{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:46:28Z","timestamp":1775069188903,"version":"3.50.1"},"reference-count":46,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Aiming at the imbalance between accuracy and real-time of existing fatigue driving detection models, and the accuracy is lower in low illumination, an LDIE-FDNet (Lightweight Dynamic Image Enhancement-Enabled Real-time Fatigue Driving Detection Network) is designed. Enhance the image by MSR-LIENET (Multi-Scale Retinex-Based Low-Light Image Enhancement Network); Through GSConv_C3k2 module, lightweight design, efficient capture of remote context information, reduction of parameters and calculation, and variable convolution kernel design and feature segmentation and mosaic are adopted to enhance feature extraction ability; Through DHFAR-Net (Dynamic Hierarchical Feature Aggregation and Reconstruction Network), combined with DySample and SDI (Semantic and Detail Infusion), the semantic information and detail information are enhanced. Through multi-level feature fusion, the model can better capture the information of various targets, reduce the situation of missing detection and false detection, thus improving the overall detection effect, and does not need high-resolution boot features as input. It has lower reasoning delay, memory occupation, floating-point operation times, and parameter number; Through the PIoU (Powerfull-IoU) loss function, IoU is calculated pixel by pixel, which can better optimize the positioning of rotating rectangular frames and deal with high aspect ratio targets, reduce the overlap of background areas and improve the detection effect. Finally, a fatigue driving detection model including maximum closing time (MCT) and maximum yawn duration (MYD) is proposed. Experiments show that mAP increases by 0.6% to 99.2, Params reduce by 24%, GFLOPs increase by 14.3% and FPS increases by 23.1% on the YawDD data set. On the DMS data set, mAP increased by 0.7% to 92.9, Params reduce by 24%, GFLOPs increased by 14.3%, and FPS increased by 20.5%. The proposed method enhances both accuracy and efficiency in fatigue detection while effectively balancing precision with real-time performance.<\/jats:p>","DOI":"10.1371\/journal.pone.0346055","type":"journal-article","created":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T17:29:25Z","timestamp":1775064565000},"page":"e0346055","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["LDIE-FDNet: Lightweight dynamic image enhancement-enabled real-time fatigue driving detection network"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0878-4129","authenticated-orcid":true,"given":"Chunyu","family":"Dong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tinglei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2026,4,1]]},"reference":[{"issue":"3","key":"pone.0346055.ref001","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3635141","article-title":"Deformation Gated Recurrent Network for Lane-level Abnormal Driving Behavior Recognition","volume":"10","author":"G Shen","year":"2024","journal-title":"ACM Trans Spatial Algorithms Syst"},{"key":"pone.0346055.ref002","doi-asserted-by":"crossref","first-page":"113204","DOI":"10.1016\/j.eswa.2020.113204","article-title":"Driver fatigue transition prediction in highly automated driving using physiological features","volume":"147","author":"F Zhou","year":"2020","journal-title":"Exp Syst Appl"},{"key":"pone.0346055.ref003","doi-asserted-by":"crossref","unstructured":"Zhang YF, Gao XY, Zhu JY, Zheng WL. A novel approach to driving fatigue detection using forehead EOG. In: International IEEE\/EMBS Conference on Neural Engineering, 2015. https:\/\/doi.org\/10.1109\/NER.2015.7146721","DOI":"10.1109\/NER.2015.7146721"},{"key":"pone.0346055.ref004","doi-asserted-by":"crossref","unstructured":"Borghini G, Vecchiato G, Colosimo A, Wei D, Astolfi L. Assessment of Mental Fatigue During Car Driving by Using High Resolution EEG Activity and Neurophysiologic Indices. Conference proceedings:. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference. 