Multi-threshold image segmentation techniques based on intelligent optimization algorithms show great potential in low-cost,real-time applications.These methods are efficient even with limited computational resources....Multi-threshold image segmentation techniques based on intelligent optimization algorithms show great potential in low-cost,real-time applications.These methods are efficient even with limited computational resources.This paper proposes a multi-strategy improved red-billed blue magpie optimizer(MIRBMO)for Kapur multi-threshold image segmentation,aiming to enhance segmentation quality.First,Sobol sequences with elite reverse learning are used to optimize the distribution of the initial population,accelerating the optimization process.Second,lens imaging reverse learning is introduced to help the algorithm escape local optima.Finally,the golden sine strategy is adopted to increase the search space diversity and explore potential optimal solutions.The algorithm’s performance is evaluated using the 8 classic benchmark test functions,and results show that MIRBMO outperforms red-billed blue magpie optimizer(RBMO)in optimization capability and demonstrates clear advantages over other intelligent optimization algorithms.When applied to Kapur multi-threshold segmentation,MIRBMO yields a threshold combination with higher entropy values and produces segmented images with superior peak signal-to-noise ratio(PSNR),structural similarity index measure(SSIM),and feature similarity index measure(FSIM)values,indicating its strong application potential.展开更多
This paper addresses a modified auxiliary model stochastic gradient recursive parameter identification algorithm(M-AM-SGRPIA)for a class of single input single output(SISO)linear output error models with multi-thresho...This paper addresses a modified auxiliary model stochastic gradient recursive parameter identification algorithm(M-AM-SGRPIA)for a class of single input single output(SISO)linear output error models with multi-threshold quantized observations.It proves the convergence of the designed algorithm.A pattern-moving-based system dynamics description method with hybrid metrics is proposed for a kind of practical single input multiple output(SIMO)or SISO nonlinear systems,and a SISO linear output error model with multi-threshold quantized observations is adopted to approximate the unknown system.The system input design is accomplished using the measurement technology of random repeatability test,and the probabilistic characteristic of the explicit metric value is employed to estimate the implicit metric value of the pattern class variable.A modified auxiliary model stochastic gradient recursive algorithm(M-AM-SGRA)is designed to identify the model parameters,and the contraction mapping principle proves its convergence.Two numerical examples are given to demonstrate the feasibility and effectiveness of the achieved identification algorithm.展开更多
In order to improve the global search ability of biogeography-based optimization(BBO)algorithm in multi-threshold image segmentation,a multi-threshold image segmentation based on improved BBO algorithm is proposed.Whe...In order to improve the global search ability of biogeography-based optimization(BBO)algorithm in multi-threshold image segmentation,a multi-threshold image segmentation based on improved BBO algorithm is proposed.When using BBO algorithm to optimize threshold,firstly,the elitist selection operator is used to retain the optimal set of solutions.Secondly,a migration strategy based on fusion of good solution and pending solution is introduced to reduce premature convergence and invalid migration of traditional migration operations.Thirdly,to reduce the blindness of traditional mutation operations,a mutation operation through binary computation is created.Then,it is applied to the multi-threshold image segmentation of two-dimensional cross entropy.Finally,this method is used to segment the typical image and compared with two-dimensional multi-threshold segmentation based on particle swarm optimization algorithm and the two-dimensional multi-threshold image segmentation based on standard BBO algorithm.The experimental results show that the method has good convergence stability,it can effectively shorten the time of iteration,and the optimization performance is better than the standard BBO algorithm.展开更多
