# US 2023/0069401 A1 · Real Time Kinematic Analyses of Body Motion

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0069401 A1
- Document ID: US20230069401A1
- Status: Published application
- Kind: A1
- Application number: 17/972,021
- Filed: 2022-10-24
- Published: 2023-03-02
- Earliest claimed: 2020-11-12
- Assignees: Disney Enterprises, Inc.
- Applicants: Disney Enterprises, Inc.
- Inventors: Kevin John Prince; Carlos Augusto Dietrich; Dirk Van Dall
- Web page: https://patentgrep.com/patent/US20230069401A1

## CPC

- G06T 7/55: from multiple images
- G06V 40/28: {Recognition of hand or arm movements, e.g. recognition of deaf sign language (static hand signs G06V40/113)}
- G06F 18/23: Clustering techniques
- G06T 7/251: {involving models}
- G06V 10/762: using clustering, e.g. of similar faces in social networks
- G06V 20/42: {of sport video content}
- G06V 20/44: {Event detection}
- G06V 40/23: {Recognition of whole body movements, e.g. for sport training}
- G06T 2207/10016: Video; Image sequence
- G06T 2207/20044: Skeletonization; Medial axis transform
- G06T 2207/20076: Probabilistic image processing
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30196: Human being; Person
- G06T 2207/30221: Sports video; Sports image
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Systems and methods are presented for generating statistics associated with a performance of a participant in an event, wherein pose data associated with the participant, performing in the event, are processed in real time. Pose data associated with the participant may comprise positional data of a skeletal representation of the participant. Actions performed by the participant may be determined based on a comparison of segments of the participant's pose data to motion patterns associated with actions of interests.

## Claims

### Claim at position 1

1-20. (canceled)

### Claim 21

A method comprising:
receiving a first sequence of positional data associated with a first performance of a first participant in an event;
receiving a second sequence of positional data associated with a second performance of a second participant in the event;
detecting, based the first sequence of positional data and the second sequence of positional data, movements of the first participant and the second participant; and
determining, based on the movements of the first participant and the second participant, a collision between the first participant and the second participant.

### Claim 22 (depends on 21)

The method of claim 21, further comprising:
generating the first sequence of positional data and the second sequence of positional data based on an analysis of video content captured by one or more cameras positioned at a site of the event.

### Claim 23 (depends on 21)

The method of claim 21, wherein detecting comprises:
extracting a first segment of positional data from the first sequence of positional data;
comparing the extracted first segment to one or more motion patterns, wherein each of the one or more motion patterns is associated with an action of interest; and
determining, based on a match between the extracted first segment and at least one motion pattern of the one or more motion patterns, an action performed by the first participant, wherein the determined action corresponds to an action of interest associated with the at least one matching motion pattern.

### Claim 24 (depends on 23)

The method of claim 23, wherein each of the one or more motion patterns is associated with a data structure containing positional data, representative of an action of interest, and metadata, the metadata comprises one or more of a motion pattern identity, the action of interest, an identity of the first participant that performed the action of interest, or a list of events associated with the action of interest.

### Claim 25 (depends on 23)

The method of claim 23, further comprising:
updating a pool of clusters, comprising the one or more motion patterns, with a new motion pattern associated with the extracted segment, the updating comprises computing an assignment score with respect to each of the clusters and adding, based on the computed assignment scores, the new motion pattern to one of the clusters.

### Claim 26 (depends on 21)

The method of claim 21, further comprising:
generating the first sequence of positional data and the second sequence of positional data based on an analysis of sensor data captured by one or more cameras sensors at a site of the event.

### Claim 27 (depends on 26)

The method of claim 26, wherein detecting comprises:
extracting a first segment of positional data from the first sequence of positional data;
comparing the extracted first segment to one or more motion patterns, wherein each of the one or more motion patterns is associated with an action of interest; and
determining, based on a match between the extracted first segment and at least one motion pattern of the one or more motion patterns, an action performed by the first participant, wherein the determined action corresponds to an action of interest associated with the at least one matching motion pattern.

### Claim 28 (depends on 21)

The method of claim 21, further comprising:
computing a location of the collision.

### Claim 29 (depends on 21)

The method of claim 21, further comprising:
computing an intensity of the collision.

### Claim 30

An apparatus comprising:
a processor; and
a memory storing instructions that, when executed by the processor, cause the apparatus to:
receive a first sequence of positional data associated with a first performance of a first participant in an event;
receive a second sequence of positional data associated with a second performance of a second participant in the event;
detect, based the first sequence of positional data and the second sequence of positional data, movements of the first participant and the second participant; and
determine, based on the movements of the first participant and the second participant, a collision between the first participant and the second participant.

### Claim 31 (depends on 30)

The apparatus of claim 30, wherein the memory stories additional instructions that, when executed by the processor, cause the apparatus to:
generate the first sequence of positional data and the second sequence of positional data based on an analysis of video content captured by one or more cameras positioned at a site of the event.

### Claim 32 (depends on 30)

The apparatus of claim 30, wherein detecting comprises:
extracting a first segment of positional data from the first sequence of positional data;
comparing the extracted first segment to one or more motion patterns, wherein each of the one or more motion patterns is associated with an action of interest; and
determining, based on a match between the extracted first segment and at least one motion pattern of the one or more motion patterns, an action performed by the first participant, wherein the determined action corresponds to an action of interest associated with the at least one matching motion pattern.

### Claim 33 (depends on 32)

The apparatus of claim 32, wherein each of the one or more motion patterns is associated with a data structure containing positional data, representative of an action of interest, and metadata, the metadata comprises one or more of a motion pattern identity, the action of interest, an identity of the first participant that performed the action of interest, or a list of events associated with the action of interest.

### Claim 34 (depends on 32)

The apparatus of claim 32, wherein the memory stories additional instructions that, when executed by the processor, cause the apparatus to:
update a pool of clusters, comprising the one or more motion patterns, with a new motion pattern associated with the extracted segment, the updating comprises computing an assignment score with respect to each of the clusters and adding, based on the computed assignment scores, the new motion pattern to one of the clusters.

### Claim 35 (depends on 30)

The apparatus of claim 30, wherein the memory stories additional instructions that, when executed by the processor, cause the apparatus to:
generate the first sequence of positional data and the second sequence of positional data based on an analysis of sensor data captured by one or more cameras sensors at a site of the event.

### Claim 36 (depends on 35)

The apparatus of claim 35, wherein detecting comprises:
extracting a first segment of positional data from the first sequence of positional data;
comparing the extracted first segment to one or more motion patterns, wherein each of the one or more motion patterns is associated with an action of interest; and
determining, based on a match between the extracted first segment and at least one motion pattern of the one or more motion patterns, an action performed by the first participant, wherein the determined action corresponds to an action of interest associated with the at least one matching motion pattern.

### Claim 37 (depends on 30)

The apparatus of claim 30, wherein the memory stories additional instructions that, when executed by the processor, cause the apparatus to:
compute a location of the collision.

### Claim 38 (depends on 30)

The apparatus of claim 30, wherein the memory stories additional instructions that, when executed by the processor, cause the apparatus to:
compute an intensity of the collision.

### Claim 39

A method comprising:
receiving a sequence of positional data associated with a performance of a participant in an event;
detecting, based on the sequence of positional data, one or more actions performed by the participant;
measuring, based on the detected one or more actions, an energy exerted by the participant; and
generating statistics based on the measured energy exerted by the participant.

### Claim 40 (depends on 39)

The method of claim 39, wherein measuring the energy comprises:
computing a kinetic energy generated by a joint or a dominant arm of the participant.
