Driver Yawning Detection Based on Subtle Facial Action Recognition

Various investigations have shown that driver fatigue is the main cause of traffic accidents. Research on use computer vision techniques to detect signs from facial actions, such as yawning, has demonstrated good potential. However, accurate and robust detection yawning difficult because complicated actions expressions drivers in real driving environment. Several same mouth deformation yawning. Thus, a novel approach detecting based subtle action recognition proposed this study alleviate abovementioned problems. A 3D deep learning network with low time sampling characteristic for recognition. This uses convolutional bidirectional long short-term memory networks spatiotemporal feature extraction adopts SoftMax classification. keyframe selection algorithm designed select most representative frame sequence actions. rapidly eliminates redundant frames using image histograms computation cost detects outliers by median absolute deviation. series experiments are also conducted YawDD benchmark self-collected datasets. Compared several state-of-the-art methods, method high rates can effectively distinguish similar