Code underlying the publication: A Hybrid Spatial-temporal Deep Learning Architecture for Lane Detection

Codes for the paper<strong>Dong, Y.</strong>, Patil, S., van Arem, B., &amp; Farah, H. (2023). A Hybrid Spatial-temporal Deep Learning Architecture for Lane Detection. <em>Computer-Aided Civil and Infrastructure Engineering</em>, <em>38</em>(1), pp.67–86.<br>Accurate and reliable lane detection is vital for the safe performance of lane-keeping assistance and lane departure warning systems. However, under certain challenging circumstances, it is difficult to get satisfactory performance in accurately detecting the lanes from one single image as mostly done in current literature. Since lane markings are continuous lines, the lanes that are difficult to be accurately detected in the current single image can potentially be better deduced if information from previous frames is incorporated. This study proposes a novel hybrid spatial–temporal (ST) sequence-to-one deep learning architecture. This architecture makes full use of the ST information in multiple continuous image frames to detect the lane markings in the very last frame. Specifically, the hybrid model integrates the following aspects: (a) the single image feature extraction module equipped with the spatial convolutional neural network; (b) the ST feature integration module constructed by ST recurrent neural network; (c) the encoder–decoder structure, which makes this image segmentation problem work in an end-to-end supervised learning format. Extensive experiments reveal that the proposed model architecture can effectively handle challenging driving scenes and outperforms available state-of-the-art methods.<br>

本代码对应论文：Dong, Y.、Patil, S.、van Arem, B. 与 Farah, H. (2023)。《面向车道检测的混合时空深度学习架构》，刊载于《计算机辅助土木工程与基础设施工程（Computer-Aided Civil and Infrastructure Engineering）》第38卷第1期，第67-86页。

准确可靠的车道检测对于车道保持辅助系统与车道偏离预警系统的安全运行至关重要。然而，在部分挑战性驾驶场景中，现有研究大多采用的单图像车道检测方法难以取得令人满意的检测精度。鉴于车道标线属于连续线条，若结合前序视频帧的信息，原本在单张图像中难以精准检测的车道，有望实现更可靠的推导。本研究提出一种新颖的混合时空（Spatial-Temporal, ST）序列到单输出深度学习架构。该架构充分利用多幅连续图像帧中的时空信息，以检测最后一帧的车道标线。具体而言，该混合模型整合了以下三个模块：(a) 搭载空间卷积神经网络的单图像特征提取模块；(b) 由时空循环神经网络构建的时空特征融合模块；(c) 编码器-解码器结构，使得该图像分割问题能够以端到端监督学习的范式开展训练。大量实验结果表明，所提出的模型架构可有效应对复杂驾驶场景，且性能优于现有主流先进方法。