%0 Journal Article
%T 基于YOLOv8的驾驶员分心状态识别算法研究<br>Research on Driver Distracted State Recognition Algorithm Based on YOLOv8
%A 庞夏君
%A 刘玉情
%J Software Engineering and Applications
%P 38-48
%@ 2325-2278
%D 2026
%I Hans Publishing
%R 10.12677/sea.2026.151005
%X 准确、快速检测分心驾驶行为对于提高道路安全和预防交通事故至关重要。从驾驶员分心驾驶行为特点出发&#65292;提出了基于改进YOLOv8n的分心驾驶行为检测算法。首先是引入了简单注意力机制(SimAM)对每个特征图进行自归一化&#65292;强调具有有价值信息的特征图&#65292;抑制复杂背景中的冗余信息干扰。其次为了提高对小目标物体的检测性能&#65292;增加了小目标检测层&#65292;使模型能够更准确地检测和定位尺寸较小的目标&#65292;提高目标检测系统在复杂场景下的稳定性和鲁棒性。最后在公开和收集到的数据集上进行了验证&#65292;模型精度提高了4.2%。分心驾驶检测准确率分别达到90.4%验证了所提模型在辅助驾驶时分心驾驶检测和降低事故风险方面的卓越性能。<br>Accurate and rapid detection of distracted driving behavior is critical to improving road safety and preventing traffic accidents. Based on the characteristics of drivers&#8217; distracted driving behavior, an improved YOLOv8n distracted driving behavior detection algorithm is proposed. Firstly, a simple attention mechanism (SimAM) is introduced to self-normalize each feature map, emphasizing the feature maps with valuable information and suppressing the interference of redundant information in complex background. Secondly, in order to improve the detection performance of small target objects, a small target detection layer is added, so that the model can detect and locate smaller targets more accurately, and improve the stability and robustness of the target detection system in complex scenes. Finally, the accuracy of the model is improved by 4.2% on the published and collected data sets. The accuracy of distracted driving detection reached 90.4% respectively, which verified the excellent performance of the proposed model in detecting distracted driving and reducing accident risk during assisted driving.
%K 分心驾驶&#65292
%K YOLOv8n&#65292
%K 注意力机制&#65292
%K 小目标检测<br>Distracted Driving
%K YOLOv8n
%K Attention Mechanism
%K Small Target Detection
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=135465