# US 2026/0248107 A1 · System and method for markerless biomechanics of equines

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

- Number: US 2026/0248107 A1
- Document ID: US20260248107A1
- Status: Published application
- Kind: A1
- Application number: 19/546,897
- Filed: 2026-02-23
- Published: 2026-08-27
- Earliest claimed: 2025-02-25
- Assignees: Southwest Research Institute
- Applicants: Southwest Research Institute
- Inventors: Omar D. MEDJAOURI; Sarah K. SHAFFER; Brian C. SWENSON
- Web page: https://patentgrep.com/patent/US20260248107A1

## CPC

- A01K 29/005: {Monitoring or measuring activity}
- G06T 7/75: {involving models}
- A61D 99/00: Subject matter not provided for in other groups of this subclass
- G06T 7/246: using feature-based methods, e.g. the tracking of corners or segments
- G06T 7/248: {involving reference images or patches}
- G06T 7/251: {involving models}
- G06T 7/60: Analysis of geometric attributes
- G06T 7/73: using feature-based methods
- G06T 7/74: {involving reference images or patches}
- G06T 7/80: Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
- H04N 23/90: Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums
- G06T 2207/10016: Video; Image sequence
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30241: Trajectory
- A01K: ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- A61D: VETERINARY INSTRUMENTS, IMPLEMENTS, TOOLS, OR METHODS
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

In an approach to markerless biomechanics of equines, a method includes: receiving a plurality of camera views from a plurality of markerless video cameras; calibrating the plurality of markerless video cameras to create camera calibration information for each of the plurality of markerless video cameras; predicting a two-dimensional location of skeletal landmarks in each of the plurality of camera views; performing triangulation to reconstruct a three-dimensional location of each predicted landmark based on the predicted two-dimensional location of the skeletal landmarks and the camera calibration information; regionally scaling a musculoskeletal model using the three-dimensional location of each predicted landmark; and performing inverse kinematics on the musculoskeletal model to produce kinematic trajectories.

## Claims

### Claim 1

A method for markerless biomechanics of equines, the method comprising:
receiving a plurality of camera views from a plurality of markerless video cameras;
predicting a two-dimensional location of skeletal landmarks in each of the plurality of camera views;
performing triangulation to reconstruct a three-dimensional location of each predicted landmarks based on a predicted two-dimensional location of the skeletal landmarks and camera calibration information for each of the plurality of markerless video cameras;
regionally scaling a musculoskeletal model using the three-dimensional location of each of the predicted landmarks; and
performing inverse kinematics on the musculoskeletal model to produce kinematic trajectories.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
calibrating the plurality of markerless video cameras to create the camera calibration information for each of the plurality of markerless video cameras, wherein the camera calibration information includes at least one of intrinsic parameters and extrinsic parameters.

### Claim 3 (depends on 2)

The method of claim 2, wherein:
the intrinsic parameters of each of the plurality of markerless video cameras include at least one of an intrinsic matrix (K) and a distortion coefficients (d); and
the extrinsic parameters of each of the plurality of markerless video cameras include at least one of a rotation matrix (R) and a translation vector (t).

### Claim 4 (depends on 1)

The method of claim 1, wherein predicting the two-dimensional location of the skeletal landmarks in each of the plurality of camera views uses a convolutional neural network (CNN).

### Claim 5 (depends on 1)

The method of claim 1, wherein performing the triangulation to reconstruct the three-dimensional location of each of the predicted landmarks based on the predicted two-dimensional location of the skeletal landmarks and the camera calibration information for each of the plurality of markerless video cameras comprises:
selecting two-dimensional points from different camera views of the of the plurality of camera views;
measuring an error between a resulting three-dimensional point and the two-dimensional point; and
selecting the two-dimensional point and the three-dimensional point having a lowest error.

### Claim 6 (depends on 2)

The method of claim 2, wherein the triangulation is performed using a random sample consensus (RANSAC) algorithm.

### Claim 7 (depends on 6)

The method of claim 6, wherein the RANSAC algorithm comprises:
for each video frame in each of the plurality of camera views:
selecting one or more pairs of two-dimensional skeletal landmarks;
for each selected pair of the one or more pairs of two-dimensional skeletal landmarks:
computing one or more three-dimensional rays originating at a source camera for each of the two-dimensional skeletal landmarks using the intrinsic parameters and the extrinsic parameters of the source camera;
locating a nearest point to each of the one or more three-dimensional rays for each of the one or more pairs of two-dimensional skeletal landmarks to obtain one or more candidate three-dimensional locations for each of the two-dimensional skeletal landmarks;
calculating a first number of inliers and a second number of outliers for each of the one or more candidate three-dimensional locations;
selecting a best candidate location of the one or more candidate three-dimensional locations that minimizes the second number of the outliers; and
projecting the best candidate location into each of the plurality of camera views to derive a horse rectangular region of interest on a following frame for each of the plurality of camera views.

### Claim 8 (depends on 1)

The method of claim 1, wherein the musculoskeletal model is regionally scaled using the three-dimensional location of one or more of the predicted landmarks.

### Claim 9 (depends on 1)

The method of claim 1, wherein the inverse kinematics is performed using a software platform.

