Advertisement

Spp-U-net: Deep Neural Network for Road Region Segmentation

  • Yang Zhang
  • Dawei Luo
  • Dengfeng YaoEmail author
  • Hongzhe Liu
Conference paper
  • 2 Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1143)

Abstract

In order to better solve the problem about lack of real time in road region segmentation algorithm, this paper designs a deep neural network of road region segmentation Spp-U-net with U-net structure as the core. In addition, the use of spatial pyramid pooling (Spp) to replace the conventional pooling makes up for the lack of accuracy of the Spp-U-net network. The accuracy of Spp-U-net network algorithm is improved compared with U-net model. The model has strong real-time performance on the road segmentation problem under the premise of ensuring accuracy.

Keywords

Road segmentation Spatial pyramid pooling Convolutional neural network 

Notes

Acknowledgements

This work was supported by the National Natural Science Foundation of China (NSFC) under grant no. 61433015: 61602040, the National Social Science Foundation of China under grant no. 14ZDB154, the key project of the National Language Committee (ZDI135-31), the support plan for high level teacher team construction in Beijing municipal universities (IDHT20170511), the Science and Technology project of Beijing Educational Committee (KM201711417006) and Premium Funding Project for Academic Human Resources Development in Beijing Union University (BPHR2019CZ05).

References

  1. 1.
    Xu, X.Z., Ding, S.F., Shi, Z.Z., Jia, W.K.: New theory and method of image segmentation. Chin. Image Graph. J. (08) (2018)Google Scholar
  2. 2.
    Otsu, N.A.: Threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1), 62–66 (2007)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Boykov, Y.Y., Jolly, M.P.: Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images. Computer vision, 2001. In: Proceedings the Eighth IEEE International Conference on ICCV, vol. 1, pp. 105–112 (2001)Google Scholar
  4. 4.
    He, K., Gkioxari, G., Dollar, P., et al.: Mask R-CNN. In: IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 99, p. 1 (2017)Google Scholar
  5. 5.
    Yu, C., Wang, J., Peng, C., et al.: BiSeNet: bilateral segmentation network for real-time semantic segmentation. Eur. Conf. Comput. Vis. 1–17 (2018)Google Scholar
  6. 6.
    Kendall, A., Badrinarayanan, V., Cipolla, R.: Bayesian SegNet: Model uncertainty in deep convolutional encoder-decoder architectures for scene understanding. Preprint at arXiv:1511.02680 (2015)
  7. 7.
    Chen, L.C., Papandreou, G., Kokkinos, I., et al.: Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834–848 (2018)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2021

Authors and Affiliations

  • Yang Zhang
    • 1
  • Dawei Luo
    • 1
  • Dengfeng Yao
    • 1
    • 2
    • 3
    Email author
  • Hongzhe Liu
    • 1
  1. 1.Beijing Key Laboratory of Information Service EngineeringBeijing Union UniversityBeijingChina
  2. 2.Lab of Computational Linguistics, School of HumanitiesTsinghua UniversityBeijingChina
  3. 3.Center for Psychology and Cognitive ScienceTsinghua UniversityBeijingChina

Personalised recommendations