In order to obtain the image of airframe damage region and provide the input data for aircraft intelligent maintenance,a multi-dimensional and multi-threshold airframe damage region division method based on correlatio...In order to obtain the image of airframe damage region and provide the input data for aircraft intelligent maintenance,a multi-dimensional and multi-threshold airframe damage region division method based on correlation optimization is proposed.On the basis of airframe damage feature analysis,the multi-dimensional feature entropy is defined to realize the full fusion of multiple feature information of the image,and the division method is extended to multi-threshold to refine the damage division and reduce the impact of the damage adjacent region’s morphological changes on the division.Through the correlation parameter optimization algorithm,the problem of low efficiency of multi-dimensional multi-threshold division method is solved.Finally,the proposed method is compared and verified by instances of airframe damage image.The results show that compared with the traditional threshold division method,the damage region divided by the proposed method is complete and accurate,and the boundary is clear and coherent,which can effectively reduce the interference of many factors such as uneven luminance,chromaticity deviation,dirt attachment,image compression,and so on.The correlation optimization algorithm has high efficiency and stable convergence,and can meet the requirements of aircraft intelligent maintenance.展开更多
Hiding secret data in digital images is one of the major researchfields in information security.Recently,reversible data hiding in encrypted images has attracted extensive attention due to the emergence of cloud servi...Hiding secret data in digital images is one of the major researchfields in information security.Recently,reversible data hiding in encrypted images has attracted extensive attention due to the emergence of cloud services.This paper proposes a novel reversible data hiding method in encrypted images based on an optimal multi-threshold block labeling technique(OMTBL-RDHEI).In our scheme,the content owner encrypts the cover image with block permutation,pixel permutation,and stream cipher,which preserve the in-block correlation of pixel values.After uploading to the cloud service,the data hider applies the prediction error rearrangement(PER),the optimal threshold selection(OTS),and the multi-threshold labeling(MTL)methods to obtain a compressed version of the encrypted image and embed secret data into the vacated room.The receiver can extract the secret,restore the cover image,or do both according to his/her granted authority.The proposed MTL labels blocks of the encrypted image with a list of threshold values which is optimized with OTS based on the features of the current image.Experimental results show that labeling image blocks with the optimized threshold list can efficiently enlarge the amount of vacated room and thus improve the embedding capacity of an encrypted cover image.Security level of the proposed scheme is analyzed and the embedding capacity is compared with state-of-the-art schemes.Both are concluded with satisfactory performance.展开更多
Automatic edge detection of an image is considered a type of crucial information that can be extracted by applying detectors with different techniques. It is a main tool in pattern recognition, image segmentation, and...Automatic edge detection of an image is considered a type of crucial information that can be extracted by applying detectors with different techniques. It is a main tool in pattern recognition, image segmentation, and scene analysis. This paper introduces an edge-detection algorithm, which generates multi-threshold values. It is based on non-Shannon measures such as Havrda & Charvat’s entropy, which is commonly used in gray level image analysis in many types of images such as satellite grayscale images. The proposed edge detection performance is compared to the previous classic methods, such as Roberts, Prewitt, and Sobel methods. Numerical results underline the robustness of the presented approach and different applications are shown.展开更多
Multi-threshold image segmentation divides an image into regions with distinct features. However,as the number of thresholds increases,its computational complexity grows exponentially. To address this issue,an improve...Multi-threshold image segmentation divides an image into regions with distinct features. However,as the number of thresholds increases,its computational complexity grows exponentially. To address this issue,an improved transient search optimization(ITSO) algorithm is proposed to overcome the limitations of the original transient search optimization(TSO) algorithm,such as susceptibility to local optima and low convergence accuracy. ITSO enhances the diversity of initial solutions through a dynamic reflection learning strategy based on the Beta distribution,improves exploration capability using a Cauchy inverse cumulative distribution operator,and balances exploration and exploitation through a dynamic perturbation strategy. Tests on CEC2022 demonstrate that ITSO outperforms the dandelion optimizer(DO),tunicate swarm algorithm(TSA), whale optimization algorithm(WOA),golden jackal optimization(GJO),TSO,goose algorithm(GOOSE),and love evolution algorithm(LEA). When applied to image segmentation,ITSO achieves superior performance in terms of Otsu fitness,peak signal-to-noise ratio(PSNR),structural similarity(SSIM),and feature similarity(FSIM),showcasing its strong research value and application potential.展开更多
