cheind/dest

:panda_face: One Millisecond Deformable Shape Tracking Library (DEST)

50
/ 100
Established

This tool helps researchers, developers, and engineers quickly and accurately identify and track specific points (landmarks) on deformable shapes, such as human faces, within images or video. You input an image or video, optionally with a rough estimate of the shape's location (like a face detector output), and it outputs the precise coordinates of the landmarks. This is ideal for anyone working with real-time analysis of dynamic visual data.

291 stars. No commits in the last 6 months.

Use this if you need a high-performance solution for real-time tracking of facial landmarks or other deformable shapes in video streams or images.

Not ideal if your primary goal is general object detection or if you require tracking of rigid, non-deforming objects.

facial-analysis video-annotation biometrics human-computer-interaction computer-vision-engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

291

Forks

106

Language

C++

License

BSD-3-Clause

Last pushed

Dec 29, 2016

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/cheind/dest"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.