ST-LaneNet: Lane Line Detection Method Based on Swin Transformer and LaneNet

The advancement of autonomous driving heavily relies on the ability to accurate lane lines detection.As deep learning and computer vision technologies evolve,a variety of deep learning-based methods for lane line detection have been proposed by researchers in the field.However,owing to the simple appearance of lane lines and the lack of distinctive features,it is easy for other objects with similar local appearances to interfere with the process of detecting lane lines.The precision of lane line detection is limited by the unpredictable quantity and diversity of lane lines.To address the aforementioned challenges,we propose a novel deep learning approach for lane line detection.This method leverages the Swin Transformer in conjunction with LaneNet(called ST-LaneNet).The experience results showed that the true positive detection rate can reach 97.53%for easy lanes and 96.83%for difficult lanes(such as scenes with severe occlusion and extreme lighting conditions),which can better accomplish the objective of detecting lane lines.In 1000 detection samples,the average detection accuracy can reach 97.83%,the average inference time per image can reach 17.8 ms,and the average number of frames per second can reach 64.8 Hz.The programming scripts and associated models for this project can be accessed openly at the following GitHub repository:https://github.com/Duane 711/Lane-line-detec tion-ST-LaneNet.

Lane Line Detection Based on Improved PINet

Accurate perception of lane line information is one of the basic requirements of unmanned driving technology, which is related to the localization of the vehicle and the determination of the forward direction. In this paper, multi-level constraints are added to the lane line detection model PINet, which is used to improve the perception of lane lines. Predicted lane lines in the network are predicted to have real and imaginary attributes, which are used to enhance the perception of features around the lane lines, with pixel-level constraints on the lane lines;images are converted to bird’s-eye views, where the parallelism between lane lines is reconstructed, with lane line-level constraints on the predicted lane lines;and vanishing points are used to focus on the image hierarchy, with image-level constraints on the lane lines. The model proposed in this paper meets both accuracy (96.44%) and real-time (30 + FPS) requirements, has been tested on the highway on the ground, and has performed stably.

A self-organization formation configuration based assignment probability and collision detection

The formation control of multiple unmanned aerial vehicles(multi-UAVs)has always been a research hotspot.Based on the straight line trajectory,a multi-UAVs target point assignment algorithm based on the assignment probability is proposed to achieve the shortest overall formation path of multi-UAVs with low complexity and reduce the energy consumption.In order to avoid the collision between UAVs in the formation process,the concept of safety ball is introduced,and the collision detection based on continuous motion of two time slots and the lane occupation detection after motion is proposed to avoid collision between UAVs.Based on the idea of game theory,a method of UAV motion form setting based on the maximization of interests is proposed,including the maximization of self-interest and the maximization of formation interest is proposed,so that multi-UAVs can complete the formation task quickly and reasonably with the linear trajectory assigned in advance.Finally,through simulation verification,the multi-UAVs target assignment algorithm based on the assignment probability proposed in this paper can effectively reduce the total path length,and the UAV motion selection method based on the maximization interests can effectively complete the task formation.

LDNet:structure-focused lane detection based on line deformation

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.

融合CBAM注意力机制与可变形卷积的车道线检测

为满足自动驾驶及汽车高级驾驶辅助系统(ADAS)对车道线检测准确性和实时性的要求,提出一种融合卷积块注意力机制(CBAM)与可变形卷积网络(DCN)的车道线检测方法CADCN。在特征提取模块中嵌入CBAM注意力机制,增强有用特征并抑制无用特征响应;引入可变形卷积替换常规卷积,用带偏移的采样学习车道线的几何形变,提高卷积核的建模能力;基于行锚分类思想,对行方向上的位置进行选择和分类分析,预测车道线的位置信息,提高车道线检测模型的实时性。在车道线公开数据集上对所提CADCN方法进行训练及验证,在满足实时性的情况下,CADCN方法在TuSimple数据集上准确率达到96.63%,在CULane数据集上综合评估指标F1平均值达到74.4%,验证了所提方法的有效性。

基于注意力机制与线锚信息传递的车道线检测

车道线检测是自动驾驶领域的关键技术,目前仍面临较多挑战。车道线监督信号的稀疏性以及复杂场景下的遮挡、阴影等因素会影响检测的准确率与实时性。基于此,提出了一种融合CBAM注意力机制与线锚特征聚合模块的车道线检测模型,提出的算法在Tusimple和CULane数据集分别达到96.19%的准确率和76.24%的综合F1得分,通过实车测试表明,该算法检测帧率为67 fps,可以在复杂交通场景下进行实时检测,较好地解决了车道线遮挡问题。