Multilevel threshold image segmentation divides an image into several regions with distinct characteristics.While effective,its computational complexity increases exponentially with the number of thresholds,highlighti...Multilevel threshold image segmentation divides an image into several regions with distinct characteristics.While effective,its computational complexity increases exponentially with the number of thresholds,highlighting the need for more efficient and stable methods.An improved sparrow search algorithm(ISSA)that combines multiple strategies to address the dependency on the initial population and solution accuracy issues in the basic sparrow search algorithm(SSA)was proposed in this paper.ISSA leverages circle chaotic mapping to enhance population diversity,a tangent flight operator to improve search diversity,and a triangular random walk to perturb the optimal solution,thereby enhancing global search capability and avoiding local optima.Performance evaluations on 16 benchmark functions demonstrate that ISSA surpasses the gray wolf optimizer(GWO),whale optimization algorithm(WOA),rat swarm optimizer(RSO),moth-flame optimization(MFO),and SSA in terms of search speed,accuracy,and robustness.When applied to multilevel threshold image segmentation,ISSA excels in Kapur's maximum entropy,peak signal-to-noise ratio(PSNR),structural similarity(SSIM),and feature similarity(FSIM),highlighting its significant research value and application potential in the field of image segmentation.展开更多
多交路运营是中国城市轨道交通网络化运营组织的重要组成部分,研究乘客在多交路运营条件下的出行选择行为,对把握乘客出行规律、满足多样化出行需求具有重要意义.基于随机后悔最小化模型,引入乘客对路径属性感知的异质性,构建融合效用...多交路运营是中国城市轨道交通网络化运营组织的重要组成部分,研究乘客在多交路运营条件下的出行选择行为,对把握乘客出行规律、满足多样化出行需求具有重要意义.基于随机后悔最小化模型,引入乘客对路径属性感知的异质性,构建融合效用与后悔机制的多尺度混合模型,克服了传统模型未考虑路径熟悉度导致的乘客出行行为与实际出行行为之间的决策偏差.通过整合容忍阈值与决策惯性,提出一种多交路出行选择建模方法,基于典型案例的陈述偏好(stated preference,SP)调查数据,完成模型参数估计与性能验证.研究结果表明,乘客对出行时间属性的容忍阈值为6.98 min;相较于基准模型,考虑决策惯性的模型在似然值、贝叶斯信息准则(Bayesian information criterion,BIC)及命中率指标上均表现更优,表明其具备更强的数据拟合能力;支付意愿分析进一步揭示乘客愿意为服务提升承担额外时间成本,从而验证了所提模型的有效性与实用性.展开更多
As a major agricultural country, China suffers from severe meteorological drought almost every year.Previous studies have applied a single threshold to identify the onset of drought events, which may cause problems to...As a major agricultural country, China suffers from severe meteorological drought almost every year.Previous studies have applied a single threshold to identify the onset of drought events, which may cause problems to adequately characterize long-term patterns of droughts.This study analyzes meteorological droughts in China based on a set of daily gridded(0.5° 9 0.5°) precipitation data from 1961 to 2014. By using a multi-threshold run theory approach to evaluate the monthly percentage of precipitation anomalies index(Pa), a drought events sequence was identified at each grid cell. The spatiotemporal variations of drought in China were further investigated based on statistics of the frequency, duration,severity, and intensity of all drought events. Analysis of the results show that China has five distinct meteorological drought-prone regions: the Huang-Huai-Hai Plain, Northeast China, Southwest China, South China coastal region,and Northwest China. Seasonal analysis further indicates that there are evident spatial variations in the seasonal contribution to regional drought. But overall, most contribution to annual drought events in China come from the winter. Decadal variation analysis suggests that most of China's water resource regions have undergone an increase in drought frequency, especially in the Liaohe, Haihe, and Yellow River basins, although drought duration and severity clearly have decreased after the 1960 s.展开更多
该文运用Dlib人脸检测模型与人脸检测模板匹配方法,通过计算EAR、MAR、pitch、yaw和roll参数,采用多阈值判定研究疲驾驶员疲劳状态,并将该算法在Raspberry Pi 5硬件平台实现,搭建疲劳驾驶检测预警系统,最后通过公开数据集验证该系统对...该文运用Dlib人脸检测模型与人脸检测模板匹配方法,通过计算EAR、MAR、pitch、yaw和roll参数,采用多阈值判定研究疲驾驶员疲劳状态,并将该算法在Raspberry Pi 5硬件平台实现,搭建疲劳驾驶检测预警系统,最后通过公开数据集验证该系统对于驾驶员面部疲劳状态检测及提醒的准确性和良好的系统性能。EAR、MAR、HPE 3种判断准则在公开数据集Drowsiness、YawDD及自制数据集上分别达到95.6%、96%与96%的平均正确率;在面部无遮挡的情况下,该系统实时帧率达到20 FPS,基本可实时对驾驶员疲劳状态作出相应提醒,同时具备较高的准确率。展开更多
驾驶员在实际驾驶的过程中会存在面部遮挡场景,例如戴眼镜、戴口罩等,传统单一通过提取驾驶员面部特征进行疲劳检测的Dlib算法不再适用。该文结合Dlib与YOLO11使用多阈值判定,对传统Dlib疲劳检测算法进行改进,给出戴眼镜、戴口罩等驾驶...驾驶员在实际驾驶的过程中会存在面部遮挡场景,例如戴眼镜、戴口罩等,传统单一通过提取驾驶员面部特征进行疲劳检测的Dlib算法不再适用。该文结合Dlib与YOLO11使用多阈值判定,对传统Dlib疲劳检测算法进行改进,给出戴眼镜、戴口罩等驾驶员面部遮挡场景的疲劳检测算法,并在Raspberry Pi 5硬件平台,使用公开数据集验证改进算法对于驾驶员疲劳检测的准确性。另外,改进算法还可以对吸烟、打电话等这类分心驾驶行为进行检测和语音提醒,对疲劳和分心行为实现更全面的检测和预警。展开更多
基金Supported by the National Key R&D Program of China:Science and Technology Innovation 2030-‘New Generation Artificial Intelligence’Major Project(2022ZD0119000)the Natural Science Foundation of Shaanxi Province(2025JC-YBMS-736,2025JC-YBMS-343)the Shaanxi Province Key Research and Development Project(2025CY-YBXM-061).
