Autonomous Lane Keeping System: Lane Detection, Tracking and Control on Embedded System

다국어 초록 (Multilingual Abstract)

Autonomous lane keeping system is the key technique to autonomous driving. It includes lane detection, lane tracking and control. It has been developed enormously, but it is still a challenge work due to diff erent factors such as illumination, general hyper-parameters setting for diff erent road condition and lane boundary correction. In addition, due to imbalance on accuracy and processing time, it is hard to conduct in embedding system. In this study, an autonomous lane keeping system is developed based on deep learning. First, a lane detection and tracking system is designed, which is robust to lane boundary correction. Especially for lane detection, a light-weight network named as LaneFCNet is proposed, which can balance accuracy and processing time. Then, lane tracking was followed by detector to improve the detection performance and create autonomous driving trajectory. Finally, to brief lane fi tting problem, it was treated as ridge regression problem, which can enhance the eff ectiveness to the whole system. Experimental results show that our integrated lane detection and tracking system can trade off accuracy and processing time and the whole line keeping system is robust enough to autonomous driving.

참고문헌 (Reference)

1 Khalifa O, "Vision-based lane detection for autonomous artifi cial intelligent vehicles" 636-641, 2009

2 McCall J, "Video-based lane estimation and tracking for driver assistance : survey, system, and evaluation" 7 : 20-37, 2006

3 Simonyan K, "Very deep convolutional networks for large-scale image recognition, arXiv preprint"

4 Lee S, "VPGNet: vanishing point guided network for lane and road marking detection and recognition"

5 Neven D, "Towards end-to-end lane detection: an instance segmentation approach" 770-778, 2018

6 Coedts M, "The cityscapes dataset for semantic urban scene understanding" 3213-3223, 2016

7 Pan X, "Spatial as Deep: Spatial CNN for Traffi c Scene Understanding"

8 Shi W, "Real-time single image and video super-resolution using an effi cient subpixel convolutional neural network" 1874-1883, 2016

9 Aly M, "Real time detection of lane markers in urban streets" 7-12, 2008

10 Liu M, "Online multiple object tracking using confi dence score-based appearance model learning and hierarchical data association" 13 : 312-318, 2019

11 김남훈, "One Shot Extrinsic Calibration of a Camera and Laser Range Finder Using Vertical Planes" 대한전기학회 14 (14): 917-922, 2019

12 Kang C, "Multirate lane-keeping system with kinematic vehicle model" 67 : 9211-9222, 2018

13 Liang A, "LineNet: a zoomable CNN for crowdsourced high defi nition maps modeling in urban environments"

14 Wang J, "Lane detection based on random hough transform on region of interesting" 1735-1740, 2010

15 McCall J, "Lane change intent analysis using robust operators and sparse bayesian learning" 8 : 431-440, 2007

16 Truong Q, "Lane boundaries detection algorithm using vector lane concept" 2319-2325, 2008

17 강창묵, "Kinematics-based Fault-tolerant Techniques: Lane Prediction for an Autonomous Lane Keeping System" 제어·로봇·시스템학회 16 (16): 1293-1302, 2018

18 Sun TY, "HSI color model-based lanemarking detection" 1168-1172, 2006

19 LeCun Y, "Gradientbased learning applied to document recognition" 86 : 2278-2324, 1998

20 Long J, "Fully convolutional networks for semantic segmentation" 3431-3440, 2015

21 Jung S, "Efficient lane detection based on spatiotemporal images" 17 : 289-295, 2016

22 Krähenbühl P, "Effi cient inference in fully connected CRFS with Gaussian edge potentials" 109-117, 2011

23 Paszke A, "ENet: a deep neural network architecture for realtime semantic segmentation"

24 Mohsen G, "EL-GAN:embedding loss driven generative adversarial networks for lane detection"

25 He K, "Deep residual learning for image recognition" 770-778, 2016

26 Li J, "Deep neural network for structural prediction and lane detection in traffic scene" 28 : 690-703, 2018

27 Li X, "Deep neural network for structural prediction and lane detection in traffi c scene" 28 : 690-703, 2016

28 Fabio A, "Autonomous unmanned aerial vehicles in search and rescue missions using real-time cooperative model predictive control" 19 : 4067-4088, 2019

29 Huval B, "An empirical evaluation of deep learning on highway driving, arXiv preprint"

30 Lee JW, "An effective lane detection and tracking method using statistical modeling of color and lane edge-orientation" 1586-1591, 2009

31 Chu Z, "Active disturbance rejection control applied to automated steering for lane keeping in autonomous vehicles" 74 : 13-21, 2018

32 He B, "Accurate and robust lane detection based on dual-view convolutional neutral network" 1041-1046, 2016

33 Angelos A, "A situation-adaptive lane-keeping support system : overview of the SAFELANE approach" 11 : 617-629, 2010

34 Canny J, "A computational approach to edge detection" 8 : 679-698, 1986

35 Nedevschi S, "3D lane detection system based on stereovision" 161-166, 2004