Akhil Appu SHETTY, Vadakekara Itty GEORGE, Chempi Gurudas NAYAK, Raviraj SHETTY

Performance analysis of a fuzzy disparity selector for stereo matching of image segments under radiometric variations

Stereo matching algorithms generate disparity maps, which contain the depth information of the environment, from two or more images of a scene taken from different viewpoints. The process of obtaining dense disparity maps is a problem which is still being actively researched. The presence of radiometric differences in the images only further complicates the stereo matching problem. In the present research work, the images are initially split into small patches of pixels, such that pixels in each patch have similar intensities. The authors attempt to study the effect of the parameters, namely, tuning parameter ‘ α ’ and the number of segments, while the images are subjected to variations in exposure and illumination. The value ‘ α ’ performs the function of a weight signifying the contribution of each data cost, when the two data costs are combined in a linear fashion. Lastly, the results of this methodology are compared with other methods that try to tackle the problem of stereo matching under radiometric variations

PDF

___

[1] Yoon KJ. Stereo matching based on nonlinear diffusion with disparity-dependent support weights. IET Computer Vision 2012; 6 (4): 306-313.
[2] Heo YS, Lee KM, Lee SU. Illumination and camera invariant stereo matching. In: IEEE Conference on Computer Vision and Pattern Recognition; Anchorage, AK, USA;2008 pp. 1-8.
[3] Scharstein D, Szeliski R. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Inter- national Journal of Computer Vision 2002; 47: 7-42.
[4] Yang Q. A non-local cost aggregation method for stereo matching. In: IEEE Conference on Computer Vision and Pattern Recognition; Providence, RI, USA; 2012 pp. 1402-1409.
[5] Yang G, Zhao H, Shi J, Deng Z, Jia J. SegStereo: Exploiting Semantic Information for Disparity Estimation. In: Proceedings of the European Conference on Computer Vision; Beijing, China; 2018. pp. 660-676.
[6] Cheng X, Wang P, Yang R. Learning depth with convolutional spatial propagation network. arXiv preprint arXiv:1810.02695; 2018.
[7] Song X, Zhao X, Fang L, Hu H. EdgeStereo: An Effective Multi-Task Learning Network for Stereo Matching and Edge Detection. arXiv preprint arXiv:1903.01700; 2019.
[8] Szeliski R. Computer vision: algorithms and applications. Berlin, Germany: Springer Press, 2010.
[9] Kanade T, Kano H, Kimura S, Yoshida A, Od K. Development of a video-rate stereo machine. In: IEEE Int. Conference on Intelligent Robots and Systems;Pittsburgh, PA, USA; 1995. pp. 95-100.
[10] Simoncelli EP, Adelson EH, Heeger DJ. Probability distributions of optical flow. In: IEEE Conference on Computer Vision and Pattern Recognition; Maui, HI, USA; 1991. pp. 310-315.
[11] Mattoccia S, Tombari F, Di Stefano L. Fast full-search equivalent template matching by enhanced bounded correlation. IEEE Transactions on Image Processing 2008; 4 : 528-538.
[12] Tomasi C, Manduchi R. Bilateral filtering for gray and color images. In: IEEE International Conference on Computer Vision; Bombay, India; 1998. pp. 839-846.
[13] Zabih R, Woodfill J. Non-parametric local transforms for computing visual correspondence. In: European Confer- ence on Computer Vision; Berlin, Heidelberg, Germany; 1994. pp. 151-158.
[14] Mei X, Sun X, Zhou M, Jiao S, Wang H, Zhang X. Building an accurate stereo matching system on graphics hardware. In: IEEE International Conference on Computer Vision; Barcelona, Spain; 2011. pp. 467-474.
[15] Hamzah RA, Ibrahim H, Hassan AHA. Stereo matching algorithm based on per pixel difference adjustment, iterative guided filter and graph segmentation. ournal of Visual Communication and Image Representation 2017; 42: 145-160.
[16] Zhu H, Yin J, Yuan D. SVCV: segmentation volume combined with cost volume for stereo matching. IET Computer Vision 2017; 11 (8): 733-743.
[17] Lee DH, Chang JY, Heo YS. Stereo matching using cost volume fusion for high dynamic range scenes. Electronics Letters 2017; 53 (23): 1522-1524.
[18] Roszkowski M. Stereo matching with superpixels. In : Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments; Wilga, Poland; 2012. pp. 1-9.
[19] Heo YS, Lee KM, Lee SU. Robust stereo matching using adaptive normalized cross-correlation. IEEE Transactions on Pattern Analysis and Machine Intelligence 2011; 33 (4): 807-822.
[20] Hirschmuller H. Stereo processing by semiglobal matching and mutual information. IEEE Transactions on Pattern Analysis and Machine Intelligence 2008; 30 (2): 328-341.
[21] Hirschmuller H, Scharstein D. Evaluation of stereo matching costs on images with radiometric differences. IEEE Transactions on Pattern Analysis and Machine Intelligence 2008; 29: 1582-1599.
[22] Yaman M, Kalkan S. Performance evaluation of similarity measures for dense multimodal stereo vision. Journal of Electronic Imaging 2016; 25: 1-31.
[23] Pluim JP, Maintz JA, Viergever MA. Image registration by maximization of combined mutual information and gradient information. IEEE Transactions on Medical Imaging 2000; 19 (8): 809-814.
[24] Qu Y, Jiang J, Deng X, Zheng Y. Robust local stereo matching under varying radiometric conditions. IET Computer Vision 2014; 8 (4): 263-276.
[25] Baydoun M, Al-Alaoui MA. Enhancing stereo matching with varying illumination through histogram information and normalized cross correlation. In: IEEE International Conference on Systems, Signals and Image Processing ;Bucharest, Romania; 2013. pp. 5-9.
26] Jiao J, Wang R, Wang W, Dong S, Wang Z, Gao W. Local stereo matching with improved matching cost and disparity refinement. IEEE MultiMedia 2014; 21: 16-27.
[27] Tombari F, Mattoccia S, Di Stefano L, Addimanda E. Near real-time stereo based on effective cost aggregation. In: IEEE International Conference on Pattern Recognition; Tampa, FL, USA; 2008. pp. 1-4.
[28] Xu Y, Zhao Y, Ji M. Local stereo matching with adaptive shape support window based cost aggregation. Applied Optics 2014; 53 (29): 6885-6892.
[29] Egnal G. Mutual information as a stereo correspondence measure. University of Pennsylvania, Department of Computer and Information Science.
[30] Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Süsstrunk S. SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Transactions on Pattern Analysis and Machine Intelligence 2014; 34: 2274-2282.
[31] Ross TJ. Fuzzy logic with engineering applications. 3rd ed. University of New Mexico, New Jersey, USA: John Wiley & Sons, 2009.
[32] Shetty AA, George VI, Nayak CG, Shetty R. Fuzzy logic based disparity selection using multiple data costs for stereo correspondence. Turkish Journal of Electrical Engineering & Computer Sciences 2019; 27: 377-391.
[33] Mroz F, Breckon TP. An empirical comparison of real-time dense stereo approaches for use in the automotive environment. EURASIP Journal on Image and Video Processing 2012; 13: 1-19.