Advertisement

Semantic Segmentation of Street Scenes Using Disparity Information

  • Hanwen Hu
  • Xu ZhaoEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11901)

Abstract

In this work, we address the task of semantic segmentation in street scenes. Recent approaches based on convolutional neural networks have shown excellent results on several semantic segmentation benchmarks. Most of them, however, only exploit RGB information. Due to the development of stereo matching algorithms, disparity maps can be more easily acquired. Structural information encoded in disparity can be treated as supplementary information of RGB images, which is expected to boost performance. Therefore, in this work we propose to fuse disparity information in street scene understanding task. And we design four methods to incorporate disparity information into semantic segmentation framework. They are summation, multiplication, concatenation and channel concatenation. Besides, disparity map can be utilized as ground truth of a regression task, guiding the learning of semantic segmentation as a loss term. Comprehensive experiments on KITTI and Cityscapes datasets show that each method can achieve performance improvement. The experimental results validate the effectiveness of disparity information to street scene semantic segmentation tasks.

Keywords

Semantic segmentation Disparity 

Notes

Acknowledgments

This work is supported by: National Natural Science Foundation of China (U1764264, 61673269, 61273285).

References

  1. 1.
    Abadi, M., et al.: Tensorflow: a system for large-scale machine learning. In: OSDI 2016, pp. 265–283 (2016)Google Scholar
  2. 2.
    Alhaija, H.A., Mustikovela, S.K., Mescheder, L., Geiger, A., Rother, C.: Augmented reality meets deep learning for car instance segmentation in urban scenes. In: British Machine Vision Conference, vol. 1, p. 2 (2017)Google Scholar
  3. 3.
    Chang, J.R., Chen, Y.S.: Pyramid stereo matching network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5410–5418 (2018)Google Scholar
  4. 4.
    Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.: Semantic image segmentation with deep convolutional nets and fully connected CRFs. In: ICLR, San Diego, United States, May 2015. https://hal.inria.fr/hal-01263610
  5. 5.
    Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: 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
  6. 6.
    Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)
  7. 7.
    Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. arXiv preprint arXiv:1802.02611 (2018)
  8. 8.
    Chollet, F.: Xception: deep learning with depthwise separable convolutions. arXiv preprint arXiv:1610.02357 (2017)
  9. 9.
    Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR, pp. 3213–3223 (2016)Google Scholar
  10. 10.
    Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 248–255. IEEE (2009)Google Scholar
  11. 11.
    Eigen, D., Fergus, R.: Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2650–2658 (2015)Google Scholar
  12. 12.
    Gupta, S., Girshick, R., Arbeláez, P., Malik, J.: Learning rich features from RGB-D images for object detection and segmentation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 345–360. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-10584-0_23CrossRefGoogle Scholar
  13. 13.
    Hazirbas, C., Ma, L., Domokos, C., Cremers, D.: FuseNet: incorporating depth into semantic segmentation via fusion-based CNN architecture. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10111, pp. 213–228. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-54181-5_14CrossRefGoogle Scholar
  14. 14.
    Krähenbühl, P., Koltun, V.: Efficient inference in fully connected CRFs with Gaussian edge potentials. In: Advances in Neural Information Processing Systems, pp. 109–117 (2011)Google Scholar
  15. 15.
    Lin, G., Milan, A., Shen, C., Reid, I.: Refinenet: multi-path refinement networks for high-resolution semantic segmentation. In: CVPR (2017)Google Scholar
  16. 16.
    Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)Google Scholar
  17. 17.
    Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. In: ICCV, pp. 1520–1528 (2015)Google Scholar
  18. 18.
    Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-24574-4_28CrossRefGoogle Scholar
  19. 19.
    Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018)Google Scholar
  20. 20.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
  21. 21.
    Wang, J., Wang, Z., Tao, D., See, S., Wang, G.: Learning common and specific features for RGB-D semantic segmentation with deconvolutional networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 664–679. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46454-1_40CrossRefGoogle Scholar
  22. 22.
    Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)
  23. 23.
    Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2881–2890 (2017)Google Scholar
  24. 24.
    Zheng, S., et al.: Conditional random fields as recurrent neural networks. In: ICCV, pp. 1529–1537 (2015)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of AutomationShanghai Jiao Tong UniversityShanghaiChina

Personalised recommendations