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...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.展开更多
针对修建在高寒区的隧道衬砌存在的所处环境恶劣、冻害频发、衬砌图像干扰因素多、冻害目标尺度不一致及传统人工目视检测方法效率低下且成本昂贵等问题,提出了基于HRNetV2的高寒区隧道衬砌冻害检测方法。首先以HRNetV2为基础模型,提出...针对修建在高寒区的隧道衬砌存在的所处环境恶劣、冻害频发、衬砌图像干扰因素多、冻害目标尺度不一致及传统人工目视检测方法效率低下且成本昂贵等问题,提出了基于HRNetV2的高寒区隧道衬砌冻害检测方法。首先以HRNetV2为基础模型,提出改进模型,在主干特征提取网络结合迁移学习的知识,在结构中引入注意力机制以加强模型对于冻害特征的学习能力,并使用Focalloss作为损失函数以解决类别不平衡问题。为验证改进后模型的性能,使用高清摄像头采集高寒区隧道衬砌冻害图像,经过裁剪及数据增强等手段,建立一个包含2800张图像的冻害数据集。实验结果表明,改进后的模型在冻害数据集上的平均交并比(mean intersection over union,mIoU)可达到89.05%,相比原始模型提升了5.41%,在面对复杂形态冻害时展现出较好的鲁棒性,可直接应用于高分辨率原图;且在综合性能上优于DeeplabV3+、U-Net、PSPNet三种模型。所提方法可准确、安全地实现衬砌冻害智能检测,可为高寒区隧道智能化运维提供一定技术支持。展开更多
文摘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.
文摘针对修建在高寒区的隧道衬砌存在的所处环境恶劣、冻害频发、衬砌图像干扰因素多、冻害目标尺度不一致及传统人工目视检测方法效率低下且成本昂贵等问题,提出了基于HRNetV2的高寒区隧道衬砌冻害检测方法。首先以HRNetV2为基础模型,提出改进模型,在主干特征提取网络结合迁移学习的知识,在结构中引入注意力机制以加强模型对于冻害特征的学习能力,并使用Focalloss作为损失函数以解决类别不平衡问题。为验证改进后模型的性能,使用高清摄像头采集高寒区隧道衬砌冻害图像,经过裁剪及数据增强等手段,建立一个包含2800张图像的冻害数据集。实验结果表明,改进后的模型在冻害数据集上的平均交并比(mean intersection over union,mIoU)可达到89.05%,相比原始模型提升了5.41%,在面对复杂形态冻害时展现出较好的鲁棒性,可直接应用于高分辨率原图;且在综合性能上优于DeeplabV3+、U-Net、PSPNet三种模型。所提方法可准确、安全地实现衬砌冻害智能检测,可为高寒区隧道智能化运维提供一定技术支持。