Multi-lane line detection and tracking network based on spatial semantics segmentation

SHI Jinpeng; ZHANG Xu

doi:10.37188/OPE.20233109.1357

您当前的位置：

首页 >

文章列表页 >

Multi-lane line detection and tracking network based on spatial semantics segmentation

Information Sciences | 更新时间：2023-05-15

- Multi-lane line detection and tracking network based on spatial semantics segmentation
- Optics and Precision Engineering Vol. 31, Issue 9, Pages: 1357-1365(2023)
- 作者机构：
  
  上海工程技术大学机械与汽车工程学院，上海 201620
- 作者简介：
- 基金信息：
- DOI：10.37188/OPE.20233109.1357
  CLC： U491.6
- Received：13 July 2022，
  
  Revised：30 August 2022，
  
  Published：10 May 2023
- 稿件说明：
移动端阅览
石金鹏,张旭.基于空间语义分割的多车道线检测跟踪网络[J].光学精密工程,2023,31(09):1357-1365.

SHI Jinpeng,ZHANG Xu.Multi-lane line detection and tracking network based on spatial semantics segmentation[J].Optics and Precision Engineering,2023,31(09):1357-1365.
石金鹏,张旭.基于空间语义分割的多车道线检测跟踪网络[J].光学精密工程,2023,31(09):1357-1365. DOI： 10.37188/OPE.20233109.1357.

SHI Jinpeng,ZHANG Xu.Multi-lane line detection and tracking network based on spatial semantics segmentation[J].Optics and Precision Engineering,2023,31(09):1357-1365. DOI： 10.37188/OPE.20233109.1357.

摘要

基于深度学习的目标检测网络在车道线识别领域依旧存在车道区别不明显，识别精度低，误检率、漏检率高等问题。为了解决这些问题，提出了一种基于空间实例分割的轻量级车道检测跟踪网络。该方法在编码部分使用VGG16网络和空间卷积神经网络来提高网络结构学习空间关系的能力，解决了预测车道线出现模糊、不连续等问题；基于LaneNet将编码输出后的两个分支任务相耦合，以改进前景与背景识别效果不佳和车道间区分不明显的问题。最后，该方法在TuSimple数据集中与其他

http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=43439245&type=

http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=43439243&type=

1.60866666

2.37066650

种基于语义分割的车道线算法进行对比。实验表明，本文算法的准确率评分为

http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=43439257&type=

http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=43439246&type=

8.12800026

2.37066650

%，误检率与漏检率均优于其他网络，并且误检率与漏检率相比于LaneNet分别降低了

http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=43439279&type=

http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=43439260&type=

8.04333401

2.37066650

%和

http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=43439284&type=

http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=43439267&type=

6.51933336

2.37066650

%，基本满足实时车道线检测跟踪的要求。

Abstract

Target detection networks based on deep learning has some problems in the field of lane line recognition， such as unclear lane differences， low recognition accuracy， a high false detection rate， and a high missed detection rate. To solve the aforementioned problems， a lightweight lane detection and tracking network， SCNNLane， based on spatial instance segmentation， was proposed. In the coding part， the VGG16 network and the spatial convolution neural network （SCNN） were applied to improve the ability of the network structure to learn spatial relationships， which solved the problems of blurring and discontinuity in lane prediction. Simultaneously， based on LaneNet， two branch tasks after encoding the output were coupled to improve poor foreground and background recognition and indistinguishability between lanes. Finally， the method was compared with five other semantic segmentation-based lane-line algorithms by using the TuSimple dataset. Experimental results show that the accuracy of this algorithm is 97.12%， and the false detection rate and missed detection rate are reduced by 44.87% and 12.7% respectivel， as compared with LaneNet， thus meeting the demand of real-time lane line detection.

