Efficient Sparse to Dense Stereo Matching Technique

  • Piyush BhandariEmail author
  • Meiqing Wu
  • Nazia Aslam
  • Siew-Kei Lam
  • Maheshkumar Kolekar
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1022)


Acquiring accurate dense depth maps with low computational complexity is crucial for real-time applications that require 3D reconstruction. The current sensors capable of generating dense maps are expensive and bulky, while compact low-cost sensors can only generate the sparse map measurements reliably. To overcome this predicament, we propose an efficient stereo analysis algorithm that constructs a dense disparity map from the sparse measurements. Our approach generates a dense disparity map with low computational complexity using local methods. The algorithm has much less computation time than the existing dense stereo matching techniques and has a high visual accuracy. Experiments results performed on KITTI and Middlebury datasets show that our algorithm has much less running time while providing accurate disparity maps.


Depth estimation Sparse to dense Stereo matching Interpolation 


  1. 1.
    Scharwchter, T., Schuler, M., Franke, U.: Visual guard rail detection for advanced highway assistance systems. In: 2014 IEEE Intelligent Vehicles Symposium Proceedings, June 2014, pp. 900–905 (2014)Google Scholar
  2. 2.
    Hne, C., Sattler, T., Pollefeys, M.: Obstacle detection for self-driving cars using only monocular cameras and wheel odometry. In: 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Sept 2015, pp. 5101–5108 (2015)Google Scholar
  3. 3.
    Pallauf, J., Wagner, J., Len, F.P.: Evaluation of state-dependent pedestrian tracking based on finite sets. IEEE Trans. Instrument. Measurem. 64(5), 1276–1284 (2015)CrossRefGoogle Scholar
  4. 4.
    Gao, S., Han, Z., Li, C., Ye, Q., Jiao, J.: Real-time multipedestrian tracking in traffic scenes via an rgb-d-based layered graph model. IEEE Trans. Intell. Transp. Syst. 16(5), 2814–2825 (2015)CrossRefGoogle Scholar
  5. 5.
    John, V., Englebienne, G., Krose, B.: Person re-identification using height-based gait in colour depth camera. In: 2013 IEEE International Conference on Image Processing, Sept 2013, pp. 3345–3349 (2013)Google Scholar
  6. 6.
    Wu, A., Zheng, W.S., Lai, J.H.: Depth-based person reidentification. In: 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR), Nov 2015, pp. 026–030 (2015)Google Scholar
  7. 7.
    Kolekar, M.H., Sengupta, S.: Bayesian network-based customized highlight generation for broadcast soccer videos. IEEE Trans. on Broadcast. 61(2), 195–209 (2015)CrossRefGoogle Scholar
  8. 8.
    Kolekar, M.H.: Bayesian belief network based broadcast sports video indexing. Int. Springer J. Multimedia Tools Appl. 54, 27–54 (2011)Google Scholar
  9. 9.
    Kolekar, M.H., Palaniappan, K., Sengupta, S., Seetharaman, G.: Semantic concept mining based on hierarchical event detection for soccer video indexing. Int. J. Multimedia 4(5), 298–312 (2009)Google Scholar
  10. 10.
    Kolekar, M.H., Talbar, S.N., Sontakke, T.R.: Texture segmentation using fractal signature. IETE J. Res. India 46(5), 319–323 (2000)Google Scholar
  11. 11.
    Kolekar, M.H., Dash, D.P.: A nonlinear feature based epileptic seizure detection using least square support vector machine classifier. IEEE Region 10 Conference TENCON 2015Google Scholar
  12. 12.
    Chatterjee, S., Bhandari, P., Kolekar, M.H.: Feature extraction and segmentation techniques in static hand gesture recognition system. In: Book Chapter of Book on Hybrid Intelligence for Image Analysis and Understanding. John Wiley Publication, UK (2017)Google Scholar
