Camera based pest management sprayer

Patent metadata

Field	Value
Publication number	US-12075770-B2
Application number	US-202017598273-A
Country	US
Kind code	B2
Filing date	Mar 25, 2020
Priority date	Mar 26, 2019
Publication date	Sep 3, 2024
Grant date	Sep 3, 2024

Abstract

Method for pest treatment of a plantation field, controlling device for controlling a pest treatment of a plantation field and a treatment device having said controlling device, wherein the treatment considers a pest insect population and a beneficial insect population.

First claim

The invention claimed is:

1. A method for pest treatment of a plantation field, the method comprising:
taking (S 10 ) an image ( 10 ) from a predetermined range ( 310 ) of a plantation of the plantation field ( 300 );
recognizing (S 20 ) items ( 20 ) on the taken image ( 10 ) of the predetermined range;
identifying (S 30 ) one or a plurality of patterns ( 31 , 32 , . . . 39 ) of an insect population based on the recognized items and a database ( 90 ) having stored samples of an insect population ( 931 , 932 , . . . 939 );
determining (S 40 ) a measure of a quantity of insect population based on the identified patterns; and
controlling (S 50 ) a treatment arrangement ( 60 ) of a treatment device ( 200 ) based on the determined quantity of insect population,
wherein controlling (S 50 ) of a treatment arrangement ( 60 ) includes activating (S 60 ) a treatment unit ( 61 , 62 , 63 ) if a quantity of a first type ( 931 , 932 ) and/or a second type ( 933 , 934 ) of pest insects extends a predetermined threshold (tp), and blocking a treatment unit ( 61 , 62 , 63 ) from being activated if a quantity of a particular type of beneficial insects ( 936 , 937 ) extends a predetermined threshold (tb).

2. The method according to claim 1 , wherein controlling (S 50 ) of a treatment arrangement ( 60 ) is conducted based on a lookup table having stored a relation of a quantity of pest insect population and a quantity of beneficial insect population and a respective quantitative activation grade for a treatment unit ( 61 , 62 , 63 ) being allocated to a respective relation.

3. The method according to claim 1 , wherein recognizing (S 20 ) items ( 20 ) on a taken image ( 10 ) is conducted based on a spectral detection of at least one pixel, in particular a red-green-near infrared RGNIR detection of at least one pixel, wherein a pattern ( 31 , 32 , . . . 39 ) is based on a location of the at least one detected pixel in a color space, in particular an RGNIR color space.

4. The method according to claim 1 , wherein identifying (S 30 ) one or a plurality of patterns ( 31 , 32 , . . . 39 ) of an insect population is based on an algorithm fed by stored samples of an insect population ( 931 , 932 , . . . 939 ) of the database ( 90 ).

5. The method according to claim 1 , wherein an identified pattern ( 31 , 32 , . . . 39 ) of an insect population is stored as a sample of an insect population ( 931 , 932 , . . . 939 ) in the database ( 90 ).

6. The method according to claim 1 , wherein recognizing (S 10 ) items ( 20 ) is conducted on a plurality of predetermined ranges ( 310 , 320 , 330 ) simultaneously, wherein identifying (S 30 ) one or a plurality of patterns ( 31 , 32 , . . . 39 ) of an insect population is conducted on the plurality of predetermined ranges, respectively, wherein determining (S 40 ) a measure of a quantity of insect population is conducted on the plurality of predetermined ranges, respectively, wherein controlling (S 50 ) a treatment arrangement ( 60 ) of a treatment device ( 200 ) is conducted for one or a plurality of treatment units ( 61 , 62 , 63 ) being allocated to a respective one of the plurality of predetermined ranges ( 310 , 320 , 330 ).

7. The method according to claim 1 , wherein recognizing (S 20 ) items ( 20 ) on the image ( 10 ) includes at least one of a recognition of a shape ( 21 ), a wing beat frequency and spectral signature ( 22 ) of a particular type of insect, in particular in an RGNIR color space of a particular type of insect.

