北京交通大学学报2023，Vol.47Issue(5)：34-39,6.DOI:10.11860/j.issn.1673-0291.20220088
基于特征关联的车道线检测算法
Lane detection algorithm based on feature correlation
摘要
Abstract
Addressing the challenges posed by the elongated and easily occluded nature of lane lines in lane de-tection tasks,this study introduces the Cross Convolution Net(C-Net),an instance segmentation network structured on an encoder-decoder architecture,for effective lane detection and recognition.Firstly,a feature as-sociation mechanism based on cross convolution is proposed.Through two consecutive cross-convolution op-erations on the down-sampled feature map,a connection is established between individual feature points and the global features,thereby enlarging the receptive field of the feature map to enhance the network's inferential capabilities.Furthermore,5 dual-channel up-sampling modules are used to up-sample the cross-convolution feature map,yielding the instance segmentation result of lane lines.Finally,the network is trained and com-pared on the Tusimple dataset.The results show that C-Net can achieve an accuracy rate of 96.52%,with low false detection and missed detection rates,highlighting its robust lane detection capabilities.关键词
深度学习/卷积神经网络/车道线检测/交叉卷积Key words
deep learning/convolutional neural network/lane detection/cross convolution分类
信息技术与安全科学引用本文复制引用
王朝京,刘彪,刘国豪,边浩毅..基于特征关联的车道线检测算法[J].北京交通大学学报,2023,47(5):34-39,6.基金项目
国家自然科学基金(L201021) （L201021）
浙江省科技厅软科学项目(2021C25005) （2021C25005）
浙江省交通运输厅科技计划项目(2021032) National Natural Science Foundation of China(L201021) （2021032）
Soft Science Research Project of Zhejiang Province(2021C25005) （2021C25005）
Science and Technology Project of Zhejiang Provincial Department of Transportation(2021032) （2021032）
