CoChat

Deep Hough Transform for Semantic Line Detection

Open access
Zhao, Kai, Han, Qi, Zhang, Chang-Bin, Xu, Jun, Cheng, Ming-Ming · 2021 · IEEE Transactions on Pattern Analysis and Machine Intelligence
Cited by 187

The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.

Abstract

We focus on a fundamental task of detecting meaningful line structures, a.k.a., semantic line, in natural scenes. Many previous methods regard this problem as a special case of object detection and adjust existing object detectors for semantic line detection. However, these methods neglect the inherent characteristics of lines, leading to sub-optimal performance. Lines enjoy much simpler geometric property than complex objects and thus can be compactly parameterized by a few arguments. To better exploit the property of lines, in this paper, we incorporate the classical Hough transform technique into deeply learned representations and propose a one-shot end-to-end learning framework for line detection. By parameterizing lines with slopes and biases, we perform Hough transform to translate deep representations into the parametric domain, in which we perform line detection. Specifically, we aggregate features along candidate lines on the feature map plane and then assign the aggregated features to corresponding locations in the parametric domain. Consequently, the problem of detecting semantic lines in the spatial domain is transformed into spotting individual points in the parametric domain, making the post-processing steps, i.e., non-maximal suppression, more efficient. Furthermore, our method makes it easy to extract contextual line features that are critical for accurate line detection. In addition to the proposed method, we design an evaluation metric to assess the quality of line detection and construct a large scale dataset for the line detection task. Experimental results on our proposed dataset and another public dataset demonstrate the advantages of our method over previous state-of-the-art alternatives. The dataset and source code is available at https://mmcheng.net/dhtline/.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tpami.2021.3077129

Cites

14 of 14 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 65

  1. 10.1007/978-3-030-58545-7_15 · DOI
  2. 10.1109/TPAMI.1986.4767808 · doi:10.1109/tpami.1986.4767808
  3. 10.1109/ICCV.2019.00894 · DOI
  4. 10.1109/TPAMI.2018.2815688 · DOI · Paper page
  5. 10.1007/978-3-030-58539-6_42 · DOI · Paper page
  6. 10.1007/s41095-019-0149-9 · DOI · Paper page
  7. 10.1109/TPAMI.2019.2924417 · DOI · Paper page
  8. 10.1109/TPAMI.2014.2345401 · DOI · Paper page
  9. 10.1109/CVPR.2014.360 · DOI · Paper page
  10. 10.1007/s41095-020-0173-9 · DOI
  11. 10.1109/ICCV.2017.350 · DOI
  12. 10.1111/j.1467-8659.2009.01616.x · DOI · Paper page
  13. 10.4324/9780080556161 · DOI
  14. 10.1109/TIP.2019.2936746 · DOI
  15. 10.1145/2508363.2508381 · DOI
  16. 10.1109/ICIP.2018.8451621 · DOI
  17. 10.1109/ACCESS.2019.2936289 · DOI
  18. 10.1007/978-3-319-46448-0_40 · DOI · Paper page
  19. 10.1109/CVPR.2016.60 · DOI · Paper page
  20. 10.1007/s41095-019-0160-1 · DOI
  21. Krages, 2012, Photography: The Art of Composition
  22. 10.1145/2508363.2508371 · DOI
  23. 10.1145/1661412.1618470 · DOI
  24. 10.1007/s41095-020-0158-8 · DOI
  25. 10.1016/0031-3203(81)90009-1 · DOI · Paper page
  26. 10.1016/j.patcog.2007.04.003 · DOI · Paper page
  27. 10.1049/ip-vis:19951434 · doi:10.1049/ip-vis:19951434
  28. 10.1016/0734-189X(90)90123-D · DOI
  29. 10.1016/0031-3203(91)90073-E · DOI · Paper page
  30. 10.1016/j.patrec.2011.06.001 · DOI · Paper page
  31. Caplin, 2008, Art and Design in Photoshop
  32. 10.1109/CVPR.2019.00727 · DOI
  33. 10.1109/ICCV.2015.169 · DOI · Paper page
  34. 10.1109/TPAMI.2018.2878849 · DOI · Paper page
  35. 10.1109/ICCV.2015.164 · DOI · Paper page
  36. Radon, 2005, über die bestimmung von funktionen durch ihre integralwerte längs gewisser mannigfaltigkeiten,, 69, 262
  37. Sobel, 1973, A 3x3 Isotropic Gradient Operator for Image Processing,, Pattern Classification Scene Anal., 271
  38. 10.1109/CVPR42600.2020.00012 · DOI · Paper page
  39. 10.1109/CVPR42600.2020.00011 · DOI · Paper page
  40. 10.1109/TC.1976.1674627 · DOI
  41. 10.1016/j.patcog.2014.12.020 · DOI
  42. 10.1109/TPAMI.1987.4767964 · DOI · Paper page
  43. 10.1109/TIP.2005.863021 · DOI · Paper page
  44. 10.1109/ICCV.2019.00937 · DOI · Paper page
  45. 10.1109/ICCV.2019.00349 · DOI
  46. Etemadi, Robust segmentation of edge data,, 311
  47. 10.1109/ICPR.1996.546737 · doi:10.1109/icpr.1996.546737
  48. 10.1109/TPAMI.2008.300 · DOI · Paper page
  49. 10.1016/j.patcog.2012.09.020 · DOI · Paper page
  50. 10.1109/TIM.2013.2283741 · DOI · Paper page
  51. 10.1109/IJCNN.2017.7966418 · DOI
  52. 10.1109/CVPR.2018.00072 · DOI · Paper page
  53. 10.1109/ICCV.2019.00105 · DOI · Paper page
  54. 10.1109/CVPR42600.2020.00286 · DOI
  55. 10.1109/CVPR.2019.00524 · DOI · Paper page
  56. 10.1109/ICCV.2019.00625 · DOI
  57. 10.1109/CVPR42600.2020.00893 · DOI
  58. Rubner, 2000, The earth mover’s distance as a metric for image retrieval,, Int. J. Comput. Vis., 40, 99, 10.1023/A:1026543900054 · DOI · Paper page
  59. 10.1016/S0734-189X(86)80047-0 · DOI · Paper page
  60. 10.1109/TPAMI.2017.2723009 · DOI · Paper page
  61. 10.5555/3454287.3455008 · doi:10.5555/3454287.3455008
  62. 10.1007/s11432-020-3097-4 · DOI
  63. Simonyan, Very deep convolutional networks for large-scale image recognition,
  64. 10.1109/CVPR.2017.660 · DOI · Paper page
  65. 10.1109/TPAMI.2019.2938758 · DOI · Paper page

Cited by

See all 187

Metadata

Authors
Zhao, K., Han, Q., Zhang, C.-B., Xu, J., & Cheng, M.-M.
Venue
IEEE Transactions on Pattern Analysis and Machine Intelligence
Published
2021
Volume
44
Issue
9
Pages
1-1
ISSN
  • 0162-8828 (ISSN-L)
  • 2160-9292
  • 1939-3539
OpenAlex
W3011098590
Cited by
187
References
14
FWCI
11.73
Type
journal article
Language
en
Open access
green
Funders
  • National Key Research and Development Program of China (2018AAA0100400)
  • Natural Science Foundation of Tianjin City (17JCJQJC43700)
  • National Natural Science Foundation of China (61620106008, 61922046, 62002176)
  • ST innovation project from Chinese Ministry of Education

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.