Using Sparse-Point Disparity Estimation and Spatial Propagation to Construct Dense Disparity Map for Stereo Endoscopic Images

  • Wen-Nung Lie
  • Hsi-Hung Huang
  • Shih-Wei Huang
  • Kai-Che Liu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10749)

Abstract

Disparity estimation for stereo endoscopic images is difficult due to their lack of distinct textures for matching. Many well-known algorithms fail in this kind of application to estimate a reliable dense disparity map. In this paper, we propose a strategy of using a sparse feature point set to estimate reliable disparity values, which are then propagated to other non-feature points to form the final dense disparity map. Our selected feature points include: SIFT, Canny-edge, Canny-edge-dilated, and grid points. The algorithms for disparity propagation are based on bilateral interpolation and refinement. Experiments show that our algorithm is successful in shaping the instruments in disparity map. This is helpful in 3D display for human perception. Disparity estimation for endoscopic images is still an open issue. Our preliminary result still presents some space for improvement.

Keywords

Minimally invasive surgery Stereo matching Sparse Depth propagation 

References

  1. 1.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell. 23(11), 1222–1239, November 2001Google Scholar
  2. 2.
    Kolmogorov, V., Zabih, R.: Computing visual correspondence with occlusions via graph cuts. In: Proceedings of International Conference on Computer Vision, vol. II, pp. 508–515 (2001)Google Scholar
  3. 3.
    Hong, L., Chen, G.: Segment-based stereo matching using graph cuts. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, vol. I, pp. 74–81 (2004)Google Scholar
  4. 4.
    Sun, J., Zheng, N.-N., Shum, H.-Y.: Stereo matching using belief propagation. IEEE Trans. Pattern Anal. Mach. Intell. 25(7), 787–800, July 2003Google Scholar
  5. 5.
    Yang, Q., Wang, L., Yang, R., Stewenius, H., Nister, D.: Stereo matching with color-weighted correlation, hierarchical belief propagation and occlusion handling. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, June 2006Google Scholar
  6. 6.
    Klaus, A., Sormann, M., Karner, K.: Segment-based stereo matching using belief propagation and a self-adapting dissimilarity measure. In: Proceedings of International Conference on Pattern Recognition (2006)Google Scholar
  7. 7.
    Veksler, O.: Fast variable window for stereo correspondence using integral images. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1, pp. 556–561 (2003)Google Scholar
  8. 8.
    Yuan, D., Cheng, F., Zhang, H.: Dense stereo matching based on edge constraint and variable windows. In: Proceedings of IEEE International Conference on Robotics and Biomimetics, pp. 1912–1917 (2011)Google Scholar
  9. 9.
    Qiu, M., Zhang, Y.: Feature guided multi-window area-based matching method for urban remote sensing stereo pairs. In: Proceedings of IEEE International Conference on Geoscience and Remote Sensing Symposium (IGARSS), pp. 1912–1917 (2011)Google Scholar
  10. 10.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 2(60), 91–110 (2004)CrossRefGoogle Scholar
  11. 11.
    Yan, X., Yang, Y., Er, G., Dai, Q.: Depth map generation for 2D-to-3D conversion by limited user inputs and depth propagation. In: Proceedings of IEEE International Conference the True Vision-Capture, Transmission and Display of 3D Video (3DTV-CON), pp. 1–4, May 2011Google Scholar
  12. 12.
    Rother, C., Blake, A., Kolmogorov, V.: Grabcut – interactive foreground extraction using iterated graph cuts. ACM Trans. Graph. 23(3), 309–314 (2004)Google Scholar
  13. 13.
    Spangenberg, R., Langner, T., Adfeldt, S., Rojas, R.: Large scale semi-global matching on the CPU. In: Proceedings of the IEEE Intelligent Vehicles Symposium Proceedings, pp. 195–201, June 2014Google Scholar
  14. 14.
    Yang, Q., Wang, L., Yang, R., Stewenius, H., Nister, D.: Stereo matching with color-weighted correlation, hierarchical belief propagation, and occlusion handling. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 31(3), 492–504 (2009)Google Scholar
  15. 15.
    Yoon, K., Kweon, I.: Adaptive support-weight approach for correspondence search. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 28, 650–656 (2006)Google Scholar
  16. 16.
    Boughorbel, F.: A new multiple-windows depth from stereo algorithm for 3D displays. In: Proceedings of IEEE International Conference on Capture, Transmission and Display of 3D Video (3DTV-CON), Kos Island, pp. 1–4, May 2007Google Scholar
  17. 17.
    Gerrits, M., Bekaert, P.: Local stereo matching with segmentation-based outlier rejection. In: Proceedings of IEEE International Conference on Computer and Robot Vision (CRV), New York, USA, p. 66, June 2006Google Scholar
  18. 18.
    Zhang, K., Lu, J., Lafruit, G.: Scalable stereo matching with locally adaptive polygon approximation. In: Procedings of IEEE International Conference on Image Processing (ICIP), pp. 313–316, October 2008Google Scholar
  19. 19.
    Zhang, K., Lu, J., Lafruit, G.: Cross-based local stereo matching using orthogonal integral images. IEEE Trans. Circuits Syst. Video Tech. 19(7), 1073–1079 (2009)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Wen-Nung Lie
    • 1
  • Hsi-Hung Huang
    • 1
  • Shih-Wei Huang
    • 2
  • Kai-Che Liu
    • 3
  1. 1.Department of Electrical EngineeringNational Chung Cheng UniversityChia-YiTaiwan, ROC
  2. 2.Chang Bing Show Chwan Memorial HospitalLukangTaiwan, ROC
  3. 3.Medical Image Research DepartmentAsian Institute of TeleSurgery/IRCAD-TaiwanLukangTaiwan, ROC

Personalised recommendations