In recent years,the country has spent significant workforce and material resources to prevent traffic accidents,particularly those caused by fatigued driving.The current studies mainly concentrate on driver physiologi...In recent years,the country has spent significant workforce and material resources to prevent traffic accidents,particularly those caused by fatigued driving.The current studies mainly concentrate on driver physiological signals,driving behavior,and vehicle information.However,most of the approaches are computationally intensive and inconvenient for real-time detection.Therefore,this paper designs a network that combines precision,speed and lightweight and proposes an algorithm for facial fatigue detection based on multi-feature fusion.Specifically,the face detection model takes YOLOv8(You Only Look Once version 8)as the basic framework,and replaces its backbone network with MobileNetv3.To focus on the significant regions in the image,CPCA(Channel Prior Convolution Attention)is adopted to enhance the network’s capacity for feature extraction.Meanwhile,the network training phase employs the Focal-EIOU(Focal and Efficient Intersection Over Union)loss function,which makes the network lightweight and increases the accuracy of target detection.Ultimately,the Dlib toolkit was employed to annotate 68 facial feature points.This study established an evaluation metric for facial fatigue and developed a novel fatigue detection algorithm to assess the driver’s condition.A series of comparative experiments were carried out on the self-built dataset.The suggested method’s mAP(mean Average Precision)values for object detection and fatigue detection are 96.71%and 95.75%,respectively,as well as the detection speed is 47 FPS(Frames Per Second).This method can balance the contradiction between computational complexity and model accuracy.Furthermore,it can be transplanted to NVIDIA Jetson Orin NX and quickly detect the driver’s state while maintaining a high degree of accuracy.It contributes to the development of automobile safety systems and reduces the occurrence of traffic accidents.展开更多
In order to improve the accuracy and reliability of the driving fatigue detection based on a single feature, a new detection algorithm based on multiple features is proposed. Two direct driver＇s facial features refle...In order to improve the accuracy and reliability of the driving fatigue detection based on a single feature, a new detection algorithm based on multiple features is proposed. Two direct driver＇s facial features reflecting fatigue and one indirect vehicle behavior feature indicating fatigue are considered. Meanwhile, T-S fuzzy neural network（TSFNN）is adopted to recognize the driving fatigue of drivers. For the structure identification of the TSFNN, subtractive clustering（SC） is used to confirm the fuzzy rules and their correlative parameters. Moreover, the particle swarm optimization （PSO）algorithm is improved to train the TSFNN. Simulation results and experiments on vehicles show that the proposed algorithm can effectively improve the convergence speed and the recognition accuracy of the TSFNN, as well as enhance the correct rate of driving fatigue detection.展开更多
As the significant branch of intelligent vehicle networking technology, the intelligent fatigue driving detection technology has been introduced into the paper in order to recognize the fatigue state of the vehicle dr...As the significant branch of intelligent vehicle networking technology, the intelligent fatigue driving detection technology has been introduced into the paper in order to recognize the fatigue state of the vehicle driver and avoid the traffic accident. The disadvantages of the traditional fatigue driving detection method have been pointed out when we study on the traditional eye tracking technology and traditional artificial neural networks. On the basis of the image topological analysis technology, Haar like features and extreme learning machine algorithm, a new detection method of the intelligent fatigue driving has been proposed in the paper. Besides, the detailed algorithm and realization scheme of the intelligent fatigue driving detection have been put forward as well. Finally, by comparing the results of the simulation experiments, the new method has been verified to have a better robustness, efficiency and accuracy in monitoring and tracking the drivers＇ fatigue driving by using the human eye tracking technology.展开更多
To investigate the effects of plateau environments on driving fatigue,heart rate and electroencephalogram(EEG)signals were chosen as indicators to characterize driving fatigue.The study analyzed the variation in these...To investigate the effects of plateau environments on driving fatigue,heart rate and electroencephalogram(EEG)signals were chosen as indicators to characterize driving fatigue.The study analyzed the variation in these indicators as drivers transitioned into fatigued stages.By examining the sample entropy of EEG signals and the heart rate variation coefficient,a complex indicator of driving fatigue(CIDF)was established using principal component analysis to overcome the limitations of single-indicator methods.According to the CIDF values,the driving fatigue states in plateau areas were subdivided into three categories,including alertness,mild fatigue,and severe fatigue,by cluster analysis.Optimal binning determined thresholds for different driving fatigue states,which were validated through variance analysis.The results indicate that the CIDF values effectively distinguish the driving fatigue states of drivers in plateau areas.The CIDF thresholds for the alertness and the mild fatigue states are 0.34 and 0.50,respectively.A CIDF value greater than 0.50 indicates that the driver is in a severe fatigue state.展开更多
The purpose of this study was to assess the effects of reducing driving fatigue with magnitopuncture stimuli on Dazhui (DU14) point and Neiguan (PC6) points using heart rate (HR), reaction time (RT) testing, critical ...The purpose of this study was to assess the effects of reducing driving fatigue with magnitopuncture stimuli on Dazhui (DU14) point and Neiguan (PC6) points using heart rate (HR), reaction time (RT) testing, critical flicker fusion frequency (CFF) and subjective evaluation. Twenty healthy subjects were randomly divided into two groups: A-group (study group) and B-group (control group). All subjects were required to be well rested before the experiment. The subjects were engaged in high speed driving at a constant vehicle velocity of 80 km/h continuously for three hours on a test course simulating an expressway. During the driving magnitopunctures were applied to the Dazhui (DU14) point and Neiguan (PC6) points for the A-group when the subject performed the task for two and half hours, and for the B-group magnitopunctures were applied to non-acupuncture points at the same time session. In this study RT exbited a significant delay in B-group (P<0.01) but no found in A-group after the driving task. CFF and subjective evaluation also exhibited significant differences between the two groups after the driving task (P<0.05). The findings showed that magnitopuncture stimuli on Dazhui (DU14) point and Neiguan (PC6) points could reduce the effects of driving fatigue.展开更多
