GB2549452A

GB2549452A - Tracking an animal

Info

Publication number: GB2549452A
Application number: GB1603578.4A
Authority: GB
Inventors: Chartsias Agisilaos; Alexander Heward James; Kokarakis Emmanouil; Lesley Scott; Radford Sillito Rowland; Douglas Armstrong James
Original assignee: Actual Analytics Ltd
Current assignee: Actual Analytics Ltd
Priority date: 2016-03-01
Filing date: 2016-03-01
Publication date: 2017-10-25
Also published as: GB201603578D0

Abstract

Disclosed is a method of determining a location L of a tag 12 carried by an animal 10 within an environment 110, and a method of tracking said animal, using a distribution of wireless tag detectors 20, at different locations L, comprising: determining which of the different wireless detectors have detected the tag; and processing multiple different locations at which the tag has been detected to provide a single location for the tag at a first time. The processing may involve selecting one location or averaging the locations. The detectors 20 may detect in a fixed sequence 30, such that detectors with overlapping detection ranges detect sequentially. Also disclosed is a system and computer programme for running the method. Also disclosed is a method of tracking multiple animals, each carrying a separate tag, within the same observation environment.

Description

TITLE

Tracking an animal TECHNOLOGICAL FIELD

Embodiments of the present invention relate to tracking an animal. In particular, tracking an animal carrying a tag within an environment using a distribution of wireless detectors, at different locations, for detecting the tag.

BACKGROUND

It would be desirable to improve the automated tracking of an animal carrying a tag within an environment using a distribution of wireless detectors, at different locations, for detecting the tag.

BRIEF SUMMARY

According to various, but not necessarily all, embodiments of the invention there is provided a method of determining a location of a tag carried by an animal within an environment, using a distribution of wireless detectors, at different locations, for detecting the tag, the method comprising: determining which of the different locations have wireless detectors that have detected the tag; processing multiple different locations at which the tag has been detected to provide a single location for the tag at a first time.

According to various, but not necessarily all, embodiments of the invention there is provided a system comprising: an environment for an animal carrying a tag; a distribution of wireless detectors, at different locations, for detecting the tag; and processing circuitry configured to determine which of the different locations have wireless detectors that have detected the tag by processing multiple different locations at which the tag has been detected to provide a single location for the tag at a first time.

According to various, but not necessarily all, embodiments of the invention there is provided a computer program that when run on a processor performs determining which wireless detectors, in a distribution of wireless detectors at different locations, have detected a tag; processing multiple different locations at which the tag has been detected to provide a single location for the tag at a first time.

According to various, but not necessarily all, embodiments of the invention there is provided examples as claimed in the appended claims.

BRIEF DESCRIPTION

For a better understanding of various examples that are useful for understanding the brief description, reference will now be made by way of example only to the accompanying drawings in which:

Fig 1 illustrates an example of a system for tracking an animal (not shown) carrying a tag or more than one animal (not shown) each carrying a different tag;

Fig 2 illustrates an example of a distribution of multiple wireless detectors suitable for detecting different tags;

Fig 3 illustrates an example of the system where detection of multiple tags using multiple detectors occurs in a time divided manner, each of the multiple wireless detectors having an exclusive detector time frame for performing a read operation; Fig 4 illustrates that within each exclusive detector time frame, each of the multiple tags may have an exclusive tag time slot;

Fig 5 illustrates an example of a method; and Fig 6 illustrates an example of a controller.

DETAILED DESCRIPTION

The figures illustrate a method of tracking an animal 10 carrying a tag 12 within an environment 120 comprising a distribution 110 of wireless detectors 20, at different locations U, for detecting the tag 12, the method comprising: determining which of the different locations L,, have wireless detectors 20 that have detected the tag 12; and processing multiple different locations L, at which the tag 12 has been detected to provide a single location for the tag 12.

Fig 1 illustrates an example of a system 100 for tracking an animal (not shown) carrying a tag or more than one animal (not shown) each carrying a different tag.

The system 100 provides an environment 120 , for the animal or animals. In this example, the environment 120 is an observational environment monitored by one or more cameras 140, 142. The environment 120 is provided in this example by a containment unit which may be made of transparent plastic.

