Lane Detection Algorithm Based on Introduction of Improved GAN Network in Night Vision Environment

doi:10.3778/j.issn.1002-8331.2204-0330

Abstract

Abstract: The lane detection methods based on deep learning have effectively promoted the development of automatic driving technology. However, these methods still have some shortcomings in dealing with the problem of lane detection in night vision environment. Aiming at the problems of low illumination and weak detection accuracy in lane detection in night vision environment, this paper combines the attentive mechanism-based generative adversarial network（Attentive GAN） and spatial convolutional neural network（SCNN） algorithm to propose a lane detection method for night vision environment. Firstly, the Attentive GAN network is used to improve the quality of night road images, highlight the lane features in the road images, and then ResNet-18 is used to extract features, and then the SCNN network is used to transfer the image information row by row and column by column, and the cubic spline curve is used to carry out the information transfer. The probability map is fitted to obtain the final lane detection result. This paper uses the simulated TuSimple dataset to verify the detection performance of the proposed method. The experimental results show that the laned etection method in this paper has great performance of lane detection in night vision environment.

Key words: lane detection at night, attentive generative adversarial networks（GAN）, ResNet-18 network, spatial convolutional neural network（SCNN）

摘要： 基于深度学习的车道线检测方法有效地促进了自动驾驶技术的发展，然而这些方法在处理夜视场景下车道线检测问题仍然存在一定的不足。针对夜视场景下车道线检测存在的检测精度弱问题，将基于注意力机制的生成对抗网络（attentive GAN）和空间卷积神经网络（spatial convolutional neural network，SCNN）算法相结合，提出一种针对夜视场景的车道线检测方法。该方法利用Attentive GAN网络提高夜间道路图像质量，突出道路图像中的车道线特征，再利用ResNet-18网络提取车道线特征，随后利用SCNN网络进行图像信息的逐行逐列传递，并利用三次样条曲线进行概率图拟合，得到最终的车道线检测结果。在利用模拟后的TuSimple数据集验证了方法的检测性能，实验结果表明，提出的车道线检测方法在夜视场景下具有良好的车道线检测性能。

关键词: 夜间车道线检测, 注意力机制的生成对抗网络（Attentive GAN）, ResNet-18网络, 空间卷积神经网络（SCNN）

LIU Yan, QIU Tiantian, XIAO Yanqiu, ZHU Fubao, WANG Jingwen. Lane Detection Algorithm Based on Introduction of Improved GAN Network in Night Vision Environment[J]. Computer Engineering and Applications, 2023, 59(15): 214-222.

刘岩, 仇甜甜, 肖艳秋, 朱付保, 王靖雯. 融合改进GAN网络的夜视环境车道线检测[J]. 计算机工程与应用, 2023, 59(15): 214-222.

