METHOD FOR GENERATING AN APPLICATION MAP FOR TREATING A FIELD WITH AN AGRICULTURAL EQUIPMENT

Abstract

Method for generating an application map (20) for treating a field with an agricultural equipment comprising the following steps: providing (S10) a field map (10) of a field to be treated; determining (S20) areas in the field map (10) with a weed and/or pest infestation by using an image classification algorithm; and generating (S30) an application map (20) specifying areas for treating the field with an agricultural equipment, wherein the application map (20) is based on the determined areas infested by weed and/or pest infestation; wherein the method further comprises the step of providing boundary data with respect to the field.

Claims

1. A method for generating an application map (20) for treating a field with an agricultural equipment comprising the following steps: providing (S10) a field map (10) of a field to be treated; determining (S20) areas in the field map (10) with a weed and/or pest infestation by using an image classification algorithm; generating (S30) an application map (20) specifying areas for treating the field with an agricultural equipment, wherein the application map (20) is based on the determined areas infested by weed and/or pest infestation; and providing boundary data with respect to the field.

2. The method according to claim 1, wherein the method further comprises the step of generating (S40) control data and/or a control map (30) configured to be used for controlling an agricultural equipment, wherein the agricultural equipment is a spraying machine or a mechanical/electrical control device.

3. The method according to claim 1, wherein the field map (10) is generated based on at least one image of the field, wherein the field map (10) is based on several images of the field and/or parts of the field, wherein the several images are stitched together to provide the field map (10).

4. The method according to claim 3, wherein the at least one image or the several images are provided by at least one image collection device wherein the image collection device is an aircraft device.

5. The method according to claim 4, wherein the method further comprises the step of generating image collection path data for at least one image collection device, wherein the image collection path data comprises data with respect to path locations, position marks, flight heights, landing zones and/or image locations.

6. The method according to claim 4, wherein the image collection device comprises a communication interface configured to directly or indirectly send the collected images to a computer device, wherein the computer device is configured to execute the image classification algorithm and to generate the application map (20).

7. The method according to claim 1, wherein the application map (20) is divided in cells, and wherein for each cell a weed and/or pest infestation value is provided as a percent value.

8. The method according to claim 7, wherein the control data and/or control map (30) is divided in cells corresponding to the cells of the application map (20) and wherein a threshold value for each cell is applied when generating the control data and/or control map (30) such that the cells having a weed and/or pest infestation above the threshold value are treated by the agricultural equipment.

9. The method according to claim 8, wherein when generating the control data and/or control map (30) also the neighboring cells of a cell having a weed and/or pest infestation above the threshold value are treated by the agricultural equipment.

10. The method according to claim 7, wherein the control data and/or control map (30) comprises associated application rate data and/or recommended herbicides and/or insecticide data.

11. The method according to claim 1, wherein the image classification algorithm is based on the results of a machine learning algorithm.

12. Use of a field map (10) in the method according to claim 1 for determining areas in the field map (10) with a weed and/or pest infestation by using an image classification algorithm.

13. Use of an application map (20) in the method according to claim 1 for generating control data and/or a control map (30) configured to be used for controlling an agricultural equipment, wherein the agricultural equipment is preferably a spraying machine or a mechanical/electrical control device.

14. Use of image collection path data in the method according to claim 1, wherein the image collection path data comprises data with respect to path locations, position marks, flight heights, landing zones and/or image locations.

15. Agricultural equipment configured to be controlled by control data and/or a control map (30) provided by the method according to claim 1.

16. A system for generating an application map (20) for treating a field with an agricultural equipment, the system comprising: at least one processing unit configured to generate and provide a field map (10) of a field to be treated; at least one processing unit configured to determine areas in the field map (10) with a weed and/or pest infestation by using an image classification algorithm; and at least one processing unit configured to generate and provide an application map (20) specifying areas for treating the field with an agricultural equipment, wherein the application map (20) is based on the determined areas infested by weed and/or pest infestation.

17. A non-transitory computer-readable storage medium having instructions encoded thereon which, when executed by a processor, cause the processor to carry out the method of claim 1.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In the following, the invention is described exemplarily with reference to the enclosed figure, in which

[0061] FIG. 1 is a schematic view of a method according to the preferred embodiment of the present invention;

[0062] FIG. 2 is a schematic view of a field map used in the preferred embodiment of the invention;

[0063] FIG. 3 is a schematic view of an application map used in the preferred embodiment of the invention;

[0064] FIG. 4 is a schematic view of a control map used in the preferred embodiment of the invention; and

[0065] FIG. 5 is a schematic view of a robotic vehicle acquiring imagery of a field.

DETAILED DESCRIPTION OF AN EMBODIMENT

[0066] FIG. 1 is a schematic view of a method according to a preferred embodiment of the present invention. In the following, an exemplary order of the steps according to the preferred embodiment of the present invention is explained in view of a field map 10 shown in FIG. 2, an application map 20 shown in FIG. 3 and a control map 30 shown in FIG. 4.

[0067] In a step S10, a field map 10 of a field to be treated is provided. In the preferred embodiment, images have been taken by an image collection device, here a drone. In this respect, image collection path data have been provided to the drone comprising data with respect to path locations, position marks, flight heights, landing zones and/or image locations. The image collection path data have been generated based on the predetermined boundaries of the field using an analysis algorithm optimizing the collection path, i.e. providing maximum coverage in minimal time with minimal number of breaks, landings etc. This makes it possible for the drone to automatically take the individual images without a user having to control the drone. The images have been provided to a computer device for stitching the taken images together and for providing/generating the field map 10. Notably, the individual images can be transmitted immediately after they have been taken or after all images have been taken as a group. In this respect, it is preferred that the image collection device comprises a respective communication interface configured to directly or indirectly send the collected images to the computer device, e.g. cloud computing solutions, a centralized or decentralized computer system, a computer center, etc. Preferably, the images are automatically transferred from the image collection device to the computer device, e.g. via an upload center or a cloud connectivity during collection using an appropriate wireless communication interface, e.g. a mobile interface, long range WLAN etc. Even if it is preferred that the collected images are transferred via a wireless communication interface, it is also possible that the image collecting device comprises an on-site data transfer interface, e.g. a USB-interface, from which the collected images may be received via a manual transfer and which are then transferred to a respective computer device for further processing.