The system 100, in this example but not necessarily all examples comprises one or more cameras. A side-mounted camera 140 provides a side view of the environment 120. A top-mounted camera 142 provides a top view of the environment 120.

The system 100 comprises a distribution 110 of wireless detectors at different locations L, inside or outside the environment 120 for detecting the tag or tags within the environment 120.

Processing circuitry 130 receives inputs from the distribution 110 of wireless detectors and, if present, the cameras 140,142. The processing circuitry 130 is configured to determine which of the different locations U, have a wireless detector that has detected the tag or tags and process the multiple different locations L, at which a tag has been detected to provide a single location for the tag. The processing circuitry 130 may, for example, be provided as a computer, a microcontroller or an application specific circuit.

Fig 2 illustrates an example of a distribution 110 of multiple wireless detectors 20 suitable for detecting different tags 12. Each of the multiple wireless detectors 20 has a fixed position at a location L|.

Each of the tags 12 is carried by a different animal 10. A first animal 10A carries the first tag 12A but not the second tag 12B or third tag 12C. A second animal 10B carries the second tag 12B but not the first tag 10A or the third tag 12C. A third animal IOC carries the third tag 12C but not the first tag 10A or the second tag 12B. When an animal 10 carries a tag 12, it may carry the tag externally or internally. The tag 12 may, for example, be worn by r attached to the animal 10 or may, for example, be implanted into the animal 10.

In this example, but not necessarily all examples, the distribution 110 of multiple wireless detectors 20 is a two-dimensional arrangement. In this example, but not necessarily all examples, the distribution 110 of multiple wireless detectors 20 is a an array of wireless sensors 20 arranged in regularly spaced rows and regularly spaced columns. In this example, the two-dimensional arrangement of wireless sensors 20 is parallel to and located underneath a floor of the environment 120.

Each wireless detector 20 is capable of detecting each of the tags 12A, 12B, 12C. The system 100 may be used for tracking one or more animals 10 of the same species, each carrying a different tag 12.

For each tag 12: the system determines which of the different locations L, have a wireless detector 20 that has detected the tag 12 and processes multiple different locations at which the tag has been detected, to provide a single location for the tag 12.

In some but not necessarily all examples, the system 100 is configured to process the multiple different locations L, to provide a single location for the tag 12 by averaging the multiple different locations.

In some but not necessarily all examples, the system 100 is configured to process the multiple different locations L, to provide a single location for the tag 12 by selecting one of the multiple different locations.

In some but not necessarily all examples, the system 100 is configured to process the multiple different locations L, to provide a single location for the tag 12 by using a pattern, in space and time, of locations at which the tag is detected, including the multiple different locations, to estimate a location of the tag at the first time.

The pattern may extend for a period of time before the first time and/or the pattern may extend for a period of time after the first time.

In some examples, the first time may correspond to a measurement period during which the tag 12 was detected at the multiple locations. In other examples, the first time may correspond to a measurement period different to the measurement periods during which the tag was detected at the multiple locations.

The system 100 may process the multiple different locations to provide a single location for the tag 12 by filtering the locations for the tag using a statistical filter to assess locations of the tag, including the multiple different locations, overtime. The statistical filter may, for example, estimate a trajectory of a tag by calculating a moving average (mean or median), by performing Savitzky-Golay smoothing, or Gaussian smoothing. The statistical filter may, for example, remove noise arising when a substantially stationary tag has readings that fluctuate between two wireless detectors 20.

The wireless detectors 20 may have at least partially overlapping detection ranges and a tag 12 at an actual location L, may be detected by one or more wireless detectors 20 which may or may not be at location L,. It is therefore possible to have a single tag 12 detected by more than one wireless detector 20 at different locations L,. This results in ambiguity concerning the location of the detected tag 12 and frustrates accurate tracking of the animal 10 carrying the detected tag 12. The processing performed by the system 100 may remove this ambiguity.

It is therefore possible to have a single tag 12 that oscillates or fluctuates between detection by a small set of wireless detectors 20 at different but neighbouring locations L, This results in ambiguity concerning the location of the detected tag 12 and frustrates accurate tracking of the animal 10 carrying the detected tag 12. The processing performed by the system 100 may remove this ambiguity.

