基于实例分割的车道线检测及自适应拟合算法

doi:10.11772/j.issn.1001-9081.2019112030

计算机应用 ›› 2020, Vol. 40 ›› Issue (7): 1932-1937.DOI: 10.11772/j.issn.1001-9081.2019112030

基于实例分割的车道线检测及自适应拟合算法

田锦¹, 袁家政², 刘宏哲¹

1. 北京市信息服务工程重点实验室(北京联合大学), 北京 100101;
2. 北京开放大学智能教育研究院, 北京 100081

收稿日期:2019-12-02 修回日期:2020-01-14 出版日期:2020-07-10 发布日期:2020-06-29
通讯作者: 袁家政
作者简介:田锦(1994-),男,山西临汾人,硕士研究生,主要研究方向:深度学习、实例分割;袁家政(1971-),男,湖南湘潭人,教授,博士,主要研究方向:视觉计算、智能驾驶;刘宏哲(1971-),女,河北保定人,教授,博士,主要研究方向:视觉认知计算、人工智能。
基金资助:
国家自然科学基金资助项目（61571045，61871028，61871039，61802019）；北京市自然科学基金资助项目（KZ201951160050）；长城学者支持项目（CIT&TCD20190313）；北京联合大学研究生资助项目。

Instance segmentation based lane line detection and adaptive fitting algorithm

TIAN Jin¹, YUAN Jiazheng², LIU Hongzhe¹

1. Beijing Key Laboratory of Information Service Engineering(Beijing Union University), Beijing 100101, China;
2. Institute of Intelligent Education, Beijing Open University, Beijing 100081, China

Received:2019-12-02 Revised:2020-01-14 Online:2020-07-10 Published:2020-06-29
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61571045, 61871028, 61871039, 61802019), the Natural Science Foundation of Beijing (KZ201951160050), the Great Wall Scholars Program (CIT&TCD20190313), the Beijing Union University Project for Graduate Students.

摘要/Abstract

摘要： 车道线检测是智能驾驶系统的重要组成部分。传统车道线检测方法高度依赖手动选取特征，工作量大，在受到物体遮挡、光照变化和磨损等复杂场景的干扰时精度不高，因此设计一个鲁棒的检测算法面临着很大挑战。为了克服这些缺点，提出了一种基于深度学习实例分割方法的车道线检测模型。该模型基于改进的Mask R-CNN模型，首先利用实例分割模型对道路图像进行分割，提高车道特征信息的检测能力；然后使用聚类模型提取离散的车道线特征信息点；最后提出一种自适应拟合的方法，结合直线和多项式两种拟合方法对不同视野内的特征点进行拟合，生成最优车道线参数方程。实验结果表明，该方法提高了检测速度，在不同场景下都具有较好的检测精度，能够实现对各种复杂实际条件下的车道线信息的鲁棒提取。

关键词: 车道线检测, 智能驾驶, 深度学习, 实例分割, 自适应拟合

Abstract: Lane line detection is an important part of intelligent driving system. The traditional lane line detection method relies heavily on manual selection of features, which requires a large amount of work and has low accuracy when it is interfered by complex scenes such as object occlusion, illumination change and road abrasion. Therefore, designing a robust detection algorithm faces a lot of challenges. In order to overcome these shortcomings, a lane line detection model based on deep learning instance segmentation method was proposed. This model is based on the improved Mask R-CNN model. Firstly, the instance segmentation model was used to segment the lane line image, so as to improve the detection ability of lane line feature information. Then, the cluster model was used to extract the discrete feature information points of lane lines. Finally, an adaptive fitting method was proposed, and two fitting methods, linear and polynomial, were used to fit the feature points in different fields of view, and the optimal lane line parameter equation was generated. The experimental results show that the method improves the detection speed, has better detection accuracy in different scenes, and can achieve robust extraction of lane line information in various complex practical conditions.

Key words: lane line detection, intelligent driving, deep learning, instance segmentation, adaptive fitting

中图分类号:

TP391.4

田锦, 袁家政, 刘宏哲. 基于实例分割的车道线检测及自适应拟合算法[J]. 计算机应用, 2020, 40(7): 1932-1937.