The quantitative detector of driver fatigue presents appropriate warnings and helps to prevent traffic accidents.The aim of this study was to quantifiably evaluate driver mental fatigue using the power spectral analys...The quantitative detector of driver fatigue presents appropriate warnings and helps to prevent traffic accidents.The aim of this study was to quantifiably evaluate driver mental fatigue using the power spectral analysis of the blood pressure variability (BPV) and subjective evaluation. In this experiment twenty healthy male subjects were required to perform a driving simulator task for 3-hours. The physiological variables for evaluating driver mental fatigue were spectral values of blood pressure variability (BPV)including very low frequency (VLF), low frequency (LF),high frequency (HF). As a result, LF, HF and LF/HF showed high correlations with driver mental fatigue but not found in VLF. The findings represent a possible utility of BPV spectral analysis in quantitatively evaluating driver mental fatigue.展开更多
to the chroma distribution diversity （CDD） between lip color and skin color, the lip color area is segmented by the back propagation neural network （BPNN） with three typical color features. Isolated noisy points o...to the chroma distribution diversity （CDD） between lip color and skin color, the lip color area is segmented by the back propagation neural network （BPNN） with three typical color features. Isolated noisy points of the lip color area in binary image are eliminated by a proposed re- gion connecting algorithm. An improved integral projection algorithm is presented to locate the lip boundary. Whether a driver is fatigued is recognized by the ratio of the frame number of the images with mouth opening continuously to the total image frame number in every 20s. The experiments show that the proposed algorithm provides higher correct rate and reliability for fatigue driving detec- tion, and is superior to the single color feature-based method in the lip color segmention. Besides, it improves obviously the accuracy and speed of the lip boundary location compared with the traditional integral projection algrothm.展开更多
A comprehensive quantification method of fatigue degree is proposed concerning subjective and objective quantifications.Using the fatigue degree test software,fatigue degree is objectively quantified by analyzing the ...A comprehensive quantification method of fatigue degree is proposed concerning subjective and objective quantifications.Using the fatigue degree test software,fatigue degree is objectively quantified by analyzing the reaction and operation abilities of drivers about traffic signals.By comparison experiment with that EEG signal based,multivariate statistical analysis and fusion identification based on BP neural network(BPNN) results show that the experimental procedure is simple and practical,and the proposed method can reveal the correlation between fatigue feature parameters and fatigue degree in theory,and also can achieve accurate and reliable quantification of fatigue degree,especially under the associated action of multiple fatigue feature parameters.展开更多
Based on the analysis of commonly used driver fatigue detection methods, this paper proposes a comprehensive monitoring technology for fatigue driving based on driver behavior characteristics, heart rate change charac...Based on the analysis of commonly used driver fatigue detection methods, this paper proposes a comprehensive monitoring technology for fatigue driving based on driver behavior characteristics, heart rate change characteristics and vehicle behavior. Through an engineering example, the application test situation is analyzed to comprehensively judge the driver's fatigue driving state.展开更多
Long-time driving and monotonous visual environment increase the safety risk of driving in an extra-long tunnel.Driving fatigue can be effectively relieved by setting the visual fatigue relief zone in the tunnel.Howev...Long-time driving and monotonous visual environment increase the safety risk of driving in an extra-long tunnel.Driving fatigue can be effectively relieved by setting the visual fatigue relief zone in the tunnel.However,the setting form of visual fatigue relief zone,such as its length and location,is difficult to be designed and quantified.By integrating virtual reality(VR)apparatus with wearable electroencephalogram(EEG)-based devices,a hybrid method was proposed in this study to assist analyzers to formulate the layout of visual fatigue relief zone in the extra-long tunnel.The virtual environment of this study was based on an 11.5 km extra-long tunnel located in Yunnan Province in China.The results indicated that the use of natural landscape decoration inside the tunnel could improve driving fatigue with the growth rate of attention of the driver increased by more than 20%.The accumulation of driving fatigue had a negative effect on the fatigue relief.The results demonstrated that the optimal location of the fatigue relief zone was at the place where driving fatigue had just occurred rather than at the place where a certain amount of driving fatigue had accumulated.展开更多
This investigation was to evaluate the driving fatigue based on power spectral analysis of heart rate variability (HRV) under vertical vibration. Forty healthy male subjects (29.7±3.5 years) were randomly divided...This investigation was to evaluate the driving fatigue based on power spectral analysis of heart rate variability (HRV) under vertical vibration. Forty healthy male subjects (29.7±3.5 years) were randomly divided into two groups, Group A (28.8±4.3 years) and Group B (30.6±2.7 years). Group A (experiment group) was required to perform the simulated driving and Group B (control group) kept calm for 90 min. The frequency domain indices of HRV such as low frequency (0.04 0.15 Hz, LF), high frequency (0.150.4 Hz, HF), LF/HF together with the indices of hemodynamics such as blood pressure (BP) and heart rate (HR) of the subjects between both groups were calculated and analyzed after the simulated driving. There were significances of the former indices between both groups (P<0.05). All the data collected after experiment of Group A was observed the remarkable linear correlation (P<0.05) and parameters and errors of their linear regression equation were stated (α=0.05, P<0.001) in this paper, respectively. The present study investigated that sympathetic activity of the subjects enhanced after the simulated driving while parasympathetic activities decreased. The sympathovagal balance was also improved. As autonomic function indictors of HRV reflected fatigue level, quantitative evaluation of driving mental fatigue from physiological reaction could be possible.展开更多
Rotary bending fatigue tests were carried out with two kinds of materials, S43C and S50C, using the front engine and front drive shaft （FF shaft） of vehicle. The specimens were induction hardened about 1.0mm depth f...Rotary bending fatigue tests were carried out with two kinds of materials, S43C and S50C, using the front engine and front drive shaft （FF shaft） of vehicle. The specimens were induction hardened about 1.0mm depth from the specimen surface, and the hardness value on the surface was about HRC56-60. The tested environment temperatures were -30, 25 and 80℃ in order to look over effect of the induction hardening and the environmental temperatures on the fatigue characteristics. The fatigue limit of induction hardened specimens increased more about 45% than non-hardened specimens showing that the endurances of S43C and S50C were 98.1 and 107.9MPa in non-hardened samples, 147.1 and 156.9MPa in hardened samplesrespectably. The maximum tensile and compressive stress on the small circular defect was about ＋250 and -450MPa respectively when circular defect is situated on top and bottom. The fatigue life increased 80, 25 and -30℃ in order regardless of hardening. In comparison of the fatigue lives on the basis of tested result at 25℃, the fatigue lives of non-hardened specimens decreased about 35%, but that of hardened specimens decreased about only 5% at 80℃ more than at 25℃. And fatigue life of non-hardened and hardened specimens were about 110% and 120% higher at -30℃ than that of 25℃. Based on the result of stress distribution near the defect, the tensile and compressive stress repeatedly generated by load direction were the largest on the small circular defect due to the stress concentration.展开更多
