MULTISCALE DYNAMIC FEATURES BASED DRIVER FATIGUE DETECTION

Abstract

Driver fatigue is a significant factor in many traffic accidents. We propose a novel approach for driver fatigue detection from facial image sequences, which is based on multiscale dynamic features. First, Gabor filters are used to get a multiscale representation for image sequences. Then Local Binary Patterns are extracted from each multiscale image. To account for the temporal aspect of human fatigue, the LBP image sequence is divided into dynamic units, and a histogram of each dynamic unit is computed and concatenated as dynamic features. Finally a statistical learning algorithm is applied to extract the most discriminative features from the multiscale dynamic features and construct a strong classifier for fatigue detection. The proposed approach is validated under real-life fatigue conditions. The test data includes 600 image sequences with illumination and pose variations from 30 people's videos. Experimental results show the validity of the proposed approach, and a correct rate of 98.33% is achieved which is much better than the baselines.