A Driver State Detection Method Based on Facial Expression

Abstract

The invention discloses a driver state detection method based on facial expressions. Through gray scale, Gamma correction and PCA dimension reduction processing, the size of the facial image is reduced and the features are enhanced. On this basis, the present invention constructs a convolutional neural network for facial expression recognition composed of sequentially connected four-layer structure, average pooling layer, dropout layer and softmax classifier. The number of parameters is small. At the same time, the inception structure is designed A new form is adopted, the traditional regular convolution 3*3 convolution is split into 1*3 convolution and 3*1 convolution, which saves a lot of parameters, speeds up operations and reduces overfitting. And a layer of nonlinear extension model expression ability is added, which can process more and richer spatial features and increase feature diversity. This inception structure design makes the facial expression recognition volume neural network more lightweight, and at the same time has a better detection effect, which improves the accuracy of driver state detection.

Description

technical field [0001] The invention belongs to the technical field of driver status, and more particularly, relates to a driver status detection method based on facial expression, that is, a method of detecting the driver's facial expression in real time and thereby judging the current driving status of the driver. method. Background technique [0002] The driver's driving state plays a crucial role in safe driving. By detecting the driver's driving state in real time, the driver's safe driving can be well ensured. [0003] At present, the analysis and judgment of the driver's driving state is mainly divided into two categories: contact type and non-contact type. Among them, the contact method mainly uses wearable devices to detect the physiological signals such as the driver's brain electrical signal and myoelectric signal to determine the driver's driving state. The main disadvantage of this method is that the detection process will affect the driver's safe driving. And...

AI Technical Summary

Problems solved by technology

[0005] However, the existing driver state detection based on facial tags has a large number of parameters and low calculation speed, which affects the real-time performance of driver state detection.

At the same time, the accuracy needs to be improved

Images