|本期目录/Table of Contents|

[1]李海华,万热华,陈小玲,等.一种基于逆透视变换的车道线检测方法[J].工业仪表与自动化装置,2021,(02):97-100.[doi:10.19950/j.cnki.cn61-1121/th.2021.02.022]
 LI Haihua,WAN Rehua,CHEN Xiaoling,et al.A lane line detection method based on inverse perspective transformation[J].Industrial Instrumentation & Automation,2021,(02):97-100.[doi:10.19950/j.cnki.cn61-1121/th.2021.02.022]
点击复制

一种基于逆透视变换的车道线检测方法

《工业仪表与自动化装置》[ISSN:1000-0682/CN:61-1121/TH]

卷:
期数:
2021年02期
页码:
97-100
栏目:
出版日期:
2021-04-15

文章信息/Info

Title:
A lane line detection method based on inverse perspective transformation
作者:
李海华1万热华2陈小玲1范 娟1
1. 文华学院 机械与电气工程学部,湖北 武汉 430074;
2. 中船黄埔文冲船舶有限公司,广东 广州 510715
Author(s):
LI Haihua1WAN Rehua2CHEN Xiaoling1FAN Juan1
1.Department of Mechanical and Electrical Engineering, Wenhua College, Hubei Wuhan 430074, China;
2.CSSC Huangpu Wenchong Shipbuilding Company Limited, Guangdong Guangzhou 510715, China
关键词:
车道线检测逆透视图高斯滤波Bezier拟合
Keywords:
lane line detection inverse perspective view Gaussian filtering Bezier fitting
分类号:
TP391.41
DOI:
10.19950/j.cnki.cn61-1121/th.2021.02.022
文献标志码:
A
摘要:
该文基于逆透视变换技术提出了一种车道线检测方法。将道路图像映射为逆透视图,用二维高斯滤波器对图像进行滤波,然后进行阈值处理;用Hough变换提取车道线的线条曲线,利用三阶Bezier样条曲线拟合算法进行直线拟合,获得车道线的检测结果。实验表明,该方法在图像较清晰的情况下,检测近距离的车道线获得了较好的效果,适用于平坦路面下的白色和黄色等车道线检测。
Abstract:
This paper proposes a lane line detection method based on the inverse perspective transform technology.The road image is mapped into an inverse perspective image,and the image is filtered with a two-dimensional Gaussian filter,and then threshold processing is performed.The line curve of the lane line is extracted by Hough transform,and the third-order Bezier spline curve fitting algorithm is used to fit the straight line to obtain the detection result of the lane line.Experiments show that this method can detect lane lines at close distances when the image is clear,it is suitable for white and yellow lane line detection on flat roads.

参考文献/References:

[1] 吴一全,刘莉.基于视觉的车道线检测方法研究进展[J]. 仪器仪表学报,2019,40(12):92-109.

[2] 李忠东.麻省理工学院致力于自动驾驶技术研究[J].轻型汽车技术,2018(Z3):39-45.
[3] ALY Mohamed.Real time detection of lane markers in urban streets[C].2008 IEEE Intelligent Vehicles Symposium, Netherlands,2008:7-12.
[4] 刘萍,孙耀航.基于反透视变换的车道线检测算法[J].计算机与数字工程,2019,47(03):678-681.
[5] 吴骅跃,赵祥模.基于IPM和边缘图像过滤的多干扰车道线检测[J].中国公路学报,2020,33(05):153-164.
[6] 姜立标,李静轩.基于改进Hough变换与双点去除R最小二乘法的车道线检测优化算法[J].科学技术与工程,2020,20(05):2070-2076.
[7] 田锦,袁家政,刘宏哲.基于实例分割的车道线检测及自适应拟合算法[J].计算机应用,2020,40(07):1932-1937.
[8] 蔡英凤,张田田,王海,等.基于实例分割和自适应透视变换算法的多车道线检测[J].东南大学学报(自然科学版),2020,50(04):775-781.
[9] 阎翔,谌海云,蒋钰,等.基于计算机视觉的车道线检测与识别[J].工业仪表与自动化装置,2020(01):118-121.
[10] WANG Wei,LIN Hui,WANG Junshu.CNN based lane detection with instance segmentation in edge-cloud computing[J].Journal of Cloud Computing:Advances,Systems and Applications,2020,9(6):44957-44966.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期:2020-08-18

基金项目:
湖北省教育厅科学研究项目(B2015192)

作者简介:
李海华(1980),男,湖北荆门人,副教授,研究方向为光电检测及自动控制。

通信作者:
陈小玲(1987),女,湖北武汉人,文华学院,讲师,研究方向为电机调速及电气控制算法研究。
更新日期/Last Update: 1900-01-01