Robust Estimation of Driver Posture in the Presence of Lighting Changes

摘要

In this study, we aim for posture estimation that considers the influence of lighting changes. We propose an algorithm that considers a bad condition by using 3D data and 2D animation. The decrease of the gaze forward rate caused by the psychological condition and ensuing tiredness is a problem of safety driving. There is a technique for detecting looking away and looking down for a long time by estimation of the driver's face posture from the image as this method of settlement. However, the conventional technique uses images in the posture estimation, which has the problem of a strong influence on the lighting condition and the size of the database. This technique pays too much attention to lighting changes 3D data and texture information. Making the database solved these problems; the accuracy average obtained was 89% and the estimation speed was 6 f/s.