SYSTEM AND METHOD FOR MEASURING KEY FEATURES OF A ROTARY MILKING PARLOR ARRANGEMENT, COMPUTER PROGRAM AND NON-VOLATILE DATA CARRIER
20220222802 · 2022-07-14
Inventors
Cpc classification
G06V10/768
PHYSICS
A01J5/007
HUMAN NECESSITIES
G06V10/62
PHYSICS
International classification
A01J5/007
HUMAN NECESSITIES
G06V10/62
PHYSICS
Abstract
A rotating platform having a plurality of stalls is provided, each of the stalls being configured to house a respective animal during milking. The stalls are separated from one another by delimiting structures. A camera registers three-dimensional image data of the rotating platform within a field of view. A controller receives the image data that has been registered while the rotating platform completes at least one full revolution around its rotation axis. The controller processes the image data to derive a set of key features of the rotating platform, and then stores the set of key features in a data storage, which is configured to make the set of key features available for use at a later point in time.
Claims
1. A system for measuring a set of key features of a rotary milking parlor arrangement, which includes a rotating platform with a plurality of stalls each of which is configured to house a respective animal during milking, said stalls being separated from one another by delimiting structures, the system comprising: a camera configured to register three-dimensional image data of the rotating platform within a field of view; and a controller configured configured to: receive the image data that has been registered while the rotating platform completes at least one full revolution around a rotation axis of the rotating platform, process the image data to derive the set of key features, and store the set of key features in a data storage which is configured to make the set of key features available for use at a later point in time.
2. The system according to claim 1, wherein the image data are registered while the rotating platform is empty of animals.
3. The system according to claim 1, wherein the controller is further configured to: compare first and second amounts of image data with one another, the first amount of image data having been registered while the rotating platform is empty of animals the second amount of image data having been registered while at least one animal is present on the rotating platform, and based on said comparison, determine at least one visual object in the first and second amounts of image data that represents an object forming part of the rotating platform.
4. The system according to claim 1, wherein the controller is further configured to: process the image data to identify at least one recurring pattern therein, the at least one recurring pattern representing a visual characteristic that is identical for all of said stalls on the rotating platform.
5. The system according to claim 1, wherein the set of key features comprises data describing one or more physical characteristics of one or more of: (i) at least one of the stalls, (ii) at least one of the delimiting structures, (iii) at least one piece of fixed equipment disposed in at least one of said stalls, and (iv) a structure disposed on a stationary part of the rotary milking parlor.
6. The system according to claim 4, wherein the controller is further configured to: associate at least one of the at least one identified recurring pattern with a respective one of the at least one piece of fixed equipment arranged at a particular position in each of said stalls, the particular position being the same position for all of said stalls on the rotating platform.
7. The system according to claim 1, wherein the controller is further configured to: retrieve the set of key features from the data storage, and based on the retrieved set of key features, control a robotic arm to perform at least one action in relation to a milk-producing animal located on the rotating platform.
8. The system according to claim 1, wherein the controller is further configured to: retrieve the set of key features from the data storage, and based on the retrieved set of key features run a search procedure investigating whether or not an entry window is available to control a robotic arm to perform an action relating to a milk-producing animal located in one of said stalls.
9. The system according to claim 1, wherein the set of key features comprises a respective width measure of each of said stalls.
10. The system according to claim 1, wherein the set of key features comprises a respective height measure of the delimiting structures separating said stalls from one another.
11. The system according to claim 1, wherein the set of key features comprises a respective depth measure of each of said stalls.
12. The system according to claim 10, wherein the at least one piece of fixed equipment constitutes a portion of the delimiting structures.
13. The system according to claim 1, wherein the controller is further configured to determine a current rotation angle of the rotating platform based on: currently registered image data, and stored data retrieved from the data storage.
14. The system according to claim 13, wherein the controller is configured to determine a rotation speed of the rotating platform based on: image data registered at at least two points in time, and stored data retrieved from the data storage.
