DRTFace lib

[Detect | Recognize | Track] Face

Introduction

DRTFace is a C++ library, which allows for real-time detection, tracking and recognition of faces and objects in videos and image sequences. It can estimate gender, age, race and emotions

Human analytics is the capture and analysis of measured human responses and behavior. Our face analysis algorithms are able to recognize and understand how people feel in video. Main keyfeatures of the library are:

  • Arbitrary number of faces
  • Position of the face, the eyes, nose and mouth
  • Gender and race classification
  • Age estimation
  • Emotions recognition (“sad”, “calm”, and “happy”)
DRTFace

Hyperlapse Stabilization

Project X Hyperlapse Stabilization is a technology that removes annoying shaky motion from videos and creates smooth and stabilized time lapses from image sequences. Video stabilization is an important video enhancement technology which is in great demand in timelapse and hyperlapse photography. We dewelop a practical and robust approach of video stabilization that produces stabilized videos with good visual quality:

See more details…

DRTFace in Publications

 

  • Active Illumination for Variational Space-Time Stereo

  • Rapid Stereo-Vision Enhanced Face Recognition