It is possible to have a measurement period in which a tag 12 is not detected but which is detected in neighbouring measurement periods. This results in ambiguity concerning the location of the detected tag 12 at the measurement period and frustrates accurate tracking of the animal 10 carrying the detected tag 12. The processing performed by the system 100 may remove this ambiguity.

Fig 3 illustrates that in at least some examples detection of a tag 12 is time divided between multiple wireless detectors 20. There is a fixed sequence 30 in which the wireless detectors 20 detect. In the example illustrated the sequence of detection is column by column, alternating the direction of the sequence within a column between adjacent columns to produce a zigzag sequence 30. The timing of the operation of the wireless detectors 20 within the sequence 30 is such that wireless detectors 20 with overlapping detection ranges preferably do not detect simultaneously but detect sequentially.

In the example illustrated in Fig 3, the system 100 may perform detection of multiple tags 12 using multiple detectors 20 in a time divided manner. For example, in some but not necessarily all implementations, each of the multiple wireless detectors 20 has an exclusive detector time frame Fj. which is not synchronous with or does not overlap in time a detector time frame Fj of the another of the multiple detectors 20 within its range. . A read operation for tags 12 is performed intermittently by the wireless detectors 20. A particular wireless detector 20 at location U performs a read operation over a measurement period 200 corresponding to a detector time frame F,.

In the example of Fig 4, within each exclusive detector time frame F,, each of the multiple tags 12 has an exclusive tag time slot Sj which does not overlap a tag time slot of another of the multiple tags 12. A wireless detector 20 may perform a read operation for a tag 12 by transmitting a ping. Each different tag 12 may have a constant different delay from receiving the ping to providing a response identifying the tag 12 in the respective tag time slot Sj.

Each tag 12 may be a radio frequency identification (RFID) tag.

In some but not necessarily all examples, some or all of the tags 12 are configured to report one or more measurements performed at the animal 10. Examples of measurements include physiological measurements such as for example temperature and/or heart beat.

Fig 5 illustrates an example of a method 500 comprising: at block 502 measuring location Li(tm) of the tag Tj at time tm by determining which of the different locations L, have wireless detectors 20 that have detected the tag Tj, then at block 504, if an uncertainty concerning a location Li(tj) of the tag Tj at time tj is greater than a threshold, then processing multiple different measured locations L, for tag Tjto determine a location Li(tj) of the tag Tj at time tj.

In one example, time tj is in the same measurement period At as time tm.and measuring location Li(tm) of the tag T| during that measurement period identifies multiple different locations where different wireless detectors 20 have detected the tag Tj.

Ambiguity arises because during the single measurement period At there are multiple locations L, of the tag Tj. The threshold used at block 504 is the existence of more than one detected location U of the tag Tj during a single measurement period At.

The system 100 may process the multiple ambiguous locations to produce a single location by, for example, taking a mean of the multiple locations or selecting one of the multiple ambiguous locations or using a statistical filter as described previously. The selection may be according to a rule e.g. ‘leftmost’ or may be based on other detected locations U of the tag Tj during other different measurement periods.

Thus the system 100 provides a single location for the tag 12 at a first time using multiple different locations for the tag 12 at the first time i.e. during the same measurement period and not necessarily simultaneous.

This approach deals with situations arising because the detection ranges of the wireless detectors 20 overlap and a tag 12 may then be detected at multiple positions, during the same measurement period, where the detection ranges overlap. In another example, ambiguity arises because during a series of successive measurement periods At the location Lj of the tag Tj switches between only a small number of values e.g. 2 or 3 values. That is the locations flutters but the tag is substantially stationary. In this example, the threshold used in block 504 is that the location Uof the tag Tj repeatedly changes between a few values during adjacent measurement periods At

Thus the system 100 provides a single location for the tag 12 at a first time using a sequence of detected locations for the tag 12 including a detected location for the tag at the first time and one or more detected locations for the tag before the first time and/or after the first time. For example, the system 100 may be configured to select as a location of the tag at the first time either the actual detected location of the tag at the first time or a location for the tag from the sequence of locations for the tag, adjacent in time the first time.

