Driver Distraction Detection Algorithm Based on High-Order Global Interaction Features

Chuanghui Zhang

doi:10.54097/0cmmyb47

Authors

Chuanghui Zhang

DOI:

https://doi.org/10.54097/0cmmyb47

Keywords:

Global Interaction, YOLO, Distracted Driving, Attention Mechanism

Abstract

Distracted driving behavior is one of the main causes of road traffic safety problems. In view of the problems of high model complexity, unstable detection performance and high hardware cost of existing distraction detection algorithms, this paper proposes a driver distraction detection algorithm based on high-order global interaction features. First, the backbone network is reconstructed using the C3-HB module, in which the HorNet recursive gated convolution is used to learn the long-range dependencies of the image and obtain high-order features, and the bottleneck in the C3 module is replaced by Hornet Block, which improves the detection accuracy of small targets and complex scenes; secondly, the global parallel attention mechanism PGAM is designed to enhance the perception ability of global interaction features and reduce local information loss; finally, the loss function of YOLOv5s is replaced by α-CIOU, which effectively balances the difficult and easy samples and further optimizes the detection effect of driver distraction. Experiments show that the model proposed in this paper achieves an mAP50 of 97.32% on the State Farm dataset and the self-built dataset. While improving the detection accuracy, the number of parameters is only 8.68M and the computational complexity is 12.80GFLOPs, showing excellent comprehensive performance and is suitable for tasks that require real-time and high precision.

Downloads

Download data is not yet available.

References

Khan, M.N. and S. Das, Advancing traffic safety through the safe system approach: A systematic review. Accident Analysis & Prevention, 2024. 199: p. 107518.

[2] Kashevnik, A., et al., Driver distraction detection methods: A literature review and framework. IEEE Access, 2021. 9: p. 60063-60076.

[3] Bouhsissin, S., N. Sael, and F. Benabbou, Driver behavior classification: A systematic literature review. IEEE Access, 2023. 11: p. 14128-14153.

[4] Tran, D., et al. Real-time detection of distracted driving using dual cameras. in 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). 2020. IEEE.

[5] Peng, Q., C. Zheng, and C. Chen. A dual-augmentor framework for domain generalization in 3d human pose estimation. in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2024.

[6] Ren, W., N. Jin, and L. OuYang, Phase space graph convolutional network for chaotic time series learning. IEEE Transactions on Industrial Informatics, 2024.

[7] Lou, C. and X. Nie, Research on lightweight-based algorithm for detecting distracted driving behaviour. Electronics, 2023. 12(22): p. 4640.

[8] Du, Y., et al., Optimizing road safety: Advancements in lightweight YOLOv8 models and GhostC2f design for real-time distracted driving detection. Sensors, 2023. 23(21): p. 8844.

[9] Jocher, G., et al., ultralytics/yolov5: v6. 2-yolov5 classification models, apple m1, reproducibility, clearml and deci. ai integrations. Zenodo, 2022.

[10] Wang, C.-Y., et al. CSPNet: A new backbone that can enhance learning capability of CNN. in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops. 2020.

[11] [Wang, K., et al. Panet: Few-shot image semantic segmentation with prototype alignment. in proceedings of the IEEE/CVF international conference on computer vision. 2019.

[12] Gong, Y., et al. Effective fusion factor in FPN for tiny object detection. in Proceedings of the IEEE/CVF winter conference on applications of computer vision. 2021.

[13] Liu, Y., Z. Shao, and N. Hoffmann, Global attention mechanism: Retain information to enhance channel-spatial interactions. arXiv preprint arXiv:2112.05561, 2021.

[14] Zhu, X., et al. An empirical study of spatial attention mechanisms in deep networks. in Proceedings of the IEEE/CVF international conference on computer vision. 2019.

[15] Qin, Z., et al. Fcanet: Frequency channel attention networks. in Proceedings of the IEEE/CVF international conference on computer vision. 2021.

Rao, Y., et al., Hornet: Efficient high-order spatial interactions with recursive gated convolutions. Advances in Neural Information Processing Systems, 2022. 35: p. 10353-10366.