References

[1] ALY M.Real time detection of lane markers in urban streets[C]//Proceedings of the 2008 IEEE Intelligent Vehicles Symposium，2008：7-12.
[2] BERTOZZI M，BROGGI A.GOLD：a parallel real-time stereo vision system for generic obstacle and lane detection[J].IEEE Transactions on Image Processing，1998，7（1）：62-81.
[3] NIU J，LU J，XU M，et al.Robust lane detection using two-stage feature extraction with curve fitting[J].Pattern Recognition，2016，59：225-233.
[4] BORKAR A，HAYES M，SMITH M T.A novel lane detection system with efficient ground truth generation[J].IEEE Transactions on Intelligent Transportation Systems，2011，13（1）：365-374.
[5] GONZALEZ J P，OZGUNER U.Lane detection using histogram-based segmentation and decision trees[C]//Proceedings of the ITSC2000 2000 IEEE Intelligent Transportation Systems Proceedings（Cat No 00TH8493）.New York，NY：IEEE，2000：346-351.
[6] LEE S，KIM J，SHIN YOON J，et al.Vpgnet：vanishing point guided network for lane and road marking detection and recognition[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：1947-1955.
[7] TABELINI L，BERRIEL R，PAIXAO T M，et al.Polylanenet：lane estimation via deep polynomial regression[C]//Proceedings of the 2020 25th International Conference on Pattern Recognition（ICPR）.New York，NY：IEEE，2021：6150-6156.
[8] LI X，LI J，HU X，et al.Line-CNN：end-to-end traffic line detection with line proposal unit[J].IEEE Transactions on Intelligent Transportation Systems，2019，21（1）：248-258.
[9] MALMIR S，SHALCHIAN M.Design and FPGA implementation of dual-stage lane detection，based on Hough transform and localized stripe features[J].Microprocessors and Microsystems，2019，64：12-22.
[10] MA C，MAO L，ZHANG Y，et al.Lane detection using heuristic search methods based on color clustering[C]//Proceedings of the 2010 International Conference on Communications，Circuits and Systems（ICCCAS）.New York，NY：IEEE，2010：368-372.
[11] SUN T Y，TSAI S J，CHAN V.HSI color model based lane-marking detection[C]//Proceedings of the 2006 IEEE Intelligent Transportation Systems Conference.New York，NY：IEEE，2006：1168-1172.
[12] WANG H，WANG Y，ZHAO X，et al.Lane detection of curving road for structural highway with straight-curve model on vision[J].IEEE Transactions on Vehicular Technology，2019，68（6）：5321-5330.
[13] LI W，QU F，WANG Y，et al.A robust lane detection method based on hyperbolic model[J].Soft Computing，2019，23（19）：9161-9174.
[14] YAN X，LI Y.A method of lane edge detection based on Canny algorithm[C]//Proceedings of the 2017 Chinese Automation Congress（CAC）.New York，NY：IEEE，2017：2120-2124.
[15] WU P C，CHANG C Y，LIN C H.Lane-mark extraction for automobiles under complex conditions[J].Pattern Recognition，2014，47（8）：2756-2767.
[16] 陈政宏，李爱娟，王希波，等.基于改进 Hough 变换的结构化道路车道线识别[J].科学技术与工程，2020，20（26）：10829-10834.
   CHEN Z H，LI A J，WANG X B，et al.Structured road lane line recognition based on improved hough transformation[J].Science Technology and Engineering，2020，20（26）：10829-10834.
[17] NEVEN D，DE BRABANDERE B，GEORGOULIS S，et al.Towards end-to-end lane detection：an instance segmentation approach[C]//Proceedings of the 2018 IEEE Intelligent Vehicles Symposium（IV）.New York，NY：IEEE，2018：286-291.
[18] PAN X，SHI J，LUO P，et al.Spatial as deep：spatial CNN for traffic scene understanding[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2018：7276-7283.
[19] ZOU Q，JIANG H，DAI Q，et al.Robust lane detection from continuous driving scenes using deep neural networks[J].IEEE Transactions on Vehicular Technology，2020，69（1）：41-54.
[20] LI W，QU F，LIU J，et al.A lane detection network based on IBN and attention[J].Multimedia Tools and Applications，2020，79（23）：16473-16486.
[21] WANG Q，HAN T，QIN Z，et al.Multitask attention network for lane detection and fitting[J].IEEE Transactions on Neural Networks and Learning Systems，2020，33（3）：1066-1078.
[22] 邓鑫，陈紫强，郭朦，等.基于光照补偿的夜间车道线检测方法[J].激光杂志，2022，43（2）：71-76.
   DENG X，CHEN Z Q，GUO M，et al.Nighttime lane line detection based on illumination compensation[J].Laser Journal，2022，43（2）：71-76.
[23] 顾德英，王娜，李文超，等.基于模型融合的低照度环境下车道线检测方法[J].东北大学学报（自然科学版），2021，42（3）：305-309.
   GU D Y，WANG N，LI W C，et al.Method of lane line detection in low illumination environment based on model fusion[J].Journal of Northeastern University（Natural Science），2021，42（3）：305-309.
[24] GOODFELLOW I J，POUGET-ABADIE J，MIRZA M，et al.Generative adversarial networks[C]//Advances in Neural Information Processing Systems，2014：2672-2680.
[25] 王照乾，孔韦韦，滕金保，等.DenseNet生成对抗网络低照度图像增强方法[J].计算机工程与应用，2022，58（8）：214-220.
   WANG Z Q，KONG W W，TENG J B，et al.Low illumination image enhancement method based on DenseNet GAN[J].Computer Engineering and Applications，2022，58（8）：214-220.
[26] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.New York，NY：IEEE，2016：770-778.
[27] 兰天翔，向子彧，刘名果，等.融合U-Net及MobileNet-V2的快速语义分割网络[J].计算机工程与应用，2021，57（17）：175-180.
LAN T X，XIANG Z Y，LIU M G，et al.Quick semantic segmentation network based on U-Net and MobileNet-V2[J].Computer Engineering and Applications，2021，57（17）：175-180.
[28] MECHI O，MEHRI M，INGOLD R，et al.Text line segmentation in historical document images using an adaptive U-Net architecture[C]//Proceedings of the 2019 International Conference on Document Analysis and Recognition（ICDAR）.New York，NY：IEEE，2019：369-374.
[29] LIU D，WEN B，LIU X，et al.When image denoising meets high-level vision tasks：a deep learning approach[J].arXiv：1706.04284，2017.
[30] JOLICOEUR-MARTINEAU A.The relativistic discrimin-ator：a key element missing from standard GAN[J].arXiv：1807.00734，2018.
[31] MAO X，LI Q，XIE H，et al.Least squares generative adversarial networks[C]//Proceedings of the IEEE International Conference on Computer Vision.New York，NY：IEEE，2017：2794-2802.
[32] ULYANOV D，VEDALDI A，LEMPITSKY V.Improved texture networks：maximizing quality and diversity in feed-forward stylization and texture synthesis[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.New York，NY：IEEE，2017：6924-6932.
[33] QIN Z，WANG H，LI X.Ultra fast structure-aware deep lane detection[C]//Proceedings of the European Conference on Computer Vision.Cham：Springer，2020：276-291.
[34] LIU L，CHEN X，ZHU S，et al.CondLaneNet：a top-to-down lane detection framework based on conditional convolution[J].arXiv：2105.05003，2021.