What does this research mean for the field?

A visual-tactile fusion framework (TransWindow) that integrates visual and seat-embedded pressure sensors achieves 98.77% accuracy in detecting dangerous driving behaviors while maintaining lower computational complexity than state-of-the-art Transformer-based methods. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

The aim is to enhance the detection of dangerous driving behaviors by integrating multiple sensor modalities.

May 17, 2026Open Access

Dangerous driving behavior detection method in vehicle intelligent cockpit based on transwindow multimodal fusion

Puntos clave

The aim is to enhance the detection of dangerous driving behaviors by integrating multiple sensor modalities.
Proposed a visual-tactile fusion framework combining visual and tactile sensor data.
Utilized a hybrid dataset from simulated and real-world scenarios for evaluation.
Compared the performance of the TransWindow model against state-of-the-art Transformer-based methods.
Achieved 98.77% accuracy in detecting dangerous driving behaviors.
Demonstrated lower computational complexity compared to existing Transformer-based approaches.
Enhanced robustness and reliability in adverse conditions like low illumination.

Resumen

Driver behavior is a critical determinant of road safety; thus, real-time monitoring of dangerous behaviors, such as fatigue and distraction, is essential for intelligent cockpit systems. However, existing in-vehicle sensing technologies are highly susceptible to environmental variations, particularly illumination changes, which result in unstable driver feature extraction. Moreover, Transformer-based models typically incur high computational overhead due to their global self-attention mechanisms, making it challenging to achieve an optimal balance between efficiency and accuracy in Driver Monitoring Systems (DMS). To address these challenges, a visual-tactile fusion framework for dangerous driving behavior detection is proposed. The framework integrates visual sensors with seat-embedded pressure sensors, enabling complementary perception across modalities. Specifically, visual cues facilitate accurate recognition of facial expressions and postures, while tactile signals remain robust under adverse conditions, such as low illumination and occlusion. This complementary fusion significantly enhances system robustness and reliability. Experimental results on a hybrid dataset collected from both simulated and real-world driving scenarios demonstrate the effectiveness of the proposed approach. Compared with state-of-the-art Transformer-based methods and their variants, the proposed TransWindow model achieves an accuracy of 98.77% while maintaining substantially lower computational complexity. These results indicate that the proposed method effectively balances accuracy and efficiency, satisfies the real-time performance of DMS, and provides a promising direction for the continuous optimization of intelligent cockpit systems.

Preguntar a la IA

Me gusta

Guardar

Ver artículo completo