[0068] In a step S20, it the areas are determined in the filed map with a weed and/or pest infestation by using an image classification algorithm. In this respect, it is preferred that the image classification algorithm is based on the results of a machine learning algorithm, e.g. neural networks. In other words, it is preferred that the field map 10, e.g. the stitched images, are fed to a trained machine learning algorithm to determine weed and/or pest infestation on the field. In a step S30, an application map 20 is generated based on the results of the image classification algorithm specifying areas for treating the field with an agricultural equipment. Notably, the application map 20 can be divided in cells, preferably in polygon-shaped cells, wherein for each cell a weed and/or pest infestation value can be provided, wherein the weed and/or pest infestation value is preferably provided as percent value.

[0069] In a preferred step S40, a control map 30 is generated which is configured to be used for controlling an agricultural equipment. The control data/control map 30 can, for example, be provided as control commands for the agricultural equipment, which can, for example, be read into a data memory of the agricultural equipment before the treatment of the field, for example, by means of a wireless communication interface, by a USB-interface or the like. In this context, it is preferred that the control data allow a more or less automated treatment of the field, i.e. that, for example, a sprayer automatically dispenses the desired herbicides and/or insecticides at the respective coordinates without the user having to intervene manually. It is particularly preferred that the control data also include control commands for driving off the field. It is to be understood that the present invention is not limited to a specific content of the control data, but may comprise any data needed to operate an agricultural equipment. It is possible to divide the control map 30 in cells corresponding to the cells of the application map 20 and wherein a threshold value for each cell is applied when generating the control map 30 such that the cells having a weed and/or pest infestation above the threshold value are flagged for a treatment by the agricultural equipment. The threshold value can be determined by a user or might be a default value. Moreover, it is also possible to adopt a threshold value dependent from the specific kind of weed and/or pest infestation. When generating the control map 30 also the neighboring cells of a cell having a weed and/or pest infestation above the threshold value can be flagged for a treatment by the agricultural equipment. Thereby, it is possible to provide an error compensation by treating also the neighboring cells of cells having a weed and/or pest infestation above the threshold to compensate potential positioning errors, e.g. GPS-errors.

[0070] Notably, it is preferred that an application map 20 and/or control data/a control map 30 can be provided more or less automatically. In this respect, it is preferred that after receiving the images by the computer device(s), an automatic workflow is triggered comprising the following steps: stitching the images to a field map 10, providing S10 the field map 10, running the image classification algorithm and determining S20 the areas in the field map 10 with a weed and/or pest infestation, generating S30 the application map 20 and generating S40 the control data/control map 30 and directly or indirectly transferring the application map 20 and/or the control data/control map 30 to an agricultural equipment/user.

[0071] FIG. 5 shows an unmanned aerial vehicle (UAV), e.g. a drone, flying over a field containing a crop, which can be used for providing/acquiring images of a field. In the crop there may be a number of weeds/pathogens, wherein two particular and different weed types are shown as an example in FIG. 5. One weed type, the taller weed shown in FIG. 5, is particularly virulent, produces numerous seeds and can significantly affect the crop yield. This weed should not be tolerated in the field containing this crop. However, it is also possible that a second type of weed shown in FIG. 5 as the shorter weed, can be beneficial to the overall biodiversity for the crop in the field, with the proviso that the number density of this weed per unit area is below a threshold value.

[0072] The UAV has a camera, and as it flies over the field imagery is acquired. The UAV also has a GPS and inertial navigation system, which enables both the position of the UAV to be determined and the orientation of the camera also to be determined. From this information the footprint of an image on the ground can be determined, such that particular parts in that image, such as the example of the first type of weed, can be located with respect to absolute geospatial coordinates. The image data acquired by the camera is preferably transferred to a processing unit external to the UAV for generating the field map. However, it is also possible that a respective program is located in the UAV such that the field map can also be provided directly by the UAV.

[0073] The present invention has been described in conjunction with a preferred embodiment as examples as well. However, other variations can be understood and effected by those persons skilled in the art and practicing the claimed invention, from the studies of the drawings, this disclosure and the claims. Notably, the present invention is not limited to a specific order of these steps. Moreover, it is also not required that the different steps are performed at a certain place or at one place, i.e. each of the steps may be performed at a different place using different equipment/data processing units. In the claims as well as in the description the word “comprising” does not exclude other elements or steps and the indefinite article “a” or “an” does not exclude a plurality. A single element or other unit may fulfill the functions of several entities or items recited in the claims. The mere fact that certain measures are recited in the mutual different dependent claims does not indicate that a combination of these measures cannot be used in an advantageous implementation.

REFERENCE SIGNS

[0074] S10 providing a field map of a field to be treated [0075] S20 determining areas in the field map with a weed and/or pest infestation by using an image classification algorithm [0076] S30 generating an application map specifying areas for treating the field with an agricultural equipment [0077] S40 generating control data and/or a control map configured to be used for controlling an agricultural equipment [0078] 10 field map of a field to be treated [0079] 20 application map specifying areas for treating the field with an agricultural equipment [0080] 30 a control map configured to be used for controlling an agricultural equipment