Driving fatigue is a physiological phenomenon that often occurs during driving.After the driver enters a fatigued state,the attentionis lax,the response is slow,and the ability todeal with emergencies is significantly...Driving fatigue is a physiological phenomenon that often occurs during driving.After the driver enters a fatigued state,the attentionis lax,the response is slow,and the ability todeal with emergencies is significantly reduced,which can easily cause traffic accidents.Therefore,studying driver fatigue detectionmethods is significant in ensuring safe driving.However,the fatigue state of actual drivers is easily interfered with by the external environment(glasses and light),which leads to many problems,such as weak reliability of fatigue driving detection.Moreover,fatigue is a slow process,first manifested in physiological signals and then reflected in human face images.To improve the accuracy and stability of fatigue detection,this paper proposed a driver fatigue detection method based on image information and physiological information,designed a fatigue driving detection device,built a simulation driving experiment platform,and collected facial as well as physiological information of drivers during driving.Finally,the effectiveness of the fatigue detection method was evaluated.Eye movement feature parameters and physiological signal features of drivers’fatigue levels were extracted.The driver fatigue detection model was trained to classify fatigue and non-fatigue states based on the extracted features.Accuracy rates of the image,electroencephalogram(EEG),and blood oxygen signals were 86%,82%,and 71%,separately.Information fusion theory was presented to facilitate the fatigue detection effect;the fatigue features were fused using multiple kernel learning and typical correlation analysis methods to increase the detection accuracy to 94%.It can be seen that the fatigue driving detectionmethod based onmulti-source feature fusion effectively detected driver fatigue state,and the accuracy rate was higher than that of a single information source.In summary,fatigue drivingmonitoring has broad development prospects and can be used in traffic accident prevention and wearable driver fatigue recognition.展开更多
In order to reduce the driving fatigue in sowing work, this paper based on heart rate （HR） as the main indicator to survey, tested and analyzed the fatigue condition of the drivers of three imported tractors and one...In order to reduce the driving fatigue in sowing work, this paper based on heart rate （HR） as the main indicator to survey, tested and analyzed the fatigue condition of the drivers of three imported tractors and one domestic tractor in sowing work. The results showed that when driving the imported tractors in sowing work, the HR increasing rate was 10.4%-14.3%, labor intensity belonged to the light level; when driving domestic tractor in sowing work, the HR increasing rate was 23.4%-33.0%, it was remarkably bigger than that of driving imported tractors （P〈0.05）, labor intensity belonged to the middle level. The main effects on driving fatigue included the control methods, tractors＇ cab environment, processing time, operating content, and so on. Finally, we proposed the concrete measures and suggestions to reduce driving fatigue and improve drivers＇ work condition.展开更多
Driving fatigue is one of the major contributors to traffic accidents and poses a serious threat to road safety.Traditional driving fatigue detection methods suffer from limitations such as low classification accuracy...Driving fatigue is one of the major contributors to traffic accidents and poses a serious threat to road safety.Traditional driving fatigue detection methods suffer from limitations such as low classification accuracy,insufficient generalization ab ility,and poor noise resistance.To address these issues,this study proposes a novel driving fatigue detection approach based on a n improved dense connection convolutional network.This method innovatively utilizes raw Electroencephalogram(EEG)signals as inp ut to the model without requiring any data preprocessing,thereby enabling end-to-end feature extraction and classification.The network enhances information flow within dense blocks to promote feature reuse,employs multi-scale convolutional layers for fe ature extraction,and integrates an attention mechanism to assign adaptive weights to multi-scale feature channels.After completing primary feature extraction through stacked dense blocks and pooling layers,a multi-class classification function is applie d to detect driving fatigue.Experimental results on the SEED-VIG driving fatigue dataset show that the proposed method achieves an accuracy of 97.32%,a precision of 96.43%,a recall of 95.78%,and an F1-score of 96.10%.Compared to traditional approaches such as Convolutional Neural Networks(CNN)and Long Short-Term Memory Networks(LSTM),the accuracy improves by 5.14%and 3.45%,respectively.This study demonstrates that the proposed method has significant practical value:on one hand,the end-to-end a rchitecture greatly simplifies the complex feature engineering required by traditional methods;on the other hand,the incorporation of feature reuse and attention mechanisms substantially enhances the model’s classification performance and generalization capability,providing a new technical perspective for intelligent driving safety monitoring.展开更多
Driving fatigue is one of the important causes of accidents in tunnel(group)sections.In this paper,in order to effectively identify the driving fatigue of tunnel(group)drivers,an eye tracker and other instruments were...Driving fatigue is one of the important causes of accidents in tunnel(group)sections.In this paper,in order to effectively identify the driving fatigue of tunnel(group)drivers,an eye tracker and other instruments were used to conduct real vehicle tests on long tunnel(group)expressways and thus obtain the eye movement,driving duration,and Karolinska sleepiness scale(KSS)data of 30 drivers.The impacts of the tunnel and non-tunnel sections on drivers were compared,and the relationship between blink indexes,such as the blink frequency,blink duration,mean value of blink duration,driving duration,and driving fatigue,was studied.A paired t-test and a Spearman correlation test were performed to select the indexes that can effectively characterize the tunnel driving fatigue.A driving fatigue detection model was then developed based on the XGBoost algorithm.The obtained results show that the blink frequency,total blink duration,and mean value of blink duration gradually increase with the deepening of driving fatigue,and the mean value of blink duration is the most sensitive in the tunnel environment.In addition,a significant correlation exists between the driving duration index and driving fatigue,which can provide a reference for improving the tunnel safety.Using the mean value of blink duration and driving duration as the characteristic indexes,the accuracy of the driving fatigue detection model based on the XGBoost algorithm reaches 98%.The cumulative and continuous tunnel proportion effectively estimates the driving fatigue state in a long tunnel(group)environment.展开更多