15. The system according to claim 1, wherein the set of key features comprises a position of the structure disposed on the stationary part of the rotary milking parlor, the structure being configured to prevent hind legs of an animal in one of said stalls from reaching outside of a safety zone for said one of said stalls.
16. A method of measuring a set of key features of a rotary milking parlor arrangement that includes a rotating platform with a plurality of stalls, each of the stalls being configured to house a respective animal during milking, said stalls being separated from one another by delimiting structures, the method comprising: registering, via a camera, three-dimensional image data of the rotating platform within a field of view; registering the image data while the rotating platform completes at least one full revolution around a rotation axis of the rotating platform; processing the registered image data to derive the set of key features; and storing the set of key features in a data storage which is configured to make the set of key features available for use at a later point in time.
17. The method according to claim 16, wherein the image data is registered while the rotating platform is empty of animals.
18. The method according to claim 16, further comprising: comparing first and second amounts of image data with one another, the first amount of image data having been registered while the rotating platform is empty of animals the second amount of image data having been registered while at least one animal is present on the rotating platform; and based on the comparing the first and second amounts of image data, determining at least one visual object in the first and second amounts of image data that represents an object forming part of the rotating platform.
19. The method according to claim 16, further comprising: processing the registered image data to identify at least one recurring pattern therein, the recurring pattern representing a visual characteristic that is identical for all of said stalls on the rotating platform.
20. The method according to claim 16, wherein the set of key features comprises data describing one or more physical characteristics of one or more of: (i) at least one of the stalls, (ii) at least one of the delimiting structures, (iii) at least one piece of fixed equipment disposed in at least one of said stalls, and (iv) a structure disposed on a stationary part of the rotary milking parlor.
21. The method according to claim 19, further comprising: associating at least one of the at least one identified recurring pattern with a respective one of the at least one piece of fixed equipment disposed at a particular position in each of said stalls, the particular position being the same for all of said stalls on the rotating platform.
22. The method according to claim 16, further comprising: retrieving the set of key features from the data storage and based on the retrieved set of key features, controlling a robotic arm to perform at least one action in relation to a milk-producing animal located on the rotating platform.
23. The method according to claim 16, wherein the set of key features comprises a respective width measure of each of said stalls.
24. The method according to claim 16, wherein the set of key features comprises a respective height measure of the delimiting structures separating said stalls from one another.
25. The method according to claim 16, wherein the set of key features comprises a respective depth measure of each of said stalls.
26. The method according to claim 24, wherein the at least one piece of fixed equipment constitutes a portion of the delimiting structures.
27. The method according to claim 16, further comprising determining a current rotation angle of the rotating platform based on: currently-registered image data, and stored data retrieved from the data storage.
28. The method according to claim 27, further comprising determining a rotation speed of the rotating platform based on: image data registered at at least two points in time, and stored data retrieved from the data storage.
29. The method according to claim 16, wherein the set of key features comprises a position of the structure disposed on the stationary part of the rotary milking parlor arrangement, the structure being configured to prevent hind legs of an animal in one of said stalls from reaching outside of a safety zone for said one of said stalls.
30. A non-transitory computer-readable medium having loaded thereon a computer program communicatively connected to a processor, the computer program comprising software configured to execute the method according to claim 16 when the computer program is run on the processor.
31. (canceled)
Description
BRIEF DESCRIPTION OF THE DRAWINGS
[0017] The invention is now to be explained more closely by means of preferred embodiments, which are disclosed as examples, and with reference to the attached drawings.
[0018]
[0019]
[0020]
DETAILED DESCRIPTION
[0021] In
[0022] According to the invention, a system for measuring a set of key features of the rotary milking parlor arrangement includes a camera 110 and a control unit 120. The camera 110 is configured to register three-dimensional image data D.sub.img3D of the rotating platform 130 within a field of view FV as illustrated in
[0023] Preferably, the camera 110 is arranged in relation to the rotating platform 130 such that the field of view FV covers at least 1.5 of the milking stalls S. Namely, this provides a substantial overlap of the image data D.sub.img3D registered in respect of each milking stall S, and thus enables high reliability in this data.
