An efficient approach for lane marking detection and classification by the combination of convolution neural network and recurrent neural network is proposed in this paper. First, convolution neural network is trained for lane marking features extraction, and then these convolution neural network features of continuous frames are transferred to recurrent neural network model for lane boundary detection and classification in the time domain. At last, a lane boundary fitting method based on dynamic programming is proposed to improve the lane detection accuracy and robustness. The method presented generates satisfactory results of lane detection and type classification under various traffic conditions according to the experimental results, which show that the approach provided in this paper outperforms traditional methods and the total lane markings classification reached 95.21% accuracy.
AlyM. Real time detection of lane markers in urban streets. In: IEEE intelligent vehicles symposium, Eindhoven, 4–6 June 2008, pp.7–12. New York: IEEE.
2.
GackstatterCHeinemannPThomasSet al. Stable road lane model based on clothoids. In: MeyerGValldorfJ (eds) Advanced microsystems for automotive applications. Berlin: Springer, 2010, pp.133–143.
3.
LooseHFrankeUStillerC. Kalman particle filter for lane recognition on rural roads. In: IEEE intelligent vehicles symposium, Xi’an, China, 3–5 June 2009, pp.60–65. New York: IEEE.
4.
SmudaPSchweigerRNeumannHet al. Multiple cue data fusion with particle filters for road course detection in vision systems. In: IEEE intelligent vehicles symposium, Tokyo, Japan, 13–15 June 2006, pp.400–405. New York: IEEE.
5.
TengZKimJHKangDJ. Real-time lane detection by using multiple cues. In: International conference on control automation and systems (ICCAS), Goyang, South Korea, 27–30 October 2010, pp.2334–2337. New York: IEEE.
6.
ChiuK-YLinS-F. Lane detection using color-based segmentation. In: IEEE intelligent vehicles symposium, Las Vegas, NV, 6–8 June 2005, pp.706–711. New York: IEEE.
7.
LópezASerratJCañeroCet al. Robust lane markings detection and road geometry computation. Int J Automot Techn2010; 11: 395–407.
8.
ZhouSJiangYXiJet al. A novel lane detection based on geometrical model and Gabor Filter. In: IEEE intelligent vehicles symposium (IV), San Diego, CA, 21–24 June 2010, pp.59–64. New York: IEEE.
9.
LiuGWrgtterFMarkeliI. Combining statistical Hough transform and particle filter for robust lane detection and tracking. In: IEEE intelligent vehicles symposium (IV), San Diego, CA, 21–24 June 2010, pp.993–997. New York: IEEE.
10.
DanescuRNedevschiS. Probabilistic lane tracking in difficult road scenarios using stereovision. IEEE T Intell Transp2009; 10: 272–282.
11.
KimZ. Robust lane detection and tracking in challenging scenarios. IEEE T Intell Transp2008; 9: 16–26.
12.
LiuWLiS. An effective lane detection algorithm for structured road in urban. In: YangJFangFSunC (eds) Intelligent science and intelligent data engineering. Berlin: Springer, 2013, pp.759–767.
13.
SunT-YTsaiS-JChanV. HSI color model based lane-marking detection. In: IEEE intelligent transportation systems conference, Toronto, ON, Canada, 17–20 September 2006, pp.1168–1172. New York: IEEE.
14.
RasmussenC. Grouping dominant orientations for ill-structured road following. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, Washington, DC, 27 June–2 July 2004, vol. 1, pp.470–477. New York: IEEE.
15.
LiJMeiXProkhorovDet al. Deep neural network for structural prediction and lane detection in traffic scene. IEEE T Neur Net Lear2016; 28: 690–703.
16.
GopalanRHongTShneierMet al. A learning approach towards detection and tracking of lane markings. IEEE T Intell Transp2012; 13: 1088–1098.
17.
KimJLeeM. Robust lane detection based on convolutional neural network and random sample consensus. In: LooCKYapKSWongKWet al. (eds) Neural information processing. Cham: Springer, 2014, pp.454–461.
18.
HuvalBWangTTandonS. An empirical evaluation of deep learning on highway driving. CoRR, abs/1504.01716, 2015.
19.
KimDUParkSHBanJHet al. Vision-based autonomous detection of lane and pedestrians. In: IEEE international conference on signal and image processing (ICSIP), Beijing, China, 13–15 August 2016, pp.680–683. New York: IEEE.
20.
De PaulaMBJungCR. Automatic detection and classification of road lane markings using onboard vehicular cameras. IEEE T Intell Transp2015; 16: 3160–3169.
21.
TsengTHYangTHChenCP. Verifying the long-range dependency of RNN language models. In: International conference on Asian language processing (IALP), Tainan, Taiwan, 21–23 November 2016, pp.75–78. New York: IEEE.
22.
SrivastavaN. Improving neural networks with dropout. PhD Thesis, University of Toronto, Toronto, ON, Canada, 2013.
23.
KoSGimSPanCet al. Road lane departure warning using optimal path finding of the dynamic programming. In: SICE-ICASE international joint conference, Busan, South Korea, 18–21 October 2006, pp.2919–2923. New York: IEEE.
24.
FischlerMABollesRC. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun ACM1981; 24: 381–395.
