Skip to main content
SpringerLink
Log in

Improved best match search method in depth recovery with descent images

  • Original Paper
  • Published:
Machine Vision and Applications Aims and scope Submit manuscript

Abstract

Searching for the best match is a key step in stereovision or 3D reconstruction with images. In our previous study, we recovered every pixel’s depth in the lower image by searching for the highest correlation in its dimensional ZNCC correlation curve in the cubic correlation matrix as the best match, but sparse reconstruction errors such as holes or spikes existed in the result. After careful analysis we found that not all the highest-correlational positions are corresponding to their correct match due to noise or similarity. Therefore, a new best match search method based on best seed propagation first strategy is proposed by considering neighborhood disparity constraints. At first, some pixels are chosen as initial seeds and inserted into a seed queue by assessing their correlation curves. Their depths are determined by the layers in the cubic correlation matrix in which they get their highest correlation value. Second, the front seed is taken out of the queue and its neighbor points are propagated as new seeds under the propagation rules. The new propagated seeds will also be inserted into the seed queue, and their depth are accordingly decided. This operation is repeated till the seed queue is null. At last, there will be some points which are never propagated as seeds according to the propagation rules. Their depths are determined by their neighbor points depth information through post processing. The comparison experiments show that the new method can improve the accuracy of the matches and reduce the reconstruction error effectively.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16

Similar content being viewed by others

References

  1. Zhang, R., Tsai, P.-S., Cryer, J.E., Shah, M.: Shape-from-shading: a survey. Patt. Anal. Mach. Intell. IEEE Trans. 21(8), 690–706 (1999)

    Article  Google Scholar 

  2. Seitz, S.M., Curless, B., Diebel, J., Scharstein, D., Szeliski, R.: A comparison and evaluation of multi-view stereo reconstruction algorithms. In: Computer vision and pattern recognition, 2006 IEEE Computer Society Conference on, vol. 1, pp 519–528. IEEE (2006)

  3. Jin, H., Soatto, S., Yezzi, A.J.: Multi-view stereo reconstruction of dense shape and complex appearance. Int. J. Comput. Vision 63(3), 175–189 (2005)

    Article  Google Scholar 

  4. Gingras, D., Lamarche, T., Bedwani, J.-L., Dupuis, É.: Rough terrain reconstruction for rover motion planning. In: Computer and Robot Vision (CRV), 2010 Canadian Conference on, pp 191–198. IEEE (2010)

  5. Xiong, Y., Olson, C.F., Matthies, L.H.: Computing depth maps from descent images. Mach. Vision Appl. 16(3), 139–147 (2005)

    Article  Google Scholar 

  6. Broxton, M.J., Nefian, A.V., Moratto, Z., Kim, T., Lundy, M., Segal, A.V.: 3d lunar terrain reconstruction from apollo images. In: Advances in Visual Computing, pp 710–719. Springer (2009)

  7. Ens, J. Lawrence, P.: An investigation of methods for determining depth from focus. In: IEEE Transactions on pattern analysis and machine intelligence, pp 97–108 (1993)

  8. Chaudhuri, S., Rajagopalan, A.: Depth from defocus: a real aperture imaging approach. Springer, New York (1999)

    Book  Google Scholar 

  9. Collins, R.T.: A space-sweep approach to true multi-image matching. In: Computer Vision and Pattern Recognition. Proceedings CVPR’96, 1996 IEEE Computer Society Conference on, pp 358–363. IEEE (1996)

  10. Soatto, S., Perona, P.: Reducing “structure from motion”: a general framework for dynamic vision. 1. modeling, pattern analysis and machine intelligence. IEEE Trans. 20(9), 933–942 (1998)

    Google Scholar 

  11. Faugeras, O., Robert, L., Laveau, S., Csurka, G., Zeller, C., Gauclin, C., Zoghlami, I.: 3-d reconstruction of urban scenes from image sequences. Comput. Vision Image Underst. 69(3), 292–309 (1998)

    Article  Google Scholar 

  12. Sturm, P., Triggs, B.: A factorization based algorithm for multi-image projective structure and motion. In: Computer Vision-ECCV’96, pp 709–720. Springer (1996)