LSTR算法的改进及在车道线检测中的应用

基于Transformer的车道预测LSTR(Lane Shape Prediction with Transformers)算法在检测车道线时存在缺少捕捉局部特征的能力和多头注意力机制中头数多余的问题.本文提出了改进LSTR算法的车道线检测方法,首先在最后一个编码器中前馈网络的后面引入CBAM(Convolutional Block Attention Module)注意力机制模块,充分利用通道和空间上的信息,捕捉特征图中更多的细节;然后对解码器中的掩码多头注意力机制进行剪枝,使用掩码单头注意力机制来进行替换,以便更多关注前一时刻的车道线信息.改进后的LSTR算法在TuSimple数据集上准确度为96.31%,明显高于PolyLaneNet(Lane Estimation via Deep Polynomial Regression)等算法,在CULane数据集上比原始算法的F1评分上升了2.11%.

融合CAM和ASPP的车道线检测算法研究

UFLD(ultra fast structure aware deep lane detection)是一种轻量化车道线检测模型,为提升模型的检测精度,对模型进行改进。引入CAM(channel attention mechanism)使模型能更关注携带重要车道线信息的特征通道和像素;为了感知车道线的细节信息,引入ASPP(atrous spatial pyramid pooling)扩大卷积过程的感受野,提高模型分割精度;搭建引入CAM和ASPP后的改进模型,并在改进的模型上进行实验。实验结果表明:在TuSimple数据集上以ResNet18为主干网络的模型检测精度由95.81%提升至95.98%,以ResNet34为主干网络的模型检测精度由95.84%提升至96.12%;在CULane数据集上,无论是以ResNet18还是以ResNet34为主干网络模型,其平均精度均有不同程度的提高。

基于YOLOP-L的多特征融合道路全景驾驶检测

目前,驾驶员视角下的交通图像检测技术成为交通领域的重要研究方向,同时提取车辆、道路、交通标志等多种特征已经成为驾驶员理解道路信息多样性的亟需任务。以往研究已在单类目标检测的特征提取方面取得了长足进步,然而,这些研究不能很好地联合应用于其他区别较大的特征检测任务中,且融合训练过程中会损失个别特征检测的精度。针对驾驶员视野范围内道路信息多样且复杂的特点,本文提出了一种基于多特征融合训练的检测模型YOLOP-L,它能够同时对多种不同特征交通目标进行融合训练,同时保证单项检测任务的精度。首先,为了解决特征融合中语义信息表达不完整的问题,设计的SP-LNet模块通过FPN与双向特征网络结合实现网络更深层次的融合,使得提取的信息更完整,从而提升道路小目标的检测性能;其次,设计新的分割头深度可分离卷积,将语义信息与局部特征融合促使多特征融合的训练准确度与速度得到进一步提升;再次,体系中设计的GDL-Focal多类混合损失函数更专注于困难样本,可用于解决样本特征不平衡的问题。最后,对比实验表明:YOLOP-L相比原YOLOP网络运行的速度更快;在车辆目标检测任务下召回率提升了2.2%;在车道线检测任务下准确率提升2.8%,车道线IoU的值较HybridNets网络下降2.45%,但较YOLOP-L网络提升1.95%;在可行驶区域分割任务下其整体检测性能提升1.1%。结果表明,在具有挑战性的BDD100K数据集上,YOLOP-L可以在复杂场景下有效解决检测精度不足和分割缺失的问题,提高了车辆识别、车道线检测以及道路行驶区域联合训练的准确性和鲁棒性。

基于改进Hough变换的车道线自动识别算法

针对复杂路况环境中路面图像杂乱或因光照不均导致的车道线不易检测等问题,提出一种基于改进Hough变换的车道线检测算法。首先对采集到的原始图像预处理,利用Canny算子对图像进行边缘增强及区域提取;其次为进一步提高算法的检测时间及准确性,提出利用滑动窗口实现阈值的自适应选取;最后结合渐进概率提出了复杂路况下的车道线检测算法。仿真实验选取KITTI数据集,结果表明,所提算法能够准确提取路面车道线,克服了复杂背景、光照不均带来的影响,与同类算法相比,文中所提的渐进概率Hough变换算法检测时间短、准确率高,具有一定的实用性和优越性。