TIAN Jin, YUAN Jiazheng, LIU Hongzhe. Instance segmentation based lane line detection and adaptive fitting algorithm[J]. Journal of Computer Applications, 2020, 40(7): 1932-1937.

参考文献

[1] LECUN Y,BENGIO Y,HINTON G. Deep learning[J]. Nature, 2015,521(7553):436-444.
[2] 张顺, 龚怡宏, 王进军. 深度卷积神经网络的发展及其在计算机视觉领域的应用[J]. 计算机学报,2019,42(3):453-482. (ZHANG S,GONG Y H,WANG J H. The development of deep convolution neural network and its applications on computer vision[J]. Chinese Journal of Computers,2019,42(3):453-482.)
[3] 陈虹, 郭露露, 宫洵, 等. 智能时代的汽车控制[J]. 自动化学报, 2019,45(x):1-20.(CHEN H,GUO L L,GONG X,et al. Automotive control in intelligent era[J]. Acta Automatica Sinica,2019, 45(x):1-20.)
[4] SIMONYAN K,ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL].[2019-04-10]. https://arxiv.org/pdf/1409.1556.pdf.
[5] HE K,ZHANG X,REN S,et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2016:770-778.
[6] LONG J,SHELHAMER E,DARRELL T. Fully convolutional networks for semantic segmentation[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2015:3431-3440.
[7] CHEN L C,PAPANDREOU G,KOKKINOS I,et al. Semantic image segmentation with deep convolutional nets and fully connected CRFs[EB/OL].[2019-05-12]. https://arxiv.org/pdf/1412.7062.pdf.
[8] CHEN L C,PAPANDREOU G,KOKKINOS I,et al. DeepLab:semantic image segmentation with deep convolutional nets,atrous convolution,and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,40(4):834-848.
[9] BADRINARAYANAN V,KENDALL A,CIPOLLA R. SegNet:a deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(12):2481-2495.
[10] 宋小娜, 芮挺, 王新晴. 结合语义边界信息的道路环境语义分割方法[J]. 计算机应用,2019,39(9):2505-2510. (SONG X N,RUI T,WANG X Q. Semantic segmentation method of road environment combined semantic boundary information[J]. Journal of Computer Applications,2019,39(9):2505-2510.)
[11] PASZKE A,CHAURASIA A,KIM S,et al. ENet:a deep neural network architecture for real-time semantic segmentation[EB/OL].[2019-06-07]. https://arxiv.org/pdf/1606.02147.pdf.
[12] 田锦, 张弛, 王永森, 等. 基于Mask R-CNN的地面标识检测[C]//中国计算机用户协会网络应用分会2018年第二十二届网络新技术与应用年会论文集. 北京:[出版者不详], 2018:59-62. (TIAN J,ZHANG C, WANG Y S. Road sign model based on Mask R-CNN[C]//Proceedings of the 22nd Annual Conference on New Network Technologies and Applications 2018,Network Application Branch,China Computer Users Association,China Computer User Association. Beijing:[s. n.],2018:59-62.)
[13] REN S,HE K,GIRSHICK R,et al. Faster R-CNN:towards realtime object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017, 39(6):1137-1149.
[14] REDMON J,FARHADI A. YOLOV3:an incremental improvement[EB/OL].[2019-04-08]. https://arxiv.org/pdf/1804.02767.pdf.
[15] ALSENAN S,YKHLEF M. Statistical machine translation context modelling with recurrent neural network and LDA[C]//Proceedings of the 2016 International Conference on Advanced Intelligent Systems and Informatics,AISC 533. Cham:Springer,2016:75-84.
[16] HERMANTO A,ADJI T B,SETIAWAN N A. Recurrent neural network language model for English-Indonesian machine translation:experimental study[C]//Proceedings of the 2015 International Conference on Science in Information Technology. Piscataway:IEEE,2015:132-136.
[17] HAIDAR M A,KURIMO M. LDA-based context dependent recurrent neural network language model using document-based topic distribution of words[C]//Proceedings of the 2017 IEEE International Conference on Acoustics,Speech and Signal Processing. Piscataway:IEEE,2017:5730-5734.
[18] KIM J,LEE M. Robust lane detection based on convolutional neural network and random sample consensus[C]//Proceedings of the 21st International Conference on Neural Information Processing, LNCS 8834. Cham:Springer,2014:454-461.
[19] HE B,AI R,YAN Y,et al. Accurate and robust lane detection based on dual-view convolutional neutral network[C]//Proceedings of the 2016 IEEE Intelligent Vehicles Symposium. Piscataway:IEEE,2016:1041-1046.
[20] BAILO O,LEE S,RAMEAU F,et al. Robust road marking detection and recognition using density-based grouping and machine learning techniques[C]//Proceedings of the 2017 IEEE Winter Conference on Applications of Computer Vision. Piscataway:IEEE,2017:760-768.
[21] GURGHIAN A,KODURI T,BAILUR S V,et al. DeepLanes:end-to-end lane position estimation using deep neural networks[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Piscataway:IEEE, 2016:38-45.
[22] CHAN T H,JIA K,GAO S,et al. PCANet:a simple deep learning baseline for image classification?[J]. IEEE Transactions on Image Processing,2015,24(12):5017-5032.
[23] LIU H,LI X. Sharp curve lane detection for autonomous driving[J]. Computing in Science and Engineering,2019,21(2):80-95.
[24] BOUMEDIENE M,OUAMRI A,DAHNOUN N. Lane boundary detection and tracking using NNF and HMM approaches[C]//Proceedings of the 2007 IEEE Intelligent Vehicles Symposium. Piscataway:IEEE,2007:1107-1111.
[25] CIMURS R,HWANG J,SUH I H. Bezier curve-based smoothing for path planner with curvature constraint[C]//Proceedings of the 1st IEEE International Conference on Robotic Computing. Piscataway:IEEE,2017:241-248.
[26] HE K,GKIOXARI G,DOLLÁR P,et al. Mask R-CNN[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway:IEEE,2017:2980-2988.

