What is it about?
Fatigue detection with 3D facial features based on binocular stereo vision
Why is it important?
Fatigue detection by 3D facial feature method is presented in this paper, with the aim of solving lowaccuracy problems with 2D facial image-detection method. The main works include (1) using two cameras to take facial binocular images, with which facial depth map is obtained, and then according to facial concave and convex features, curvature feature is used to locate stereo facial fatigue feature point in depth map; (2) based on the location of feature points, stereofacial fatigue features are extracted in depth maps, and their feature values are calculated; and (3) all stereo facial fatigue features are to form one fused facial fatigue feature vector, and with LDA algorithm, facial fatigue expressions are classified into three categories: normal status, slight fatigue status, and severe fatigue status.
Read the Original
This page is a summary of: Fatigue detection with 3D facial features based on binocular stereo vision, Integrated Computer-Aided Engineering, May 2014, IOS Press, DOI: 10.3233/ica-140476.
You can read the full text:
The following have contributed to this page