复杂场景中的快速车道线检测方法

doi:10.3778/j.issn.1002-8331.2212-0283

摘要/Abstract

摘要： 车道线检测是实现无人驾驶系统的一项重要任务。针对当前基于分割的检测方法实时性能不足的问题，提出了一种快速车道线检测方法FracLane。设计一种高效的特征提取模块，通过分形的思想构造基于聚合不同大小感受野的分形残差结构，更准确地提取车道特征。结合龙格-库塔法，使用可训练参数对分形残差结构的输出进行加权融合，构造能进一步提升网络性能的分形残差模块（FracRes）。在特征解码阶段引入一种基于行锚检测方法的车道位置预测模块（LPP），极大提高网络的检测速度。在包含多种交通场景的车道检测数据集TuSimple和CULane上进行的大量实验，结果表明，该方法在两个数据集上最高可获得97.26%的准确率和78.1的F1评分，在800×288的分辨率下，最高可获得206?FPS的推理速度。与现有检测方法相比，该方法在检测精度与速度方面都有明显提高，达到实时检测任务的需求。

关键词: 车道线检测, 行锚, 分形残差, 龙格-库塔, 卷积神经网络

Abstract: Lane detection is an essential task of unmanned systems. This paper proposes a fast lane detection method FracLane to deal with the problem of the existing segmentation-based lane detection methods with insufficient real-time performance. Firstly, an efficient fractal residual structure based on receptive fields of different sizes is designed, which improves the lane feature extraction capability by introducing the idea of the Fractal. Then, combined with the Runge-Kutta method, the output of the fractal residual structure is weighted and fused using trainable parameters to construct a fractal residual module（FracRes） that can better improve the performance of the network. Finally, a lane position prediction module（LPP） based on row anchor detection is introduced into the decoder to improve the inference speed. A large number of experiments are conducted on TuSimple and CULane that consist of multiple traffic scenarios. Results show that the accuracy and F1-measure of the proposed method are 97.26% and 78.1, respectively, and the inference speed can reach 206?FPS. Compared with the existing methods, the proposed method shows significant improvement, which adequately meets real-time task requirements.

Key words: lane detection, row anchor, fractal residual, Runge-Kutta, convolutional neural network

杜黎, 吕毅斌, 武德安, 罗雨欣. 复杂场景中的快速车道线检测方法[J]. 计算机工程与应用, 2023, 59(13): 178-185.

DU Li, LYU Yibin, WU Dean, LUO Yuxin. Fast Lane Detection Method in Complex Scenarios[J]. Computer Engineering and Applications, 2023, 59(13): 178-185.