Professional drivers are more frequently exposed to longer driving distance and travel time,leading to a higher possibility of safety risk for distraction and fatigue.The widespread and common use of commercial driver...Professional drivers are more frequently exposed to longer driving distance and travel time,leading to a higher possibility of safety risk for distraction and fatigue.The widespread and common use of commercial driver monitoring systems(DMS)provides a potential for data collection.It increases the amount of data characterizing driver behavior that can be used for further safety research.This study utilized DMS warning-based data and applied an association rule mining approach to explore risk factors contributing to hazardous materials(HAZMAT)truck driver inattention.A total of 499 HAZMAT truck driver inattentive warning events were used to find rules that will predict the occurrence of driver’s fatigue and distraction.First,Fisher’s exact tests were performed to examine the association between the frequency of driver inattentive behavior warnings and risk factors.Second,support,confidence,and lift values were used as measurements to quantify the relative strength of the association rules generated by the Apriori algorithm.Results show that speed between 40and 49 km/h,relatively longer travel time(3-6 h),freeway,tangent section,off-peak hour and clear weather condition are found to be highly associated with fatigue driving,while nighttime during 18:00 to 23:59,speed between 70 and 80 km/h,travel time between 1 and 3 h,freeways,acceleration less than 0.5 m/s^(2),visibility greater than 1000 m,and tangent roadway section are found to be highly associated with distracted driving.By focusing on the specific feature groups,these association rules would help in the development of mitigating distraction and fatigue driving countermeasures and enforcement approaches.展开更多
Purpose： To identify and appraise the published studies assessing interventions accounting for reducing fatigue and sleepiness while driving. Methods： This systematic review searched the following electronic databa...Purpose： To identify and appraise the published studies assessing interventions accounting for reducing fatigue and sleepiness while driving. Methods： This systematic review searched the following electronic databases： Medline, Science direct, Scopus, EMBASE, PsyclNFO, Transport Database, Cochrane, BIOSIS, ISI Web of Knowledge, specialist road injuries journals and the Australian Transport and Road Index database. Additional searches included websites of relevant organizations, reference lists of included studies, and issues of major injury journals published within the past 15 years. Studies were included if they investigated interventions/exposures accounting for reducing fatigue and sleepiness as the outcome, measured any potential interventions for mitigation of sleepiness and were written in English. Meta-analysis was not attempted because of the heterogeneity of the included studies. Results： Of 63 studies identified, 18 met the inclusion criteria. Based on results of our review, many interventions in the world have been used to reduce drowsiness while driving such as behavioral （talking to passengers, face washing, listening to the radio, no alcohol use, limiting the driving behavior at the time of 12 p.m. - 6 a.m. etc）, educational interventions and also changes in the environment （such as rumble strips, chevrons, variable message signs, etc）. Meta-analysis on the effect of all these in- terventions was impossible due to the high heterogeneity in methodology, effect size and interventions reported in the assessed studies. Conclusion： Results of present review showed various interventions in different parts of the world have been used to decrease drowsy driving. Although these interventions can be used in countries with high incidence of road traffic accidents, precise effect of each intervention is still unknown. Further studies are required for comparison of the efficiency of each intervention and localization of each intervention ac- cording to the traffic pattems of each country.展开更多
Driving for a long time can lead to fatigue,which can affect information processing and decision-making,potentially threatening driving safety.By exploring the generation and variation patterns of driving fatigue and ...Driving for a long time can lead to fatigue,which can affect information processing and decision-making,potentially threatening driving safety.By exploring the generation and variation patterns of driving fatigue and clarifying the application status of its detection and warning technology,traffic safety can be improved.In order to understand the research progress of driving fatigue,based on the Web of Science core database,this paper obtained 2127 English literature published from 1998 to 2023(as of May 12,2023),covering a total of 5963 authors and 6019 keywords,and the bibliometric tool VOSviewer and R-Bibliometrix are used to analyze the literatures.Firstly,the literature statistical analysis is carried out from annual distribution,country distribution,source journals,and core authors.Secondly,the research hotspots and trends are analyzed from keywords co-occurrence,high-impact literature,theme evolution,and development trends.Finally,the development trend of driving fatigue research is discussed.The result shows that the hotspots in the field of driving fatigue include driving fatigue detection,fatigue driving risk and fatigue research of professional drivers,driver alertness and coping strategies for driver fatigue,and driver fatigue under automatic driving.And the improvement of the accuracy and reliability of driving fatigue detection will be the difficult point to break through in the future.It is necessary to build a multi-disciplinary and meticulously quantified driving fatigue and its risk assessment system,and strengthen the control of fatigue risks.Research on intervention measures and education training for professional drivers needs to be deepened,while exploring the acceptance and compliance of intervention measures.Moreover,the evolution law and prevention strategies of driver fatigue under automatic conditions should be the focus of future research.展开更多
Fatigue driving is one of the important reasons of road traffic accidents, fatigue driving is refers to the driver in a long time continuous driving or physical fatigue condition, and then come into being physiologica...Fatigue driving is one of the important reasons of road traffic accidents, fatigue driving is refers to the driver in a long time continuous driving or physical fatigue condition, and then come into being physiological and psychological function disorder. In order to overcome the limitation of single sensor in the fatigue test, aimed at the requirements of monitoring on the fatigue driving, this article designed an driver fatigue monitor system based ARM926EJ-S as a controller, it is used to determine the driver＇s fatigue and reduce the traffic accident. On the basis of fully considering the source correlation and complementary, it adopts the method of multi-source information fusion; by monitoring the pulse, heart rate, temperature of the human body, steering wheel grip strength to realized the fatigue level. The system of graphical interface adopts UCGUI. Finally, testing the main function modules of early warning system, the feasibility of the proposed early warning system is verified fusion .展开更多
基金supported by the Science and Technology Bureau of Xi’an project(24KGDW0049)the Key Research and Development Programof Shaanxi(2023-YBGY-264)the Key Research and Development Program of Guangxi(GK-AB20159032).
