Aiming at the imbalance between the accuracy and real-time performance of lane detection, this paper proposes a novel vehicle road detection based on pyramid network and self-attention mechanism (namely PFSA). In this method, a two-sided multi-scale fusion network is used to realise the information exchange between shallow features and deep features, and to obtain contextual semantics. A new asymmetric convolution pyramid module is proposed, which fuses asymmetric convolution into cavity convolution layers with different expansion rates to improve feature extraction capability and reduce computation. A two-stage training method was used to train on a public data set and compared with other advanced lane detection methods. The experimental results show that the accuracy is 98.3% and the detection speed is 18.391 frames per second (fps), which is much better than other lane detection methods.
ZakariaNJShapiaiMIAbd GhaniR, et al.Lane detection in autonomous vehicles: a systematic review[J]. IEEE Access2023; 11: 3729–3765.
2.
LeeDHLiuJL. End-to-end deep learning of lane detection and path prediction for real-time autonomous driving[J]. Signal Image Video Process2023; 17: 199–205.
3.
KhanMAMHaqueMFHasanKR, et al.LLDNet: a lightweight lane detection approach for autonomous cars using deep learning[J]. Sensors2022; 22: 5595.
4.
DengTWuY. Simultaneous vehicle and lane detection via MobileNetV3 in car following scene[J]. Plos one2022; 17: e0264551.
5.
LeeMLeeJLeeD, et al.Robust lane detection via expanded self attention[C]. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision, 2022, pp.533–542.
6.
MaselloLCastignaniGSheehanB, et al.On the road safety benefits of advanced driver assistance systems in different driving contexts[J]. Transp Res Interdiscip Perspect2022; 15: 100670.
7.
WinterJDDriessenTDodouD, et al.Exploring the challenges faced by Dutch truck drivers in the era of technological advancement[J]. Front Public Health2023; 12: 1352979.
8.
KosuruVSRVenkitaramanAK. Preventing the False Negatives of Vehicle Object Detection in Autonomous Driving Control Using Clear Object Filter Technique[C]. In: 2022 Third International Conference on Smart Technologies in Computing, Electrical and Electronics (ICSTCEE), 2022, pp.1–6: IEEE.
9.
BalanGArumugamSMuthusamyS, et al.An improved deep learning-based technique for driver detection and driver assistance in electric vehicles with better performance[J]. Int Trans Electr Energy Syst2022; 2022: 1–16.
10.
GuoHKeyvan-EkbataniM. Lane change detection and prediction using real-world connected vehicle data[J]. Transp Res Part C: Emerging Technol2022; 142: 103785.
11.
NareshkumarRSuseelaGNimalaK, et al.Feasibility and Necessity of Affective Computing in Emotion Sensing of Drivers for Improved Road Safety[M]. In: Principles and Applications of Socio-Cognitive and Affective Computing. IGI Global, 2023, pp.94–115.
12.
ChangQTongY. A Hybrid Global-Local Perception Network for Lane Detection[C]. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2024, 38, pp.981–989.
13.
PengGHuangYLiH, et al.LSDNet: A lightweight self-attentional distillation network for visual place recognition[C]. In: 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022, pp.6608–6613. IEEE
14.
ZhuDQianCQuC, et al.An improved SegNet network model for accurate detection and segmentation of car body welding slags[J]. Int J Adv Manuf Technol2022; 120: 1095–1105.
15.
WangBYanXLiD. An end-to-end lane detection model with attention and residual block[J]. Computl Intell Neurosci2022; 2022.
16.
BaekSWKimMJSuddamallaU, et al.Real-time lane detection based on deep learning[J]. J Electr Eng Technol2022; 17: 655–664.
17.
AhmedANAnwarAEckelmannS, et al.Lane Marking Detection Techniques for Autonomous Driving[C]. In: Advances on P2P, Parallel, Grid, Cloud and Internet Computing: Proceedings of the 16th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing (3PGCIC-2021), 2022, pp.217–226: Springer International Publishing.
