Skip to main content
SpringerLink
Log in

Combining BRIEF and AD for Edge-Preserved Dense Stereo Matching

  • Conference paper
  • First Online:
Advanced Machine Learning Technologies and Applications (AMLTA 2021)

Part of the book series: Advances in Intelligent Systems and Computing ((AISC,volume 1339))

Abstract

Overlap between the patches from which descriptors of adjacent pixels are extracted results in edge fattening. Edge fattening can be addressed by adjusting aggregation techniques such as binary aggregation, that are proved successful in intensity-based matching, for use with descriptors. However, binary aggregation through applying masks risks descriptiveness. Therefore, an intensity-based metric such as AD (Absolute Difference) is proposed to supplement the masked binary descriptor such as BRIEF (Binary Robust Independent Elementary Features). The proposed matching cost function adaptively weights the contribution of each metric according to the patch’s content. The proposed hybrid metric reduces the error by up to 2.86% without adding computational complexity by re-using values that are already computed. The latest version of Middlebury stereo dataset and evaluation SDK (Software Development Kit) are used to evaluate the results .

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 229.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 299.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Alahi, A., Ortiz, R., Vandergheynst, P.: FREAK: fast retina keypoint. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, pp. 510–517. IEEE, June 2012

    Google Scholar 

  2. Bay, H., Ess, A., Tuytelaars, T., Van Gool, L.: Speeded-up robust features (SURF). Comput. Vis. Image Underst. 110(3), 346–359 (2008)

    Article  Google Scholar 

  3. Calonder, M., Lepetit, V., Strecha, C., Fua, P.: BRIEF: binary robust independent elementary features. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) Computer Vision - ECCV 2010, pp. 778–792. Springer, Berlin Heidelberg (2010)

    Chapter  Google Scholar 

  4. Liu, C., Yuen, J., Torralba, A.: SIFT flow: dense correspondence across scenes and its applications. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 978–994 (2011)

    Article  Google Scholar 

  5. Chatoux, H., Lecellier, F., Fernandez-Maloigne, C.: Comparative study of descriptors with dense key points, pp. 1988–1993. IEEE (2016)

    Google Scholar 

  6. Kayım, G.: Evaluation of 2D local image descriptors and feature encoding methods for depth image based object class recognition. Master’s thesis, Bogazici University, Istanbul, Turkey (2014)

    Google Scholar 

  7. Hammam, A., Alshazly, M.H., Abdelmgeid, A., Ali, G.W.: An Experimental evaluation of binary feature descriptors. In: Proceedings of the International Conference on Advanced Intelligent Systems and Informatics 2017, vol. 639, pp. 181–191, Cham, Springer International Publishing (2018)

    Google Scholar 

  8. Heikkilä, M., Pietikäinen, M., Schmid, C.: Description of interest regions with local binary patterns. Pattern Recog. 42(3), 425–436 (2009)

    Article  Google Scholar 

  9. Heinly, J., Dunn, E., Frahm, J.M.: Comparative evaluation of binary features. In: Computer Vision–ECCV 2012, pp. 759–773 Springer (2012)

    Google Scholar 

  10. Ibrahim, H.I., Khaled, H., Seada, N.A., Faheem, H.: Parallel dense binary stereo matching using CUDA. In: 2020 15th International Conference on Computer Engineering and Systems (ICCES). IEEE (in-press)

    Google Scholar 

  11. Kai, H., Xiaowen, W., Yunfeng, G.: Adaptive support-weight stereo matching algorithm based on sift descriptors. J. Tianjin Univ. (Sci. Technol.), 15, p. 9 (2016)

    Google Scholar 

  12. Zhang, K., Li, J., Li, Y., Hu, W., Sun, L., Yang, S.: Binary stereo matching. In: 2012 21st International Conference on Pattern Recognition (ICPR), pp. 356–359. IEEE (2012)

    Google Scholar 

  13. Yoon, K.J., Kweon, I.S.: Adaptive support-weight approach for correspondence search. IEEE Trans. Pattern Anal. Mach. Intell. 28(4), 650–656 (2006)

    Article  Google Scholar 

  14. Leutenegger, S., Chli, M., Siegwart, R.Y.: BRISK: binary robust invariant scalable keypoints. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 2548–2555. IEEE (2011)

    Google Scholar 

  15. Levi, G., Hassner, T.: LATCH: learned arrangements of three patch codes. In: 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1–9. IEEE (2016)

    Google Scholar 

  16. Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–101 (2004)

    Article  Google Scholar 

  17. Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Gool, L.V.: A comparison of affine region detectors. Int. J. Comput. Vis. 65(1–2), 43–72 (2005)

    Article  Google Scholar 

  18. Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 27(10), 1615–1630 (2005)

    Article  Google Scholar 

  19. Min, D., Lu, J., Do, M.N.: A revisit to cost aggregation in stereo matching: how far can we reduce its computational redundancy? In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 1567–1574. IEEE (2011)

    Google Scholar 

  20. Ojala, T., Pietikäinen, M., Mäenpää, T.: A generalized local binary pattern operator for multiresolution gray scale and rotation invariant texture classification. In: International Conference on Advances in Pattern Recognition, pp. 399–408. Springer (2001)