基于轻量化U^(2)-Net的车道线检测算法研究

针对车道线遮挡、道路阴影等多车道驾驶环境下提取的车道线特征信息缺失造成预测车道线模糊、不连续等问题,提出一种基于轻量化U^(2)-Net的车道线检测算法。首先,以轻量化U^(2)-Net的残差U形模块(RSU)和多特征尺度融合获得全局信息丰富的车道线特征;其次,对车道线特征进行逐像素阈值判断,并选择最小二乘法结合感兴趣区域(ROI)中车道线簇进行车道线的拟合,实现多车道线检测并确认自车道线区域;最后,在图森(TuSimple)数据集上进行验证与分析。验证结果表明,所提出的车道线检测算法的平均准确率达到98.4%,相比于其他车道线检测网络,该算法的网络参数量较少,准确率较高。

基于传统边缘算子的车道线识别研究

车道线识别检测技术是汽车实现自动驾驶的关键技术之一,利用图像低级特征提取技术实现边缘检测是车道线识别的最佳方法之一。为解决传统车道线检测易误检、漏检、效率低等问题,利用结构化道路条件下车道线图像,在去噪、滤波等预处理后对获取的图像进行ROI区域提取。基于传统边缘检测算子边缘提取方法,发现Roberts等算子在考虑环境因素下检测结果存在细节边缘提取不足的问题。通过比较发现,利用霍夫变换改进的Canny算子边缘检测方法不仅能够有效提高检测结果的精确度,而且能够同时提升运行速度。该方法能够有效避免传统边缘检测方法检测结果误差大的问题,具有较强的鲁棒性和抗干扰性。

基于YOLOv7和图像分块的车道线破损检测算法

提出了一种结合YOLOv7和图像分块的车道线破损检测方法。首先,利用YOLOv7模型检测并提取车道线区域。其次,运用Otsu法计算每个子块的阈值及子块背景区域和目标区域的灰度均值差值,以此实现二值化。然后,采用双线性插值法平滑图像,实现车道线分割,并利用拓扑结构分析法提取车道线轮廓。最后,设计了像素统计、直线拟合、割断检测3种方法判断车道线是否破损。实验结果表明:在不同场景下,该算法在破损车道线检测中的精确率为91.79%,具有较好的检测效果和一定的应用价值。

适用于右转辅助的非机动车道检测

为避免传统车辆或无人驾驶车辆在右转时与快速行驶的自行车发生碰撞的风险,需要在转弯前稳定地检测出非机动车道,并实时定位骑车者.为实现该目标,通过调整初始代价及代价聚合,完成更为精确的非机动车道图像立体匹配;基于改进的Hough变换算法,对路面上的非机动车道线进行识别和提取;之后结合立体视觉来获取非机动车道的精确三维坐标.实验结果表明:所提方法可以在大部分场景下检测出不同类型的非机动车道,且具有较高的精确度,适用于广义非机动车道检测,对于先进驾驶辅助系统或无人驾驶车辆实现全道路场景识别起到了积极的辅助作用.

基于改进SCNN网络的车道线检测算法

车道线检测是车道保持系统、车道偏离告警系统的实现前提。为了进一步提升检测的精度,本文将深度学习与车道线检测结合提出一种融合改进的SCNN车道线识别算法。该方法以改进的SCNN网络为基础,引入PSA注意力模块,并将其与VGG(Visual Geometry Group)网络相结合提出融合上下文信息的车道线识别网络VGG-K,帮助每层中行和列像素之间进行消息传递,增强其对连续变换目标的识别能力,然后利用二次曲线模型拟合得到最终的车道线检测结果。将改进的模型在CULane数据集上进行测试,结果表明:该方法在正常场景下的综合评价指标F1数值达到92.1,恶劣场景下的数值达到75.3,与其他模型对比可知,本文算法检测能力显著提升,对于多种复杂状况下的车道线具有更好的识别效果。

