System for determining anatomical feature orientation
The systems and methods disclosed herein provide determination of an orientation of a feature towards a reference target. As a non-limiting example, a system consistent with the present disclosure may include a processor, a memory, and a single camera affixed to the ceiling of a room occupied by a person. The system may analyze images from the camera to identify any objects in the room and their locations. Once the system has identified an object and its location, the system may prompt the person to look directly at the object. The camera may then record an image of the user looking at the object. The processor may analyze the image to determine the location of the user's head and, combined with the known location of the object and the known location of the camera, determine the direction that the user is facing. This direction may be treated as a reference value, or “ground truth.” The captured image may be associated with the direction, and the combination may be used as training input into an application.
1. An apparatus for determining an orientation of an anatomical feature, the apparatus comprising:
memory;
instructions;
processor circuitry to execute the instructions to:
prompt a subject within an environment to look toward a target within the environment;
identify an anatomical feature of the subject;
determine a location of the anatomical feature of the subject; and
determine an orientation of the anatomical feature of the subject based on a position of the anatomical feature, a location of the target, and machine learning circuitry,
wherein the machine learning circuitry is trained using a plurality of training images that include metadata identifying respective orientations of the anatomical feature included in the respective training image.
2. The apparatus of claim 1 , wherein the processor circuitry is to cause a camera to capture an image of the anatomical feature of the subject oriented toward the location of the target.
3. The apparatus of claim 1 , wherein the processor circuitry is to prompt the subject by causing emission of at least one of a sound or a visual cue.
4. The apparatus of claim 1 , wherein the anatomical feature is a facial feature of the subject.
5. The apparatus of claim 1 , wherein one or more of the plurality of training images includes the subject.
6. The apparatus of claim 1 , wherein one or more of the plurality of training images lack includes the subject.
7. A system for determining an orientation of an anatomical feature, the system comprising:
a storage device to store at least images and data;
processor circuitry to:
identify an anatomical feature of a subject within an environment;
prompt a subject within an environment to orient the anatomical feature toward an object within the environment;
determine a location of the anatomical feature of the subject within the environment;
determine a location of the target within the environment; and
determine an orientation of the anatomical feature based on the location of the anatomical feature, the location of the target, and machine learning circuitry,
wherein the machine learning circuitry is trained using a plurality of training images that include metadata identifying respective orientations of the anatomical feature included in the respective training image.
8. The system of claim 7 , wherein the processor circuitry is to cause a camera to capture an image of the anatomical feature of the subject oriented toward the location of the object and store the captured image on the storage device.
9. The system of claim 7 , wherein the processor circuitry is to prompt the subject to orient the anatomical feature toward the object by causing emission of at least one of a sound or a visual cue.
10. The system of claim 7 , wherein the anatomical feature is a head of the subject.
11. The system of claim 7 , wherein at least a portion of the plurality of training images include training images in which the subject appears.
12. The system of claim 7 , wherein at least a portion of the plurality of training images include training images in which the subject does not appear.
13. A method for determining an orientation of an anatomical feature, the method comprising:
prompting a subject within an environment to look toward a target within the environment;
identifying, by executing instructions with a processor, an anatomical feature of the subject;
determining, by executing instructions with the processor, a location of the anatomical feature; and
determining, by executing instructions with the processor, an orientation of the anatomical feature of the subject based on a position of the anatomical feature, a location of the target, and a machine learning application,
wherein the machine learning application is trained using a plurality of training images that include metadata identifying respective orientations of at least one anatomical feature included in the respective training image.
14. The method of claim 13 , further including causing, by executing instructions with the processor, a camera to capture an image of the anatomical feature of the subject oriented toward the location of the target.
15. The method of claim 14 , further including:
generating, by executing instructions with the processor, metadata based, at least in part, on the determined orientation of the anatomical feature in the environment; and
associating, by executing instructions with the processor, the metadata with the captured image.
16. The method of claim 15 , further including storing, by executing instructions with the processor, the captured image with the associated metadata on a storage device.
17. One or more computer-readable storage devices or storage disks having instructions stored thereon which, when executed by one or more processors, cause the one or more processors to at least:
identify an anatomical feature of a subject within an environment;
prompt a subject within an environment to orient the anatomical feature toward a target within the environment;
determine a location of the anatomical feature; and
determine an orientation of the anatomical feature based on the location of the anatomical feature, a location of the target, and machine learning based training using a plurality of training images that include metadata identifying respective orientations of at least one anatomical feature included in the respective training image.
18. The one or more computer-readable storage devices or storage disks of claim 17 , wherein the instructions, when executed by the one or more processors, cause the one or more processors to cause a camera to capture an image of the anatomical feature of the subject oriented toward the location of the target.
19. The one or more computer-readable storage devices or storage disks of claim 18 , wherein the instructions, when executed by the one or more processors, cause the one or more processors to:
generate metadata based, at least in part, on the determined orientation of the anatomical feature in the environment; and
associate the metadata with the captured image.
20. The one or more computer-readable storage devices or storage disks of claim 19 , wherein the instructions, when executed by the one or more processors, cause the one or more processors to store the captured image with the associated metadata.