[0024] The control unit 120 is configured to process the registered image data D.sub.img3D. This may involve comparing, e.g. via a subtractive operation, first and second amounts of image data D.sub.img3D with one another, where the first amount of image data D.sub.img3D has been registered while the rotating platform 130 is empty of animals, and the second amount of image data D.sub.img3D has been registered while at least one animal is present on the rotating platform 130. Based on this comparison, the control unit 120 is preferably configured to determine at least one visual object in the first and second amounts of image data D.sub.img3D that represents an object forming part of the rotating platform 130.
[0025] Preferably, the camera 110 is a time-of-flight (ToF) camera, i.e. a range imaging camera system that resolves distance based on the known speed of light. According to the invention, however, the camera 110 may be any alternative imaging system capable of determining the respective distances to the objects being imaged, for example a 2D camera emitting structured light or a combined light detection and ranging (LIDAR) camera system. Moreover, the three-dimensional image data D.sub.img3D may be dynamic. This means that the three-dimensional image data D.sub.img3D can be represented by a video sequence and/or be built up from multiple still images.
[0026] The rotating platform 130 has a plurality of stalls S, where each stall S is configured to house a respective animal during milking. The stalls S are separated from one another by delimiting structures, for example in the form of rails DS1 and DS2 respectively.
[0027] Specifically, the control unit 120 is configured to receive the image data D.sub.img3D having been registered while the rotating platform 130 completes at least one full revolution around its rotation axis, for instance in a forward rotation direction RF. The control unit 120 is further configured to process the image data D.sub.img3D to derive the set of key features, and store the set of key features in a data storage 140. The data storage 140, in turn, is configured to make the set of key features available for use at a later point in time, e.g. by the control unit 120. Thus, the data storage 140 may contain a digital storage medium, such as a hard drive, a Solid State Drive (SSD)/Flash memory and/or a Random Access Memory (RAM).
[0028] The set of key features may contain a first parameter reflecting a respective width measure W.sub.S of each of the stalls S. Since the stalls S are shaped as truncated triangles, the width measure W.sub.S may either express a width at an outer edge of the rotating platform 130, a width at an inner edge thereof, or both.
[0029] Alternatively, or additionally, the set of key features may contain a second parameter reflecting a respective height measure H.sub.S of the delimiting structures, e.g. DS1 and DS2, that separate the stalls S from one another.
[0030] Alternatively, or additionally, the set of key features may contain a third parameter reflecting a respective depth measure D.sub.S of each of the stalls S. For example, the depth measure D.sub.S may be represented by a distance between the above-mentioned outer and inner edges of the rotating platform 130.
[0031] During operation of the rotary milking parlor arrangement, the control unit 120 is preferably configured to retrieve the set of key features W.sub.S, H.sub.S and/or D.sub.S from the data storage 140. Based on the retrieved set of key features W.sub.S, H.sub.S and/or D.sub.S, the control unit 120 is further preferably configured to run a search procedure, which investigates whether or not an entry window is available for controlling a robotic arm to perform an action relating to a milk-producing animal that is located in one of the stalls S. Naturally, according to the invention, the set of key features W.sub.S, H.sub.S and/or D.sub.S may equally well be retrieved by any unit or device other than the control unit 120, which unit or device is configured to control one or more robotic arms during operation of the rotary milking parlor arrangement.
[0032] According to one embodiment of the invention, the set of key features contains data describing the physical characteristics of at least one piece of fixed equipment that is arranged in at least one of the stalls S. For example, the at least one piece of fixed equipment may be represented by a cabinet or a rack for holding a milking cluster.
[0033] Of course, the at least one piece of fixed equipment EQ1 and/or EQ2 may also constitute a portion of the delimiting structures DS1 and/or DS2.
