Reverse and boundary attention network for road segmentation

Jee Young Sun, Seung Wook Kim, Sang Won Lee, Ye Won Kim, Sung Jea Ko

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Road segmentation is an essential task to perceive the driving environment in autonomous driving and advanced driver assistance systems. With the development of deep learning, road segmentation has achieved great progress in recent years. However, there still remain some problems including the inaccurate road boundary and the illumination variations such as shadows and over-exposure regions. To solve these problems, we propose a residual learning-based network architecture with residual refinement module composed of the reverse attention and boundary attention units for road segmentation. The network first predicts a coarse road region from deeper-level feature maps and gradually refines the prediction by learning the residual in a top-down approach. The reverse and boundary attention units in residual refinement module guide the network to focus on the features in the previously missing region and the region near the road boundary. In addition, we introduce the boundary-aware weighted loss to reduce the false prediction. Experimental results demonstrate that the proposed approach outperforms the state-of-the-art methods in terms of the segmentation accuracy in various benchmark datasets for traffic scene understanding.

Original languageEnglish
Title of host publicationProceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages876-885
Number of pages10
ISBN (Electronic)9781728150239
DOIs
Publication statusPublished - 2019 Oct
Event17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019 - Seoul, Korea, Republic of
Duration: 2019 Oct 272019 Oct 28

Publication series

NameProceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019

Conference

Conference17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019
CountryKorea, Republic of
CitySeoul
Period19/10/2719/10/28

Keywords

  • Boundary attention
  • Boundary aware loss
  • Residual learning
  • Reverse attention
  • Road segmentation
  • Traffic scene understanding

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

Sun, J. Y., Kim, S. W., Lee, S. W., Kim, Y. W., & Ko, S. J. (2019). Reverse and boundary attention network for road segmentation. In Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019 (pp. 876-885). [9022120] (Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCVW.2019.00116