文摘In recent years,the country has spent significant workforce and material resources to prevent traffic accidents,particularly those caused by fatigued driving.The current studies mainly concentrate on driver physiological signals,driving behavior,and vehicle information.However,most of the approaches are computationally intensive and inconvenient for real-time detection.Therefore,this paper designs a network that combines precision,speed and lightweight and proposes an algorithm for facial fatigue detection based on multi-feature fusion.Specifically,the face detection model takes YOLOv8(You Only Look Once version 8)as the basic framework,and replaces its backbone network with MobileNetv3.To focus on the significant regions in the image,CPCA(Channel Prior Convolution Attention)is adopted to enhance the network’s capacity for feature extraction.Meanwhile,the network training phase employs the Focal-EIOU(Focal and Efficient Intersection Over Union)loss function,which makes the network lightweight and increases the accuracy of target detection.Ultimately,the Dlib toolkit was employed to annotate 68 facial feature points.This study established an evaluation metric for facial fatigue and developed a novel fatigue detection algorithm to assess the driver’s condition.A series of comparative experiments were carried out on the self-built dataset.The suggested method’s mAP(mean Average Precision)values for object detection and fatigue detection are 96.71%and 95.75%,respectively,as well as the detection speed is 47 FPS(Frames Per Second).This method can balance the contradiction between computational complexity and model accuracy.Furthermore,it can be transplanted to NVIDIA Jetson Orin NX and quickly detect the driver’s state while maintaining a high degree of accuracy.It contributes to the development of automobile safety systems and reduces the occurrence of traffic accidents.
基金The National Key Technologies R & D Program during the 11th Five-Year Plan Period(No.2009BAG13A04)the Ph.D.Programs Foundation of Ministry of Education of China(No.200802861061)the Transportation Science Research Project of Jiangsu Province(No.08X09)
文摘In order to improve the accuracy and reliability of the driving fatigue detection based on a single feature, a new detection algorithm based on multiple features is proposed. Two direct driver＇s facial features reflecting fatigue and one indirect vehicle behavior feature indicating fatigue are considered. Meanwhile, T-S fuzzy neural network（TSFNN）is adopted to recognize the driving fatigue of drivers. For the structure identification of the TSFNN, subtractive clustering（SC） is used to confirm the fuzzy rules and their correlative parameters. Moreover, the particle swarm optimization （PSO）algorithm is improved to train the TSFNN. Simulation results and experiments on vehicles show that the proposed algorithm can effectively improve the convergence speed and the recognition accuracy of the TSFNN, as well as enhance the correct rate of driving fatigue detection.
基金supported by the National Natural Science Foundation of China(61272357,61300074,61572075)
文摘As the significant branch of intelligent vehicle networking technology, the intelligent fatigue driving detection technology has been introduced into the paper in order to recognize the fatigue state of the vehicle driver and avoid the traffic accident. The disadvantages of the traditional fatigue driving detection method have been pointed out when we study on the traditional eye tracking technology and traditional artificial neural networks. On the basis of the image topological analysis technology, Haar like features and extreme learning machine algorithm, a new detection method of the intelligent fatigue driving has been proposed in the paper. Besides, the detailed algorithm and realization scheme of the intelligent fatigue driving detection have been put forward as well. Finally, by comparing the results of the simulation experiments, the new method has been verified to have a better robustness, efficiency and accuracy in monitoring and tracking the drivers＇ fatigue driving by using the human eye tracking technology.
基金The National Natural Science Foundation of China(No.51768063,51868068).
文摘To investigate the effects of plateau environments on driving fatigue,heart rate and electroencephalogram(EEG)signals were chosen as indicators to characterize driving fatigue.The study analyzed the variation in these indicators as drivers transitioned into fatigued stages.By examining the sample entropy of EEG signals and the heart rate variation coefficient,a complex indicator of driving fatigue(CIDF)was established using principal component analysis to overcome the limitations of single-indicator methods.According to the CIDF values,the driving fatigue states in plateau areas were subdivided into three categories,including alertness,mild fatigue,and severe fatigue,by cluster analysis.Optimal binning determined thresholds for different driving fatigue states,which were validated through variance analysis.The results indicate that the CIDF values effectively distinguish the driving fatigue states of drivers in plateau areas.The CIDF thresholds for the alertness and the mild fatigue states are 0.34 and 0.50,respectively.A CIDF value greater than 0.50 indicates that the driver is in a severe fatigue state.
文摘The purpose of this study was to assess the effects of reducing driving fatigue with magnitopuncture stimuli on Dazhui (DU14) point and Neiguan (PC6) points using heart rate (HR), reaction time (RT) testing, critical flicker fusion frequency (CFF) and subjective evaluation. Twenty healthy subjects were randomly divided into two groups: A-group (study group) and B-group (control group). All subjects were required to be well rested before the experiment. The subjects were engaged in high speed driving at a constant vehicle velocity of 80 km/h continuously for three hours on a test course simulating an expressway. During the driving magnitopunctures were applied to the Dazhui (DU14) point and Neiguan (PC6) points for the A-group when the subject performed the task for two and half hours, and for the B-group magnitopunctures were applied to non-acupuncture points at the same time session. In this study RT exbited a significant delay in B-group (P<0.01) but no found in A-group after the driving task. CFF and subjective evaluation also exhibited significant differences between the two groups after the driving task (P<0.05). The findings showed that magnitopuncture stimuli on Dazhui (DU14) point and Neiguan (PC6) points could reduce the effects of driving fatigue.
