Skip to main content

Depth perception and spatial localization from MediaPipe face mesh coordinates. Tracks within an inch at 5ft distance from the camera

Project description

Holosense

Tracks the location of your face in 3 dimensions relative to the camera, using coordinates from MediaPipe FaceMesh.

How to use

Holosense is setup like this.

from holosense import SpatialTracker

spatial_tracker = SpatialTracker(
    fov=78.5,
    aspectratio=16/9,
    eyedistance=4,
    eyenosedistance=3,
    single_output=True
    )

The keyword arguments represent the camera's field of view, image aspect ratio, distance between the corners of the eye of the user, distance between the corner of the eye and tip of the nose of the user, and whether the program provides a single set of coordinates (if it is set to true) or a list with the coordinates of both eyes and the nose.

Now, to use the tracker, run:

res = spatial_tracker.calculatePosition(face_landmarks)

where face_landmarks are the facial landmarks determined by mediapipe facemesh

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

holosense-0.1.0.tar.gz (4.6 kB view details)

Uploaded Source

Built Distribution

holosense-0.1.0-py3-none-any.whl (5.3 kB view details)

Uploaded Python 3

File details

Details for the file holosense-0.1.0.tar.gz.

File metadata

  • Download URL: holosense-0.1.0.tar.gz
  • Upload date:
  • Size: 4.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.9.19

File hashes

Hashes for holosense-0.1.0.tar.gz
Algorithm Hash digest
SHA256 d321a0c03a38e820723a5f6ada5434507ae9101c20ad139460b66266bba459f5
MD5 9c7a11271346692c9acefd3d791de241
BLAKE2b-256 bfbdd25066c0c00c5b894f837196c76a2fdcc314d52e99c844be4c9812d3d871

See more details on using hashes here.

File details

Details for the file holosense-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: holosense-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 5.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.9.19

File hashes

Hashes for holosense-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 25075149f7ca0247e6b28cdcd96f00d4274878ab9bd0fcd033a20cf050e37968
MD5 98d88feea7d913c92d1a14edecf200ef
BLAKE2b-256 b22163225db791ae7a522448f21f2e7fe783822466a4423b40b0c5ff66e9e40d

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page