Advertisement

Semantic Line Detection Using Mirror Attention and Comparative Ranking and Matching

Conference paper
  • 575 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12365)

Abstract

A novel algorithm to detect semantic lines is proposed in this paper. We develop three networks: detection network with mirror attention (D-Net) and comparative ranking and matching networks (R-Net and M-Net). D-Net extracts semantic lines by exploiting rich contextual information. To this end, we design the mirror attention module. Then, through pairwise comparisons of extracted semantic lines, we iteratively select the most semantic line and remove redundant ones overlapping with the selected one. For the pairwise comparisons, we develop R-Net and M-Net in the Siamese architecture. Experiments demonstrate that the proposed algorithm outperforms the conventional semantic line detector significantly. Moreover, we apply the proposed algorithm to detect two important kinds of semantic lines successfully: dominant parallel lines and reflection symmetry axes. Our codes are available at https://github.com/dongkwonjin/Semantic-Line-DRM.

Keywords

Semantic lines Line detection Attention Ranking Matching 

Notes

Acknowledgement

This work was supported in part by the Agency for Defense Development (ADD) and Defense Acquisition Program Administration (DAPA) of Korea under grant UC160016FD and in part by the National Research Foundation of Korea (NRF) through the Korea Government (MSIP) under grant NRF-2018R1A2B3003896.

Supplementary material

Supplementary material 1 (mp4 11016 KB)

504476_1_En_8_MOESM2_ESM.pdf (44.8 mb)
Supplementary material 2 (pdf 45906 KB)