文摘The quantitative detector of driver fatigue presents appropriate warnings and helps to prevent traffic accidents.The aim of this study was to quantifiably evaluate driver mental fatigue using the power spectral analysis of the blood pressure variability (BPV) and subjective evaluation. In this experiment twenty healthy male subjects were required to perform a driving simulator task for 3-hours. The physiological variables for evaluating driver mental fatigue were spectral values of blood pressure variability (BPV)including very low frequency (VLF), low frequency (LF),high frequency (HF). As a result, LF, HF and LF/HF showed high correlations with driver mental fatigue but not found in VLF. The findings represent a possible utility of BPV spectral analysis in quantitatively evaluating driver mental fatigue.
基金Supported by the National High Technology Research and Development Programme of China （No. 2009AA01 Z311,2009AA01 Z314）, the Na- tional Natural Science Foundation of China （No. 60905045, 60775057） , and College Student＇ s Practice and Innovation Trainning Project of Jiangsu Province （No. N1885012112, N1885012152）.
文摘to the chroma distribution diversity （CDD） between lip color and skin color, the lip color area is segmented by the back propagation neural network （BPNN） with three typical color features. Isolated noisy points of the lip color area in binary image are eliminated by a proposed re- gion connecting algorithm. An improved integral projection algorithm is presented to locate the lip boundary. Whether a driver is fatigued is recognized by the ratio of the frame number of the images with mouth opening continuously to the total image frame number in every 20s. The experiments show that the proposed algorithm provides higher correct rate and reliability for fatigue driving detec- tion, and is superior to the single color feature-based method in the lip color segmention. Besides, it improves obviously the accuracy and speed of the lip boundary location compared with the traditional integral projection algrothm.
基金Supported by the National Nature Science Foundation of China(No.61304205,61203273,61103086,41301037)the Open Funding Project of State Key Laboratory of Virtual Reality Technology and Systems,Beihang University(No.BUAA-VR-13KF-04)+1 种基金Jiangsu Ordinary University Science Research Project(No.13KJB120007)Innovation and Entrepreneurship Training Project of College Students(No.201410300153,201410300165)
文摘A comprehensive quantification method of fatigue degree is proposed concerning subjective and objective quantifications.Using the fatigue degree test software,fatigue degree is objectively quantified by analyzing the reaction and operation abilities of drivers about traffic signals.By comparison experiment with that EEG signal based,multivariate statistical analysis and fusion identification based on BP neural network(BPNN) results show that the experimental procedure is simple and practical,and the proposed method can reveal the correlation between fatigue feature parameters and fatigue degree in theory,and also can achieve accurate and reliable quantification of fatigue degree,especially under the associated action of multiple fatigue feature parameters.
文摘Based on the analysis of commonly used driver fatigue detection methods, this paper proposes a comprehensive monitoring technology for fatigue driving based on driver behavior characteristics, heart rate change characteristics and vehicle behavior. Through an engineering example, the application test situation is analyzed to comprehensively judge the driver's fatigue driving state.
基金Project(2018YFB2101000) supported by the National Key R&D Program of ChinaProject(20YF1451400) supported by Shanghai Sailing Program,ChinaProject(SLDRCE19-A-14) supported by the Research Fund of State Key Laboratory for Disaster Reduction in Civil Engineering,China。
文摘Long-time driving and monotonous visual environment increase the safety risk of driving in an extra-long tunnel.Driving fatigue can be effectively relieved by setting the visual fatigue relief zone in the tunnel.However,the setting form of visual fatigue relief zone,such as its length and location,is difficult to be designed and quantified.By integrating virtual reality(VR)apparatus with wearable electroencephalogram(EEG)-based devices,a hybrid method was proposed in this study to assist analyzers to formulate the layout of visual fatigue relief zone in the extra-long tunnel.The virtual environment of this study was based on an 11.5 km extra-long tunnel located in Yunnan Province in China.The results indicated that the use of natural landscape decoration inside the tunnel could improve driving fatigue with the growth rate of attention of the driver increased by more than 20%.The accumulation of driving fatigue had a negative effect on the fatigue relief.The results demonstrated that the optimal location of the fatigue relief zone was at the place where driving fatigue had just occurred rather than at the place where a certain amount of driving fatigue had accumulated.
文摘This investigation was to evaluate the driving fatigue based on power spectral analysis of heart rate variability (HRV) under vertical vibration. Forty healthy male subjects (29.7±3.5 years) were randomly divided into two groups, Group A (28.8±4.3 years) and Group B (30.6±2.7 years). Group A (experiment group) was required to perform the simulated driving and Group B (control group) kept calm for 90 min. The frequency domain indices of HRV such as low frequency (0.04 0.15 Hz, LF), high frequency (0.150.4 Hz, HF), LF/HF together with the indices of hemodynamics such as blood pressure (BP) and heart rate (HR) of the subjects between both groups were calculated and analyzed after the simulated driving. There were significances of the former indices between both groups (P<0.05). All the data collected after experiment of Group A was observed the remarkable linear correlation (P<0.05) and parameters and errors of their linear regression equation were stated (α=0.05, P<0.001) in this paper, respectively. The present study investigated that sympathetic activity of the subjects enhanced after the simulated driving while parasympathetic activities decreased. The sympathovagal balance was also improved. As autonomic function indictors of HRV reflected fatigue level, quantitative evaluation of driving mental fatigue from physiological reaction could be possible.