关键词

Keywords

references

TOROYAN T . Global status report on road safety ［J］. Injury Prevention ， 2009 ， 15 （ 4 ）： 286 . doi: 10.1136/ip.2009.023697 http://dx.doi.org/10.1136/ip.2009.023697

HUVAL B ， WANG T ， TANDON S ， et al . An Empirical Evaluation of Deep Learning on Highway Driving ［EB/OL］. 2015 ： arXiv ： 1504 . 01716 . https：//arxiv.org/abs/1504.01716 https://arxiv.org/abs/1504.01716 "

HILLEL A B ， LERNER R ， LEVI D ， et al . Recent progress in road and lane detection： a survey ［J］. Machine Vision and Applications ， 2014 ， 25 （ 3 ）： 727 - 745 . doi: 10.1007/s00138-011-0404-2 http://dx.doi.org/10.1007/s00138-011-0404-2

何旭光，江磊，罗一平，等 . 基于Hough变换的车道线检测算法设计［J］. 农业装备与车辆工程， 2019 ， 57 （ 11 ）： 90 - 91， 107 . doi: 10.3969/j.issn.1673-3142.2019.11.022 http://dx.doi.org/10.3969/j.issn.1673-3142.2019.11.022

HE X G ， JIANG L ， LUO Y P ， et al . Design of lane detection algorithm based on Hough transform ［J］. Agricultural Equipment & Vehicle Engineering ， 2019 ， 57 （ 11 ）： 90 - 91， 107 . （in Chinese） . doi: 10.3969/j.issn.1673-3142.2019.11.022 http://dx.doi.org/10.3969/j.issn.1673-3142.2019.11.022

马泉钧，何自超，林邦演，等 . 基于图像处理的长距离车道线检测［J］. 河南科技， 2019 （ 29 ）： 111 - 113 . doi: 10.3969/j.issn.1003-5168.2019.29.042 http://dx.doi.org/10.3969/j.issn.1003-5168.2019.29.042

MA Q J ， HE Z CH ， LIN B Y ， et al . Long distance lane detection based on image processing ［J］. Henan Science and Technology ， 2019 （ 29 ）： 111 - 113 . （in Chinese） . doi: 10.3969/j.issn.1003-5168.2019.29.042 http://dx.doi.org/10.3969/j.issn.1003-5168.2019.29.042

KRIZHEVSKY A ， SUTSKEVER I ， HINTON G E . ImageNet classification with deep convolutional neural networks ［C］. Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 1. 36，2012 ， Lake Tahoe， Nevada. New York ： ACM ， 2012 ： 1097 - 1105 .

ZEILER M D ， FERGUS R . Visualizing and Understanding Convolutional Networks ［EB/OL］. 2013 ： arXiv ： 1311 . 2901 . https：//arxiv.org/abs/1311.2901 https://arxiv.org/abs/1311.2901 ". doi: 10.1007/978-3-319-10590-1_53 http://dx.doi.org/10.1007/978-3-319-10590-1_53

崔文靓，王玉静，康守强，等 . 基于改进YOLOv3算法的公路车道线检测方法［J］. 自动化学报， 2022 ， 48 （ 6 ）： 1560 - 1568 . doi: 10.16383/j.aas.c190178 http://dx.doi.org/10.16383/j.aas.c190178

CUI W Q ， WANG Y J ， KANG S Q ， et al . Highway lane line detection method based on improved YOLOv3 algorithm ［J］. Journal of Automation . 2022 ， 48 （ 6 ）： 1560 - 1568 . （in Chinese） . doi: 10.16383/j.aas.c190178 http://dx.doi.org/10.16383/j.aas.c190178

王若霄，徐智勇，张建林 . 跨深度的卷积特征增强目标检测算法［J］. 计算机工程与设计， 2020 ， 41 （ 7 ）： 1864 - 1871 . doi: 10.16208/j.issn1000-7024.2020.07.011 http://dx.doi.org/10.16208/j.issn1000-7024.2020.07.011

WANG R X ， XU ZH Y ， ZHANG J L . Cross-depth convolutional feature enhancement algorithm for object detection ［J］. Computer Engineering and Design ， 2020 ， 41 （ 7 ）： 1864 - 1871 . （in Chinese） . doi: 10.16208/j.issn1000-7024.2020.07.011 http://dx.doi.org/10.16208/j.issn1000-7024.2020.07.011