2012.","DOI":"10.1109\/EMBC.2012.6347469"},{"key":"pone.0346055.ref005","doi-asserted-by":"crossref","unstructured":"Amidei A, Poli A, Iadarola G, Tramarin F, Pavan P, Spinsante S, et al. Driver drowsiness detection based on variation of skin conductance from wearable device. In: 2022 IEEE International Workshop on Metrology for Automotive (MetroAutomotive). 2022. p. 94\u20138.","DOI":"10.1109\/MetroAutomotive54295.2022.9854871"},{"issue":"1","key":"pone.0346055.ref006","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1109\/TVT.2021.3130152","article-title":"A Novel Learning Model of Driver Fatigue Features Representation for Steering Wheel Angle","volume":"71","author":"Z Li","year":"2022","journal-title":"IEEE Trans Veh Technol"},{"issue":"3","key":"pone.0346055.ref007","doi-asserted-by":"crossref","first-page":"495","DOI":"10.3390\/s17030495","article-title":"Online Detection of Driver Fatigue Using Steering Wheel Angles for Real Driving Conditions","volume":"17","author":"Z Li","year":"2017","journal-title":"Sensors (Basel)"},{"issue":"9","key":"pone.0346055.ref008","doi-asserted-by":"crossref","first-page":"155014771987245","DOI":"10.1177\/1550147719872452","article-title":"A fuzzy recurrent neural network for driver fatigue detection based on steering-wheel angle sensor data","volume":"15","author":"Z Li","year":"2019","journal-title":"Int J Distrib Sensor Netw"},{"key":"pone.0346055.ref009","doi-asserted-by":"crossref","unstructured":"McDonald A D, Schwarz C, Lee J D, Brown T L. Real-time detection of drowsiness related lane departures using steering wheel angle. Proceedings of the human factors and ergonomics society annual meeting. Sage CA: Los Angeles, CA: Sage Publications. 2012. 2201\u20135.","DOI":"10.1177\/1071181312561464"},{"issue":"2","key":"pone.0346055.ref010","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1049\/htl.2017.0020","article-title":"Real-time eye tracking for the assessment of driver fatigue","volume":"5","author":"J Xu","year":"2018","journal-title":"Healthc Technol Lett"},{"key":"pone.0346055.ref011","doi-asserted-by":"crossref","first-page":"274","DOI":"10.1016\/j.neucom.2019.02.014","article-title":"Driver\u2019s fatigue recognition based on yawn detection in thermal images","volume":"338","author":"M Knapik","year":"2019","journal-title":"Neurocomputing"},{"issue":"5","key":"pone.0346055.ref012","first-page":"73","article-title":"A Driver Face Monitoring System for Fatigue and Distraction Detection","volume":"2013","author":"MH Sigari","year":"2013","journal-title":"Int J Veh Technol"},{"key":"pone.0346055.ref013","doi-asserted-by":"crossref","first-page":"173440","DOI":"10.1109\/ACCESS.2020.3025818","article-title":"Driver Fatigue Detection Method Based on Eye States With Pupil and Iris Segmentation","volume":"8","author":"Q Zhuang","year":"2020","journal-title":"IEEE Access"},{"key":"pone.0346055.ref014","doi-asserted-by":"crossref","unstructured":"Zhao T, Wang Z, Bai X. Research on fatigue driving detection based on computer vision. 2022 International Conference on Intelligent Transportation, Big Data & Smart City (ICITBS). IEEE; 2022. p. 318\u201321.","DOI":"10.1109\/ICITBS55627.2022.00075"},{"key":"pone.0346055.ref015","doi-asserted-by":"crossref","unstructured":"Zhang B. Design of face recognition fatigue driving detection system based on improved YOLO algorithm. In: 2023 International Conference on Mechatronics, IoT and Industrial Informatics (ICMIII), 2023. 602\u20136.","DOI":"10.1109\/ICMIII58949.2023.00126"},{"issue":"9","key":"pone.0346055.ref016","doi-asserted-by":"crossref","first-page":"4689","DOI":"10.3390\/app12094689","article-title":"Driving Fatigue Detection Based on the Combination of Multi-Branch 3D-CNN and Attention Mechanism","volume":"12","author":"W Xiang","year":"2022","journal-title":"Appl Sci"},{"issue":"8","key":"pone.0346055.ref017","doi-asserted-by":"crossref","first-page":"5074","DOI":"10.3390\/app13085074","article-title":"Adaptive Driver Face Feature Fatigue Detection Algorithm Research","volume":"13","author":"H Zheng","year":"2023","journal-title":"Appl Sci"},{"issue":"7","key":"pone.0346055.ref018","doi-asserted-by":"crossref","first-page":"3826","DOI":"10.1109\/TIV.2023.3268070","article-title":"A