    Google Scholar 

  21. Ojala, T., Pietikainen, M., Maenpaa, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. Pattern Anal. Mach. Intell. 24(7), 971–987 (2002)

    Article  Google Scholar 

  22. Peng, X., Bouzerdoum, A., Phung, S.L.: Efficient cost aggregation for feature-vector-based wide-baseline stereo matching. EURASIP J. Image Video Process. 2018(1) (2018)

    Google Scholar 

  23. Rookiepig: rookiepig/binarystereo

    Google Scholar 

  24. Rublee, E., Rabaud, V., Konolige, K., Bradski, G.: ORB: an efficient alternative to SIFT or SURF, pp. 2564–2571. IEEE (2011)

    Google Scholar 

  25. Kim, S., Kang, S.-J.: Young Hwan Kim: Real-time stereo matching using extended binary weighted aggregation. Digit. Sig. Process. 53, 51–61 (2016)

    Article  Google Scholar 

  26. Scharstein, D., Hirschmüller, H., Kitajima, Y., Krathwohl, G., Nešić, N., Wang, X., Westling, P.: High-resolution stereo datasets with subpixel-accurate ground truth. In: German Conference on Pattern Recognition, pp. 31–42. Springer (2014)

    Google Scholar 

  27. Sizintsev, M., Kuthirummal, S., Samarasekera, S., Kumar, R., Sawhney, H.S., Chaudhry, A.: GPU accelerated realtime stereo for augmented reality (2010)

    Google Scholar 

  28. Strecha, C., Bronstein, A., Bronstein, M., Fua, P.: LDAHash: improved matching with smaller descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 34(1), 66–78 (2012)

    Article  Google Scholar 

  29. Tola, E., Lepetit, V., Fua, P.: DAISY: an efficient dense descriptor applied to wide-baseline stereo. IEEE Trans. Pattern Anal. Mach. Intell. 32(5), 815–830 (2010)

    Article  Google Scholar 

  30. Vinay, A., Kumar, C.A., Shenoy, G.R., Murthy, K.N.B., Natarajan, S.: ORB-PCA based feature extraction technique for face recognition. Procedia Comput. Sci. 58, 614–621 (2015)

    Article  Google Scholar 

  31. Mei, X., Sun, X., Zhou, M., Jiao, S., Wang, H., Zhang, X.: On building an accurate stereo matching system on graphics hardware. In: 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), pp. 467–474. IEEE (2011)

    Google Scholar 

  32. Xiao, X., Tian, Z., Xu, C., Li, Z., Wang, X.: Fast stereo matching using adaptive window based disparity refinement. J. Multi. Theory Appl. 2368, 5956 (2016)

    Google Scholar 

  33. Ke, Y., Sukthankar, R.: PCA-SIFT: a more distinctive representation for local image descriptors. In: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004, Washington, DC, USA, vol. 2, pp. 506–513. IEEE (2004)

    Google Scholar 

  34. Yang, Y., Duan, F., Ma, L., Jiang, J.: A robust method for constructing rotational invariant descriptors. Sig. Process. Image Commun. 60, 224–236 (2018)

    Article  Google Scholar 

  35. Yao, Q., Xu, X.: Freak descriptor with spatial pyramid kernel for scene categorization. In: Proceedings of the 2015 International Conference on Mechatronics, Electronic, Industrial and Control Engineering, Shenyang, China, Atlantis Press (2015)

    Google Scholar 

  36. Kim, Y.-H., Koo, J., Lee, S.: Adaptive descriptor-based robust stereo matching under radiometric changes. Pattern Recogn. Lett. 78, 41–47 (2016)

    Article  Google Scholar 

  37. Zabih, R., Woodfill, J.: Non-parametric local transforms for computing visual correspondence. In: European Conference on Computer Vision, pp. 151–158. Springer (1994)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Faculty of Computer and Information Science, Ain Shams University, Cairo, Egypt

    Hanaa I. F. Ibrahim, H. Khaled, Noha A. Seada & H. M. Faheem

Authors
  1. Hanaa I. F. Ibrahim
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. H. Khaled
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Noha A. Seada
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. H. M. Faheem
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to H. M. Faheem .

Editor information

Editors and Affiliations

  1. Information Technology Department, Cairo University, Computer and Information Faculty, Giza, Egypt

    Aboul-Ella Hassanien

  2. College of Information Science and Engineering, Fujian University of Technology, Fuzhou, Fujian, China

    Kuo-Chi Chang

  3. International Center for Informatics Research, Beijing Jaiotong University, Beijing, China

    Tang Mincong

Rights and permissions

Reprints and permissions

Copyright information

© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Ibrahim, H.I.F., Khaled, H., Seada, N.A., Faheem, H.M. (2021). Combining BRIEF and AD for Edge-Preserved Dense Stereo Matching. In: Hassanien, AE., Chang, KC., Mincong, T. (eds) Advanced Machine Learning Technologies and Applications. AMLTA 2021. Advances in Intelligent Systems and Computing, vol 1339. Springer, Cham. https://doi.org/10.1007/978-3-030-69717-4_104

Download citation

Publish with us

Policies and ethics

Search

Navigation