Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Aug 6;25(15):4832.
doi: 10.3390/s25154832.

YOLO-FDCL: Improved YOLOv8 for Driver Fatigue Detection in Complex Lighting Conditions

Genchao Liu  1 , Kun Wu  2 , Wei Lan  2 , Yunjie Wu  3
Affiliations

YOLO-FDCL: Improved YOLOv8 for Driver Fatigue Detection in Complex Lighting Conditions

Genchao Liu et al. Sensors (Basel). .

Abstract

Accurately identifying driver fatigue in complex driving environments plays a crucial role in road traffic safety. To address the challenge of reduced fatigue detection accuracy in complex cabin environments caused by lighting variations, we propose YOLO-FDCL, a novel algorithm specifically designed for driver fatigue detection under complex lighting conditions. This algorithm introduces MobileNetV4 into the backbone network to enhance the model's ability to extract fatigue-related features in complex driving environments while reducing the model's parameter size. Additionally, by incorporating the concept of structural re-parameterization, RepFPN is introduced into the neck section of the algorithm to strengthen the network's multi-scale feature fusion capabilities, further improving the model's detection performance. Experimental results show that on the YAWDD dataset, compared to the baseline YOLOv8-S, precision increased from 97.4% to 98.8%, recall improved from 96.3% to 97.5%, mAP@0.5 increased from 98.0% to 98.8%, and mAP@0.5:0.95 increased from 92.4% to 94.2%. This algorithm has made significant progress in the task of fatigue detection under complex lighting conditions. At the same time, this model shows outstanding performance on our self-developed Complex Lighting Driving Fatigue Dataset (CLDFD), with precision and recall improving by 2.8% and 2.2%, respectively, and improvements of 3.1% and 3.6% in mAP@0.5 and mAP@0.5:0.95 compared to the baseline model, respectively.

Keywords: Mobilenetv4; RepFPN; YOLOv8; driver fatigue detection; multi-scale feature fusion.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1
The network structure of YOLOV8.
Figure 2
Figure 2
The network structure of YOLO-FDCL.
Figure 3
Figure 3
The network structure of UIB.
Figure 4
Figure 4
Repconv training as well as inference schematics, and RepBlock structure diagrams.
Figure 5
Figure 5
Sample frames from the YAWDD dataset.
Figure 6
Figure 6
Sample frames from the CLDFD.
Figure 7
Figure 7
YOLO-FDCL detection results.
Figure 8
Figure 8
Comparing the performance results of the YOLOv8-S and YOLO-FDCL algorithms.
Figure 9
Figure 9
Comparison of heatmap results between YOLOv8-S and YOLO-FDCL algorithms.
See this image and copyright information in PMC

References

    1. Muhammad K., Ullah A., Lloret J., Del Ser J., De Albuquerque V.H.C. Deep learning for safe autonomous driving: Current challenges and future directions. IEEE Trans. Intell. Transp. Syst. 2021;22:4316–4336. doi: 10.1109/TITS.2020.3032227. - DOI
    1. NHTSA . Overviewof Motor Vehicle Crashes. NHTSA; Washington, DC, USA: 2022. [(accessed on 15 March 2025)]. Available online: https://crashstats.nhtsa.dot.gov/Api/Public/ViewPublication/813266.
    1. Owens J. Prevalence of Drowsy Driving Crashes: Estimates from a Large-Scale Naturalistic Driving Study. AAA Foundation for Traffic Safety; Washington, DC, USA: 2018.
    1. Fu R., Wang H. Detection of driving fatigue by using noncontact emg and ecg signals measurement system. Int. J. Neural Syst. 2013;24:1450006. doi: 10.1142/S0129065714500063. - DOI - PubMed
    1. Oviyaa M., Renvitha P., Swathika R., Paul I.J.L., Sasirekha S. Arduino based Real Time Drowsiness and Fatigue Detection for Bikers using Helmet; Proceedings of the 2020 2nd International Conference on Innovative Mechanisms for Industry Applications (ICIMIA); Washington, DC, USA. 5–7 March 2020; pp. 573–577.

LinkOut - more resources