© The Institution of Engineering and Technology
The stereo matching problem takes two images captured by nearby cameras and attempts to recover quantitative disparity information. Most of the existing stereo matching algorithms find it difficult to estimate disparity in the occlusion, discontinuities and textureless regions in the images. In the last few decades, a number of stereo matching methods have been proposed to overcome some of these problems. In the same line of thought, the authors propose a new feature-based stereo matching method, which consists of four basic steps – feature-based stereo correspondence, two-pass cost aggregation, disparity computation using winner-takes-all selection and finally, the disparity refinement. In the proposed method, local features of Gabor wavelet in spatial domain are used for matching cost computation and subsequently a cost aggregation step is implemented by combined use of the Kuwahara filter and the median filter. Experimental results on the Middlebury benchmark database shows that the proposed method outperforms many existing local stereo matching methods.
References
-
-
1)
-
16. Jahanbin, S., Choi, H., Bovik, A.C.: ‘Passive multimodal 2-D + 3-D face recognition using Gabor features and landmark distances’, IEEE Trans. Inf. Forensics Sec., 2011, 6, (4), pp. 1287–1304 (doi: 10.1109/TIFS.2011.2162585).
-
2)
-
28. Hosni, A., Bleyer, M., Gelautz, M.: ‘Secrets of adaptive support weight techniques for local stereo matching’, Comput. Vis. Image Underst., 2013, 117, (6), pp. 620–632 (doi: 10.1016/j.cviu.2013.01.007).
-
3)
-
40. El-Etriby, S., Al-Hamadi, A., Michaelis, B.: ‘Dense depth map reconstruction by phase difference-based algorithm under influence of perspective distortion’, J. Mach. Graphics Vis., 2006, 15, (3), pp. 349–361.
-
4)
-
17. Okajima, K.: ‘The Gabor function extracts the maximum information from input local signals’, Neural Netw., 1998, 11, (3), pp. 435–439 (doi: 10.1016/S0893-6080(98)00008-2).
-
5)
-
M.Z. Brown ,
D. Burschka ,
G.D. Hager
.
Advances in computational stereo.
IEEE Trans. Pattern Anal. Mach. Intell.
,
8 ,
993 -
1008
-
6)
-
22. Navarro, R., Tabernero, A.: ‘Gaussian wavelet transform: two alternative fast implementations for images’, J. Multidimens. Syst. Signal Process., 1991, 2, (4), pp. 421–436 (doi: 10.1007/BF01937176).
-
7)
-
42. Scharstein, D., Pal, C.: ‘Learning conditional random fields for stereo’. Proc. Int. Conf. Computer Vision and Pattern Recognition, 2007, pp. 1–8.
-
8)
-
41. Nalpantidis, L., Gasteratos, A.: ‘Stereo vision for robotic applications in the presence of non-ideal lighting conditions’, Image Vis. Comput., 2010, 28, (6), pp. 940–951 (doi: 10.1016/j.imavis.2009.11.011).
-
9)
-
10. Gerrits, M., Bekaert, P.: ‘Local stereo matching with segmentation-based outlier rejection’. Proc. Canadian Conf. on Computer and Robot Vision, 2006, pp. 66–66.
-
10)
-
33. Scharstein, D., Szeliski, R.: ‘High-accuracy stereo depth maps using structured light’. Proc. Int. Conf. Computer Vision and Pattern Recognition, 2003, pp. 195–202.
-
11)
-
37. Ma, L., Li, J., Ma, J., et al: ‘A modified census transform based on the neighborhood information for stereo matching algorithm’. Proc. Int. Conf. Image and Graphics, 2013, pp. 533–538.
-
12)
-
34. El-Etriby, S., Al-Hamadi, A., Michaelis, B.: ‘Dense stereo correspondence with slanted surface using phase-based algorithm’. Proc. Int. Symposium Industrial Electronics, 2007, pp. 1807–1813.
