Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Advances in Computer, Signals and Systems
  4. Vol 7, Issue 8, 2023

Research on Lane Line Detection Based on Around View System

Download as PDF

DOI: 10.23977/acss.2023.070801 | Downloads: 18 | Views: 417

Author(s)

Zhou Su 1,2, Li Keda 1, Zhu Xiaofeng 1

Affiliation(s)

1 School of Automotive Engineering, Tongji University, Shanghai, China
2 Shanghai Zhongqiao Vocational and Technical University, Shanghai, China

Corresponding Author

Zhou Su

ABSTRACT

Traditional lane detection methods are limited by factors such as camera position and perspective, and often encounter issues such as false detection and missed detection. This article conducts research on lane detection methods from the perspective of multi camera BEV, and proposes a circular lane detection method based on convolutional neural networks (CNN). In order to solve the occlusion problem perceived from traditional forward looking perspectives, an around system was constructed using multiple cameras, and a multi classification semantic segmentation network was innovatively designed to predict obstructions, greatly reducing the false detection rate of obstructed lane lines. After verification, the algorithm proposed in this article can achieve good lane line detection results in different environments.

KEYWORDS

Around view system, lane detection, semantic segmentation

CITE THIS PAPER

Zhou Su, Li Keda, Zhu Xiaofeng, Research on Lane Line Detection Based on Around View System. Advances in Computer, Signals and Systems (2023) Vol. 7: 1-10. DOI: http://dx.doi.org/10.23977/acss.2023.070801.

REFERENCES

[1] Qi L, Liu Y, Zhao Y, et al. Real-time lane detection algorithm based on edge detection [C]//2016 IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER) IEEE, 2016: 67-70.
[2] Xie D, Zhang M, Xie X, et al. Lane Detection Algorithm Based on HSV Color Space [C]//2019 IEEE 4th International Conference on Image, Vision and Computing (ICIVC) IEEE, 2019: 637-641. 
[3] Zare M, Gholami M, Abdi H, et al. Lane detection using the Hough transform and adaptive Gaussian filter [C]//2016 8th Conference on Information and Knowledge Technology (IKT) IEEE, 2016: 251-256. 
[4] Zhang G.,&Hu W. (2019). A Review of Lane Detection Techniques. arXiv preprint arXiv: 1906.00414. 
[5] J. Y. Bouguet, "Camera Calibration Toolbox for Matlab," in IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) Workshop, San Francisco, California, USA, 1999. 
[6] Vogel D.,&Schindler K. (2018). A Deep Network for Automatic Detection and Analysis of Road Networks in Aerial Images. IEEE Transactions on Geoscience and Remote Sensing, 56 (2), 1082-1092. 
[7] Ghafoorian M., van Tulder G., de With P. H.,&Philips W. (2018). Lane detection in challenging conditions: a deep learning approach IEEE Transactions on Intelligent Transportation Systems, 20 (3), 978-990.
[8] K. Simonyan and A. Zisserman, "Very Deep Convolutional Networks for Large Scale Image Recognition," in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014, pp. 1-14. 
[9] Chollet F. (2017). Xception: Deep learning with depthwise separable conversions. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1800-1807). 
[10] Gonzalez R. C., & Woods R. E. (2008). Digital image processing (3rd ed.). Prentice Hall.
[11] Sørensen Thorkild, and Gert Stokholm Nielsen. "Generalization of Cohen's kappa to graded classifications." International conference on bioinformatics, 1997, pp. 212-220.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 15145
Visits: 268060

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.