human-machine shared control framework considering time-varying driver characteristics","volume":"8","author":"Z Fang","year":"2023","journal-title":"IEEE Trans Intell Veh"},{"issue":"1","key":"pone.0346055.ref019","doi-asserted-by":"crossref","first-page":"2002","DOI":"10.1109\/TIV.2023.3300152","article-title":"Authority Allocation Strategy for Shared Steering Control Considering Human-Machine Mutual Trust Level","volume":"9","author":"Z Fang","year":"2024","journal-title":"IEEE Trans Intell Veh"},{"key":"pone.0346055.ref020","doi-asserted-by":"crossref","unstructured":"Selvan PS, Addula SR, Singh CE. Deep learning-enabled fetal health classification through sensor-fused IoT environment. In: 5th International Conference on Mobile Radio Communications and 5G Networks, MRCN 2024. 2025. p. 157\u201369.","DOI":"10.1007\/978-981-96-4226-7_13"},{"issue":"1","key":"pone.0346055.ref021","article-title":"A retinex-based network for low-light image enhancement with multi-scale denoising and focal-aware reflections","volume":"19","author":"P Ji","year":"2025","journal-title":"IET Image Process"},{"key":"pone.0346055.ref022","doi-asserted-by":"crossref","first-page":"1398277","DOI":"10.3389\/fpls.2024.1398277","article-title":"LCGSC-YOLO: a lightweight apple leaf diseases detection method based on LCNet and GSConv module under YOLO framework","volume":"15","author":"J Wang","year":"2024","journal-title":"Front Plant Sci"},{"issue":"9","key":"pone.0346055.ref023","doi-asserted-by":"crossref","first-page":"1630","DOI":"10.3390\/f15091630","article-title":"LD-YOLO: A Lightweight Dynamic Forest Fire and Smoke Detection Model with Dysample and Spatial Context Awareness Module","volume":"15","author":"Z Lin","year":"2024","journal-title":"Forests"},{"key":"pone.0346055.ref024","doi-asserted-by":"crossref","unstructured":"Peng Y, Chen D Z, Sonka M. U-net v2: Rethinking the skip connections of u-net for medical image segmentation. 2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI). IEEE; 2025. p. 1\u20135.","DOI":"10.1109\/ISBI60581.2025.10980742"},{"key":"pone.0346055.ref025","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-58558-7_12","article-title":"P I o U Loss: Towards Accurate Oriented Object Detection in Complex Environments","author":"Z Chen","year":"2020"},{"key":"pone.0346055.ref026","doi-asserted-by":"crossref","first-page":"107830","DOI":"10.1016\/j.bspc.2025.107830","article-title":"Optimized YOLOv11 model for lung nodule detection","volume":"107","author":"Z Liu","year":"2025","journal-title":"Biomed Signal Process Cont"},{"key":"pone.0346055.ref027","doi-asserted-by":"crossref","DOI":"10.7717\/peerj-cs.2876","article-title":"DMSA-Net: a deformable multiscale adaptive classroom behavior recognition network","volume":"11","author":"C Dong","year":"2025","journal-title":"PeerJ Comput Sci"},{"key":"pone.0346055.ref028","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.biosystemseng.2022.04.006","article-title":"YOLO5-spear: A robust and real-time spear tips locator by improving image augmentation and lightweight network for selective harvesting robot of white asparagus","volume":"218","author":"P Zhang","year":"2022","journal-title":"Biosyst Eng"},{"key":"pone.0346055.ref029","article-title":"CARAFE: Unified Content-Aware ReAssembly of FEatures","author":"J Wang","year":"2021","journal-title":"IEEE Trans Softw Eng"},{"key":"pone.0346055.ref030","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1613\/jair.1156","article-title":"SAPA: A Multi-objective Metric Temporal Planner","volume":"20","author":"M Do","year":"2003","journal-title":"JAIR"},{"key":"pone.0346055.ref031","doi-asserted-by":"crossref","DOI":"10.1090\/psapm\/040\/1059485","article-title":"The Hadamard product","author":"RA Horn","year":"1990","journal-title":"Proc Sympos Appl Math"},{"issue":"1","key":"pone.0346055.ref032","doi-asserted-by":"crossref","first-page":"282","DOI":"10.23919\/cje.2023.00.256","article-title":"An Improved YOLOv7 Tiny Algorithm for Vehicle and Pedestrian Detection with Occlusion in Autonomous Driving","volume":"34","author":"J