文摘Rotary bending fatigue tests were carried out with two kinds of materials, S43C and S50C, using the front engine and front drive shaft （FF shaft） of vehicle. The specimens were induction hardened about 1.0mm depth from the specimen surface, and the hardness value on the surface was about HRC56-60. The tested environment temperatures were -30, 25 and 80℃ in order to look over effect of the induction hardening and the environmental temperatures on the fatigue characteristics. The fatigue limit of induction hardened specimens increased more about 45% than non-hardened specimens showing that the endurances of S43C and S50C were 98.1 and 107.9MPa in non-hardened samples, 147.1 and 156.9MPa in hardened samplesrespectably. The maximum tensile and compressive stress on the small circular defect was about ＋250 and -450MPa respectively when circular defect is situated on top and bottom. The fatigue life increased 80, 25 and -30℃ in order regardless of hardening. In comparison of the fatigue lives on the basis of tested result at 25℃, the fatigue lives of non-hardened specimens decreased about 35%, but that of hardened specimens decreased about only 5% at 80℃ more than at 25℃. And fatigue life of non-hardened and hardened specimens were about 110% and 120% higher at -30℃ than that of 25℃. Based on the result of stress distribution near the defect, the tensile and compressive stress repeatedly generated by load direction were the largest on the small circular defect due to the stress concentration.
基金the Fundamental Research Funds for the Central Universities(GrantNo.IR2021222)received by J.Sthe Future Science and Technology Innovation Team Project of HIT(216506)received by Q.W.
文摘Driving fatigue is a physiological phenomenon that often occurs during driving.After the driver enters a fatigued state,the attentionis lax,the response is slow,and the ability todeal with emergencies is significantly reduced,which can easily cause traffic accidents.Therefore,studying driver fatigue detectionmethods is significant in ensuring safe driving.However,the fatigue state of actual drivers is easily interfered with by the external environment(glasses and light),which leads to many problems,such as weak reliability of fatigue driving detection.Moreover,fatigue is a slow process,first manifested in physiological signals and then reflected in human face images.To improve the accuracy and stability of fatigue detection,this paper proposed a driver fatigue detection method based on image information and physiological information,designed a fatigue driving detection device,built a simulation driving experiment platform,and collected facial as well as physiological information of drivers during driving.Finally,the effectiveness of the fatigue detection method was evaluated.Eye movement feature parameters and physiological signal features of drivers’fatigue levels were extracted.The driver fatigue detection model was trained to classify fatigue and non-fatigue states based on the extracted features.Accuracy rates of the image,electroencephalogram(EEG),and blood oxygen signals were 86%,82%,and 71%,separately.Information fusion theory was presented to facilitate the fatigue detection effect;the fatigue features were fused using multiple kernel learning and typical correlation analysis methods to increase the detection accuracy to 94%.It can be seen that the fatigue driving detectionmethod based onmulti-source feature fusion effectively detected driver fatigue state,and the accuracy rate was higher than that of a single information source.In summary,fatigue drivingmonitoring has broad development prospects and can be used in traffic accident prevention and wearable driver fatigue recognition.
基金"211" Talent Start-up Fund Project of Northeast Agricultural University (183)
文摘In order to reduce the driving fatigue in sowing work, this paper based on heart rate （HR） as the main indicator to survey, tested and analyzed the fatigue condition of the drivers of three imported tractors and one domestic tractor in sowing work. The results showed that when driving the imported tractors in sowing work, the HR increasing rate was 10.4%-14.3%, labor intensity belonged to the light level; when driving domestic tractor in sowing work, the HR increasing rate was 23.4%-33.0%, it was remarkably bigger than that of driving imported tractors （P〈0.05）, labor intensity belonged to the middle level. The main effects on driving fatigue included the control methods, tractors＇ cab environment, processing time, operating content, and so on. Finally, we proposed the concrete measures and suggestions to reduce driving fatigue and improve drivers＇ work condition.
文摘Driving fatigue is one of the major contributors to traffic accidents and poses a serious threat to road safety.Traditional driving fatigue detection methods suffer from limitations such as low classification accuracy,insufficient generalization ab ility,and poor noise resistance.To address these issues,this study proposes a novel driving fatigue detection approach based on a n improved dense connection convolutional network.This method innovatively utilizes raw Electroencephalogram(EEG)signals as inp ut to the model without requiring any data preprocessing,thereby enabling end-to-end feature extraction and classification.The network enhances information flow within dense blocks to promote feature reuse,employs multi-scale convolutional layers for fe ature extraction,and integrates an attention mechanism to assign adaptive weights to multi-scale feature channels.After completing primary feature extraction through stacked dense blocks and pooling layers,a multi-class classification function is applie d to detect driving fatigue.Experimental results on the SEED-VIG driving fatigue dataset show that the proposed method achieves an accuracy of 97.32%,a precision of 96.43%,a recall of 95.78%,and an F1-score of 96.10%.Compared to traditional approaches such as Convolutional Neural Networks(CNN)and Long Short-Term Memory Networks(LSTM),the accuracy improves by 5.14%and 3.45%,respectively.This study demonstrates that the proposed method has significant practical value:on one hand,the end-to-end a rchitecture greatly simplifies the complex feature engineering required by traditional methods;on the other hand,the incorporation of feature reuse and attention mechanisms substantially enhances the model’s classification performance and generalization capability,providing a new technical perspective for intelligent driving safety monitoring.
基金supported by the National Natural Science Foundation of China(52362050,52472347)Science and Technology Project of Shandong Transportation Department(2022KJ-044)+1 种基金“Hongliu Excellent Young”Talents Support Program of Lanzhou University of Technologythe Fundamental Research Funds for the Cornell University,CHD University(300102223505)。
文摘Driving fatigue is one of the important causes of accidents in tunnel(group)sections.In this paper,in order to effectively identify the driving fatigue of tunnel(group)drivers,an eye tracker and other instruments were used to conduct real vehicle tests on long tunnel(group)expressways and thus obtain the eye movement,driving duration,and Karolinska sleepiness scale(KSS)data of 30 drivers.The impacts of the tunnel and non-tunnel sections on drivers were compared,and the relationship between blink indexes,such as the blink frequency,blink duration,mean value of blink duration,driving duration,and driving fatigue,was studied.A paired t-test and a Spearman correlation test were performed to select the indexes that can effectively characterize the tunnel driving fatigue.A driving fatigue detection model was then developed based on the XGBoost algorithm.The obtained results show that the blink frequency,total blink duration,and mean value of blink duration gradually increase with the deepening of driving fatigue,and the mean value of blink duration is the most sensitive in the tunnel environment.In addition,a significant correlation exists between the driving duration index and driving fatigue,which can provide a reference for improving the tunnel safety.Using the mean value of blink duration and driving duration as the characteristic indexes,the accuracy of the driving fatigue detection model based on the XGBoost algorithm reaches 98%.The cumulative and continuous tunnel proportion effectively estimates the driving fatigue state in a long tunnel(group)environment.