In another example, ambiguity arises because a tag 12 has not been read during a measurement period. Ambiguity arises because during a single measurement period At there is no location L, of the tag T. The threshold used at block 504 is that there is no location Uof the tag T, during a single measurement period At.

The system 100 is configured to provide a single location for the tag 12 at a first time, at which a location of the tag 12 has not been detected, using at least a first location for the tag preceding the first time and at least a second location for the tag following the first time. For example, the system may be configured to generate a location for the tag 12 at the first time by interpolating between the first location and the second location.

The system 100 may, for example, identify that that tag 12 is moving along a trajectory including the single location, and determine the single location for the tag 12 at the first time as that corresponding to a location according to the trajectory at the first time.

Where the system 100 comprises a video camera or video cameras, the system 100 may synchronize the detection of locations of tags 12 with a frame of captured video including the animal carrying a tag 12. The system 100 may, for example, be configured to use computer vision to track the animal 10 carrying the tag 12 within the captured video and this can be used to estimate additional locations of the animal 10 carrying the tag 12 either for time periods where a detected location is absent or to provide locations at a frequency higher than the read rate of the wireless detectors 20.

The system 100 may be configured to identify interaction between two animals 10 when a tag 12 carried by one of the animals 10 is located at the same or similar location as a different tag 12 carried by the other one of the animals 10.

The system 100 may be configured to process different portions of the video based on time variation of a detected location of the tag, to identify a movement performed by the animal 10 carrying the tag 12. For example, a machine learning algorithm may be used to identify movement types e.g. walk, run, stay, investigate. The machine learning algorithm may be trained on non-noisy data representing distinct movement types e.g. walk, run, stay, investigate, and/or distinct individual behaviours e.g. rearing, eating, drinking, grooming C and/or social behaviours between two or more animals e.g. mating, communal grooming, fighting.

Referring back to Fig 1, implementation of a processing circuitry 130 may be as q controller. The controller 130 may be implemented in hardware alone, have certain aspects in software including firmware alone or can be a combination of hardware and software (including firmware).

As illustrated in Fig 6 the controller 130 may be implemented using instructions that enable hardware functionality, for example, by using executable computer program instructions 64 in a general-purpose or special-purpose processor 62 that may be stored on a computer readable storage medium (disk, memory etc) to be executed by such a processor 62.

The processor 62 is configured to read from and write to the memory 60. The processor 62 may also comprise an output interface via which data and/or commands are output by the processor 62 and an input interface via which data and/or commands are input to the processor 62.

The memory 60 stores a computer program 64 comprising computer program instructions (computer program code) that controls the operation of the apparatus 100 when loaded into the processor 62. The computer program instructions, of the computer program 64, provide the logic and routines that enables the apparatus to perform the methods illustrated in Figs 5. The processor 62 by reading the memory 60 is able to load and execute the computer program 64.

The apparatus or system 100 therefore comprises: at least one processor 62; and at least one memory 60 including computer program code 64 the at least one memory 60 and the computer program code 64 configured to, with the at least one processor 62, cause the apparatus 100 at least to perform: determining which of the different locations have wireless detectors that have detected a tag 12; processing multiple different locations at which the tag has been detected to provide a single location for the tag 12 at a first time.

As illustrated in Fig 6, the computer program 64 may arrive at the apparatus 100 via any suitable delivery mechanism 70. The delivery mechanism 70 may be, for example, a non-transitory computer-readable storage medium, a computer program product, a memory device, a record medium such as a compact disc read-only memory (CD-ROM) or digital versatile disc (DVD), an article of manufacture that tangibly embodies the computer program 64. The delivery mechanism may be a signal configured to reliably transfer the computer program 64. The apparatus 100 may propagate or transmit the computer program 64 as a computer data signal.

Although the memory 60 is illustrated as a single component/circuitry it may be implemented as one or more separate components/circuitry some or all of which may be integrated/removable and/or may provide permanent/semi-permanent/ dynamic/cached storage.

Although the processor 62 is illustrated as a single component/circuitry it may be implemented as one or more separate components/circuitry some or all of which may be integrated/removable. The processor 62 may be a single core or multi-core processor.