-
13)
-
7. B-Zin, B., Dupont, R., Bartoli, A.: ‘A general dense image matching framework combining direct and feature-based costs’. Proc. Int. Conf. on Computer Vision, 2013, pp. 185–192.
-
14)
-
38. Nalpantidis, L., Gasteratos, A.: ‘Biologically and psychophysically inspired adaptive support weights algorithm for stereo correspondence’, Robot. Auton. Syst., 2010, 58, (5), pp. 457–464 (doi: 10.1016/j.robot.2010.02.002).
-
15)
-
24. Twardowski, T., Cyganek, B., Borgosz, J.: ‘Gradient based dense stereo matching’. Proc. Int. Conf. Image Analysis and Recognition, 2004, pp. 721–728.
-
16)
-
14. Lee, T.S.: ‘Image representation using 2D Gabor wavelets’, IEEE Trans. Pattern Anal. Mach. Intell., 1996, 18, (10), pp. 959–971 (doi: 10.1109/34.541406).
-
17)
-
6. Zabih, R., Woodfill, J.: ‘Non-parametric local transforms for computing visual correspondence’. Proc. European Conf. on Computer Vision, 1994, pp. 151–158.
-
18)
-
11. Hosni, A., Bleyer, M., Gelautz, M., et al: ‘Local stereo matching using geodesic support weights’. Proc. IEEE Int. Conf. on Image Processing, 2009, pp. 2093–2096.
-
19)
-
13. De-Maeztu, L., Mattoccia, S., Villanueva, A., et al: ‘Linear stereo matching’. Proc. Int. Conf. on Computer Vision, 2011, pp. 1708–1715.
-
20)
-
21)
-
D. Sharstein ,
R. Szeliski
.
A taxonomy and evaluation of dense two-frame stereo correspondence algorithms.
Int. J. Comput. Vis.
,
7 -
42
-
22)
-
8. Pinggera, P., Breckon, T., Bischof, H.: ‘On cross-spectral stereo matching using dense gradient features’. Proc. British Machine Vision Conference, 2012, pp. 526.1–526.12.
-
23)
-
20. Bhuyan, M.K., Malathi, T.: ‘Review of the application of matrix information theory in video surveillance’, in Nielsen, F., Bhatia, R. (Eds.): ‘Matrix information geometry’ (Springer, 2012), pp. 293–321.
-
24)
-
43. Hirschmüller, H., Scharstein, D.: ‘Evaluation of cost functions for stereo matching’. Proc. Int. Conf. Computer Vision and Pattern Recognition, 2007, pp. 1–8.
-
25)
-
5. Eklund, M.P., Farag, A.A., El-Melegy, M.T.: ‘Robust correspondence methods for stereo vision’, Int. J. Pattern Recognit. Artif. Intell., 3003, 17, (7), pp. 1059–1079 (doi: 10.1142/S0218001403002861).
-
26)
-
5. Hosni, A., Rhemann, C., Bleyer, M., Rother, C., Gelautz, M.: ‘Fast cost-volume filtering for visual correspondence and beyond’, IEEE Trans. Pattern Anal. Mach. Intell., 2013, 35, (2), pp. 504–511 (doi: 10.1109/TPAMI.2012.156).
-
27)
-
31. Papari, G., Petkov, N., Campisi, P.: ‘Artistic Edge and Corner Enhancing Smoothing’, IEEE Trans. Image Process., 2007, 16, (10), pp. 2449–2461 (doi: 10.1109/TIP.2007.903912).
-
28)
-
26. Mattoccia, S., Giardino, S., Gambini, A.: ‘Accurate and efficient cost aggregation strategy for stereo correspondence based on approximated joint bilateral filtering’. Proc. Asian Conf. Computer Vision, 2009, pp. 371–382.
