Comparison of the Deep Learning Methods Applied on Human Eye Detection

Abstract

For the fatigue driving detection of a driver wearing a mask, the traditional fatigue driving detection method cannot effectively detect the face. The characteristics of the mouth area are disappeared due to the mask’s occlusion. Therefore, the extraction of fatigue features in the eye area becomes very important. The accuracy of the eye area detection will directly affect the performance of the fatigue driving detection algorithm. At present, YOLOv3 and Faster-RCNN are both excellent models in the field of target detection. Therefore, this article uses the same data set and sets the same training parameters during training. Under a unified evaluation standard, the YOLOv3 model and the Faster-RCNN model are evaluated. Experimental results show that YOLOv3 has a better effect on human eye detection under the same conditions.