PAN X G ， SHI J P ， LUO P ， et al . Spatial as deep： spatial CNN for traffic scene understanding ［J］. Proceedings of the AAAI Conference on Artificial Intelligence ， 2018 ， 32 （ 1 ）. doi: 10.1609/aaai.v32i1.12301 http://dx.doi.org/10.1609/aaai.v32i1.12301

PIZZATI F ， GARCÍA F . Enhanced free space detection in multiple lanes based on single CNN with scene identification ［C］. 2019 IEEE Intelligent Vehicles Symposium （IV）. 912，2019 ， Paris， France. IEEE ， 2019 ： 2536 - 2541 . doi: 10.1109/ivs.2019.8814181 http://dx.doi.org/10.1109/ivs.2019.8814181

刘彬，刘宏哲 . 基于改进Enet网络的车道线检测算法［J］. 计算机科学， 2020 ， 47 （ 4 ）： 142 - 149 . doi: 10.11896/jsjkx.190500021 http://dx.doi.org/10.11896/jsjkx.190500021

LIU B ， LIU H ZH . Lane detection algorithm based on improved enet network ［J］. Computer Science ， 2020 ， 47 （ 4 ）： 142 - 149 . （in Chinese） . doi: 10.11896/jsjkx.190500021 http://dx.doi.org/10.11896/jsjkx.190500021

HOU Q B ， ZHANG L ， CHENG M M ， et al . Strip pooling： rethinking spatial pooling for scene parsing ［C］. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. 1319，2020 ， Seattle， WA， USA. IEEE ， 2020 ： 4002 - 4011 . doi: 10.1109/cvpr42600.2020.00406 http://dx.doi.org/10.1109/cvpr42600.2020.00406

NEVEN D ， DE BRABANDERE B ， GEORGOULIS S ， et al . Towards end-to-end lane detection： an instance segmentation approach ［C］. 2018 IEEE Intelligent Vehicles Symposium （IV）. 2630，2018 ， Changshu， China. IEEE ， 2018 ： 286 - 291 . doi: 10.1109/ivs.2018.8500547 http://dx.doi.org/10.1109/ivs.2018.8500547

SIMONYAN K ， ZISSERMAN A . Very deep convolutional networks for large-scale image recognition ［J］. CoRR ， 2014 ， abs/1409. 1556 .

BOLYA D ， ZHOU C ， XIAO F Y ， et al . YOLACT： real-time instance segmentation ［C］. 2019 IEEE/CVF International Conference on Computer Vision （ICCV）. 272，2019 ， Seoul， Korea （South）. IEEE ， 2020 ： 9156 - 9165 . doi: 10.1109/iccv.2019.00925 http://dx.doi.org/10.1109/iccv.2019.00925

CHEN H ， SUN K Y ， TIAN Z ， et al . BlendMask： top-down meets bottom-up for instance segmentation ［C］. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. 1319，2020 ， Seattle， WA， USA. IEEE ， 2020 ： 8570 - 8578 . doi: 10.1109/cvpr42600.2020.00860 http://dx.doi.org/10.1109/cvpr42600.2020.00860

Views

579

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Transfer learning techniques for semantic segmentation of machine vision inspection and identification based on label-reserved Softmax algorithms

Inverse perspective mapping of pavement image combining semantic and 3D information

Polarized image feature fusion in power inspection

Machine vision-based method for measuring micro-volume liquid in transparent tubes

Multi-scale context-aware network for road extraction in remote sensing images

Related Author

Guixiong LIU

Jian HUANG

XIA Xiaohua

GAO Xiaofei

DUAN Zhiwei

FENG Xinmiao

NI Mengyao

PENG Yuanlong

Related Institution

School of Mechanical and Automotive Engineering， South China University of Technology

Key Laboratory of Road Construction Technology and Equipment，Ministry of Education，Chang' an University

School of Optical and Electronic Information， Huazhong University of Science and Technology

State Grid Information & Telecommunication Branch

State Grid JiangXi Electric Power Supply Co

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