文摘Multi-threshold image segmentation techniques based on intelligent optimization algorithms show great potential in low-cost,real-time applications.These methods are efficient even with limited computational resources.This paper proposes a multi-strategy improved red-billed blue magpie optimizer(MIRBMO)for Kapur multi-threshold image segmentation,aiming to enhance segmentation quality.First,Sobol sequences with elite reverse learning are used to optimize the distribution of the initial population,accelerating the optimization process.Second,lens imaging reverse learning is introduced to help the algorithm escape local optima.Finally,the golden sine strategy is adopted to increase the search space diversity and explore potential optimal solutions.The algorithm’s performance is evaluated using the 8 classic benchmark test functions,and results show that MIRBMO outperforms red-billed blue magpie optimizer(RBMO)in optimization capability and demonstrates clear advantages over other intelligent optimization algorithms.When applied to Kapur multi-threshold segmentation,MIRBMO yields a threshold combination with higher entropy values and produces segmented images with superior peak signal-to-noise ratio(PSNR),structural similarity index measure(SSIM),and feature similarity index measure(FSIM)values,indicating its strong application potential.
基金This work was supported by the National Natural Science Foundation of China(62076025).
文摘This paper addresses a modified auxiliary model stochastic gradient recursive parameter identification algorithm(M-AM-SGRPIA)for a class of single input single output(SISO)linear output error models with multi-threshold quantized observations.It proves the convergence of the designed algorithm.A pattern-moving-based system dynamics description method with hybrid metrics is proposed for a kind of practical single input multiple output(SIMO)or SISO nonlinear systems,and a SISO linear output error model with multi-threshold quantized observations is adopted to approximate the unknown system.The system input design is accomplished using the measurement technology of random repeatability test,and the probabilistic characteristic of the explicit metric value is employed to estimate the implicit metric value of the pattern class variable.A modified auxiliary model stochastic gradient recursive algorithm(M-AM-SGRA)is designed to identify the model parameters,and the contraction mapping principle proves its convergence.Two numerical examples are given to demonstrate the feasibility and effectiveness of the achieved identification algorithm.
基金Science and Technology Plan of Gansu Province(No.144NKCA040)
文摘In order to improve the global search ability of biogeography-based optimization(BBO)algorithm in multi-threshold image segmentation,a multi-threshold image segmentation based on improved BBO algorithm is proposed.When using BBO algorithm to optimize threshold,firstly,the elitist selection operator is used to retain the optimal set of solutions.Secondly,a migration strategy based on fusion of good solution and pending solution is introduced to reduce premature convergence and invalid migration of traditional migration operations.Thirdly,to reduce the blindness of traditional mutation operations,a mutation operation through binary computation is created.Then,it is applied to the multi-threshold image segmentation of two-dimensional cross entropy.Finally,this method is used to segment the typical image and compared with two-dimensional multi-threshold segmentation based on particle swarm optimization algorithm and the two-dimensional multi-threshold image segmentation based on standard BBO algorithm.The experimental results show that the method has good convergence stability,it can effectively shorten the time of iteration,and the optimization performance is better than the standard BBO algorithm.