基于实例分割的车道线检测及自适应拟合算法

Instance segmentation based lane line detection and adaptive fitting algorithm

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	谢德峰, 吉建民. 融入句法感知表示进行句法增强的语义解析[J]. 计算机应用, 2021, 41(9): 2489-2495.
[2]	代雨柔, 杨庆, 张凤荔, 周帆. 基于自监督学习的社交网络用户轨迹预测模型[J]. 计算机应用, 2021, 41(9): 2545-2551.
[3]	马佳良, 陈斌, 孙晓飞. 基于改进的Faster R-CNN的通用目标检测框架[J]. 计算机应用, 2021, 41(9): 2712-2719.
[4]	陈成瑞, 孙宁, 何世彪, 廖勇. 面向C-V2X通信的基于深度学习的联合信道估计与均衡算法[J]. 计算机应用, 2021, 41(9): 2687-2693.
[5]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[6]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[7]	郑志强, 胡鑫, 翁智, 王雨禾, 程曦. 基于改进DenseNet的牛眼图像特征提取方法[J]. 计算机应用, 2021, 41(9): 2780-2784.
[8]	何正海, 线岩团, 王蒙, 余正涛. 融合句法指导与字符注意力机制的案情阅读理解方法[J]. 计算机应用, 2021, 41(8): 2427-2431.
[9]	樊玮, 李晨炫, 邢艳, 黄睿, 彭洪健. 航空发动机损伤图像的二分类到多分类递进式检测网络[J]. 计算机应用, 2021, 41(8): 2352-2357.
[10]	曾祥银, 郑伯川, 刘丹. 基于深度卷积神经网络和聚类的左右轨道线检测[J]. 计算机应用, 2021, 41(8): 2324-2329.
[11]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[12]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[13]	高钦泉, 黄炳城, 刘文哲, 童同. 基于改进CenterNet的竹条表面缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1933-1938.
[14]	冯兴杰, 张天泽. 基于分组卷积进行特征融合的全景分割算法[J]. 计算机应用, 2021, 41(7): 2054-2061.
[15]	杜炎, 吕良福, 焦一辰. 基于模糊推理的模糊原型网络[J]. 计算机应用, 2021, 41(7): 1885-1890.