-
29)
-
19. Nestares, O., Navarro, R., Portilla, J., et al: ‘Efficient spatial-domain implementation of a multiscale image representation based on gabor functions’, J. Electron. Imaging, 1998, 7, pp. 166–173 (doi: 10.1117/1.482638).
-
30)
-
29. Richardt, C., Orr, D., Davies, I., et al: ‘Real-time spatiotemporal stereo matching using the dual-crossbilateral grid’. Proc. European Conf. Computer Vision, 2010, pp. 510–523.
-
31)
-
3. Fusiello, A., Roberto, V., Trucco, E.: ‘Symmetric stereo with multiple windowing’, Int. J. Pattern Recognit. Artif. Intell., 2000, 14, (8), pp. 1053–1066 (doi: 10.1142/S0218001400000696).
-
32)
-
15. Hu, H.: ‘Enhanced gabor feature based classification using a regularized locally tensor discriminant model for multiview gait recognition’, IEEE Trans. Circuits Systems Video Tech., 2013, 23, (7), pp. 1274–1286 (doi: 10.1109/TCSVT.2013.2242640).
-
33)
-
36. Solariseir, M.S., Othman, M.F.: ‘A new fast and robust stereo matching algorithm for robotic systems’, Adv. Intell. Syst. Comput., 2013, 209, pp. 281–290 (doi: 10.1007/978-3-642-37371-8_31).
-
34)
-
32. Ma, Z., He, K., Wei, Y., et al: ‘Constant time weighted median filtering for stereo matching and beyond’. Proc. Int. Conf. Computer Vision and Pattern Recognition, 2013, pp. 1–8.
-
35)
-
T. Kanade ,
M. Okutomi
.
A stereo matching algorithm with an adaptive window: theory and experiment.
IEEE Trans. Patt. Anal. Mach. Intell.
,
9 ,
920 -
932
-
36)
-
14. Heo, Y.S., Lee, K.M., Lee, S.U.: ‘Robust stereo matching using adaptive normalized cross-correlation’, IEEE Trans. Pattern Anal. Mach. Intell., 2011, 33, (4), pp. 807–822 (doi: 10.1109/TPAMI.2010.136).
-
37)
-
39. Ambrosch, K., Kubinger, W.: ‘Accurate hardware-based stereo vision’, Comput. Vis. Image Underst., 2010, 114, (11), pp. 1303–1316 (doi: 10.1016/j.cviu.2010.07.008).
-
38)
-
27. Yang, Q., Tan, K., Ahuja, N.: ‘Real-time O(1) bilateral filtering’. Proc. Int. Conf. Computer Vision and Pattern Recognition, 2009, pp. 557–564.
-
39)
-
30. He, K., Sun, J., Tang, X.: ‘Guided image filtering’, IEEE Trans. Image Process., 2013, 35, (6), pp. 1397–1409.
-
40)
-
35. Humenberger, M., Zinner, C., Weber, M., et al: ‘A fast stereo matching algorithm suitable for embedded real-time systems’, Comput. Vis. Image Underst., 2010, 114, (11), pp. 1180–1202 (doi: 10.1016/j.cviu.2010.03.012).
-
41)
-
18. Bhagavathy, S., Tesic, J., Manjunath, B.S.: ‘On the Rayleigh nature of Gabor filter outputs’. Proc. Int. Conf. on Image Processing, 2003, pp. 745–748.
-
42)
-
K.J. Yoon ,
I.S. Kweon
.
Adaptive support-weight approach for correspondence search.
Trans. Pattern Anal. Mach. Intell.
,
4 ,
650 -
656
-
43)
-
21. Pollen, D.A., Ronner, S.F.: ‘Visual cortical neurons as localized spatial frequency filters’, IEEE Trans. Syst. Man Cybern., 1983, 13, (5), pp. 907–916 (doi: 10.1109/TSMC.1983.6313086).
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2014.0210
Related content
content/journals/10.1049/iet-cvi.2014.0210
pub_keyword,iet_inspecKeyword,pub_concept
6
6