提出了一个名为CBAM-EfficientNetB0的框架,旨在解决低参数条件下司机分心行为识别准确率低的问题.它集成了 CBAM注意力机制,包括通道注意力模块和空间注意力模块.这使得网络更加关注重要的特征信息,从而提高了特征的区分度和表达能力.通过将模型的优化器转换为SGD,并获得优化的学习率和动量参数,提高了模型的识别准确率和收敛性.CBAM-EfficientNetB0 在 State Farm Distracted Driver Detection 数据集上达到了 96.8％的准确率.结果显示,与同类的框架相比,它在低参数条件下表现良好.
Study of Driver Distraction Detection Based on the EfficientNetB0
The article proposes a framework named CBAM-EfficientNetB0,aiming to address the issue of low accuracy in distracted driver behavior recognition under low-parameter conditions.It integrates CBAM attention mechanisms,including channel attention modules and spatial attention mod-ules.This enables the network to focus more on important feature information,thereby improving fea-ture discriminability and expressiveness.By converting the model's optimizer to SGD and obtaining opti-mized learning rate and momentum parameters,the model's recognition accuracy and convergence are improved.CBAM-EfficientNetB0 achieves an accuracy of 96.8％on the State Farm distracted driver detection dataset.The results demonstrate its strong performance under low-parameter conditions compared to similar frameworks.
万方数据
维普
