基于SegNet的非结构道路可行驶区域语义分割
作者:
中图分类号:

U461

基金项目:

国家自然科学基金青年基金项目(61304189);中央高校基本业务费专项资金重点项目(XDJK2015B028);重庆市工业和信息化重点实验室2019年度开放课题(19AKC8)。


The semantic segmentation of driving regions on unstructured road based on segnet architecture
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [21]
  • |
  • 相似文献 [20]
  • |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    为了增强自动驾驶车辆对非结构化道路中可行驶区域的场景理解能力,基于SegNet深度学习网络结构,提出了一种针对非结构道路的可行驶区域语义分割方法。在传统的卷积神经网络基础上,构建编码解码深度卷积神经网络,用于自动习得图片中非结构化道路的特征,通过在数据集上进行训练和学习,得到图像语义分割模型,可直接用该模型预测非结构道路中的可行驶区域,实现自动驾驶车辆在非结构道路中行驶时的环境感知。实验结果表明,研究方法分割效果和精确度提升明显,Dice相似度和Jaccard相似系数均可达80%以上。

    Abstract:

    To improve the autonomous vehicle's ability to understand the scene of unstructured road driving regions, a semantic segmentation method of unstructured road for autonomous vehicle based on SegNet architecture is proposed. Deep convolutional encoder-decoder architecture is formed by traditional convolutional neural networks, and it can learn the feature map of unstructured roads automatically. By learning and training in the datasets, image semantic segmentation model can be acquired and used to predict the feasible driving area of unstructured roads directly, which is important for autonomous vehicle's scene understanding. The proposed approach outperforms in precision and segmentation consequent, while Dice coefficient reaches more than 80%.

    参考文献
    [1] 王科, 黄智, 钟志华. 基于不定Bezier变形模板的城市道路检测算法[J]. 机械工程学报, 2013, 49(8):143-150.WANG Ke, HUANG Zhi, ZHONG Zhihua. Algorithm for urban road detection based on uncertain bezier deformable template[J]. Journal of Mechanical Engineering, 2013, 49(8):143-150. (in Chinese)
    [2] 曹婷, 王欢. 基于二值空间线特征的道路检测方法[J]. 计算机工程与应用, 2018, 54(6):161-167. CAO Ting, WANG Huan. Road detection based on binary spatial ray feature[J]. Computer Engineering and Applications, 2018, 54(6):161-167. (in Chinese)
    [3] 李晓航, 郭佳, 彭富伦, 等. 一种改进的基于Hough变换的道路图像检测方法[J]. 应用光学, 2016, 37(2):229-234. LI Xiaohang, GUO Jia, PENG Fulun, et al. Improved algorithm of road detection based on Hough transform[J]. Journal of Applied Optics, 2016, 37(2):229-234. (in Chinese)
    [4] 刘富, 袁雨桐, 李洋. 基于纹理特征的非结构化道路分割算法[J]. 计算机应用, 2015, 35(S2):271-273. LIU Fu, YUAN Yutong, LI Yang. Segmentation algorithm of unstructured road based on texture feature[J]. Journal of Computer Applications, 2015, 35(S2):271-273.(in Chinese)
    [5] 吴骅跃,段里仁.基于RGB熵和改进区域生长的非结构化道路识别方法[J].吉林大学学报,2019,3:727-735. WU Huaye, DUAN Liren.Unstructured road detection method based on RGB entropy and improved region growing[J].Journal of Jilin University,2019,3:727-735.
    [6] 熊思, 李磊民, 黄玉清. 基于小波变换和K-means的非结构化道路检测[J]. 计算机工程, 2014, 40(2):158-161.XIONG Si, LI Leimin, HUANG Yuqing. Unstructured road detection based on wavelet transform and K-means[J]. Computer Engineering, 2014, 40(2):158-161.(in Chinese)
    [7] Deng J, Dong W, Socher R, et al. ImageNet:a large-scale hierarchical image database[C/OL]. 2009 IEEE Conference on Computer Vision and Pattern Recognition. New York, USA:IEEE,2009(2009-08-18)[2019-09-25].https://ieeexplore.ieee.org/document/5206848.
    [8] Alex K, Ilya S, Geoffrey E H. Image net classification with deep convolutional neural networks[J]. Neural Information Processing Systems, 2012, 141(5):1097-1105.
    [9] Karen S, Andrew Z. Very deep convolutional networks for large-scale image recognition[J/OL].Computer Science,2014[2019-09-25]. https://www.researchgate.net/publication/265385906_Very_Deep_Convolutional_Networks_for_Large-Scale_Image_Recognition.
    [10] Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions[C/OL]. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). New York, USA:IEEE,2015(2015-10-15)[2019-09-25].https://ieeexplore.ieee.org/document/7298594.
    [11] He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition[C/OL]. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). New York, USA:IEEE, 2016(2016-12-12)[2019-09-25]. https://ieeexplore.ieee.org/document/7780459.
    [12] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation[C/OL]. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). New York, USA:IEEE, 2015(2015-10-15)[2019-09-25]. https://ieeexplore.ieee.org/document/7298965.
    [13] 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.
    [14] Fisher Yu, Vladlen Koltun. Multi-scale context aggregation by dilated convolutions[J/OL]. arXiv:Computer Vision and Pattern Recognition, 2015[2019-09-25]. https://arxiv.org/abs/1511.07122.
    [15] Ravì D, Bober M, Farinella G M, et al. Semantic segmentation of images exploiting DCT based features and random forest[J]. Pattern Recognition, 2016, 52:260-273.
    [16] Ranft B, Stiller C. The role of machine vision for intelligent vehicles[J]. IEEE Transactions on Intelligent Vehicles, 2016, 1(1):8-19.
    [17] Noh H, Hong S, Han B. Learning deconvolution network for semantic segmentation[C/OL]. 2015 IEEE International Conference on Computer Vision (ICCV). New York, USA:IEEE,2015(2015-02-18)[2019-09-25].https://ieeexplore.ieee.org/document/7410535.
    [18] 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.
    [19] Sergey Ioffe, Christian Szegedy. Batch normalization:accelerating deep network training by reducing Internal covariate shift[J/OL]. arXiv:Learning, 2015[2019-09-25]. https://arxiv.org/abs/1502.03167.
    [20] Teichmann M, Weber M, Zöllner M, et al. MultiNet:real-time joint semantic reasoning for autonomous driving[C]//2018 IEEE Intelligent Vehicles Symposium (IV).New York,USA:IEEE,2018:1013-1020.
    [21] Geiger A, Lenz P, Stiller C, et al. Vision meets robotics:The KITTI dataset[J]. International Journal of Robotics Research, 2013, 32(11):1231-1237.
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

张凯航,冀杰,蒋骆,周显林.基于SegNet的非结构道路可行驶区域语义分割[J].重庆大学学报,2020,43(3):79-87.

复制
分享
文章指标
  • 点击次数:1077
  • 下载次数: 1405
  • HTML阅读次数: 1154
  • 引用次数: 0
历史
  • 收稿日期:2019-07-21
  • 在线发布日期: 2020-03-31
文章二维码