Towards generalizable distance estimation by leveraging graph information

John Kevin Cava, Todd Houghton, Hongbin Yu

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

Abstract

Approximating the distance of objects present in an image remains an important problem for computer vision applications. Current SOTA methods rely on formulating this problem to convenience depth estimation at every pixel; however, there are limitations that make such solutions non-generalizable (i.e varying focal length). To address this issue, we propose reformulating distance approximation to a per-object detection problem and leveraging graph information extracted from the image to potentially achieve better generalizability on data acquired at multiple focal lengths.

Original languageEnglish (US)
Title of host publicationProceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4603-4605
Number of pages3
ISBN (Electronic)9781728150239
DOIs
StatePublished - Oct 2019
Event17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019 - Seoul, Korea, Republic of
Duration: Oct 27 2019Oct 28 2019

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
Period10/27/1910/28/19

Keywords

  • Distance estimation
  • GCN

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Towards generalizable distance estimation by leveraging graph information'. Together they form a unique fingerprint.

  • Cite this

    Cava, J. K., Houghton, T., & Yu, H. (2019). Towards generalizable distance estimation by leveraging graph information. In Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019 (pp. 4603-4605). [9022009] (Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCVW.2019.00565