[0034] Ideally, at least one of the at least one piece of fixed equipment EQ1 and/or EQ2 is arranged at a particular position in each of the stalls S, which particular position is the same for all the stalls S on the rotating platform 130. Consequently, a subset of key features describing this piece of fixed equipment in one of the stalls S can be reused in all the other stalls S on the rotating platform 130. Such use of a repeating pattern highly improves the reliability of the registered information.
[0035] The control unit 120 may For example, be configured to associate at least one identified recurring pattern with a respective one of the at least one piece of fixed equipment EQ1 and/or EQ2 being arranged at a particular position in each of said stalls S, which particular position is the same for all of said stalls S on the rotating platform 130. This, in turn, facilitates determining which visual objects in the image data D.sub.img3D that form part of the rotating platform 130, as such, and which visual objects that represent other entities, e.g. animals. Consequently, it is rendered comparatively straightforward for the control unit 120 to estimate a velocity of the rotating platform 130 and/or to control a robotic arm to perform actions in relation to animals located on the rotating platform 130.
[0036] According to one embodiment of the invention, the control unit 120 is further configured to determine a current rotation angle of the rotating platform 130. This rotation angle is determined based on currently registered image data D.sub.img3D, e.g. a fresh video image frame representing the rotating platform 130 within the field of view FV, and stored data that have been retrieved from the data storage 140, for instance in the form of a set of key features derived from a historic video image frame representing the rotating platform 130.
[0037] Further, according to another embodiment of the invention, the control unit 120 is configured to determine a rotation speed of the rotating platform 130. The rotation speed is derived based on image data D.sub.img3D registered at at least two points in time, and stored data retrieved from the data storage 140, e.g. key features describing the width measure W.sub.S of the stalls S, the height measure H.sub.S of the delimiting structures DS1 separating the stalls from one another and/or the depth D.sub.S measure of the stalls S.
[0038] Thereby, the data in the data storage 140 may not only be used to control a robotic arm, however also to control the rotary platform 130 as such.
[0039] To enhance the data quality of the set of key features it is preferable to include a position P.sub.KR of a structure 135 therein, which structure 135 is arranged on a stationary part of the rotary milking parlor arrangement. The structure 135 may thus be a so-called kick rail, i.e. a structure configured to prevent the hind legs of an animal in one of said stalls S from reaching outside of a safety zone for said one of said stalls S. The position P.sub.KR may be a measure reflecting an elevation of the structure 135 relative to a part of the rotary milking parlor arrangement that has a known location, such as the rotating platform 130,
[0040] It is generally advantageous if the control unit 120 and the camera 130 are configured to effect the above-described procedure in an automatic manner by executing a computer program 127. Therefore, the control unit 120 may include a memory unit 125, i.e. non-volatile data carrier, storing the computer program 127, which, in turn, contains software for making processing circuitry in the form of at least one processor 125 in the central control unit 120 execute the above-described actions when the computer program 127 is run on the at least one processor 125.
[0041] In order to sum up, and with reference to the flow diagram in
[0042] In a first step 310, three-dimensional image data of the rotating platform are registered via a camera. The three-dimensional image data are registered within a field of view of the camera.
[0043] Then, in a step 320, the image data are stored; and in a subsequent step, 330, it is checked if a rotary platform of said arrangement has completed a full revolution. If so, a step 340 follows; and otherwise, the procedure loops back to step 310.
[0044] In step 340, the image data are processed to derive the set of key features.
[0045] Thereafter, in a step 350, the set of key features are stored in a data storage, which is configured to make the set of key features available for use at a later point in time. Subsequently, the procedure ends.
[0046] All of the process steps, as well as any sub-sequence of steps, described with reference to
[0047] The term “comprises/comprising” when used in this specification is taken to specify the presence of stated features, integers, steps or components. However, the term does not preclude the presence or addition of one or more additional features, integers, steps or components or groups thereof.
[0048] The invention is not restricted to the described embodiments in the figures, but may be varied freely within the scope of the claims.