Li Pu, Liu Ziye, Shan Hangguan, Chen Chen
College of Information Science & Electronic Engineering, Zhejiang University, Hangzhou 310027, China.
Xidian Hangzhou Institute of Technology, Xidian University, Hangzhou 311200, China.
Sensors (Basel). 2025 Mar 12;25(6):1769. doi: 10.3390/s25061769.
Recognizing dangerous driving actions is critical for improving road safety in modern transportation systems. Traditional Driver Monitoring Systems (DMSs) often face challenges in terms of lightweight design, real-time performance, and robustness, especially when deployed on resource-constrained embedded devices. This paper proposes a novel method based on 3D skeletal data, combining Graph Spatio-Temporal Feature Representation (GSFR) with a Broad Learning System (BLS) to overcome these challenges. The GSFR method dynamically selects the most relevant keypoints from 3D skeletal data, improving robustness and reducing computational complexity by focusing on essential driver movements. The BLS model, optimized with sparse feature selection and Principal Component Analysis (PCA), ensures efficient processing and real-time performance. Additionally, a dual smoothing strategy, consisting of sliding window smoothing and an Exponential Moving Average (EMA), stabilizes predictions and reduces sensitivity to noise. Extensive experiments on multiple public datasets demonstrate that the GSFR-BLS model outperforms existing methods in terms of accuracy, efficiency, and robustness, making it a suitable candidate for practical deployment in embedded DMS applications.
识别危险驾驶行为对于提高现代交通系统的道路安全至关重要。传统的驾驶员监测系统（DMS）在轻量化设计、实时性能和鲁棒性方面常常面临挑战，尤其是在部署于资源受限的嵌入式设备时。本文提出了一种基于三维骨骼数据的新颖方法，将图时空特征表示（GSFR）与广义学习系统（BLS）相结合，以克服这些挑战。GSFR方法从三维骨骼数据中动态选择最相关的关键点，通过聚焦驾驶员的关键动作提高鲁棒性并降低计算复杂度。经稀疏特征选择和主成分分析（PCA）优化的BLS模型确保了高效处理和实时性能。此外，由滑动窗口平滑和指数移动平均（EMA）组成的双重平滑策略稳定了预测并降低了对噪声的敏感度。在多个公共数据集上进行的大量实验表明，GSFR-BLS模型在准确性、效率和鲁棒性方面优于现有方法，使其成为嵌入式DMS应用中实际部署的合适候选方案。
