access icon free Improvement of stereo matching algorithm based on sum of gradient magnitude differences and semi-global method with refinement step

© The Institution of Engineering and Technology
Received 23/10/2017, Published 06/06/2018

A new stereo matching algorithm which uses improved matching cost computation and optimisation using the semi-global method (SGM) is proposed. The absolute difference is sensitive to low textured regions and high noise on the stereo images with radiometric distortions. To get over these problems, sum of gradient magnitude differences has been introduced at the first stage. This method is strong against the radiometric differences on the stereo images. Hence, this approach will reduce the error of preliminary data for stereo corresponding process. The SGM is used at the aggregation, and optimisation stage uses 16 different directions of 2D path. Additionally, the iterative guided filter is utilised at the refinement stage which minimises the errors and increases the accuracy. The proposed work produces accurate results and performs much better compared with some established algorithms based on the standard stereo benchmarking evaluation from the Middlebury and KITTI.

Inspec keywords: gradient methods; iterative methods; radiometry; optimisation; image filtering; distortion; stereo image processing; image matching

Other keywords: radiometric distortions; stereo corresponding process; sum of gradient magnitude differences; SGM; refinement step; low textured regions; stereo matching algorithm; 2D path direction; iterative guided filter; error reduction; semiglobal method; optimisation stage; standard stereo benchmarking evaluation; improved matching cost computation; stereo images; absolute difference

Subjects: Interpolation and function approximation (numerical analysis); Optimisation techniques; Optimisation techniques; Computer vision and image processing techniques; Image recognition; Filtering methods in signal processing; Interpolation and function approximation (numerical analysis)

References

    1. 1)
    2. 2)
    3. 3)
      • 6. Bricola, J.C., Bilodeau, M., Beucher, S.: ‘Morphological processing of stereoscopic image superimpositions for disparity map estimation’. 2016, hal-01330139.
    4. 4)
      • 9. Peña, D., Sutherland, A.: ‘Disparity estimation by simultaneous edge drawing’. Asian Conf. on Computer Vision, Taipei, Taiwan, November 2016, pp. 124–135.
    5. 5)
    6. 6)
      • 10. Yang, Q.: ‘A non-local cost aggregation method for stereo matching’. Conf. on Computer Vision and Pattern Recognition, Providence, RI, USA, June 2012, pp. 1402–1409.
    7. 7)
      • 8. Richardt, C., Kim, H., Valgaerts, L., et al: ‘Dense wide-baseline scene flow from two handheld video cameras’. Int. Conf. on 3D Vision, Stanford, CA, USA, October 2016, pp. 276–285.
    8. 8)
    9. 9)
      • 7. Kitagawa, M., Shimizu, I., Sara, R.: ‘High accuracy local stereo matching using DoG scale map’. Int. Conf. on Machine Vision Applications, Nagoya, Japan, May 2017, pp. 258–261.
    10. 10)
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2017.3956
Loading

Related content

content/journals/10.1049/el.2017.3956
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading