컨벌루션 신경망을 사용한 다중 차선 인식
Multi-lanes Detection using Convolutional Neural Network
1
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
In this study, the multi-lane detection problem is expressed as a CNN-based regression problem, and the lane boundary coordinates are selected as outputs. In addition, we described lanes as fifth-order polynomials and distinguished the ego lane and the side lanes so that we could make the prediction lanes accurately. By eliminating the network branch arrangement and the lane boundary coordinate vector outside the image proposed by Chougule’s method, it was possible to eradicate meaningless data learning in CNN and increase the fast training and performance speed. And we confirmed that the average prediction error was small in the performance evaluation even though the proposed method compared with Chougule’s method under harsher conditions. In addition, even in a specific image with many errors, the predicted lanes did not deviate significantly, meaningful results were derived, and we confirmed robust performance.
Abstract
In this study, the multi-lane detection problem is expressed as a CNN-based regression problem, and the lane boundary coordinates are selected as outputs. In addition, we described lanes as fifth-order polynomials and distinguished the ego lane and the side lanes so that we could make the prediction lanes accurately. By eliminating the network branch arrangement and the lane boundary coordinate vector outside the image proposed by Chougule’s method, it was possible to eradicate meaningless data learning in CNN and increase the fast training and performance speed. And we confirmed that the average prediction error was small in the performance evaluation even though the proposed method compared with Chougule’s method under harsher conditions. In addition, even in a specific image with many errors, the predicted lanes did not deviate significantly, meaningful results were derived, and we confirmed robust performance.
참고문헌 (19)
- A. B. Hillel, "Recent Progress in Road and Lane Detection : A Survey", Machine Vision and Applications, 25(3), pp.727~745 (2014)
- 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)
- 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)
- 황광복, "CNN을 이용한 자율주행차 조향 제어", 한국정보통신학회논문지, 24(7), pp.834~841 (2020), 한국정보통신학회[DOI]
- 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
- 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)
- M. Beyeler, "Vision-based robust road lane detection in urban environments", Proc. IEEE Int. Conf. Robotics and Automation (ICRA), pp.4920~4925 (2014)
- 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)
- W. V. Gansbeke, "End-to-end lane detection through differentiable least-squares fitting", ICCV Workshop (2019)
- S. Chougule, "Reliable multilane detection and classification by utilizing CNN as a regression network", ECCV Workshop (2018)
- M. Ghafoorian, "EL-GAN : Embedding loss driven generative adversarial networks for lane detection", ECCV Workshop (2019)
- "The tusimple lane challenge"[URL]
- V. S. Bottazzi, "Robot intelligence technology and applications 2", pp.677~687 (2014), Springer
- R. K. Satzoda, "Efficient lane and vehicle detection with integrated synergies(ELVIS)", 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp.708~713 (2014)
- A. Gurghian, "DeepLanes : End-To-End Lane Position Estimation using Deep Neural Networks", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp.38~45 (2016)
- 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)
- D. Neven, "Towards end-to-end lane detection : an instance segmentation approach", 2018 IEEE intelligent vehicles symposium (IV), pp.286~291 (2018)
- X. Zhang, "Shufflenet : An extremely efficient convolutional neural network for mobile devices", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.6848~6856 (2018)