基于迁移学习和AlexNet的驾驶员行为状态识别方法

为了解决传统基于神经网络算法的驾驶员行为状态识别系统精度过于依赖大量训练样本的问题，本文提出将迁移学习理论和AlexNet引入到驾驶员行为状态的识别研究中。首先对驾驶员行为特征及状态进行深入分析，对驾驶员7种驾驶状态进行了定义，构建了驾驶员状态信息采集系统；然后对基于卷积神经网络的驾驶员状态识别方法研究，建立了驾驶员状态数据集，构建了基于AlexNet卷积神经网络的状态监测系统，通过迁移学习完成了卷积神经网络识别模型。最后通过实验验证了本文提出的驾驶员状态识别算法对7种驾驶员状态识别的有效性。实验表明：该系统准确率达到97.8%，且在实验设备中运行速度达到70帧/分钟，满足较高的准确率要求与实时性要求。

Research on Driver Behavior Recognition Method Based on Migration Learning and AlexNet

In order to solve the problem that the accuracy of the traditional neural network-based driver behavior state recognition system is too dependent on a large number of training samples, this paper proposes to introduce the migration learning theory and AlexNet into the identification research of driver behavior state. Firstly, the driver''s behavior characteristics and state are analyzed in depth, and the driver''s seven driving states are defined. The driver state information acquisition system is constructed. Then the driver state recognition method based on convolutional neural network is studied to establish driving. Based on the state data set, a condition monitoring system based on AlexNet convolutional neural network is constructed. The convolutional neural network recognition model is completed through migration learning. Finally, the effectiveness of the driver state recognition algorithm proposed in this paper is verified for seven kinds of driver state recognition. Experiments show that the accuracy of the system reaches 97.8%, and the running speed in the experimental equipment reaches 70 frames/minute, which meets the high accuracy requirements and real-time requirements.