基金supported by the Aeronautical Science Foundation of China(No.20151067003)。
文摘In order to obtain the image of airframe damage region and provide the input data for aircraft intelligent maintenance,a multi-dimensional and multi-threshold airframe damage region division method based on correlation optimization is proposed.On the basis of airframe damage feature analysis,the multi-dimensional feature entropy is defined to realize the full fusion of multiple feature information of the image,and the division method is extended to multi-threshold to refine the damage division and reduce the impact of the damage adjacent region’s morphological changes on the division.Through the correlation parameter optimization algorithm,the problem of low efficiency of multi-dimensional multi-threshold division method is solved.Finally,the proposed method is compared and verified by instances of airframe damage image.The results show that compared with the traditional threshold division method,the damage region divided by the proposed method is complete and accurate,and the boundary is clear and coherent,which can effectively reduce the interference of many factors such as uneven luminance,chromaticity deviation,dirt attachment,image compression,and so on.The correlation optimization algorithm has high efficiency and stable convergence,and can meet the requirements of aircraft intelligent maintenance.
基金the Ministry of Science and Technology of Taiwan,Grant Number MOST 110-2221-E-507-003.
文摘Hiding secret data in digital images is one of the major researchfields in information security.Recently,reversible data hiding in encrypted images has attracted extensive attention due to the emergence of cloud services.This paper proposes a novel reversible data hiding method in encrypted images based on an optimal multi-threshold block labeling technique(OMTBL-RDHEI).In our scheme,the content owner encrypts the cover image with block permutation,pixel permutation,and stream cipher,which preserve the in-block correlation of pixel values.After uploading to the cloud service,the data hider applies the prediction error rearrangement(PER),the optimal threshold selection(OTS),and the multi-threshold labeling(MTL)methods to obtain a compressed version of the encrypted image and embed secret data into the vacated room.The receiver can extract the secret,restore the cover image,or do both according to his/her granted authority.The proposed MTL labels blocks of the encrypted image with a list of threshold values which is optimized with OTS based on the features of the current image.Experimental results show that labeling image blocks with the optimized threshold list can efficiently enlarge the amount of vacated room and thus improve the embedding capacity of an encrypted cover image.Security level of the proposed scheme is analyzed and the embedding capacity is compared with state-of-the-art schemes.Both are concluded with satisfactory performance.
文摘Automatic edge detection of an image is considered a type of crucial information that can be extracted by applying detectors with different techniques. It is a main tool in pattern recognition, image segmentation, and scene analysis. This paper introduces an edge-detection algorithm, which generates multi-threshold values. It is based on non-Shannon measures such as Havrda & Charvat’s entropy, which is commonly used in gray level image analysis in many types of images such as satellite grayscale images. The proposed edge detection performance is compared to the previous classic methods, such as Roberts, Prewitt, and Sobel methods. Numerical results underline the robustness of the presented approach and different applications are shown.
基金supported by the National Key Research and Development Program of China (2022ZD0119000)
文摘Multi-threshold image segmentation divides an image into regions with distinct features. However,as the number of thresholds increases,its computational complexity grows exponentially. To address this issue,an improved transient search optimization(ITSO) algorithm is proposed to overcome the limitations of the original transient search optimization(TSO) algorithm,such as susceptibility to local optima and low convergence accuracy. ITSO enhances the diversity of initial solutions through a dynamic reflection learning strategy based on the Beta distribution,improves exploration capability using a Cauchy inverse cumulative distribution operator,and balances exploration and exploitation through a dynamic perturbation strategy. Tests on CEC2022 demonstrate that ITSO outperforms the dandelion optimizer(DO),tunicate swarm algorithm(TSA), whale optimization algorithm(WOA),golden jackal optimization(GJO),TSO,goose algorithm(GOOSE),and love evolution algorithm(LEA). When applied to image segmentation,ITSO achieves superior performance in terms of Otsu fitness,peak signal-to-noise ratio(PSNR),structural similarity(SSIM),and feature similarity(FSIM),showcasing its strong research value and application potential.