参考文献

[1] HILLEL A B，LERNER R，LEVI D，et al.Recent progress in road and lane detection：a survey[J].Machine Vision and Applications，2014，25（3）：727-745.
[2] LIU G L，WORGOTTER F，MARKELIC I.Combining statistical Hough transform and particle filter for robust lane detection and tracking[C]//Proceedings of 2010 IEEE Intelligent Vehicles Symposium，La Jolla，CA，USA，June 21-24，2010：993-997.
[3] 吕侃徽，张大兴.基于改进Hough变换耦合密度空间聚类的车道线检测算法[J].电子测量与仪器学报，2020，34（12）：172-180.
LYU K H，ZHANG D X.Lane detection algorithm based on improved Hough transform coupled density space clustering[J].Journal of Electronic Measurement and Instrument，2020，34（12）：172-180.
[4] 储卫东，王国胤，王进.缩微交通环境下的车道标识线检测[J].计算机科学与探索，2012，6（10）：919-926.
CHU W D，WANG G Y，WANG J.Lane detection in miro-traffic environment[J].Journal of Frontiers of Computer Science and Technology，2012，6（10）：919-926.
[5] TANG J G，LI S B，LIU P.A review of lane detection methods based on deep learning[J].Pattern Recognition，2021，111：107623.
[6] NEVEN D，BRABANDERE B D，GEORGOULIS S，et al.Towards end-to-end lane detection：an instance segmentation approach[C]//Proceedings of 2018 IEEE Intelligent Vehicles Symposium（IV），Changshu，China，June 26-30，2018：286-291.
[7] LEE S，KIM J，SHIN Y 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，Venice，Italy，October 22-29，2017：1947-1955.
[8] PAN X G，SHI J P，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.
[9] HOU Y N，MA Z，LIU C X，et al.Learning lightweight lane detection CNNs by self attention distillation[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，Seoul，Korea，October 27-November 2，2019：1013-1021.
[10] XU H，WANG S J，CAI X Y，et al.CurveLane-NAS：unifying lane?sensitive architecture search and adaptive point blending[C]//Proceedings of the European Conference on Computer Vision，Glasgow，United Kingdom，August 23-28，2020：689-704.
[11] 徐哲钧，张暐，郭昊，等.雾天车道线识别方法：FoggyCULane数据集的创建[J].计算机工程与应用，2022，58（14）：227-235.
XU Z J，ZHANG W，GUO H，et al.Lane detection under foggy conditions via FoggyCULane dataset[J].Computer Engineering and Applications，2022，58（14）：227-235.
[12] TABELINI L，BERRIEL R，PAIXAO T M，et al.PloyLaneNet：lane estimation via deep polynomial regression[C]//Proceedings of the 25th International Conference on Pattern Recognition，Milan，Italy，Jan 10-15，2021：6150-6156.
[13] FENG Z Y，GUO S H，TAN X，et al.Rethinking efficient lane detection via curve modeling[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，New Orleans，Louisiana，June 21-24，2022：17062-17070.
[14] QIN Z Q，WANG H Y，LI X.Ultra fast structure-aware deep lane detection[C]//Proceedings of the European Conference on Computer Vision，Glasgow，United Kingdom，August 23-28，2020：276-291.
[15] LIU L Z，CHEN X H，ZHU S Y，et al.CondLaneNet：a top-to-down lane detection framework based on conditional convolution[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，Virtual，March 10，2021：3773-3782.
[16] BENGIO Y.Learning deep architectures for AI[J].Foundations and Trends in Machine Learning，2009，2（1）：1-127.
[17] HE K M，ZHANG X Y，REN S Q，et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，Las Vegas，NV，USA，June 27-30，2016：770-778.
[18] ZHANG X C，LI Z Z，CHEN C L，et al.PolyNet：a pursuit of structural diversity in very deep networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，Honolulu，HI，USA，July 21-26，2017：3900-3908.
[19] SANDLER M，HOWARD A，ZHU M L，et al.MobileNetV2：inverted residuals and linear bottlenecks[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，Salt Lake City，Utah，June 19-21，2018：4510-4520.
[20] GUSTAV L，MICHAEL M，GREGORY S.FractalNet：ultra-deep neural networks without residuals[J].arXiv：1605.07648，2016.
[21] WEI N E.A proposal on machine learning via dynamical systems[J].Communications in Mathematics and Statistics，2017，1（5）：1-11.
[22] 陈剑涛，黄德天，陈健，等.改进的二阶龙格-库塔超分辨率算法[J].华侨大学学报（自然科学版），2022，43（1）：127-134.
CHEN J T，HUANG D T，CHEN J，et al.Improved second?order Runge?Kutta super?resolution algorithm[J].Journal of Huaqiao University（Natural Science），2022，43（1）：127-134.
[23] LU Y P，ZHONG A X，LI Q Z，et al.Beyond finite layer neural networks：bridging deep architectures and numerical differential equations[J].Proceedings of Machine Learning Research，2018，80：3276-3285.
[24] 杜鹏，李超，石剑平，等.基于阿当姆斯捷径连接的深度神经网络模型压缩方法[J].计算机工程与科学，2021，43（11）：2043-2048.
DU P，LI C，SHI J P，et al.A deep neural network model compression method based on Adams shortcut connection[J].Computer Engineering & Science，2021，43（11）：2043-2048.
[25] WANG Y J，LIN C T.Runge-Kutta neural network for identification of dynamical systems in high accuracy[J].IEEE Transactions on Neural Networks，1998，9（2）：294-307.