References

  1. 1.
  2. 2.
  3. 3.
    Akinlar, C., Topal, C.: EDLines: a real-time line segment detector with a false detection control. Pattern Recogn. Lett. 32(13), 1633–1642 (2011)CrossRefGoogle Scholar
  4. 4.
    Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: Proceedings of ICLR (2015)Google Scholar
  5. 5.
    Chen, S., Zhang, C., Dong, M.: Deep age estimation: from classification to ranking. IEEE Trans. Multimedia 20(8), 2209–2222 (2017)CrossRefGoogle Scholar
  6. 6.
    Chen, S., Zhang, C., Dong, M., Le, J., Rao, M.: Using ranking-CNN for age estimation. In: Proceedings of IEEE CVPR (2017)Google Scholar
  7. 7.
    Chu, R., Sun, Y., Li, Y., Liu, Z., Zhang, C., Wei, Y.: Vehicle re-identification with viewpoint-aware metric learning. In: Proceedings of IEEE ICCV (2019)Google Scholar
  8. 8.
    Cicconet, M., Birodkar, V., Lund, M., Werman, M., Geiger, D.: A convolutional approach to reflection symmetry. Pattern Recogn. Lett. 95, 44–50 (2017)CrossRefGoogle Scholar
  9. 9.
    Cicconet, M., Hildebrand, D.G., Elliott, H.: Finding mirror symmetry via registration and optimal symmetric pairwise assignment of curves: algorithm and results. In: Proceedings of IEEE ICCV Workshops (2017)Google Scholar
  10. 10.
    Corbetta, M., Shulman, G.L.: Control of goal-directed and stimulus-driven attention in the brain. Nat. Rev. Neurosci. 3(3), 201–215 (2002)CrossRefGoogle Scholar
  11. 11.
    Desolneux, A., Moisan, L., Morel, J.M.: Meaningful alignments. Int. J. Comput. Vis. 40(1), 7–23 (2000)CrossRefGoogle Scholar
  12. 12.
    Diaz, R., Marathe, A.: Soft labels for ordinal regression. In: Proceedings of IEEE CVPR (2019)Google Scholar
  13. 13.
    Ding, S., Lin, L., Wang, G., Chao, H.: Deep feature learning with relative distance comparison for person re-identification. Pattern Recogn. 48(10), 2993–3003 (2015)CrossRefGoogle Scholar
  14. 14.
    Elawady, M., Ducottet, C., Alata, O., Barat, C., Colantoni, P.: Wavelet-based reflection symmetry detection via textural and color histograms. In: Proceedings of IEEE ICCV Workshops (2017)Google Scholar
  15. 15.
    Freeman, M.: The Photographer’s Eye: Composition and Design for Better Digital Photos. Focal Press, Waltham (2007)CrossRefGoogle Scholar
  16. 16.
    Funk, C., et al.: 2017 ICCV Challenge: Detecting symmetry in the wild. In: Proceedings of IEEE ICCV (2017)Google Scholar
  17. 17.
    Gao, X., Hoi, S.C., Zhang, Y., Wan, J., Li, J.: SOML: sparse online metric learning with application to image retrieval. In: Proceedings of AAAI (2014)Google Scholar
  18. 18.
    Girshick, R.: Fast R-CNN. In: Proceedings of IEEE ICCV (2015)Google Scholar
  19. 19.
    Guo, C., Yamabe, T., Mita, S.: Robust road boundary estimation for intelligent vehicles in challenging scenarios based on a semantic graph. In: Intelligent Vehicles Symposium. IEEE (2012)Google Scholar
  20. 20.
    Hillel, A.B., Lerner, R., Levi, D., Raz, G.: Recent progress in road and lane detection: a survey. Mach. Vis. Appl. 25(3), 727–745 (2014)CrossRefGoogle Scholar
  21. 21.
    Hoi, S.C., Liu, W., Chang, S.F.: Semi-supervised distance metric learning for collaborative image retrieval and clustering. ACM Trans. Multimed. Comput. Commun. Appl. 6(3), 1–26 (2010)CrossRefGoogle Scholar
  22. 22.
    Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of IEEE CVPR (2018)Google Scholar
  23. 23.
    Huang, K., Wang, Y., Zhou, Z., Ding, T., Gao, S., Ma, Y.: Learning to parse wireframes in images of man-made environments. In: Proceedings of IEEE CVPR (2018)Google Scholar
  24. 24.
    Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Pattern Anal. Mach. Intell. 20(11), 1254–1259 (1998)CrossRefGoogle Scholar
  25. 25.
    Jetley, S., Lord, N.A., Lee, N., Torr, P.H.S.: Learn to pay attention. In: Proceedings of ICLR (2018)Google Scholar
  26. 26.
    Kong, S., Shen, X., Lin, Z., Mech, R., Fowlkes, C.: Photo aesthetics ranking network with attributes and content adaptation. In: Proceedings of ECCV (2016)Google Scholar
  27. 27.
    Koo, H.I., Cho, N.I.: Skew estimation of natural images based on a salient line detector. J. Electron. Imaging 22(1), 013020 (2013)CrossRefGoogle Scholar
  28. 28.
    Lee, J.T., Kim, H.U., Lee, C., Kim, C.S.: Semantic line detection and its applications. In: Proceedings of IEEE ICCV (2017)Google Scholar
  29. 29.
    Lee, J.T., Kim, H.U., Lee, C., Kim, C.S.: Photographic composition classification and dominant geometric element detection for outdoor scenes. J. Vis. Commun. Image Represent. 55, 91–105 (2018)CrossRefGoogle Scholar
  30. 30.