  13. Li, R., Ma, F., Xu, F., Matthies, L., Olson, C., Xiong, Y.: Mars rover localization using descent and rover imagery-result of the field test at silver lake, ca. In: ASPRS Annual Conference, pp 22–26 (2000)

  14. Ma, F., Di, K., Li, R., Matthies, L., Olson, C.: Incremental mars rover localization using descent and rover imagery. In: ASPRS Annual Conference, pp 25–27 (2001)

  15. Meng, C., Zhou, N., Xue, X., Jia, Y.: Homography-based depth recovery with descent images. Mach. Vision Appl. 24, 1093–1106 (2013)

    Article  Google Scholar 

  16. Pei, M., Jia, Y.: 3d reconstruction under camera motion along optic axis. J. Comput. Aided Design Comput. Graphics 17(3), 534–539 (2005)

    Google Scholar 

  17. Zhang, D., Wang, Y., Tian, J., Wang, C., Guo, Q.: Efficient 3d reconstruction using monocular vision. J. Astronaut. 29(1), 289–294 (2008)

    Google Scholar 

  18. Yang, Q., Wang, L., Ahuja, N.: A constant-space belief propagation algorithm for stereo matching. In: Computer vision and pattern recognition (CVPR), 2010 IEEE Conference on, pp 1458–1465. IEEE (2010)

  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: Computer Vision (ICCV), 2011 IEEE International Conference on, pp 1567–1574. IEEE (2011)

  20. De-Maeztu, L., Mattoccia, S., Villanueva, A., Cabeza, R.: Linear stereo matching. In: Computer Vision (ICCV), 2011 IEEE International Conference on, pp 1708–1715. IEEE (2011)

  21. Min, D., Lu, J., Do, M.: Joint histogram based cost aggregation for stereo matching. Patt. Anal. Mach. Intell. IEEE Trans. 35(10), 2539–2545 (2013)

    Article  Google Scholar 

  22. Lhuillier, M., Quan, L.: Match propagation for image-based modeling and rendering. Patt. Anal. Mach. Intell. IEEE Trans. 24(8), 1140–1146 (2002)

    Article  Google Scholar 

  23. Lhuillier, M., Quan, L.: A quasi-dense approach to surface reconstruction from uncalibrated images. Patt. Anal. Mach. Intell. IEEE Trans. 27(3), 418–433 (2005)

    Article  Google Scholar 

  24. http://vision.middlebury.edu/stereo/data/

  25. Dufournaud, Y., Schmid, C., Horaud, R.: Matching images with different resolutions. In: Computer vision and pattern recognition. Proceedings. IEEE Conference on, vol. 1, pp 612–618. IEEE (2000)

  26. Fang, K.: Bicubic b-spline interpolation surface. Chin. Math. Theory Appl. 21(3), 66–68 (2001)

    Google Scholar 

  27. Zhang, Z.: A flexible new technique for camera calibration. Patt. Anal. Machine Intell. IEEE Trans. 22(11), 1330–1334 (2000)

    Article  Google Scholar 

Download references

Acknowledgments

This research was supported by the National Key Technology Program under contact of 2013BAF07B02, the Fundamental Research Funds for the Central Universities under contact no. YWF-14-YHXY-005, no. YWF-14-YHXY-015, the National Natural Science Foundation of China under contact no. 61233005, and China Academy of Space Technology. And thanks Ph.D. Wu Fuxiang to help to provide the synthetic descent images in 3D computer graphics software.

Author information

Authors and Affiliations

  1. Image Processing Center, School of Astronautics, Beihang University, Beijing, 100191, China

    Cai Meng & Na Zhou

  2. China Academy of Space Technology, Beijing, 100094, China

    Yang Jia

Authors
  1. Cai Meng
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Na Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yang Jia
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Cai Meng.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Meng, C., Zhou, N. & Jia, Y. Improved best match search method in depth recovery with descent images. Machine Vision and Applications 26, 251–266 (2015). https://doi.org/10.1007/s00138-015-0666-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00138-015-0666-1

Keywords

Search

Navigation