基金supported by the National Key R&D Program of China:Science and Technology Innovation 2030(2022ZD0119000)。
文摘Multilevel threshold image segmentation divides an image into several regions with distinct characteristics.While effective,its computational complexity increases exponentially with the number of thresholds,highlighting the need for more efficient and stable methods.An improved sparrow search algorithm(ISSA)that combines multiple strategies to address the dependency on the initial population and solution accuracy issues in the basic sparrow search algorithm(SSA)was proposed in this paper.ISSA leverages circle chaotic mapping to enhance population diversity,a tangent flight operator to improve search diversity,and a triangular random walk to perturb the optimal solution,thereby enhancing global search capability and avoiding local optima.Performance evaluations on 16 benchmark functions demonstrate that ISSA surpasses the gray wolf optimizer(GWO),whale optimization algorithm(WOA),rat swarm optimizer(RSO),moth-flame optimization(MFO),and SSA in terms of search speed,accuracy,and robustness.When applied to multilevel threshold image segmentation,ISSA excels in Kapur's maximum entropy,peak signal-to-noise ratio(PSNR),structural similarity(SSIM),and feature similarity(FSIM),highlighting its significant research value and application potential in the field of image segmentation.
文摘多交路运营是中国城市轨道交通网络化运营组织的重要组成部分,研究乘客在多交路运营条件下的出行选择行为,对把握乘客出行规律、满足多样化出行需求具有重要意义.基于随机后悔最小化模型,引入乘客对路径属性感知的异质性,构建融合效用与后悔机制的多尺度混合模型,克服了传统模型未考虑路径熟悉度导致的乘客出行行为与实际出行行为之间的决策偏差.通过整合容忍阈值与决策惯性,提出一种多交路出行选择建模方法,基于典型案例的陈述偏好(stated preference,SP)调查数据,完成模型参数估计与性能验证.研究结果表明,乘客对出行时间属性的容忍阈值为6.98 min;相较于基准模型,考虑决策惯性的模型在似然值、贝叶斯信息准则(Bayesian information criterion,BIC)及命中率指标上均表现更优,表明其具备更强的数据拟合能力;支付意愿分析进一步揭示乘客愿意为服务提升承担额外时间成本,从而验证了所提模型的有效性与实用性.
基金provided by the National Basic Research Program of China (2012CB955403)the National Natural Science Foundation of China (41425002)the National Youth Top-notch Talent Support Program in China
文摘As a major agricultural country, China suffers from severe meteorological drought almost every year.Previous studies have applied a single threshold to identify the onset of drought events, which may cause problems to adequately characterize long-term patterns of droughts.This study analyzes meteorological droughts in China based on a set of daily gridded(0.5° 9 0.5°) precipitation data from 1961 to 2014. By using a multi-threshold run theory approach to evaluate the monthly percentage of precipitation anomalies index(Pa), a drought events sequence was identified at each grid cell. The spatiotemporal variations of drought in China were further investigated based on statistics of the frequency, duration,severity, and intensity of all drought events. Analysis of the results show that China has five distinct meteorological drought-prone regions: the Huang-Huai-Hai Plain, Northeast China, Southwest China, South China coastal region,and Northwest China. Seasonal analysis further indicates that there are evident spatial variations in the seasonal contribution to regional drought. But overall, most contribution to annual drought events in China come from the winter. Decadal variation analysis suggests that most of China's water resource regions have undergone an increase in drought frequency, especially in the Liaohe, Haihe, and Yellow River basins, although drought duration and severity clearly have decreased after the 1960 s.
文摘该文运用Dlib人脸检测模型与人脸检测模板匹配方法,通过计算EAR、MAR、pitch、yaw和roll参数,采用多阈值判定研究疲驾驶员疲劳状态,并将该算法在Raspberry Pi 5硬件平台实现,搭建疲劳驾驶检测预警系统,最后通过公开数据集验证该系统对于驾驶员面部疲劳状态检测及提醒的准确性和良好的系统性能。EAR、MAR、HPE 3种判断准则在公开数据集Drowsiness、YawDD及自制数据集上分别达到95.6%、96%与96%的平均正确率;在面部无遮挡的情况下,该系统实时帧率达到20 FPS,基本可实时对驾驶员疲劳状态作出相应提醒,同时具备较高的准确率。
文摘驾驶员在实际驾驶的过程中会存在面部遮挡场景,例如戴眼镜、戴口罩等,传统单一通过提取驾驶员面部特征进行疲劳检测的Dlib算法不再适用。该文结合Dlib与YOLO11使用多阈值判定,对传统Dlib疲劳检测算法进行改进,给出戴眼镜、戴口罩等驾驶员面部遮挡场景的疲劳检测算法,并在Raspberry Pi 5硬件平台,使用公开数据集验证改进算法对于驾驶员疲劳检测的准确性。另外,改进算法还可以对吸烟、打电话等这类分心驾驶行为进行检测和语音提醒,对疲劳和分心行为实现更全面的检测和预警。