  13. 13.
    Liu, L.K., Nguyen, T.D.: Sparse reconstruction for disparity maps using combined wavelet and contourlet transforms. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2014, pp. 3553–3557 (2014)Google Scholar
  14. 14.
    Hawe, S., Diepold, K., Kleinsteuber, M.: Dense disparity maps from sparse disparity measurements. In: 2011 IEEE International Conference on Computer Vision (ICCV 2011), vol. 00, no. undefined, pp. 2126–2133 (2011)Google Scholar
  15. 15.
    Gehrig, S.K., Eberli, F., Meyer, T.: A Real-Time Low-Power Stereo Vision Engine Using Semi-Global Matching, pp. 134–143. Berlin, Heidelberg: Springer (2009)Google Scholar
  16. 16.
    Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? In: The Kitti Vision Benchmark Suite Conference on Computer Vision and Pattern Recognition (CVPR) (2012)Google Scholar
  17. 17.
    Scharstein, D., Szeliski, R., Zabih, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. In: Proceedings of IEEE Workshop on Stereo and Multi-baseline Vision (SMBV 2001), pp. 131–140 (2001)Google Scholar
  18. 18.
    Scharstein, D., Szeliski, R.: High-accuracy stereo depth maps using structured light. In: Proceedings of 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, June 2003, pp. I195–I202 (2003)Google Scholar
  19. 19.
    Scharstein, D., Pal, C.: Learning conditional random fields for stereo. In: 2007 IEEE Conference on Computer Vision and Pattern Recognition, June 2007, pp. 1–8 (2007)Google Scholar
  20. 20.
    Scharstein, D., Hirschmuller, H., Kitajima, Y., Krathwohl, G., Nesic, N., Wang, X., Westling, P.: High-Resolution Stereo Datasets with Subpixel-Accurate Ground Truth, pp. 31–42. Springer International Publishing, Cham (2014)Google Scholar
  21. 21.
    Van den Bergh, M., Boix, X., Roig, G., Van Gool, L.: Seeds: superpixels extracted via energy-driven sampling. Int. J. Comput. Vision 111(3), 298–314 (2015)MathSciNetCrossRefGoogle Scholar
  22. 22.
    Zabih, R., Woodfill, J.: Non-parametric Local Transforms for Computing Visual Correspondence. Springer, Berlin, Heidelberg, pp. 151–158 (1994)Google Scholar
  23. 23.
    Hirschmuller, H., Scharstein, D.: Evaluation of stereo matching costs on images with radiometric differences. IEEE Trans. Pattern Anal. Mach. Intell. 31(9), 1582–1599 (2009)CrossRefGoogle Scholar
  24. 24.
    Fife, W.S., Archibald, J.K.: Improved census transforms for resource-optimized stereo vision. IEEE Trans. Circ. Syst. Video Technol. 23(1), 60–73 (2013)CrossRefGoogle Scholar
  25. 25.
    Einecke, N., Eggert, J.: A multi-block-matching approach for stereo. In: 2015 IEEE Intelligent Vehicles Symposium (IV), June 2015, pp. 585–592Google Scholar
  26. 26.
    Li, F., Li, E., Shafiee, M.J., Wong, A., Zelek, J.: Dense depth map reconstruction from sparse measurements using a multilayer conditional random field model. In: 2015 12th Conference on Computer and Robot Vision (CRV), June 2015, pp. 86–93 (2015)Google Scholar
  27. 27.
    Geiger, A., Roser, M., Urtasun, R.: Efficient Large-scale Stereo Matching, pp. 25–38. Springer, Berlin, Heidelberg (2011)Google Scholar
  28. 28.
    Čech, J., Sanchez-Riera, J., Horaud, R.: Scene flow estimation by growing correspondence seeds. In: CVPR 2011, pp. 3129–3136, June 2011Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Piyush Bhandari
    • 1
    Email author
  • Meiqing Wu
    • 2
  • Nazia Aslam
    • 1
  • Siew-Kei Lam
    • 2
  • Maheshkumar Kolekar
    • 1
  1. 1.Indian Institute of TechnologyPatnaIndia
  2. 2.Nanyang Technological UniversitySingaporeSingapore

Personalised recommendations