Apparatus for fly management

Patent metadata

Field	Value
Publication number	US-2021204521-A1
Application number	US-201917056747-A
Country	US
Kind code	A1
Filing date	May 21, 2019
Priority date	May 28, 2018
Publication date	Jul 8, 2021
Grant date	—

Abstract

The present invention relates to an apparatus (10) for fly management. It is described to provide (310) a processing unit with at least one image of an agricultural environment, wherein the agricultural environment contains a plurality of bovine animals The at least one image comprises image data of at least a part of at least one bovine animal of the plurality of bovine animals The processing unit determines (320) a number of flies in the image data of the at least a part of at least one bovine animal The processing unit determines (330) information relating to fly infestation of the plurality of bovine animals The determination comprises utilisation of the determined number of flies. An output unit outputs (340) an indication relating to a treatment for fly infestation of the plurality of bovine animals based on the determined information relating to fly infestation of the plurality of bovine animals

First claim

1 . An apparatus for fly management, comprising:
an input unit; a processing unit; and an output unit; wherein, the input unit is configured to provide the processing unit with at least one image of an agricultural environment, wherein the agricultural environment contains a plurality of bovine animals; wherein, the at least one image comprises image data of at least a part of at least one bovine animal of the plurality of bovine animals; wherein, the processing unit is configured to determine a number of flies in the image data of the at least a part of at least one bovine animal; wherein, the processing unit is configured to determine information relating to fly infestation of the plurality of bovine animals, the determination comprising utilisation of the determined number of flies; and wherein, the output unit is configured to output an indication relating to a treatment for fly infestation of the plurality of bovine animals based on the determined information relating to fly infestation of the plurality of bovine animals.

2 . The apparatus according to claim 1 , wherein the image data of at least a part of at least one bovine animal comprises image data other than image data of a bovine animal that is contiguous to the bovine animal.

3 . The apparatus according to claim 1 , wherein the processing unit is configured to identify at least one particular type of fly in the image data of the at least a part of at least one bovine animal, and wherein the determined number of flies in the image data of the at least a part of at least one bovine animal is a number of flies in the image data of the at least a part of at least one bovine animal that are the at least one particular type of fly.

4 . The apparatus according to claim 1 , wherein determination of the number of flies in the image comprises implementation of an image processing algorithm to analyse the image data of the at least a part of at least one bovine animal.

5 . Apparatus according to claim 4 , wherein the image processing algorithm comprises a machine learning algorithm.

6 . The apparatus according to claim 5 , wherein the machine learning algorithm is a neural network.

7 . The apparatus according to claim 5 , wherein the machine learning algorithm is a trained machine learning algorithm, wherein the machine learning training comprises utilization of ground truth data and associated imagery.

8 . The apparatus according to claim 7 , wherein subsequent training of the machine learning algorithm comprises utilization of the image data of the at least a part of at least one bovine animal.

9 . The apparatus according to claim 8 , wherein the subsequent training comprises utilization of the determined number of flies.

10 . The apparatus according to claim 8 , wherein the input unit is configured to receive from a user a validation of the indication relating to a treatment for fly infestation of the plurality of bovine animals, and wherein the subsequent training comprises utilization of the validation.

11 . The apparatus according to claim 1 , wherein a pixel in the image data of the at least a part of at least one bovine animal projected back to the at least part of the at least one bovine animal is less than or equal to 2 mm.

12 . The apparatus according to claim 1 , wherein the indication relating to the treatment for fly infestation of the plurality of bovine animals comprises an indication of a defined infestation level of a plurality of possible infestation levels.

13 . The apparatus according to claim 1 , wherein the indication relating to the treatment for fly infestation of the plurality of bovine animals comprises a message that the plurality of bovine animals need to be treated for fly infestation.

14 . The apparatus according to claim 1 , wherein the processing unit is configured to identify at least one chemical product useable for treatment for fly infestation, and wherein the indication relating to the treatment for fly infestation of the plurality of bovine animals comprises a message relating to the at least one chemical product useable for treatment for fly infestation.

15 . The apparatus according to claim 14 , wherein the input unit is configured to enable a user to input information relating to at least one previous chemical product used for treatment of fly infestation in the agricultural environment, and wherein identification of the at least one chemical product useable for treatment for fly infestation comprises utilisation of the information relating to at least one previous chemical product used for treatment of fly infestation in the agricultural environment.

16 . The apparatus according to claim 1 , wherein the indication relating to the treatment for fly infestation of the plurality of bovine animals comprises a message that the plurality of bovine animals need not be treated for fly infestation.

17 . The apparatus according to claim 1 , wherein determination of the information relating to fly infestation of the plurality of bovine animals comprises utilization of a threshold number of flies.

18 . The apparatus according to claim 1 , wherein the at least one image comprises a plurality of images, wherein the at least one part of the at least one bovine animal comprises a plurality of parts of the at least one bovine animal, and wherein each image of the plurality of images is associated with a different part of the plurality of parts, wherein the determined number of flies in the image data of the at least a part of at least one bovine animal comprises a number of flies in each image of the plurality of images.

19 . The apparatus according to claim 18 , wherein the determination of information relating to fly infestation of the plurality of bovine animals comprises a statistical analysis of the number of flies in each image of the plurality of images.

20 . The apparatus according to claim 18 , wherein the at least one bovine animal comprises at least two bovine animals, and wherein a first part of the plurality of parts is associated with a first bovine animal of the at least one bovine animal and a second part of the plurality of parts is associated with a second bovine animal of the at least one bovine animal.

21 . The apparatus according to claim 18 , wherein each part of the plurality of parts is associated with a different bovine animal.

22 . The apparatus according to claim 18 , wherein at least one first image of the plurality of images was acquired on a different day to at least one second image of the plurality of images.

23 . The apparatus according to claim 1 , wherein the processing unit is configured to implement a segmentation algorithm to analyse the at least one image to determine the image data of the at least a part of at least one bovine animal.

24 . The apparatus according to claim 23 , wherein the segmentation algorithm is configured to determine at least one area of the at least one image that has image data of an object other than one or more flies and wherein that object is other than the at least one bovine, and wherein determination of the image data of the at least a part of at least one bovine animal comprises a deselection of the at least one area from the at least one image.

25 . The apparatus according to claim 1 , wherein the processing unit is configured to detect the at least one bovine animal, the detection comprising analysis of the at least one image.

Assignees

• Bayer Animal Health Gmbh

Inventors

• Hamaekers Veerle
• Torun Nazim
• Berns Georg

Classifications

• B64U2101/31

  for surveillance · CPC title

• B64C39/024

  of the remote controlled vehicle type, i.e. RPV · CPC title

• G06N3/08

  Learning methods · CPC title

• G06Q50/02

  Agriculture; Fishing; Forestry; Mining · CPC title

• A01K29/00 Primary

  Other apparatus for animal husbandry · CPC title