A user, such as a worker performing work in the field 400 or the owner of the field 400, can grasp the field area of the field 400 detected by the field management device 100 and the work performed in the field 400, and analyze cultivation management. Therefore, the field management device 100 reduces the input operation of information about the field 400 by a user, such as a worker performing work in the field 400 or the owner of the field 400, and supports the user's analysis of cultivation management.

(Configuration of the farm management system)
The configuration of the farm field management device 100 will be described. As shown in FIG. 5, the farm field management device 100 includes an input/output device 110, a calculation device 120, a communication device 130, and a storage device 140. The farm field management device 100 is, for example, a computer. Information for the calculation device 120 to execute processing is input to the input/output device 110. The input/output device 110 outputs a result of the processing executed by the calculation device 120. The input/output device 110 includes various input devices and output devices, such as a keyboard, a mouse, a microphone, a display, a speaker, and a touch panel. The input/output device 110 may be omitted.

The communication device 130 is electrically connected to the network 20 and communicates with each device via the network 20. The communication device 130 transfers image information acquired from the image acquisition device 50 to the calculation device 120. The communication device 130 also transfers signals generated by the calculation device 120 to the terminal 200. The communication device 130 includes various interfaces, such as a network interface card (NIC) and a universal serial bus (USB).

The storage device 140 stores various data for detecting the work area, such as the field management program 300. The storage device 140 is used as a non-transitory tangible storage medium for storing the field management program 300. The field management program 300 may be provided as a computer program product recorded on a computer-readable storage medium 1, or may be provided as a computer program product downloadable from a server.

The computing device 120 reads and executes the field management program 300 from the storage device 140, and performs various data processing to detect the field area and the work performed in the field 400. For example, the computing device 120 includes a central processing unit (CPU) and the like.

The computing device 120 reads and executes the field management program 300, thereby realizing an outline detection unit 150, a field detection unit 160, a work detection unit 170, and an output unit 180, as shown in FIG. 6. The outline detection unit 150 detects an outline 510 of an area 500 including the field 400 in the captured image. The field detection unit 160 detects the field area of the field 400 based on the outline 510 of the detected area 500. The work detection unit 170 detects work performed in the field 400 based on the captured image. The output unit 180 outputs field information related to the field 400.

Next, the configuration of the terminal 200 will be described. As shown in FIG. 7, the terminal 200 includes an input/output device 210, a computing device 220, a communication device 230, and a storage device 240. The terminal 200 includes, for example, a computer, a tablet, a mobile phone, etc. Information is input to the input/output device 210 for the computing device 220 to execute processing. The input/output device 210 also outputs the results of the processing executed by the computing device 220. The input/output device 210 includes various input devices and output devices, for example, a keyboard, a mouse, a microphone, a display, a speaker, a touch panel, etc.

The communication device 230 is electrically connected to the network 20 and communicates with the farm field management device 100 via the network 20. The communication device 230 transfers signals acquired from the farm field management device 100 to the calculation device 220. The communication device 230 also transfers signals generated by the calculation device 220 to the farm field management device 100. The communication device 230 includes various interfaces such as a transceiver used for wireless communication such as a wireless LAN (Local Area Network) or a cellular network, a NIC (Network Interface Card), and a USB (Universal Serial Bus).

The storage device 240 stores various data for displaying the field information, such as the display program 310. The storage device 240 is used as a non-transitory tangible storage medium for storing the display program 310. The display program 310 may be provided as a computer program product recorded on a computer-readable storage medium 2, or may be provided as a computer program product downloadable from a server.

The computing device 220 reads and executes the display program 310, thereby implementing the display unit 250 in cooperation with the input/output device 210 as shown in FIG. 6. The display unit 250 acquires field information from the field management device 100 and displays the field information, for example, information representing the area of the field 400 and information representing the work performed in the field 400.

(Operation of the farm management system)
The imaging device 60 shown in Fig. 1 captures an image of an area including a plurality of farm fields 400 from above, and transmits image information representing the captured images to the image acquisition device 50. For example, the imaging device 60 periodically captures an image of the farm field 400, and transmits image information representing the captured images to the image acquisition device 50. The image acquisition device 50 stores the image information transmitted from the imaging device 60. The captured images may include radio wave images, such as synthetic aperture radar (SAR) images, which are less affected by weather and are captured by using radio waves, such as SAR images, of the farm field 400. The captured images may also include light wave images captured by receiving light waves, such as visible light.