    Lim, K., Shin, N.H., Lee, Y.Y., Kim, C.S.: Order learning and its application to age estimation. In: Proceedings of ICLR (2020)Google Scholar
  31. 31.
    Liu, X., van de Weijer, J., Bagdanov, A.D.: RankIQA: learning from rankings for no-reference image quality assessment. In: Proceedings of IEEE ICCV (2017)Google Scholar
  32. 32.
    Liu, Y., Hel-Or, H., Kaplan, C.S., Van Gool, L.: Computational symmetry in computer vision and computer graphics. Found. Trends Comput. Graph. Vision 5(1–2), 1–195 (2010)zbMATHGoogle Scholar
  33. 33.
    Loy, G., Eklundh, J.O.: Detecting symmetry and symmetric constellations of features. In: Proceedings of ECCV (2006)Google Scholar
  34. 34.
    Matas, J., Galambos, C., Kittler, J.: Robust detection of lines using the progressive probabilistic hough transform. Comput. Vis. Image Understand. 78(1), 119–137 (2000)CrossRefGoogle Scholar
  35. 35.
    Park, J., Woo, S., Lee, J., Kweon, I.S.: BAM: bottleneck attention module. In: Proceedings of BMVC (2018)Google Scholar
  36. 36.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proceedings of ICLR (2015)Google Scholar
  37. 37.
    Singh, K.K., Lee, Y.J.: You reap what you sow: using videos to generate high precision object proposals for weakly-supervised object detection. In: Proceedings of IEEE CVPR (2019)Google Scholar
  38. 38.
    Sohn, K.: Improved deep metric learning with multi-class n-pair loss objective. In: Proceedings of NIPS (2016)Google Scholar
  39. 39.
    Song, O.H., Xiang, Y., Jegelka, S., Savarese, S.: Deep metric learning via lifted structured feature embedding. In: Proceedings IEEE CVPR (2016)Google Scholar
  40. 40.
    Sun, Y., Han, X., Sun, K.: Sem-LSD: A learning-based semantic line segment detector. arXiv preprint arXiv:1909.06591 (2019)
  41. 41.
    Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H., Hospedales, T.M.: Learning to compare: relation network for few-shot learning. In: Proceedings of IEEE CVPR (2018)Google Scholar
  42. 42.
    Tan, Z., Nie, X., Qian, Q., Li, N., Li, H.: Learning to rank proposals for object detection. In: Proceedings of IEEE ICCV (2019)Google Scholar
  43. 43.
    Vaswani, A., et al.: Attention is all you need. In: Proceedings of NIPS (2017)Google Scholar
  44. 44.
    Vinyals, O., Blundell, C., Lillicrap, T., kavukcuoglu, k., Wierstra, D.: Matching networks for one shot learning. In: Proceedings of NIPS (2016)Google Scholar
  45. 45.
    Von Gioi, R.G., Jakubowicz, J., Morel, J.M., Randall, G.: LSD: a fast line segment detector with a false detection control. IEEE Trans. Pattern Anal. Mach. Intell. 32(4), 722–732 (2008)CrossRefGoogle Scholar
  46. 46.
    Wang, F., et al.: Residual attention network for image classification. In: Proceedings of IEEE CVPR (2017)Google Scholar
  47. 47.
    Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Proceedings of ECCV (2018)Google Scholar
  48. 48.
    Workman, S., Zhai, M., Jacobs, N.: Horizon lines in the wild. In: Proceedings of BMVC (2016)Google Scholar
  49. 49.
    Xue, N., Bai, S., Wang, F., Xia, G.S., Wu, T., Zhang, L.: Learning attraction field representation for robust line segment detection. In: Proceedings of IEEE CVPR (2019)Google Scholar
  50. 50.
    Yu, A.W., et al.: QANet: combining local convolution with global self-attention for reading comprehension. In: Proceedings of ICLR (2018)Google Scholar
  51. 51.
    Zambaldi, V., et al.: Deep reinforcement learning with relational inductive biases. In: Proceedings of ICLR (2019)Google Scholar
  52. 52.
    Zhai, M., Workman, S., Jacobs, N.: Detecting vanishing points using global image context in a non-manhattan world. In: Proceedings of IEEE CVPR (2016)Google Scholar
  53. 53.
    Zhao, T., Wu, X.: Pyramid feature attention network for saliency detection. In: Proceedings of IEEE CVPR (2019)Google Scholar
  54. 54.
    Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ADE2020K dataset. In: Proceedings of IEEE CVPR (2017)Google Scholar
  55. 55.
    Zhou, Y., Qi, H., Huang, J., Ma, Y.: NeurVPS: neural vanishing point scanning via conic convolution. In: Proc. NIPS (2019)Google Scholar
  56. 56.
    Zhou, Y., Qi, H., Ma, Y.: End-to-end wireframe parsing. In: Proceedings of IEEE ICCV (2019)Google Scholar
  57. 57.
    Zhou, Z., Farhat, F., Wang, J.Z.: Detecting dominant vanishing points in natural scenes with application to composition-sensitive image retrieval. IEEE Trans. Multimedia 19(12), 2651–2665 (2017)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.School of Electrical EngineeringKorea UniversitySeoulKorea

Personalised recommendations