Journal of Auto-vehicle Safety Association (자동차안전학회지)

Korean Auto-vehicle Safety Association (한국자동차안전학회)
권호 표지
DOI QR코드

DOI QR Code

Multi-label Lane Detection Algorithm for Autonomous Vehicle Using Deep Learning

자율주행 차량을 위한 멀티 레이블 차선 검출 딥러닝 알고리즘

  • 박채송 (서울대학교 협동과정 인공지능전공) ;
  • 이경수 (서울대학교 기계공학부)
  • Received : 2023.09.19
  • Accepted : 2024.02.22
  • Published : 2024.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents a multi-label lane detection method for autonomous vehicles based on deep learning. The proposed algorithm can detect two types of lanes: center lane and normal lane. The algorithm uses a convolution neural network with an encoder-decoder architecture to extract features from input images and produce a multi-label heatmap for predicting lane's label. This architecture has the potential to detect more diverse types of lanes in that it can add the number of labels by extending the heatmap's dimension. The proposed algorithm was tested on an OpenLane dataset and achieved 85 Frames Per Second (FPS) in end to-end inference time. The results demonstrate the usability and computational efficiency of the proposed algorithm for the lane detection in autonomous vehicles.

Keywords

References

  1. Zhao, Xiangmo, et al., "Fusion of 3D LIDAR and camera data for object detection in autonomous vehicle applications," IEEE Sensors Journal 20.9 (2020): 4901~4913. https://doi.org/10.1109/JSEN.2020.2966034
  2. Arnold, Eduardo, et al., "A survey on 3d object detection methods for autonomous driving applications," IEEE Transactions on Intelligent Transportation Systems 20.10 (2019): 3782~3795. https://doi.org/10.1109/TITS.2019.2892405
  3. Min, Haigen, et al., "Kinematic and dynamic vehicle model-assisted global positioning method for autonomous vehicles with low-cost GPS/camera/in-vehicle sensors," Sensors 19.24 (2019): 5430.
  4. Zhang, Li, et al., "Hierarchical Road Topology Learning for Urban Mapless Driving," 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2022.
  5. Toan, Nguyen Duc, and Kim Gon Woo, "Mapless navigation with deep reinforcement learning based on the convolutional proximal policy optimization network," 2021 IEEE International Conference on Big Data and Smart Computing (BigComp). IEEE, 2021.
  6. Ronneberger, Olaf, Philipp Fischer, and Thomas Brox, "U-net: Convolutional networks for biomedical image segmentation," Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18. Springer International Publishing, 2015.
  7. Badrinarayanan, Vijay, Alex Kendall, and Roberto Cipolla, "Segnet: A deep convolutional encoder-decoder architecture for image segmentation," IEEE transactions on pattern analysis and machine intelligence 39.12 (2017): 2481~2495. https://doi.org/10.1109/TPAMI.2016.2644615
  8. Zhang, Wenhui, and Tejas Mahale, "End to end video segmentation for driving: Lane detection for autonomous car," arXiv preprint arXiv:1812.05914 (2018).
  9. Chiang, Wei-Lin, et al., "Cluster-gcn: An efficient algorithm for training deep and large graph convolutional networks," Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining. 2019.
  10. Dosovitskiy, Alexey, et al., "CARLA: An open urban driving simulator," Conference on robot learning. PMLR, 2017.
  11. Ko, Yeongmin, et al., "Key points estimation and point instance segmentation approach for lane detection," IEEE Transactions on Intelligent Transportation Systems 23.7 (2021): 8949~8958. https://doi.org/10.1109/TITS.2021.3088488
  12. Qiu, Qibo, et al., "PriorLane: A Prior Knowledge Enhanced Lane Detection Approach Based on Transformer," arXiv preprint arXiv:2209.06994 (2022).
  13. Liu, Lizhe, et al., "Condlanenet: a top-to-down lane detection framework based on conditional convolution," Proceedings of the IEEE/CVF international conference on computer vision. 2021.
  14. X. Pan, J. Shi, P. Luo, X. Wang, and X. Tang, "Spatial as deep: Spatial cnn for traffic scene understanding," in AAAI Conference on Artificial Intelligence, vol. 32, no. 1, 2018.
  15. Chen, Li, et al., "Persformer: 3d lane detection via perspective transformer and the openlane benchmark," Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXXVIII. Cham: Springer Nature Switzerland, 2022.
  16. Luo, Zhengxiong, et al., "Rethinking the heatmap regression for bottom-up human pose estimation," Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2021.
  17. Chen, Yu, et al., "Adversarial posenet: A structure-aware convolutional network for human pose estimation," Proceedings of the IEEE international conference on computer vision. 2017.