The computing device 120 of the field management device 100 shown in FIG. 5 executes the field management program 300 and starts the process shown in FIG. 8, which is a field management method. For example, the computing device 120 executes the field management program 300 when a predetermined time is reached. The computing device 120 may also execute the field management program 300 in response to a request from the computing device 220 of the terminal 200. In this case, when an operation to detect the field 400 is input to the input/output device 210, the computing device 220 of the terminal 200 outputs a signal to the computing device 120 of the field management device 100 to execute the field management program 300.

In step S110, the contour detection unit 150 implemented by the computing device 120 acquires a plurality of captured images from the image acquisition device 50. The acquired plurality of captured images include images captured at different times of an area including at least the same plurality of fields 400. For example, the area captured in the captured images includes a first field 400-1, a second field 400-2, a third field 400-3, and a fourth field 400-4, as shown in FIG. 2.

In step S120, the contour detection unit 150 detects the contour 510 of the area 500 including the field 400 in the multiple captured images. For example, the contour detection unit 150 performs edge detection processing on the captured images to detect the contour 510 of the area 500 including the field 400. For example, the area 500 of the captured image has a different display form, such as color and gradation value, from the surrounding area, as shown in the example of FIG. 3. For example, when the first area 500-1 is before the crop is harvested and the second area 500-2 and the third area 500-3 are after the crop is harvested, the color of the first area 500-1 is different from the second area 500-2 and the third area 500-3. Also, in the SAR image, the energy of the electromagnetic wave received from the first area 500-1 is different from the energy of the electromagnetic wave received from the second area 500-2 and the third area 500-3. For this reason, the contour detection unit 150 performs edge detection processing on the captured image to detect a contour 510 of the area 500 in the captured image. The detected contour 510 includes a part of the field contour, which is the contour of the field 400, as shown in FIG. 3. Furthermore, the area 500 surrounded by the detected contour 510 may include the entire area of at least one field 400.

The contour detection unit 150 performs edge detection processing on a plurality of acquired captured images, for example, the example shown in FIG. 3. In the example shown in FIG. 3, the contour detection unit 150 detects the contour 510 of the first area 500-1 including the first field 400-1 and the second field 400-2. The contour detection unit 150 also detects the contour 510 of the second area 500-2 including the third field 400-3. Furthermore, the contour detection unit 150 detects the contour 510 of the third area 500-3 including the fourth field 400-4. For this reason, in the example shown in FIG. 3, the contour detection unit 150 detects a first contour 510-1 representing the field contour between the second field 400-2 and the third field 400-3, but does not detect the field contour between the first field 400-1 and the second field 400-2.

The contour detection unit 150 performs edge detection processing on a plurality of acquired captured images, for example, the example shown in FIG. 4. In the example shown in FIG. 4, the contour detection unit 150 detects the contour 510 of the fourth area 500-4, which includes the first field 400-1. The contour detection unit 150 also detects the contour 510 of the fifth area 500-5, which includes the second field 400-2 and the third field 400-3. Furthermore, the contour detection unit 150 detects the contour 510 of the sixth area 500-6, which includes the fourth field 400-4. Therefore, in the example shown in FIG. 4, the contour detection unit 150 detects the second contour 510-2 representing the field contour between the first field 400-1 and the second field 400-2, but does not detect the field contour between the second field 400-2 and the third field 400-3.

In this way, the contour detection unit 150 detects all or part of the field contour of the field 400 in each captured image. The contour detection unit 150 may further perform post-processing, such as filtering or binarization, on the captured image that has been subjected to edge detection processing in order to detect the contour 510. Furthermore, when the area surrounded by the detected contour 510 is smaller than a predetermined area, the contour detection unit 150 may exclude the corresponding contour 510 as not including the field 400.

In step S130 shown in FIG. 8, the field detection unit 160 detects the field area of the field 400 based on the contours 510 detected in the multiple captured images. For example, the field detection unit 160 detects the field 400 surrounded by the contours 510 by superimposing the contours 510 detected in the multiple captured images. The field detection unit 160 superimposes the multiple captured images that have been subjected to edge detection processing based on the latitude and longitude information of the area captured in the captured images. The field detection unit 160 detects the field 400 surrounded by the contours 510 by superimposing the contours 510 detected in the multiple captured images at the corresponding positions.

