Don’t Hit Me! Glass Detection in Real-world Scenes

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)

View graph of relations

Author(s)

  • Haiyang Mei
  • Xin Yang
  • Yang Wang
  • Yuanyuan Liu
  • Shengfeng He
  • Qiang Zhang
  • Xiaopeng Wei

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationProceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020)
PublisherIEEE
Pages3687-3696
Publication statusPublished - 14 Jun 2020

Conference

Title2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020)
LocationVirtual
Period13 - 19 June 2020

Abstract

Glass is very common in our daily life. Existing computer vision systems neglect it and thus may have severe consequences, e.g., a robot may crash into a glass wall. However, sensing the presence of glass is not straightforward. The key challenge is that arbitrary objects/scenes can appear behind the glass, and the content within the glass region is typically similar to those behind it. In this paper, we propose an important problem of detecting glass from a single RGB image. To address this problem, we construct a large-scale glass detection dataset (GDD) and design a glass detection network, called GDNet, which explores abundant contextual cues for robust glass detection with a novel large-field contextual feature integration (LCFI) module. Extensive experiments demonstrate that the proposed method achieves more superior glass detection results on our GDD test set than state-of-the-art methods fine-tuned for glass detection.

Bibliographic Note

Research Unit(s) information for this publication is provided by the author(s) concerned.

Citation Format(s)

Don’t Hit Me! Glass Detection in Real-world Scenes. / Mei, Haiyang; Yang, Xin; Wang, Yang; Liu, Yuanyuan; He, Shengfeng; Zhang, Qiang; Wei, Xiaopeng; Lau, Rynson W.H.

Proceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020). IEEE, 2020. p. 3687-3696.

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)