Estimation method, information processing apparatus, and non-transitory computer-readable storage medium for estimating motion of animal

• US 10,638,725 B2
• Filed: 08/22/2018
• Issued: 05/05/2020
• Est. Priority Date: 02/29/2016
• Status: Active Grant

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: Yamamoto, Kiyoko
• Primary Examiner(s): Wilson, Brian
• Application Number:
  US16/108,595
• Publication Number:
  US 20180352786A1
• Time in Patent Office: Days
• CPC Class Codes: A01K 11/006 Automatic identification systems for animals, e.g. electronic devices, transponders for animals identification systems for access to feeding pens A01K1/0209; ear tags with electronic identification means A01K11/004
• CPC Class Codes: A01K 29/00 Other apparatus for animal husbandry
• CPC Class Codes: A01K 29/005 Monitoring or measuring activity, e.g. detecting heat or mating
• CPC Class Codes: A01K 67/00 Rearing or breeding animals, not otherwise provided for; New or modified breeds of animals
• CPC Class Codes: A61B 2503/40 Animals
• CPC Class Codes: A61B 5/1104 induced by stimuli or drugs; A61B5/1102 takes precedence; investigating medicinal preparations G01N33/15
• CPC Class Codes: A61B 5/112 Gait analysis

Abstract

An estimation method performed by a computer, the method comprising: distinguishing ground-off and landing timings of respective four limbs of an animal based on measurement data acquired by using a motion sensor attached to the animal which has four limbs, and identifying a limb which interlocks with a disorder of a motion waveform upon a motion of the animal, based on the distinguished ground-off and landing timings of each of the four limbs of the animal.

Claims

1. An estimation method performed by a computer, the method comprising:

executing a distinguishing process that includes distinguishing ground-off and landing timings of respective four limbs of an animal based on measurement data acquired by using a motion sensor attached in front of a chest region of the animal which has four limbs used to move in a quadrupedal manner, the measurement data indicating a movement of the chest region of the animal which has been measured by the motion sensor, and

executing a identifying process that includes identifying a limb which interlocks with a disorder of a motion waveform upon movement of the animal, based on the distinguished ground-off and landing timings of each of the four limbs of the animal.

2. The estimation method according to claim 1, the method further comprising:

executing a determining process that includes determining a gait of the animal based on the measurement data,

wherein the distinguishing process is configured to distinguish the ground-off and landing timings of each of the four limbs of the animal from the motion waveform upon the movement of the animal when the gait of the animal is determined as a walk state.

3. The estimation method according to claim 2,

wherein the distinguishing process is configured to distinguish the ground-off and landing timings of each of the four limbs of the animal from motion waveforms in an up-down direction and in a yaw axis direction when the gait of the animal is determined as the walk state, and

wherein the identifying process is configured to identify a limb having an abnormality based on the motion waveforms in at least one of a left-right direction, a front-rear direction, the up-down direction, and the yaw axis direction.

4. The estimation method according to claim 2,

wherein the distinguishing process includes

distinguishing a first point of time at which a positive side and a negative side of acceleration in a yaw axis direction are reversed to each other as the ground-off timing of a right forelimb when the acceleration in the yaw axis direction increases in a left turn direction from the point of time,

distinguishing the first point of time as the ground-off timing of a left forelimb when the acceleration in the yaw axis direction increases in a right turn direction from the point of time,

distinguishing a point of time at which the negative side of acceleration in an up-down direction is reversed into the positive side of acceleration as the landing timing of the right forelimb when the yaw axis direction is the left turn direction at the point of time,

distinguishing a point of time at which the negative side of acceleration in the up-down direction is reversed into the positive side of acceleration as the landing timing of the left forelimb when the yaw axis direction is the right turn direction at the point of time,

distinguishing an intermediate timing between the ground-off timing of the right forelimb and the ground-off timing of the left forelimb as the ground-off timing of a left hindlimb,

distinguishing an intermediate timing between the ground-off timing of the left forelimb and the ground-off timing of the right forelimb as the ground-off timing of the right hindlimb,

distinguishing an intermediate timing between the landing timing of the right forelimb and the landing timing of the left forelimb as the landing timing of the left hindlimb, and

distinguishing an intermediate timing between the landing timing of the left forelimb and the landing timing of the right forelimb as the landing timing of the right hindlimb.

5. The estimation method according to claim 1,

wherein the identifying process is configured to identify a limb having a small motion waveform in a front-rear direction as a limb having an abnormality among the limbs having the ground-off timing and the landing timing in a waveform with a large peak in the motion waveform in a left-right direction.

6. The estimation method according to claim 1,

wherein the identifying process is configured to identify a limb in which the ground-off and landing timings correspond to a period during which an actual motion waveform deviates from an ideal motion waveform by a predetermined ratio or more, as a limb having a problem.

7. An information processing apparatus for estimating a motion of an animal, the apparatus comprising:

a memory; and

a processor coupled to the memory and configured to

execute a distinguishing process that includes distinguishing ground-off and landing timings of respective four limbs of the animal based on measurement data acquired by using a motion sensor attached in front of a chest region of the animal which has four limbs used to move in a quadrupedal manner, the measurement data indicating a movement of the chest region of the animal which has been measured by the motion sensor, and

execute a identifying process that includes identifying a limb which interlocks with a disorder of a motion waveform upon movement of the animal, based on the distinguished ground-off and landing timings of each of the four limbs of the animal.

8. The information processing apparatus according to claim 7,

wherein the processor is configured to execute a determining process that includes determining a gait of the animal based on the measurement data, and

wherein the distinguishing process is configured to distinguish the ground-off and landing timings of each of the four limbs of the animal from the motion waveform upon the movement of the animal when the gait of the animal is determined as a walk state.

