Lane detection algorithms require extremely low computational costs as an important part of autonomous driving. Due to heavy backbone networks, algorithms based on pixel-wise segmentation is struggling to handle the problem of runtime consumption in the recognition of lanes. In this paper, a novel and practical methodology based on lightweight Segmentation Network is proposed, which aims to achieve accurate and efficient lane detection. Different with traditional convolutional layers, the proposed Shadow module can reduce the computational cost of the backbone network by performing linear transformations on intrinsic feature maps. Thus a lightweight backbone network Shadow-VGG-16 is built. After that, a tailored pyramid parsing module is introduced to collect different sub-domain features, which is composed of both a strip pool module based on Pyramid Scene Parsing Network (PSPNet) and a convolution attention module. Finally, a lane structural loss is proposed to explicitly model the lane structure and reduce the influence of noise, so that the pixels can fit the lane better. Extensive experimental results demonstrate that the performance of our method is significantly better than the state-of-the-art (SOTA) algorithms such as Pointlanenet and Line-CNN et al. 95.28% and 90.06% accuracy and 62.5 frames per second (fps) inference speed can be achieved on the CULane and Tusimple test dataset. Compared with the latest ERFNet, Line-CNN, SAD, F₁ scores have respectively increased by 3.51%, 2.84%, and 3.82%. Meanwhile, the result from our dataset exceeds the top performances of the other by 8.6% with an 87.09 F₁ score, which demonstrates the superiority of our method.

车道检测算法作为自动驾驶的重要组成部分，需要极低的计算成本。由于骨干网络繁重，基于像素分割的算法正努力解决车道识别中的运行时消耗问题。本文提出了一种基于轻量级分割网络的新颖实用的方法，旨在实现准确有效的车道检测。与传统的卷积层不同，所提出的影子模块可以通过对固有特征图执行线性变换来降低骨干网的计算成本。这样就建立了一个轻量级的骨干网Shadow-VGG-16。之后，引入了量身定制的金字塔解析模块来收集不同的子域特征，它由基于金字塔场景解析网络（PSPNet）的条带池模块和卷积注意模块组成。最后，提出一种车道结构损失，以对车道结构进行显式建模并减少噪声的影响，从而使像素更好地适合车道。大量的实验结果表明，我们的方法的性能明显优于诸如Pointlanenet和Line-CNN等人的最新算法（SOTA）。在CULane和Tusimple测试数据集上，可以达到95.28％和90.06％的精度以及62.5帧每秒（fps）的推理速度。与最新的ERFNet，Line-CNN，SAD，F相比 以便像素可以更好地适合车道。大量的实验结果表明，我们的方法的性能明显优于诸如Pointlanenet和Line-CNN等人的最新算法（SOTA）。在CULane和Tusimple测试数据集上，可以达到95.28％和90.06％的精度以及62.5帧每秒（fps）的推理速度。与最新的ERFNet，Line-CNN，SAD，F相比 以便像素可以更好地适合车道。大量的实验结果表明，我们的方法的性能明显优于诸如Pointlanenet和Line-CNN等人的最新算法（SOTA）。在CULane和Tusimple测试数据集上，可以达到95.28％和90.06％的精度以及62.5帧每秒（fps）的推理速度。与最新的ERFNet，Line-CNN，SAD，F相比₁分的分别提高了3.51％，2.84％和3.82％。同时，我们的数据集的结果以87.09 F _1的得分超过了其他同类产品的最高性能8.6％，这证明了我们方法的优越性。