Skip to content

Face Detection and Recognition Data Format

Simeon ADEBOLA edited this page Sep 5, 2018 · 10 revisions

This is an example of face detection and recognition's data format:

{
   "header": {
       "seq": 71251,
       "stamp": {
           "sec": 1415305737,
           "nsec": 110138944
       },
       "frame_id": "world"
   },
   "tracks": [{
       "id": 387,
       "stable_id": 1147,
       "face_name":  "Sam",
       "x": -0.89131,
       "y": 2.41851,
       "height": 1.55837,
       "age": 29.471,
       "confidence": 0.0500193
   }]
}
  • ID is the unique identification associated with the track.
  • stable_id is the stable ID for this track, generated by OpenFace's face recognition (i.e. once recognized, a person will get stable ID for the lifetime of OpenPTrack session)
  • face_name is the name of the identified closest matching face, from faces trained into the system using the drag and drop people registration tool
  • Units for x, y, and height are meters, which is true across all the other JSON message types provided in OpenPTrack.
  • age is how long that ID has been active for.
  • confidence represents the system's calculation of how reliable the track is. It refers to the OpenPTrack tracking confidence, and is unrelated to face detection/tracking.

N.B.: The packet replaces the OpenPTrack packet and is sent to the same port.

Setting Up an OpenPTrack v2 System:

Running OpenPTrack v2:

Tracking GUI

How to receive tracking data in:

  1. Tested Hardware
  2. Network Configuration
  3. Imager Mounting and Placement
  4. Calibration in Practice
  5. Quick Start Example
  6. Imager Settings
  7. Manual Ground Plane
  8. Calibration Refinement (Person-Based)
  9. Calibration Refinement (Manual)

OPT on the NVidia Jetson

Clone this wiki locally