9. The information processing apparatus according to claim 8,

wherein the distinguishing process is configured to distinguish the ground-off and landing timings of each of the four limbs of the animal from motion waveforms in an up-down direction and in a yaw axis direction when the gait of the animal is determined as the walk state, and

wherein the identifying process is configured to identify a limb having an abnormality based on the motion waveforms in at least one of a left-right direction, a front-rear direction, the up-down direction, and the yaw axis direction.

10. The information processing apparatus according to claim 8,

wherein the distinguishing process includes

distinguishing a first point of time at which a positive side and a negative side of acceleration in a yaw axis direction are reversed to each other as the ground-off timing of a right forelimb when the acceleration in the yaw axis direction increases in a left turn direction from the point of time,

distinguishing the first point of time as the ground-off timing of a left forelimb when the acceleration in the yaw axis direction increases in a right turn direction from the point of time,

distinguishing a point of time at which the negative side of acceleration in an up-down direction is reversed into the positive side of acceleration as the landing timing of the right forelimb when the yaw axis direction is the left turn direction at the point of time,

distinguishing a point of time at which the negative side of acceleration in the up-down direction is reversed into the positive side of acceleration as the landing timing of the left forelimb when the yaw axis direction is the right turn direction at the point of time,

distinguishing an intermediate timing between the ground-off timing of the right forelimb and the ground-off timing of the left forelimb as the ground-off timing of a left hindlimb,

distinguishing an intermediate timing between the ground-off timing of the left forelimb and the ground-off timing of the right forelimb as the ground-off timing of the right hindlimb,

distinguishing an intermediate timing between the landing timing of the right forelimb and the landing timing of the left forelimb as the landing timing of the left hindlimb, and

distinguishing an intermediate timing between the landing timing of the left forelimb and the landing timing of the right forelimb as the landing timing of the right hindlimb.

11. The information processing apparatus according to claim 7,

wherein the identifying process is configured to identify a limb having a small motion waveform in a front-rear direction as a limb having an abnormality among the limbs having the ground-off timing and the landing timing in a waveform with a large peak in the motion waveform in a left-right direction.

12. The information processing apparatus according to claim 7,

wherein the identifying process is configured to identify a limb in which the ground-off and landing timings correspond to a period during which an actual motion waveform deviates from an ideal motion waveform by a predetermined ratio or more, as a limb having a problem.

13. A non-transitory computer-readable storage medium storing a estimation program that causes a processor to execute a process, the process comprising:

executing a distinguishing process that includes distinguishing ground-off and landing timings of respective four limbs of an animal based on measurement data acquired by using a motion sensor attached in front of a chest region of the animal which has four limbs used to move in a quadrupedal manner, the measurement data indicating a movement of the chest region of the animal which has been measured by the motion sensor, and

executing a identifying process that includes identifying a limb which interlocks with a disorder of a motion waveform upon movement of the animal, based on the distinguished ground-off and landing timings of each of the four limbs of the animal.

14. The non-transitory computer-readable storage medium according to claim 13, the method further comprising:

executing a determining process that includes determining a gait of the animal based on the measurement data,

wherein the distinguishing process is configured to distinguish the ground-off and landing timings of each of the four limbs of the animal from the motion waveform upon the movement of the animal when the gait of the animal is determined as a walk state.

15. The non-transitory computer-readable storage medium according to claim 14,

wherein the distinguishing process is configured to distinguish the ground-off and landing timings of each of the four limbs of the animal from motion waveforms in an up-down direction and in a yaw axis direction when the gait of the animal is determined as the walk state, and

wherein the identifying process is configured to identify a limb having an abnormality based on the motion waveforms in at least one of a left-right direction, a front-rear direction, the up-down direction, and the yaw axis direction.

16. The non-transitory computer-readable storage medium according to claim 14,

wherein the distinguishing process includes

distinguishing a first point of time at which a positive side and a negative side of acceleration in a yaw axis direction are reversed to each other as the ground-off timing of a right forelimb when the acceleration in the yaw axis direction increases in a left turn direction from the point of time,

distinguishing the first point of time as the ground-off timing of a left forelimb when the acceleration in the yaw axis direction increases in a right turn direction from the point of time,

distinguishing a point of time at which the negative side of acceleration in an up-down direction is reversed into the positive side of acceleration as the landing timing of the right forelimb when the yaw axis direction is the left turn direction at the point of time,

distinguishing a point of time at which the negative side of acceleration in the up-down direction is reversed into the positive side of acceleration as the landing timing of the left forelimb when the yaw axis direction is the right turn direction at the point of time,

distinguishing an intermediate timing between the ground-off timing of the right forelimb and the ground-off timing of the left forelimb as the ground-off timing of a left hindlimb,

distinguishing an intermediate timing between the ground-off timing of the left forelimb and the ground-off timing of the right forelimb as the ground-off timing of the right hindlimb,

distinguishing an intermediate timing between the landing timing of the right forelimb and the landing timing of the left forelimb as the landing timing of the left hindlimb, and

distinguishing an intermediate timing between the landing timing of the left forelimb and the landing timing of the right forelimb as the landing timing of the right hindlimb.

17. The non-transitory computer-readable storage medium according to claim 13,

wherein the identifying process is configured to identify a limb having a small motion waveform in a front-rear direction as a limb having an abnormality among the limbs having the ground-off timing and the landing timing in a waveform with a large peak in the motion waveform in a left-right direction.

18. The non-transitory computer-readable storage medium according to claim 13,

wherein the identifying process is configured to identify a limb in which the ground-off and landing timings correspond to a period during which an actual motion waveform deviates from an ideal motion waveform by a predetermined ratio or more, as a limb having a problem.