Horizontal alignment greatly affects the speedof vehicles at rural roads. Therefore, it is necessary toanalyze and predict vehicles speed on curve sections.Numerous studies took rural two-lane as research subjectsand ...Horizontal alignment greatly affects the speedof vehicles at rural roads. Therefore, it is necessary toanalyze and predict vehicles speed on curve sections.Numerous studies took rural two-lane as research subjectsand provided models for predicting operating speeds.However, less attention has been paid to multi-lane highwaysespecially in Egypt. In this research, field operatingspeed data of both cars and trucks on 78 curve sections offour multi-lane highways is collected. With the data, correlationbetween operating speed （V85） and alignment isanalyzed. The paper includes two separate relevant analyses.The first analysis uses the regression models toinvestigate the relationships between V85 as dependentvariable, and horizontal alignment and roadway factors asindependent variables. This analysis proposes two predictingmodels for cars and trucks. The second analysisuses the artificial neural networks （ANNs） to explore theprevious relationships. It is found that the ANN modelinggives the best prediction model. The most influential variableon V85 for cars is the radius of curve. Also, for V85 fortrucks, the most influential variable is the median width.Finally, the derived models have statistics within theacceptable regions and they are conceptually reasonable.展开更多
Lane detection is a fundamental necessary task for autonomous driving.The conventional methods mainly treat lane detection as a pixel-wise segmentation problem,which suffers from the challenge of uncontrollable drivin...Lane detection is a fundamental necessary task for autonomous driving.The conventional methods mainly treat lane detection as a pixel-wise segmentation problem,which suffers from the challenge of uncontrollable driving road environments and needs post-processing to abstract the lane parameters.In this work,a series of lines are used to represent traffic lanes and a novel line deformation network(LDNet) is proposed to directly predict the coordinates of lane line points.Inspired by the dynamic behavior of classic snake algorithms,LDNet uses a neural network to iteratively deform an initial lane line to match the lane markings.To capture the long and discontinuous structures of lane lines,1 D convolution in LDNet is used for structured feature learning along the lane lines.Based on LDNet,a two-stage pipeline is developed for lane marking detection:(1) initial lane line proposal to predict a list of lane line candidates,and(2) lane line deformation to obtain the coordinates of lane line points.Experiments show that the proposed approach achieves competitive performances on the TuSimple dataset while being efficient for real-time applications on a GTX 1650 GPU.In particular,the accuracy of LDNet with the annotated starting and ending points is up to99.45%,which indicates the improved initial lane line proposal method can further enhance the performance of LDNet.展开更多
为及时识别、预测车辆的换道行为,综合考虑目标车辆及周边车辆的时空交互关系,结合时间卷积网络(Temporal Convolutional Network,TCN)的时序处理能力和长短期记忆(Long Short Term Memory,LSTM)神经网络的门控记忆机制,构建了基于TCNL...为及时识别、预测车辆的换道行为,综合考虑目标车辆及周边车辆的时空交互关系,结合时间卷积网络(Temporal Convolutional Network,TCN)的时序处理能力和长短期记忆(Long Short Term Memory,LSTM)神经网络的门控记忆机制,构建了基于TCNLSTM网络的车辆换道意图识别模型。首先,将目标车辆的驾驶意图分为直行、向左换道和向右换道3种类型,从CitySim车辆轨迹数据集中提取出目标车辆及对应同车道、左侧车道、右侧车道的相邻前车和相邻后车的轨迹数据,并利用中值滤波算法获得车辆运行状态指标。其次,针对统计学理论和机器学习方法面临的识别精度不高、训练时间长、参数更新慢等问题,提出利用膨胀卷积技术提取时间序列的时序特征,采用门控记忆单元捕捉时序特征的长期依赖关系,并以目标车辆及周边相邻车辆的速度、加速度、航向角、航向角变化率和相对位置信息等54个车辆状态指标为输入变量,以车辆的换道意图为输出变量,构建了一个基于TCN-LSTM网络的车辆换道意图识别模型。最后,对比分析了不同输入时间步长下TCN、支持向量机(Support Vector Machines,SVM)、LSTM和TCN-LSTM模型的识别精度。结果表明:输入时间序列长度为150帧时,TCN-LSTM模型的识别精度达到最高值96.67%;从整体分类精度来看,相比LSTM、TCN和SVM模型,TCN-LSTM模型的换道意图分类准确率分别提升了1.34、0.84和2.46个百分点,展现出了更高的分类性能。展开更多
为了解决车辆行驶中面对各种复杂环境车道线检测算法精度不高的问题,提出一种基于改进的UFS网络检测算法(Ultra Fast Structure-aware Deep Lane Detection,UFS).首先,采用改进的Gamma校正对待检路面图像进行校正,降低光照、阴影等的影...为了解决车辆行驶中面对各种复杂环境车道线检测算法精度不高的问题,提出一种基于改进的UFS网络检测算法(Ultra Fast Structure-aware Deep Lane Detection,UFS).首先,采用改进的Gamma校正对待检路面图像进行校正,降低光照、阴影等的影响,以提升夜间图像纹理特征。然后引入非局部神经网络模块(Non-Local Block),充分提取图像全局特征,以提高检测可靠性。最后对改进后的算法使用Tusimple、CULane数据集进行测试。结果表明:改进后的模型在物体遮挡、光照变化、阴影干扰等复杂场景下,提升了对复杂噪声与多元场景的处理能力,车道分割的准确率有所改善,具有较好的鲁棒性。展开更多
文摘Horizontal alignment greatly affects the speedof vehicles at rural roads. Therefore, it is necessary toanalyze and predict vehicles speed on curve sections.Numerous studies took rural two-lane as research subjectsand provided models for predicting operating speeds.However, less attention has been paid to multi-lane highwaysespecially in Egypt. In this research, field operatingspeed data of both cars and trucks on 78 curve sections offour multi-lane highways is collected. With the data, correlationbetween operating speed （V85） and alignment isanalyzed. The paper includes two separate relevant analyses.The first analysis uses the regression models toinvestigate the relationships between V85 as dependentvariable, and horizontal alignment and roadway factors asindependent variables. This analysis proposes two predictingmodels for cars and trucks. The second analysisuses the artificial neural networks （ANNs） to explore theprevious relationships. It is found that the ANN modelinggives the best prediction model. The most influential variableon V85 for cars is the radius of curve. Also, for V85 fortrucks, the most influential variable is the median width.Finally, the derived models have statistics within theacceptable regions and they are conceptually reasonable.
