长沙理工大学学报（自然科学版）2023，Vol.20Issue(6)：149-158,10.DOI:10.19951/j.cnki.1672-9331.20220419001
基于全连接条件随机场的车道线检测方法
Lane line detection method based on Fully Connected CRFs
摘要
Abstract
[Purposes]Optimizing the noise area and rough edges in the lane line detection results based on deep learning.[Methods]A new method combining deep learning algorithm and post-processing is proposed.The fully connected conditional random fields(Fully Connected CRFs)is introduced to modify the lane line probability map output by the ENet-SAD algorithm,fit the probability map with the original image to get the lane line detection result.The algorithm in this paper is trained and tested on the self-built data set and the CULane data set.[Findings]The results show that on the self-built data set,the F1-score of the algorithm in this paper in four scenarios of normal,strong light,shadow and occlusion were 90.0%,73.1%,81.5%,and 76.6%,respectively.On the CULane dataset,the F1-score of the algorithm in this paper in conventional scenarios reached 91.0%.[Conclusions]The lane detection algorithm proposed herein demonstrates adaptability to various environmental scenarios,and it is an effective lane line detection algorithm.关键词
车道线检测/自动驾驶/全连接条件随机场/ENet-SAD算法/自建数据集/CULane数据集Key words
lane line detection/autonomous vehicle/Fully Connected CRFs/ENet-SAD algorithm/self-built dataset/CULane dataset分类
交通工程引用本文复制引用
龙科军,郭妍慧,刘洋,桂彦,王永峰,陈旺..基于全连接条件随机场的车道线检测方法[J].长沙理工大学学报（自然科学版）,2023,20(6):149-158,10.基金项目
国家自然科学基金资助项目(52172313) （52172313）
湖南省科技创新计划项目(2020RC4048) （2020RC4048）
长沙市科技重大专项(kh2301004) Project(52172313)supported by the National Natural Science Foundation of China （kh2301004）
Project(2020RC4048)supported by Science and Technology Innovation Program of Hunan Province （2020RC4048）
Project(kh2301004)supported by Major Science and Technology Program of Changsha City （kh2301004）