18.
JiaoXLinYZhaoL. Lane line detection based on improved PINet[J]. J Comput Commun2023; 11: 47–72.
19.
ZoljodiALoniMAbadijouS, et al.3dlanenas: Neural architecture search for accurate and light-weight 3d lane detection[C]. In: International Conference on Artificial Neural Networks, 2022, pp.404–415. Cham: Springer International Publishing.
20.
LingDJinshengXBijunLI, et al.Lane detection method based on semantic segmentation and road structure[J]. J Transp Inf Saf2023; 41: 103–110.
21.
ZhouXNieXLiZ, et al.H-Net: a dual-decoder enhanced FCNN for automated biomedical image diagnosis[J]. Inf Sci2022; 613: 575–590.
22.
TabeliniLBerrielRPaixaoTM, et al.Keep your eyes on the lane: Real-time attention-guided lane detection[C]. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp.294–302.
23.
YinS. Object detection based on deep learning: a brief review[J]. IJLAI Trans Sci Eng2023; 1: 1–6.
24.
YinSWangLWangQ, et al.M2F2-RCNN: multi-functional faster RCNN based on multi-scale feature fusion for region search in remote sensing images[J]. Comput Sci Inf Syst2023; 20
25.
TengLQiaoYShafiqM, et al.FLPK-BiSeNet: federated learning based on priori knowledge and bilateral segmentation network for image edge extraction[J]. IEEE Trans on Network Service ManageJune 2023; 20(2): 1529–1542. doi: 10.1109/TNSM.2023.3273991
26.
TianCXuYZuoW, et al.Asymmetric CNN for image superresolution[J]. IEEE Trans Syst Man Cybernetics: Syst2021; 52: 3718–3730.
27.
ZhangYZhuLFengW, et al.Vil-100: A new dataset and a baseline model for video instance lane detection[C]. In: Proceedings of the IEEE/CVF international conference on computer vision, 2021, pp.15681–15690.
28.
YinSWangLShafiqM, et al.G2Grad-CAMRL: an object detection and interpretation model based on gradient-weighted class activation map** and reinforcement learning in remote sensing images[J]. IEEE J Selected Topics Appl Earth Obs Remote Sens2023; 16: 3583–3598. doi: 10.1109/JSTARS.2023.3241405
29.
WangZRenWQiuQ. Lanenet: Real-time lane detection networks for autonomous driving[J]. arxiv preprint arxiv:1807.01726. 2018.
30.
PanXShiJLuoP, et al.Spatial as deep: Spatial cnn for traffic scene understanding[C]. In: Proceedings of the AAAI conference on artificial intelligence, 2018, 32.
31.
HouYMaZLiuC, et al.Learning lightweight lane detection cnns by self attention distillation[C]. In: Proceedings of the IEEE/CVF international conference on computer vision, 2019, pp.1013–1021.
32.
QinZWangHLiX. Ultra fast structure-aware deep lane detection[C]. In: Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XXIV 16, pp.276–291: Springer International Publishing.
33.
LiuRYuanZLiuT, et al.End-to-end lane shape prediction with transformers[C]. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision, 2021, pp.3694–3702.
34.
JohnanderJDanelljanMBrissmanE, et al.A generative appearance model for end-to-end video object segmentation[C]. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp.8953–8962.
35.
VenturaCBellverMGirbauA, et al.Rvos: End-to-end recurrent network for video object segmentation[C]. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp.5277–5286.
36.
OhSWLeeJYXuN, et al.Video object segmentation using space-time memory networks[C]. In: Proceedings of the IEEE/CVF international conference on computer vision, 2019, pp.9226–9235.
37.
LiangYLiXJafariN, et al.Video object segmentation with adaptive feature bank and uncertain-region refinement[J]. Adv Neural Inf Process Syst2020; 33: 3430–3441.
38.
ZhangYWuZPengH, et al.A transductive approach for video object segmentation[C]. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp.6949–6958.