3 and 4, the field detection unit 160 superimposes the contour 510 of the region 500 at the corresponding position. The field detection unit 160 superimposes the contours 510 in the first region 500-1, the second region 500-2, the third region 500-3, the fourth region 500-4, the fifth region 500-5, and the sixth region 500-6 at the corresponding positions. As a result, the field detection unit 160 detects the first contour 510-1 between the second field 400-2 and the third field 400-3, and the second contour 510-2 between the first field 400-1 and the second field 400-2. For this reason, the field detection unit 160 detects the first field 400-1, the second field 400-2, and the third field 400-3 as different field areas. The field detection unit 160 also detects the fourth field 400-4, which does not have an adjacent field 400, as a field area.

In step S140 shown in FIG. 8, the work detection unit 170 detects work performed in the field 400 based on changes in the field 400 in images captured at different times. For example, in order to detect work performed in the field 400, the work detection unit 170 stores the work performed in the field 400 in association with the images captured before and after the work was performed. The work detection unit 170 detects, from among the changes in the stored captured images, a similar captured image that is most similar to the changes in the field 400 in the images captured at different times. The work detection unit 170 detects the work associated with the similar captured image as work performed in the field 400.

For example, in the example shown in FIG. 3, the first area 500-1 including the second field 400-2 is displayed in a display form representing crops, for example in a green color, and in the example shown in FIG. 4, the fifth area 500-5 including the second field 400-2 is displayed in a display form representing soil, for example in an earth color. In this case, the work detection unit 170 estimates that harvesting work has been performed in the second field 400-2 based on a change in the display form, for example color, of the second field 400-2 in two captured images, for example a light wave image captured using light waves (visible light). The work detection unit 170 may also estimate that cultivation work to plant crops has been performed in the field 400 when the display form in the field 400 has changed from one representing soil to one representing crops.

In step S150 shown in FIG. 8, the output unit 180 outputs field information related to the detected field 400 to the display unit 250 of the terminal 200. The field information includes area information representing the field area of the field 400 and work information representing the work performed in the field 400.

In step S160, the display unit 250 of the terminal 200 displays the field information on the input/output device 210 based on the field information received from the output unit 180 of the field management device 100. The display unit 250 displays, for example, an image showing the area of the field 400 detected on a map. The display unit 250 also displays an image showing the work performed in the field 400 in accordance with the area of the field 400. By checking the input/output device 210, the user can understand the field area of the field 400 and the work performed in the field 400, and analyze the cultivation management.

In this way, the farm field management system 1000 assists users in analyzing cultivation management.

(Modification)
The configuration described in the embodiment is an example, and the configuration can be changed as long as the function is not impaired. For example, the captured image captured by the imaging device 60 may include captured images captured by any method, or may include captured images captured by a plurality of different methods. For example, the captured image may include both an SAR image captured by using a synthetic aperture radar to capture the farm field 400, and a light wave image captured by receiving light waves.

In step S130 shown in FIG. 8, the field detection unit 160 may detect the field area of the field 400 using the contours 510 that satisfy the contour condition among the contours 510 detected from the multiple captured images. For example, the field detection unit 160 detects the field area of the field 400 using the contours 510 detected in at least a predetermined number of captured images among the multiple captured images. In this case, the field detection unit 160 determines whether the contours 510 detected in different captured images represent the same contour 510. For example, the field detection unit 160 determines whether the contours 510 represent the same contour 510 based on the extension direction of the contour 510 and the position of the contour 510. When the number of contours 510 determined to correspond to the same contour 510 among the contours 510 detected in different captured images is greater than a predetermined number, the field detection unit 160 uses the corresponding contours 510 to detect the field area of the field 400. The predetermined number may be a fixed value set in advance, or may be determined based on the number of captured images. For example, the predetermined number may be determined by multiplying the number of captured images by a predetermined ratio.

