RoaDSaVe: A Robust Lane Detection Method Based on Validity Borrowing From Reliable Lines

被引:4
作者
Maghsoumi, Hossein [1 ]
Masoumi, Nasser [2 ,3 ]
Araabi, Babak Nadjar [4 ]
机构
[1] Univ Tehran, Sch Elect & Comp Engn ECE, Coll Engn, Circuits & Syst & Test Lab CST Lab, Tehran 1439957131, Iran
[2] Univ Tehran, Sch Elect & Comp Engn, Dept Elect, Coll Engn, Tehran 1439957131, Iran
[3] Univ Tehran, Fac Entrepreneurship, Dept Technol Entrepreneurship, Tehran 1439957131, Iran
[4] Univ Tehran, Sch Elect & Comp Engn ECE, Coll Engn, Machine Learning & Computat Modeling Lab MLCM Lab, Tehran 1417466191, Iran
关键词
Autonomous driving; lane detection; physical inference; semantic segmentation; validity effectiveness; SYSTEM;
D O I
10.1109/JSEN.2023.3279052
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Lane detection is a critical but challenging task in autonomous driving, especially in complex scenes. In most of the complicated scenes, only a part of the scene is challenged, and the whole road surface is not involved. We believe that perception of the scene's structure and using information of reliable areas to detect lanes in challenging areas is the key to robust lane detection. This article proposes a novel lane detection method that can provide a reliable system even in complex situations and meet real-time requirements, called RoaDSaVe. The RoaDSaVe method consists of three major modules: scene awareness, physical inference, and validity effectiveness. The scene awareness module takes advantage of an effective combination of shallow and deep features in a neural network, resulting in a more accurate acquisition of spatial and semantic feature maps. Following that, an optimization method is used to obtain the physical parameters of the lane lines based on road and lane semantic labels. The physical inference module creates an adjusted histogram and considers locations with high scores and reliability to be valid lines. In the validity effectiveness module, the potential points are stimulated by the valid lines. If a potential line did not achieve sufficient validity in the previous module, it can still be considered valid if it meets the required score. The experiments on several public datasets show that the RoaDSaVe lane detection method has significant ability in scenes with local challenges and achieves excellent performance compared to the state-of-the-art methods.
引用
收藏
页码:14571 / 14582
页数:12
相关论文
共 35 条
[1]  
Abramov A, 2017, IEEE INT VEH SYM, P1386, DOI 10.1109/IVS.2017.7995904
[2]   Real time Detection of Lane Markers in Urban Streets [J].
Aly, Mohamed .
2008 IEEE INTELLIGENT VEHICLES SYMPOSIUM, VOLS 1-3, 2008, :165-170
[3]  
BDD100K, DIVERSE DRIVING DATA
[4]   GOLD: A parallel real-time stereo vision system for generic obstacle and lane detection [J].
Bertozzi, M ;
Broggi, A .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 1998, 7 (01) :62-81
[5]  
Chen Q, 2006, 2006 IEEE INTELLIGENT VEHICLES SYMPOSIUM, P511
[6]   Multi-Lane Detection and Tracking Using Temporal-Spatial Model and Particle Filtering [J].
Chen, Sihan ;
Huang, Libo ;
Chen, Huanlei ;
Bai, Jie .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2022, 23 (03) :2227-2245
[7]  
Deng J., 2013, P 2013 RES AD CONV S, P157
[8]  
github, TUSIMPLE TUSIMPLE BE
[9]   DALaneNet: A Dual Attention Instance Segmentation Network for Real-Time Lane Detection [J].
Guo, Zhiyang ;
Huang, Yingping ;
Wei, Hongjian ;
Zhang, Chong ;
Zhao, Baigan ;
Shao, Zheqin .
IEEE SENSORS JOURNAL, 2021, 21 (19) :21730-21739
[10]  
Han C., 2022, arXiv