YOLO 네트워크를 사용한 다중 차선 인식
Multi-Lanes Recognition using the YOLO Network
1
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
Future autonomous vehicles need to recognize the ego lanes required for lane change and the side left and right lanes differently. Therefore, multi-lane recognition is needed. In this study, using the YOLO network, mainly used for object recognition, the proposed method recognizes the ego, left and right side lanes as different objects and identifies the correct lanes. As a result of the performance evaluation on the TuSimple test data, the proposed method recognized the ego lanes and the left and right side lanes differently. It showed very stable lane recognition results. And by detecting lanes that do not exist in the ground truth of TuSimple data, the proposed method is very robust in lanes detection. Nevertheless, studies related to learning data reinforcement in which lanes are located in the center or at the left and right edges of the image and accurate network learning for lanes are needed.
Abstract
Future autonomous vehicles need to recognize the ego lanes required for lane change and the side left and right lanes differently. Therefore, multi-lane recognition is needed. In this study, using the YOLO network, mainly used for object recognition, the proposed method recognizes the ego, left and right side lanes as different objects and identifies the correct lanes. As a result of the performance evaluation on the TuSimple test data, the proposed method recognized the ego lanes and the left and right side lanes differently. It showed very stable lane recognition results. And by detecting lanes that do not exist in the ground truth of TuSimple data, the proposed method is very robust in lanes detection. Nevertheless, studies related to learning data reinforcement in which lanes are located in the center or at the left and right edges of the image and accurate network learning for lanes are needed.
참고문헌 (20)
- J. Janai, "Computer Vision for Autonomous Vehicles : Problems, Datasets and State-of-the-Art", Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
- 황광복, "CNN을 이용한 자율주행차 조향 제어", 한국정보통신학회논문지, 24(7), pp.834~841 (2020), 한국정보통신학회[DOI]
- K. V. Wees, "Product liability for ADAS; legal and human factors perspectives", European Journal of Transport and Infrastructure Research, 5(4), pp.357~372 (2020)
- A. Bar Hillel, "Recent progress in road and lane detection : A survey", Mach. Vis. Appl, 25(3), pp.727~745 (2014)
- J. E. Gayko, "Handbook of Intelligent Vehicles", pp.689~708 (2012), Springer
- M. Beyeler, "Vision-based robust road lane detection in urban environments", Proc. IEEE Int. Conf. Robotics and Automation (ICRA), pp.4920~4925 (2014)
- J. Fritsch, "A new performance measure and evaluation benchmark for road detection algorithms", Proc. 16th Int. IEEE Conf. Intelligent Transportation Systems (ITSC 2013), pp.1693~1700 (2013)
- X. Y. Li, "Lane detection and tracking using a parallel-snake approach", Journal of Intelligent Robot and System, 77(3-4), pp.597~609 (2015)
- K. H. Lim, "River flow lane detection and Kalman filtering-based B-spline lane tracking", Int. Journal of Vehicle Technology, 2012, pp.465819~ (2012)
- J. Kim, "Fast learning method for convolutional neural networks using extreme learning machine and its application to lane detection", Neural Networks, 87, pp.109~121 (2017)
- V. Badrinarayanan, "SegNet : A deep convolutional encoder-decoder architecture for image segmentation", IEEE transactions on pattern analysis and machine intelligence, 39(12), pp.2481~2495 (2017)
- W. V. Gansbeke, "End-to-end lane detection through differentiable least- squares fitting", ICCV Workshop (2019)
- A. Gurghian, "DeepLanes: End- to-end lane position estimation using deep neural networks", Proc. IEEE Conf. Computer Vision and Pattern Recognition Workshops (CVPRW), pp.38~45 (2016)
- X. Xiang, "A Fast Learning Method for Accurate and Robust Land Detection Using Two-Stage Feature Extraction with YOLO v3", Sensors, 18(12) (2018)
- 이용환, "객체 검출을 위한 CNN과 YOLO 성능 비교 실험", 반도체디스플레이기술학회지, 19(1), pp.85~92 (2020), 한국반도체디스플레이기술학회
- Redmon Joseph, "YOLO9000 : Better, Faster, Stronger", The IEEE Conference onComputer Vision and Pattern Recognition (CVPR), pp.7263~7271 (2017)
- 박성찬, "다중 차선 인식을 위한 YOLO의 적용", 한국기계기술학회지, 23(6), pp.1137~1145 (2021), 한국기계기술학회[DOI]
- "The tusimple lane challenge"[URL]
- D. Neven, "Towards end-to-end lane detection : an instance segmentation approach", 2018 IEEE intelligent vehicles symposium (IV), pp.286~291 (2018)
- S. Chougule, "Reliable multilane detection and classification by utilizing CNN as a regression network", ECCV Workshop (2018)