The face detection and tracking is a computer technology that significantly improves human-machine interaction and opens a very wide range of applications, such as driver drowsiness detection in automotive safety systems, speaker detection in video conferencing systems capable to automatically zoom to the current speaker, hands-free interfacing helping disabled people to improve their daily lives, character animations in virtual reality entertainment, audio processing, robotics, etc.
The logiFDT Face Detector and Tracker IP core finds and tracks the face and facial features in video sequences in real time and returns full 3D head pose, gaze direction, facial features coordinates and a wealth of other information. It is carefully partitioned between hardware and software to assure the highest performances (i.e. 30fps) and optimal utilization of the Xilinx Zynq-7000 AP SoC. The logiFDT IP core is prepackaged for Xilinx Vivado IP Integrator and ISE Platform Studio.
Configurable face tracking engine optimized for Xilinx® Zynq®-7000 AP SoC
Real-time face and facial features tracking:
3D head pose (translation and rotation)
Gaze direction and eye closure
Facial feature coordinates in global 3D space
Feature points specified according to the MPET-4 FBA standard
Action units describing the current facial expressing, i.e. brow raise, lips stretch...
Other tracking data...
Fully automatic operation and robust recovering from losses due to occlusions, face turning away and similar
Tracking can work on a video recorded by color, grayscale and infrared camera. For thermal video info, please contact us
Carefully HW/SW partitioned to assure max. performance and min. resources utilization
Free reference design available
Available for Xilinx Vivado® IP Integrator and ISE® Platform Studio