DSDFormer: An Innovative Transformer-Mamba Framework for Robust High-Precision Driver Distraction Identification
This addresses the problem of accurate and real-time driver distraction detection for road safety, offering a scalable solution with incremental improvements in robustness and efficiency.
The paper tackled driver distraction identification by proposing DSDFormer, a Transformer-Mamba framework with a Dual State Domain Attention mechanism and Temporal Reasoning Confident Learning for handling noisy labels, achieving state-of-the-art performance on AUC-V1, AUC-V2, and 100-Driver datasets with real-time processing on NVIDIA Jetson AGX Orin.
Driver distraction remains a leading cause of traffic accidents, posing a critical threat to road safety globally. As intelligent transportation systems evolve, accurate and real-time identification of driver distraction has become essential. However, existing methods struggle to capture both global contextual and fine-grained local features while contending with noisy labels in training datasets. To address these challenges, we propose DSDFormer, a novel framework that integrates the strengths of Transformer and Mamba architectures through a Dual State Domain Attention (DSDA) mechanism, enabling a balance between long-range dependencies and detailed feature extraction for robust driver behavior recognition. Additionally, we introduce Temporal Reasoning Confident Learning (TRCL), an unsupervised approach that refines noisy labels by leveraging spatiotemporal correlations in video sequences. Our model achieves state-of-the-art performance on the AUC-V1, AUC-V2, and 100-Driver datasets and demonstrates real-time processing efficiency on the NVIDIA Jetson AGX Orin platform. Extensive experimental results confirm that DSDFormer and TRCL significantly improve both the accuracy and robustness of driver distraction detection, offering a scalable solution to enhance road safety.