### Claim 10

A system for markerless biomechanics of equines, the system comprising:
a plurality of markerless video cameras;
camera calibration circuitry;
two-dimensional landmark location circuitry;
three-dimensional triangulation circuitry;
musculoskeletal scaling circuitry;
inverse kinematics circuitry; and
a computing device, the computing device configured to:
receive a plurality of camera views from the plurality of markerless video cameras;
calibrate the plurality of markerless video cameras using the camera calibration circuitry to create camera calibration information for each of the plurality of markerless video cameras;
predict a two-dimensional location of skeletal landmarks in each of the plurality of camera views using the two-dimensional landmark location circuitry;
perform triangulation to reconstruct a three-dimensional location of each predicted landmark based on a predicted two-dimensional location of the skeletal landmarks and the camera calibration information using the three-dimensional triangulation circuitry;
regionally scale a musculoskeletal model using the three-dimensional location of each of the predicted landmarks; and
perform inverse kinematics on the musculoskeletal model to produce kinematic trajectories.

### Claim 11 (depends on 10)

The system of claim 10, wherein the camera calibration circuitry is configured to:
determine intrinsic parameters of each of the plurality of markerless video cameras; and
determine extrinsic parameters of each of the plurality of markerless video cameras.

### Claim 12 (depends on 11)

The system of claim 11, wherein the intrinsic parameters of each of the plurality of markerless video cameras include at least one of an intrinsic matrix (K) and a distortion coefficients (d).

### Claim 13 (depends on 11)

The system of claim 11, wherein the extrinsic parameters of each of the plurality of markerless video cameras include at least one of a rotation matrix (R) and a translation vector (t).

### Claim 14 (depends on 10)

The system of claim 10, wherein the two-dimensional landmark location circuitry further comprises:
convolutional neural network (CNN) circuitry.

### Claim 15 (depends on 11)

The system of claim 11, wherein the three-dimensional triangulation circuitry further comprises:
a random sample consensus (RANSAC) algorithm.

### Claim 16 (depends on 15)

The system of claim 15, wherein the RANSAC algorithm configured to:
for each video frame in each of the plurality of camera views:
select one or more pairs of two-dimensional skeletal landmarks;
for each selected pair of the one or more pairs of two-dimensional skeletal landmarks:
compute one or more three-dimensional rays originating at a source camera for each of the two-dimensional skeletal landmarks using the intrinsic parameters and the extrinsic parameters of the source camera;
locate a nearest point to each of the one or more three-dimensional rays for each of the one or more pairs of two-dimensional skeletal landmarks to obtain one or more candidate three-dimensional locations for each of the two-dimensional skeletal landmarks;
calculate a first number of inliers and a second number of outliers for each of the one or more candidate three-dimensional locations;
select a best candidate location of the one or more candidate three-dimensional locations that minimizes the second number of the outliers; and
project the best candidate location into each of the plurality of camera views to derive a horse rectangular region of interest on a following frame for each of the plurality of camera views.

### Claim 17 (depends on 10)

The system of claim 10, wherein the musculoskeletal model is regionally scaled using the three-dimensional location of the predicted landmarks.

### Claim 18 (depends on 10)

The system of claim 10, wherein the computing device further configured to:
perform the inverse kinematics using a software platform.

### Claim 19

A method for markerless biomechanics of equines, the method comprising:
receiving a plurality of camera views from a plurality of markerless video cameras;
calibrating the plurality of markerless video cameras to create camera calibration information for each of the plurality of markerless video cameras, wherein the camera calibration information includes at least one of intrinsic parameters and extrinsic parameters;
predicting a two-dimensional location of skeletal landmarks in each of the plurality of camera views;
performing triangulation to reconstruct a three-dimensional location of each predicted landmark based on a predicted two-dimensional location of the skeletal landmarks and the camera calibration information, wherein the triangulation comprises:
for each video frame in each of the plurality of camera views:
selecting one or more pairs of two-dimensional skeletal landmarks;
for each selected pair of the one or more pairs of two-dimensional skeletal landmarks:
computing one or more three-dimensional rays originating at a source camera for each two-dimensional skeletal landmark of the one or more pairs of two-dimensional skeletal landmarks using the intrinsic parameters and the extrinsic parameters of the source camera;
locating a nearest point to each of the one or more three-dimensional rays for each of the one or more pairs of two-dimensional skeletal landmarks to obtain one or more candidate three-dimensional locations for each of the two-dimensional skeletal landmarks;
calculating a first number of inliers and a second number of outliers for each of the one or more candidate three-dimensional locations;
selecting a best candidate location of the one or more candidate three-dimensional locations that minimizes the second number of the outliers; and
projecting the best candidate location into each of the plurality of camera views to derive a horse rectangular region of interest on a following frame for each of the plurality of camera views;
regionally scaling a musculoskeletal model using the three-dimensional location of each of the predicted landmarks; and
performing inverse kinematics on the musculoskeletal model to produce kinematic trajectories.

### Claim 20 (depends on 19)

The method of claim 19, wherein predicting the two-dimensional location of the skeletal landmarks in each of the plurality of camera views uses a convolutional neural network (CNN).