基金Supported by the Science and Technology Research Project of Hubei Provincial Department of Education (No.Q20202604)。
文摘Lane detection is a fundamental necessary task for autonomous driving.The conventional methods mainly treat lane detection as a pixel-wise segmentation problem,which suffers from the challenge of uncontrollable driving road environments and needs post-processing to abstract the lane parameters.In this work,a series of lines are used to represent traffic lanes and a novel line deformation network(LDNet) is proposed to directly predict the coordinates of lane line points.Inspired by the dynamic behavior of classic snake algorithms,LDNet uses a neural network to iteratively deform an initial lane line to match the lane markings.To capture the long and discontinuous structures of lane lines,1 D convolution in LDNet is used for structured feature learning along the lane lines.Based on LDNet,a two-stage pipeline is developed for lane marking detection:(1) initial lane line proposal to predict a list of lane line candidates,and(2) lane line deformation to obtain the coordinates of lane line points.Experiments show that the proposed approach achieves competitive performances on the TuSimple dataset while being efficient for real-time applications on a GTX 1650 GPU.In particular,the accuracy of LDNet with the annotated starting and ending points is up to99.45%,which indicates the improved initial lane line proposal method can further enhance the performance of LDNet.
文摘为及时识别、预测车辆的换道行为,综合考虑目标车辆及周边车辆的时空交互关系,结合时间卷积网络(Temporal Convolutional Network,TCN)的时序处理能力和长短期记忆(Long Short Term Memory,LSTM)神经网络的门控记忆机制,构建了基于TCNLSTM网络的车辆换道意图识别模型。首先,将目标车辆的驾驶意图分为直行、向左换道和向右换道3种类型,从CitySim车辆轨迹数据集中提取出目标车辆及对应同车道、左侧车道、右侧车道的相邻前车和相邻后车的轨迹数据,并利用中值滤波算法获得车辆运行状态指标。其次,针对统计学理论和机器学习方法面临的识别精度不高、训练时间长、参数更新慢等问题,提出利用膨胀卷积技术提取时间序列的时序特征,采用门控记忆单元捕捉时序特征的长期依赖关系,并以目标车辆及周边相邻车辆的速度、加速度、航向角、航向角变化率和相对位置信息等54个车辆状态指标为输入变量,以车辆的换道意图为输出变量,构建了一个基于TCN-LSTM网络的车辆换道意图识别模型。最后,对比分析了不同输入时间步长下TCN、支持向量机(Support Vector Machines,SVM)、LSTM和TCN-LSTM模型的识别精度。结果表明:输入时间序列长度为150帧时,TCN-LSTM模型的识别精度达到最高值96.67%;从整体分类精度来看,相比LSTM、TCN和SVM模型,TCN-LSTM模型的换道意图分类准确率分别提升了1.34、0.84和2.46个百分点,展现出了更高的分类性能。
文摘为了解决车辆行驶中面对各种复杂环境车道线检测算法精度不高的问题,提出一种基于改进的UFS网络检测算法(Ultra Fast Structure-aware Deep Lane Detection,UFS).首先,采用改进的Gamma校正对待检路面图像进行校正,降低光照、阴影等的影响,以提升夜间图像纹理特征。然后引入非局部神经网络模块(Non-Local Block),充分提取图像全局特征,以提高检测可靠性。最后对改进后的算法使用Tusimple、CULane数据集进行测试。结果表明:改进后的模型在物体遮挡、光照变化、阴影干扰等复杂场景下,提升了对复杂噪声与多元场景的处理能力,车道分割的准确率有所改善,具有较好的鲁棒性。