The work detection unit 170 shown in FIG. 6 may have artificial intelligence (AI) that estimates the work performed in the field 400 from images captured before and after the work is performed. The AI learns using data that combines the work performed in the field 400 with images captured before and after the work is performed. In step S140 shown in FIG. 8, the work detection unit 170 detects the work performed in the field 400 by inputting the captured images to the trained artificial intelligence.

The captured images used by the work detection unit 170 may include multiple captured images captured by multiple different methods. For example, the work detection unit 170 may detect work performed in the field 400 using captured images captured by multiple different methods, such as a Normalized Difference Vegetation Index (NDVI) image that indicates the presence or absence and activity of vegetation, a light wave image, and a SAR image. The work detection unit 170 detects work performed in the field 400 based on each captured image before and after the work is performed and each captured image captured by the imaging device 60.

The above-described embodiments and modifications are merely examples, and the configurations described in each embodiment and modification may be modified and/or combined as desired, provided that the functions are not impaired. Furthermore, some of the functions described in the embodiments and modifications may be omitted as long as the required functions can be realized. For example, the farm field management system 1000 shown in FIG. 1 may not include the terminal 200. Furthermore, all or part of the processing of the farm field management device 100 may be executed by the terminal 200. Furthermore, all or part of the processing of the terminal 200 may be executed by the farm field management device 100. Furthermore, the farm field management program 300 may include a display program 310.

Furthermore, the farm field management device 100 does not need to include the work detection unit 170. In this case, step S140 is omitted in the process shown in FIG. 8.

Furthermore, the farm field management device 100 does not need to include the farm field detection unit 160. In this case, step S130 is omitted in the process shown in FIG. 8. The work detection unit 170 of the farm field management device 100 stores area information representing the area of the farm field 400. The work detection unit 170 detects the area of the farm field 400 in the captured image based on the stored area information, and detects the work performed in the detected farm field 400.

1, 2: Storage medium 20: Network 50: Image acquisition device 60: Imaging device 100: Farm field management device 110: Input/output device 120: Computing device 130: Communication device 140: Storage device 150: Contour detection unit 160: Farm field detection unit 170: Work detection unit 180: Output unit 200: Terminal 210: Input/output device 220: Computing device 230: Communication device 240: Storage device 250: Display unit 300: Farm field management program 310: Display program 400: Farm field 500: Area 510: Contour 1000: Farm field management system

Claims (10)

Detecting contours of areas including at least the same farm fields in a plurality of captured images taken from above at different times of an area including the farm fields;
Detecting a field area of the field surrounded by the contour based on the contour detected in the plurality of captured images;
A field management method comprising: Detecting the field includes:
The farm land management method according to claim 1 , further comprising: detecting the farm land surrounded by the contours by superimposing the contours detected in the plurality of captured images. The farm land management method according to claim 1 or 2, wherein the plurality of captured images include radio wave images captured using radio waves. The farm land management method according to claim 1 , further comprising: detecting a type of work carried out in the farm land based on changes in the farm land detected in the plurality of captured images. the plurality of captured images include light wave images captured using light waves,
Detecting a type of work performed in the field includes:
The farm land management method according to claim 4 , further comprising: detecting a type of work carried out in the farm land based on changes in the farm land in the light wave image. Detecting the type of work performed in the farm fields based on changes in the farm fields in a plurality of images captured from above at different times over an area including at least the same farm fields;
outputting work information representative of the detected type of work;
A field management method comprising: a contour detection unit that detects contours of areas including at least the same farm fields in a plurality of captured images taken from above at different times of an area including the farm fields;
a farm field detection unit that detects the farm field surrounded by the contour based on the contour detected in the plurality of captured images;
A farm management system comprising: a work detection unit that detects a type of work performed in the farm field based on changes in the farm field in a plurality of captured images taken from above an area including at least the same plurality of farm fields at different times;
an output unit that outputs work information indicating the type of the detected work;
A farm management system comprising: Detecting contours of areas including at least the same farm fields in a plurality of captured images taken from above at different times of an area including the farm fields;
Detecting a field area of the field surrounded by the contour based on the contour detected in the plurality of captured images;
A farm field management program that causes a computing device to execute the above. Detecting the type of work performed in the farm fields based on changes in the farm fields in a plurality of images captured from above at different times over an area including at least the same farm fields;
outputting work information representative of the detected type of work;
A farm field management program that causes a computing device to execute the above.

Images