Su","year":"2025","journal-title":"Chinese J Elect"},{"key":"pone.0346055.ref033","article-title":"LFIR-YOLO: Lightweight Model for Infrared Vehicle and Pedestrian Detection","volume":"24","author":"M Zhou","year":"2024","journal-title":"Sensors"},{"issue":"2","key":"pone.0346055.ref034","first-page":"511","article-title":"Automated Drowsiness Detection Through Facial Features Analysis","volume":"23","author":"W Mahdi","year":"2019","journal-title":"Computacion y Sistemas"},{"issue":"23","key":"pone.0346055.ref035","doi-asserted-by":"crossref","first-page":"7810","DOI":"10.3390\/s24237810","article-title":"Real-Time Fatigue Detection Algorithms Using Machine Learning for Yawning and Eye State","volume":"24","author":"F Makhmudov","year":"2024","journal-title":"Sensors (Basel)"},{"key":"pone.0346055.ref036","article-title":"A yawning detection dataset","author":"S Abtahi","year":"2014","journal-title":"ACM"},{"key":"pone.0346055.ref037","unstructured":"Caas PN, Diez A, Galva D, Nieto M, Rodr\u00edguez Igor. Occlusion-aware driver monitoring system using the driver monitoring dataset. 2025."},{"issue":"7","key":"pone.0346055.ref038","doi-asserted-by":"crossref","DOI":"10.3390\/e26070591","article-title":"ESE-YOLOv8: A novel object detection algorithm for safety belt detection during working at heights","volume":"26","author":"Q Zhou","year":"2024","journal-title":"Entropy"},{"issue":"7","key":"pone.0346055.ref039","first-page":"25","article-title":"YOLOv7-RDD: A Lightweight Efficient Pavement Distress Detection Model","author":"Z Ning","year":"2024","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"pone.0346055.ref040","unstructured":"Zhang H, Zhang S. Shape-IoU: More Accurate Metric Considering Bounding Box Shape and Scale. 2023."},{"key":"pone.0346055.ref041","article-title":"BiFPN-enhanced SwinDAT-based cherry variety classification with YOLOv8","author":"MV Arsoy","year":"2025","journal-title":"Scientif Rep"},{"issue":"2","key":"pone.0346055.ref042","doi-asserted-by":"crossref","DOI":"10.1007\/s11227-024-06852-w","article-title":"LiteYOLO-GHG: a lightweight YOLOv8-based algorithm for transformer bushing fault detection","volume":"81","author":"S Xiao","year":"2025","journal-title":"J Supercomput"},{"issue":"3","key":"pone.0346055.ref043","article-title":"TSSSKD-YOLO: an intelligent classification and defect detection method of insulators on transmission lines by fusing knowledge distillation in multiple scenarios","volume":"31","author":"Y Ye","year":"2025","journal-title":"Multimed Syst"},{"key":"pone.0346055.ref044","doi-asserted-by":"crossref","unstructured":"Gourisaria MK, Patel AV, Chatterjee R, Singh V. Efficient ViT: An Efficient Vision Transformer for Fire and Smoke Image Classification. In: International Conference on Smart Systems: Innovations in Computing. Springer, Singapore. 2024. https:\/\/doi.org\/10.1007\/978-981-97-3690-4_19","DOI":"10.1007\/978-981-97-3690-4_19"},{"issue":"1","key":"pone.0346055.ref045","doi-asserted-by":"crossref","first-page":"015104","DOI":"10.1063\/5.0235362","article-title":"Waste drilling fluid flocculation identification method based on improved YOLOv8n","volume":"96","author":"M Wan","year":"2025","journal-title":"Rev Sci Instrum"},{"key":"pone.0346055.ref046","doi-asserted-by":"crossref","unstructured":"Wei Z, Liu X, Qiu Y, et al. Fire and Smoke Detection Method in Diverse Scenarios Based on YOLOv8-FD. 2024 5th International Conference on Artificial Intelligence and Computer Engineering (ICAICE).0[2025-06-19]. https:\/\/doi.org\/10.1109\/ICAICE63571.2024.10863950","DOI":"10.1109\/ICAICE63571.2024.10863950"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0346055","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T17:29:34Z","timestamp":1775064574000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0346055"}},"subtitle":[],"editor":[{"given":"Jinhao","family":"Liang","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,4,1]]},"references-count":46,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4,1]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0346055","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,1]]}}}