The OKAO extractor analyses images from video files and stores the information in log files for later offline analysis. The extracted information relate to the position of the user(s) in relation to the camera, their head rotation, eye gaze information, facial expressions and smile estimation. This module also calculates user’s gaze based on head and eyes direction and outputs the information to the perception module. This module was developed using C++. It has been used with multiple video files to extract facial features information for later analysis.
Data structure of log file:
time,Faceupdown,Faceleftright,Eyesupdown,Eyesleftright,posX,posY,CloseRatioLeftEye,CloseRatioRightEye,Smile,Confidence,Neutral,Happiness,Surprise,Fear,Anger,Disgust, Sadness,GazevectorX,GazevectorY,labeled gaze
Download & Instructions
This module requires a license from OMRON corp. Academic users can contact Kozo at email@example.com to enquire about a license. It requires a HASP key. Windows will automatically recognize and download the HASP drivers.
It is advised to install a DIVX codec to make sure openCV can recognize the video input.
OKAO module accepts command line arguments for camera ID and scenario number
camera ID can be from 0 to 100
scenario can be either 1 or 2
default values are 0 and 1 (first available camera and scenario 1)
Please contact Fotis at firstname.lastname@example.org for access to these modules.