8. The method according to claim 1 , wherein the stored samples ( 931 , 932 , . . . 939 ) represent a single pest insect ( 931 , 933 ) or an agglomeration of a plurality of pest insects ( 932 , 934 ), in particular a single or an agglomeration of a plurality of potato beetles ( 931 , 932 ), a single or an agglomeration of a plurality of pollen beetles ( 933 , 934 ) or a combination thereof ( 935 ), and/or the stored samples represent a single beneficial insect ( 936 ) or an agglomeration of a plurality of beneficial insects ( 937 ), in particular a single or an agglomeration of a plurality of bees.

9. The method according to claim 1 , wherein the stored samples represent combination ( 938 , 939 ) of
a single or an agglomeration of a plurality of pest insects, in particular a single or an agglomeration of a plurality of potato beetles, and/or a single or an agglomeration of a plurality of pollen beetles, and
a single or an agglomeration of a plurality of beneficial insects, in particular a single or an agglomeration of a plurality of bees.

10. The method according to claim 1 , wherein determining (S 40 ) a measure of a quantity of insect population includes determining (S 41 ) at least one of a quantity of a particular first type of pest insects ( 931 , 932 ), in particular potato beetles, a quantity of a particular second type of pest insects ( 933 , 934 ), in particular pollen beetles, and/or a quantity of a particular third type of beneficial insects ( 936 , 937 ), in particular bees.

11. The method according to claim 1 , wherein determining (S 40 ) includes online determination of a measure of a quantity of insect population based on the identified patterns, wherein in particular during field passage images and/or scans are captured, information is collected and a localized application according to the imaged and/or scanned item is carried out; wherein image capture and/or scan capture is timed such that it correlates with the speed during passage.

12. A controlling device for a treatment device, in particular a smart sprayer ( 200 ) for pest treatment of a plantation field ( 300 ), the controlling device comprising:
an image interface ( 110 );
a treatment control interface ( 160 );
a database interface ( 190 );
an image recognition unit ( 120 ) being adapted for recognizing items ( 20 ) on an image ( 10 ) received from the image interface;
an identification unit ( 130 ) being adapted for identifying one or a plurality of patterns ( 31 , 32 , . . . 39 ) of an insect population based on the output of the image recognition unit and samples ( 931 , 932 , . . . 939 ) of an insect population being received from a database ( 90 ) having stored samples ( 931 , 932 , . . . 939 ) of a pest population via the database interface ( 190 );
a determination unit ( 140 ) being adapted for determining a measure of a quantity of insect population based on the identified patterns ( 31 , 32 , . . . 39 ); and
a controlling unit ( 150 ) being adapted for generating a controlling signal for a treatment arrangement ( 60 ) of a treatment device ( 200 ) based on the determined measure of a quantity of insect population and for outputting the controlling signal to the treatment control interface ( 160 ),
wherein the controlling unit ( 150 ) being adapted for generating an activating signal for a treatment unit ( 61 , 62 , 63 ) if a quantity of a first type ( 931 , 932 ) and/or a second type ( 933 , 934 ) of pest insects extends a predetermined threshold (tp), and generating a blocking signal for deactivating a treatment unit ( 61 , 62 , 63 ) if a quantity of a particular type of beneficial insects ( 936 , 937 ) extends a predetermined threshold (tb).

13. The controlling device according to claim 12 , wherein the image recognition unit ( 120 ) is adapted for conducting an item recognition on a plurality of predetermined ranges ( 310 , 320 , 330 ) simultaneously, wherein the identification unit ( 130 ) is adapted for identifying one or a plurality of patterns ( 31 , 32 , . . . 39 ) of an insect population on the plurality of predetermined ranges, respectively, wherein the determinati

Assignees

• Basf Agro Trademarks Gmbh

Inventors

• Janssen Ole
• Kiepe Bjoern
• Wahabzada Mirwaes
• Johnen Andreas

Classifications

• G06T7/0014

  using an image reference approach · CPC title

• A01M2200/01

  Insects · CPC title

• A01M7/0089 Primary

  Regulating or controlling systems (the delivery being related to the movement of a vehicle B05B9/06) · CPC title