Granted Patent B2

US 12,582,021 · App. 17/599,107 · Granted Mar 24, 2026

Inventor: Matthias Tempel (Leverkusen, DE)

Assignee: BASF Agro Trademarks GmbH

A01B79/005A01B79/02A01C21/002A01C21/007A01M7/0089G06T7/60G06T7/70G06V10/70G06V20/188G06T2207/10024G06T2207/10048G06T2207/20081G06T2207/30188

Abstract

Claims (52)

1 . A method for plantation treatment of a plantation field, the method comprising:

determining an application rate decision logic in the form of a configuration file comprising one or more layers, including (i) a rule for an on/off treatment decision; and (ii) a rule for determining an application rate of a treatment product based on parameters derived from object recognition, the application rate decision logic based on a combination of offline field data (Doff) relating to expected conditions on the plantation field and online field data (Don) collected during the plantation treatment of the plantation field;

capturing at least one image, each at least one image corresponding to specific locations of a plantation of a plantation field;

recognizing the objects in the captured at least one image based on historical and offline and online field data to improve object recognition accuracy and treatment efficacy;

determining the application rate for each of the specific locations based on the determined application rate decision logic and the recognized objects; and

determining a control signal(S) for controlling a treatment arrangement of a treatment device based on the determined application rate, wherein the treatment arrangement is controlled during the plantation treatment based on each instance of capturing at least one image and recognizing the objects in the corresponding image, and the application rate decision logic is adjustable based on validation data (V) indicative of the treatment efficacy.

2 . The method of claim 1 , wherein:

capturing an image of the plantation of the plantation field; recognizing the objects on the captured image, determining the application rate and determining the control signal(S) for controlling the treatment arrangement are carried out as a real time process, such that the treatment device is instantaneously controllable based on captured images of the plantation field as the treatment device traverses through the field at the time of treatment in a specific location of the plantation field.

3 . The method of claim 1 , wherein:

the application rate decision logic provides a logic to determine the application rate for treating the plantation depending on an expected efficacy loss of a crop to be cultivated in the plantation field.

4 . The method of claim 1 , wherein:

the application rate decision logic includes variable application rates depending on one or more parameter(s) derived from the image and/or object recognition.

5 . The method of claim 1 , wherein:

recognizing the objects is based on the captured image and/or geometric object profiles, modeling the geometry of the objects based on their species and/or their growth stage.

6 . The method of claim 1 , wherein:

determining the application rate based on the recognized objects includes determining object species, object growth stages and/or object density.

7 . The method of claim 1 , further comprising:

receiving the online field data (Don) by the treatment device relating to current conditions on the plantation field; and

determining the control signal(S) dependent on the determined application rate decision logic and the determined recognized objects and/or the determined online field data (Don).

8 . The method of claim 7 , wherein:

the online field data (Don) relates to current weather condition data, current plantation growth data and/or current soil data.

9 . The method of claim 1 , further comprising:

providing the validation data (V) dependent on a performance review of the treatment of the plantation; and

adjusting the application rate decision logic dependent on the validation data (V).

10 . The method of claim 9 , further comprising:

adjusting the geometric object profiles based on the validation data (V).

11 . The method of claim 1 , further comprising:

adjusting the application rate decision logic using a machine learning algorithm.

12 . A field manager system for a treatment device for plantation treatment of a plantation field, the field manager system comprising:

one or more processors configured to:

capturing at least one image, each at least one image corresponding to specific locations of a plantation of a plantation field;

receive offline field data (Doff) relating to expected conditions on the plantation field;

determine application rate decision logic of the treatment device in the form of a configuration file comprising one or more layers, including (i) a rule for an on/off treatment decision; and (ii) a rule for determining an application rate of a treatment product based on parameters derived from object recognition based on each instance of capturing at least one image, the application rate decision logic dependent on the offline field data (Doff) and online field data (Don) collected during the plantation treatment of the plantation field; and provide the application rate decision logic to the treatment device.

13 . The field manager system of claim 12 wherein the one or more processors are further configured to:

receive validation data (V), wherein the one or more processors adjust the application rate decision logic dependent on the validation data (V).

14 . A treatment system comprising the field manager system according to claim 12 .

15 . A treatment device for plantation treatment of a plant, the treatment device comprising: one or more processors configured to:

receive the application rate decision logic from the field manager system according to claim 12 ;

treat the plantation dependent on the received application rate decision logic;

recognize the objects on the captured image based on historical and offline and online field data to improve object recognition accuracy and treatment efficacy; and

determine a control signal(S) for controlling a treatment arrangement dependent on the received application rate decision logic and the recognized objects, treatment arrangement is controlled during the plantation treatment based on each of instance of capturing at least one image and recognizing the objects in the corresponding image, and the application rate decision logic is adjustable based on validation data (V) indicative of the treatment efficacy;

wherein the treatment device is connectable to the field manager system; and

wherein the treatment device activates treating the plantation based on the determined control signal(S).

16 . The treatment device of claim 15 , wherein the one or more processors are further configured to:

receive online field data (Don) relating to current conditions on the plantation field, wherein

the treatment device determines the control signal(S) for controlling treating the plantation dependent on the received application rate decision logic and the recognized objects and/or the online field data (Don).

17 . The treatment device of claim 15 ,

wherein one or a plurality of cameras capture the image of the plantation, in particular on a boom of the treatment device, wherein the treatment device recognizes the objects using red-green-blue RGB data and/or near infrared NIR data.

18 . The treatment device of claim 15 ,

wherein the treatment device is a smart sprayer, and wherein treating the plantation includes the treatment arrangement, wherein the treatment arrangement comprises a nozzle arrangement.

19 . The treatment device of claim 15 ,

wherein the treatment device comprises a plurality of cameras and the treatment arrangement comprises a plurality of nozzle arrangements, each associated to one of the plurality of cameras, such that images captured by the cameras are associated with the area to be treated by the respective nozzle arrangement.

Assignments (3)

Priority Claims (1)

Continuity (1)

References Cited (26)