基于深度强化学习的多智能体高速车道检测研究

随着汽车技术与人工智能领域的发展,高级驾驶员辅助系统越来越流行,自动驾驶技术能够极大地提高效率、降低成本。相对应的可行驶区域检测、车道线检测和车速估计等便成为了关键性的一环。一些检测方法仅检测带有粗略边界框的车道线,而忽略特定曲线车道的形状,将深度强化学习引入到了车道检测模型中,采用智能体定位点移动来实现准确的车道检测和定位。用以改善辅助驾驶系统,提高车道线识别情况。无论是对于驾驶员还是自动驾驶系统,都有很好的驾驶体验改善作用。

LaneSegNet:一种高效的车道线检测方法

车道线检测在智能交通领域占有重要地位,其检测的准确度和速度对于辅助驾驶以及自动驾驶有重要影响.针对目前深度学习方法识别车道线精度差、速度慢的问题,提出了一种高效的车道线分割方法LaneSegNet.首先基于编码和解码网络原理构建主干网络Lane-Net,用于提取车道线特征信息并分割出车道线;然后使用多尺度空洞卷积特征融合网络,可以极大地扩充模型的感受野,提取全局特征信息;最后使用混合注意力网络获取丰富的车道线特征,并增强与当前任务相关的信息.实验结果表明:在TuSimple数据集上,该方法检测车道线的准确率为97.6%;在CULane数据集上,该方法在标准路面的检测准确率达到92.5%,多种路面综合检测准确率为75.2%.本文提出的LaneSegNet车道线检测方法分割精确度和推理速度优于其他对比模型,且具有更强的适应性和鲁棒性.

一种基于Edline线特征的车道线识别算法

为了提升车道线检测的准确性和实时性,改良车道偏离预警系统的性能,提出了一种新的车道线识别算法。首先应用投影法对采集到的图像设立感兴趣区域,以此来减少图像中存在的干扰信息;其次应用一种改进后的自适应高斯滤波算法对采集所得图像进行平滑处理,减少图像中不必要的细节;最后采用边缘绘制算法进行边缘检测,在此基础上,提出一种线段检测算法——Edline算法提取边缘线,对检测到的直线段进行筛选和聚类。利用引用计数法对车道线进行跟踪和预测。结果表明,新算法的平均处理时间为17.1 ms,准确率为96.19%,将其应用在车道偏离预警系统中可以有效地提高预警效率,提升预警的准确性和响应速度。研究结果丰富了车道线识别理论,可为车道偏离预警系统的应用及基础研究提供参考。

Lane departure warning systems and lane line detection methods based on image processing and semantic segmentation:A review

Recently,the development and application of lane line departure warning systems have been in the market.For any of the systems,the key part of lane line tracking,lane line identification,or lane line departure warning is whether it can accurately and quickly detect lane lines.Since 1990 s,they have been studied and implemented for the situations defined by the good viewing conditions and the clear lane markings on road.After then,the accuracy for particular situations,the robustness for a wide range of scenarios,time efficiency and integration into higher-order tasks define visual lane line detection and tracking as a continuing research subject.At present,these kinds of lane marking line detection methods based on machine vision and image processing can be divided into two categories:the traditional image processing and semantic segmentation(includes deep learning)methods.The former mainly involves feature-based and model-based steps,and which can be classified into similarity-and discontinuity-based ones;and the model-based step includes different parametric straight line,curve or pattern models.The semantic segmentation includes different machine learning,neural network and deep learning methods,which is the new trend for the research and application of lane line departure warning systems.This paper describes and analyzes the lane line departure warning systems,image processing algorithms and semantic segmentation methods for lane line detection.

Vision-based long-distance lane perception and front vehicle location for full autonomous vehicles on highway roads

A new vision-based long-distance lane perception and front vehicle location method was developed for decision making of full autonomous vehicles on highway roads,Firstly,a real-time long-distance lane detection approach was presented based on a linear-cubic road model for two-lane highways.By using a novel robust lane marking feature which combines the constraints of intensity,edge and width,the lane markings in far regions were extracted accurately and efficiently.Next,the detected lane lines were selected and tracked by estimating the lateral offset and heading angle of ego vehicle with a Kalman filter,Finally,front vehicles were located on correct lanes using the tracked lane lines,Experiment results show that the proposed lane perception approach can achieve an average correct detection rate of 94.37% with an average false positive detection rate of 0.35%,The proposed approaches for long-distance lane perception and front vehicle location were validated in a 286 km full autonomous drive experiment under real traffic conditions.This successful experiment shows that the approaches are effective and robust enough for full autonomous vehicles on highway roads.