References to ‘computer-readable storage medium’, ‘computer program product’, ‘tangibly embodied computer program’ etc. ora ‘controller’, ‘computer’, ‘processor’ etc. should be understood to encompass not only computers having different architectures such as single /multi- processor architectures and sequential (Von Neumann)/parallel architectures but also specialized circuits such as field-programmable gate arrays (FPGA), application specific circuits (ASIC), signal processing devices and other processing circuitry. References to computer program, instructions, code etc. should be understood to encompass software for a programmable processor or firmware such as, for example, the programmable content of a hardware device whether instructions for a processor, or configuration settings for a fixed-function device, gate array or programmable logic device etc.

The blocks illustrated in the Figs 5 may represent steps in a method and/or sections of code in the computer program 64. The illustration of a particular order to the blocks does not necessarily imply that there is a required or preferred order for the blocks and the order and arrangement of the block may be varied. Furthermore, it may be possible for some blocks to be omitted.

Where a structural feature has been described, it may be replaced by means for performing one or more of the functions of the structural feature whether that function or those functions are explicitly or implicitly described.

The term ‘comprise’ is used in this document with an inclusive not an exclusive meaning. That is any reference to X comprising Y indicates that X may comprise only one Y or may comprise more than one Y. If it is intended to use ‘comprise’ with an exclusive meaning then it will be made clear in the context by referring to “comprising only one..’’ or by using “consisting”.

In this brief description, reference has been made to various examples. The description of features or functions in relation to an example indicates that those features or functions are present in that example. The use of the term ‘example’ or ‘for example’ or ‘may’ in the text denotes, whether explicitly stated or not, that such features or functions are present in at least the described example, whether described as an example or not, and that they can be, but are not necessarily, present in some of or all other examples. Thus ‘example’, ‘for example’ or ‘may’ refers to a particular instance in a class of examples. A property of the instance can be a property of only that instance or a property of the class or a property of a subclass of the class that includes some but not all of the instances in the class. It is therefore implicitly disclosed that a features described with reference to one example but not with reference to another example, can where possible be used in that other example but does not necessarily have to be used in that other example.

Although embodiments of the present invention have been described in the preceding paragraphs with reference to various examples, it should be appreciated that modifications to the examples given can be made without departing from the scope of the invention as claimed.

Features described in the preceding description may be used in combinations other than the combinations explicitly described.

Although functions have been described with reference to certain features, those functions may be performable by other features whether described or not.

Although features have been described with reference to certain embodiments, those features may also be present in other embodiments whether described or not.

Whilst endeavoring in the foregoing specification to draw attention to those features of the invention believed to be of particular importance it should be understood that the Applicant claims protection in respect of any patentable feature or combination of features hereinbefore referred to and/or shown in the drawings whether or not particular emphasis has been placed thereon. l/we claim:

Claims

1. A method of determining a location of a tag carried by an animal within an environment, using a distribution of wireless detectors, at different locations, for detecting the tag, the method comprising: determining which of the different locations have wireless detectors that have detected the tag; processing multiple different locations at which the tag has been detected to provide a single location for the tag at a first time.

2. A method of tracking one or more animals of the same species, each carrying a different tag within an observation environment using a distribution of wireless detectors, at different locations, each for detecting the different tags and having at least partially overlapping detection ranges, the method comprising, for each different tag: determining which of the different locations have wireless detectors that have detected the tag; and if there are multiple different locations at which the tag has been detected, processing the multiple different locations to provide a single location for the tag at a first time.

3. A method as claimed in claim 1 or 2, comprising: providing a single location for the tag at the first time using multiple different locations for the tag at the first time.

4. A method as claimed in claim 3, wherein providing a single location for the tag at a first time using multiple different locations for the tag at the first time comprises: selecting one of the multiple different locations.

5. A method as claimed in claim 3, wherein providing a single location for the tag at a first time using multiple different locations for the tag at the first time comprises: averaging the multiple different locations.

6. A method as claimed in claim 1 or 2, comprising: providing a single location for the tag at a first time using a sequence of detected locations for the tag including a detected location for the tag at the first time and one or more detected locations for the tag before the first time and/or after the first time.