基金supported by National Key R&D Program of China(2021YFC3001500).
文摘Professional drivers are more frequently exposed to longer driving distance and travel time,leading to a higher possibility of safety risk for distraction and fatigue.The widespread and common use of commercial driver monitoring systems(DMS)provides a potential for data collection.It increases the amount of data characterizing driver behavior that can be used for further safety research.This study utilized DMS warning-based data and applied an association rule mining approach to explore risk factors contributing to hazardous materials(HAZMAT)truck driver inattention.A total of 499 HAZMAT truck driver inattentive warning events were used to find rules that will predict the occurrence of driver’s fatigue and distraction.First,Fisher’s exact tests were performed to examine the association between the frequency of driver inattentive behavior warnings and risk factors.Second,support,confidence,and lift values were used as measurements to quantify the relative strength of the association rules generated by the Apriori algorithm.Results show that speed between 40and 49 km/h,relatively longer travel time(3-6 h),freeway,tangent section,off-peak hour and clear weather condition are found to be highly associated with fatigue driving,while nighttime during 18:00 to 23:59,speed between 70 and 80 km/h,travel time between 1 and 3 h,freeways,acceleration less than 0.5 m/s^(2),visibility greater than 1000 m,and tangent roadway section are found to be highly associated with distracted driving.By focusing on the specific feature groups,these association rules would help in the development of mitigating distraction and fatigue driving countermeasures and enforcement approaches.
文摘Purpose： To identify and appraise the published studies assessing interventions accounting for reducing fatigue and sleepiness while driving. Methods： This systematic review searched the following electronic databases： Medline, Science direct, Scopus, EMBASE, PsyclNFO, Transport Database, Cochrane, BIOSIS, ISI Web of Knowledge, specialist road injuries journals and the Australian Transport and Road Index database. Additional searches included websites of relevant organizations, reference lists of included studies, and issues of major injury journals published within the past 15 years. Studies were included if they investigated interventions/exposures accounting for reducing fatigue and sleepiness as the outcome, measured any potential interventions for mitigation of sleepiness and were written in English. Meta-analysis was not attempted because of the heterogeneity of the included studies. Results： Of 63 studies identified, 18 met the inclusion criteria. Based on results of our review, many interventions in the world have been used to reduce drowsiness while driving such as behavioral （talking to passengers, face washing, listening to the radio, no alcohol use, limiting the driving behavior at the time of 12 p.m. - 6 a.m. etc）, educational interventions and also changes in the environment （such as rumble strips, chevrons, variable message signs, etc）. Meta-analysis on the effect of all these in- terventions was impossible due to the high heterogeneity in methodology, effect size and interventions reported in the assessed studies. Conclusion： Results of present review showed various interventions in different parts of the world have been used to decrease drowsy driving. Although these interventions can be used in countries with high incidence of road traffic accidents, precise effect of each intervention is still unknown. Further studies are required for comparison of the efficiency of each intervention and localization of each intervention ac- cording to the traffic pattems of each country.
基金supported by the National Natural Science Foundation of China(Grant No.71961012)the Yunnan Provincial Department of Education Science Research Fund Project(Grant No.2024Y132)the Analysis and Testing Foundation of Kunming University of Science and Technology(Grant No.2022M20202106029).
文摘Driving for a long time can lead to fatigue,which can affect information processing and decision-making,potentially threatening driving safety.By exploring the generation and variation patterns of driving fatigue and clarifying the application status of its detection and warning technology,traffic safety can be improved.In order to understand the research progress of driving fatigue,based on the Web of Science core database,this paper obtained 2127 English literature published from 1998 to 2023(as of May 12,2023),covering a total of 5963 authors and 6019 keywords,and the bibliometric tool VOSviewer and R-Bibliometrix are used to analyze the literatures.Firstly,the literature statistical analysis is carried out from annual distribution,country distribution,source journals,and core authors.Secondly,the research hotspots and trends are analyzed from keywords co-occurrence,high-impact literature,theme evolution,and development trends.Finally,the development trend of driving fatigue research is discussed.The result shows that the hotspots in the field of driving fatigue include driving fatigue detection,fatigue driving risk and fatigue research of professional drivers,driver alertness and coping strategies for driver fatigue,and driver fatigue under automatic driving.And the improvement of the accuracy and reliability of driving fatigue detection will be the difficult point to break through in the future.It is necessary to build a multi-disciplinary and meticulously quantified driving fatigue and its risk assessment system,and strengthen the control of fatigue risks.Research on intervention measures and education training for professional drivers needs to be deepened,while exploring the acceptance and compliance of intervention measures.Moreover,the evolution law and prevention strategies of driver fatigue under automatic conditions should be the focus of future research.
文摘Fatigue driving is one of the important reasons of road traffic accidents, fatigue driving is refers to the driver in a long time continuous driving or physical fatigue condition, and then come into being physiological and psychological function disorder. In order to overcome the limitation of single sensor in the fatigue test, aimed at the requirements of monitoring on the fatigue driving, this article designed an driver fatigue monitor system based ARM926EJ-S as a controller, it is used to determine the driver＇s fatigue and reduce the traffic accident. On the basis of fully considering the source correlation and complementary, it adopts the method of multi-source information fusion; by monitoring the pulse, heart rate, temperature of the human body, steering wheel grip strength to realized the fatigue level. The system of graphical interface adopts UCGUI. Finally, testing the main function modules of early warning system, the feasibility of the proposed early warning system is verified fusion .