7. A method as claimed in claim 6, wherein providing a single location for the tag at a first time using a sequence of detected locations for the tag including a detected location for the tag at the first time and one or more detected locations for the tag before the first time and/or after the first time, comprises selecting a detected location of the tag at the first time or a location for the tag from the sequence of locations for the tag, adjacent in time the first time.

8. A method as claimed in claim 1 or 2, comprising: providing a single location for the tag at the first time, at which a location of the tag has not been detected, using at least a first location for the tag preceding the first time and at least a second location for the tag following the first time.

9. A method as claimed in claim 1 or 2, wherein providing a single location for the tag at the first time, at which a location of the tag has not been detected, using at least a first location for the tag preceding the first time and at least a second location for the tag following the first time, comprises generating a location for the tag at the first time by interpolating between the first location and the second location.

10. A method as claimed in claim 1 or 2, wherein processing the multiple different locations to provide a single location for the tag comprises determining a single location by: averaging the multiple different locations; or selecting one of the multiple different locations; or using a pattern, in space and time, of locations at which the tag is detected, including the multiple different locations, to estimate a location of the tag at the first time.

11. A method as claimed in claim 1 or 2, wherein processing the multiple different locations to provide a single location for the tag at the first time comprises identifying that that tag is moving along a trajectory including the single location, and determining a single location for the tag by at the first time corresponding to a location according to the trajectory at the first time.

12. A method as claimed in claim 1 or 2, wherein processing the multiple different locations to provide a single location for the tag comprises identifying that that tag is stationary at the single location, and determining a single location for the tag at the first time corresponding to a preceding location of the tag.

13. A method as claimed in claim 1 or 2, wherein processing the multiple different locations to provide a single location for the tag comprises filtering locations for the tag using a statistical filter to assess locations of the tag, including the multiple different locations, over time.

14. A method as claimed in any preceding claim, comprising synchronizing the single location at the first time with a frame of captured video including the animal carrying the tag.

15. A method as claimed in claim 13, comprising tracking the animal carrying the tag within the captured video.

16. A method as claimed in claim 13, 14 or 15, wherein the video is from a side-on perspective.

17. A method as claimed in any preceding claim, comprising identifying interaction between two animals when a tag carried by one of the animals is located at the same or similar location as a different tag carried by the other one of the animals.

18. A method as claimed in any preceding claim, comprising processing the location of the tag and one or more tags carried by other animals to identify a movement or behaviour or social behaviour performed by or to the animal carrying the tag.

19. A method as claimed in any preceding claim, comprising performing a read operation for the tag intermittently, at each of the wireless detectors.

20. A method as claimed in claim 19, comprising performing a read operation for the tag by transmitting a ping at different times from each of the wireless detectors. wherein the tag has a constant delay from receiving the ping to providing a response identifying the tag.

21. A method as claimed in any preceding claim, further comprising: performing detection of multiple tags using multiple detectors in a time divided manner, wherein each of the multiple wireless detectors has an exclusive detector time frame which does not overlap in time a detector time frame of the another of the multiple detectors and wherein, within each exclusive detector time frame, each of the multiple tags has an exclusive tag time slot which does not overlap a tag time slot of another of the multiple tags.

22. A method as claimed in any preceding claim, wherein the environment is provided by an animal containment unit and the wireless detectors are arranged in a two-dimensional array parallel to a floor of the animal containment unit outside the animal containment unit.

23. A method as claimed in any preceding claim, wherein the tag is a radio frequency identification tag.

24. A method as claimed in any preceding claim, wherein the tag is configured to report one or more measurements performed at the animal.

25. A system configured to perform the method of any preceding claim.

26. A computer program that when run on a processor performs the method of any of claims 1 to 24.

27. A system comprising: an environment for an animal carrying a tag; a distribution of wireless detectors, at different locations, for detecting the tag; and processing circuitry configured to determine which of the different locations have wireless detectors that have detected the tag by processing multiple different locations at which the tag has been detected to provide a single location for the tag at a first time.

28. A computer program that when run on a processor performs determining which wireless detectors, in a distribution of wireless detectors at different locations, have detected a tag; processing multiple different locations at which the tag has been detected to provide a single location for the tag at a first time.