Abstract
Estimation error in stereo matching affects a generated 3D shape seriously. To correct for the disparity error caused by the estimation error, a disparity correction method that is based on the sparsity of the signal is proposed. First, disparity values for all pixels of the basis image are obtained by stereo matching using ASWA (Adaptive Support-Weight Approach). The focus is on each pixel, and the disparity values are replaced in a block that is centered on the pixel. The disparity values are wavelet-transformed and are calculated as the norm of the wavelet coefficients. The norm is added to an evaluation function for disparity estimation, and the updated disparity value is obtained. Through qualitative and quantitative evaluations, the proposed method is compared with the conventional method in this paper, and the results show that the proposed method is able to correct the disparity error.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Schreer, O., Kauff, P., Sikora, T.: 3D video communicaion, pp. 135–136. John Wiley & Sons, Ltd. (2005)
Tomiyama, K., Katayama, M., Iwadate, Y., Imaizumi, H.: A Dynamic 3D, Object-Generating Algorithm from Multiple Viewpoints Using the Volume Intersection and Stereo Matching Methods. Image Information and Television Engineers 58(6), 797–806 (2004)
Rander, P.: A Multi-Camera Method for 3D Digitization of Dynamic. Real-World Events, CMU-RI-TR-98-12 (March 1998)
Min, D., Sohn, K.: Cost aggregation and occlusion handling with wls in stereo matching. TIP 17(8), 1431–1442 (2008)
Gerrits, M., Bekaert, P.: Local stereo matching with segmentation-based outlier rejection. In: CRV (2006)
Hirschmüller, H.: Stereo processing by semiglobal matching and mutual information. PAMI 30(2), 328–341 (2008)
Yoon, K.-J., Kweon, I.S.: Adaptive Support Weight Approach for Correspondence Search. IEEE Transactions on Pattern Analysis and Machine Intelligence 28(4), 650–656 (2006)
Yoon, K.-J., Kweon, I.-S.: Locally Adaptive Support-Weight Approach for Visual Correspondence Search. Robotics and Computer Vision Laboratory,Dept. of Electrical Engineering and Computer Science, KAIST, 373-1 Gus-eong-dong Yuseong-gu Daejeon, 305-701, Korea (2005)
Starck, J.-L., Fadili, M.J.: An Overview of Inverse Problem Regularization Using Sparsity. In: ICIP, pp. 1453–1456 (2009)
Martin, A., Fuchs, J.-J., Guillemot, C., Thoreau, D.: Sparse Representation for Image Prediction. In: EUSIPCO, pp. 1255–1259 (2007)
Sarkis, M., Diepold, K.: Towards real-time stereo usingnon-uniform image sampling and sparse dynamic programming. In: International Symposium on 3D Data Processing, Visualization and Transmission (June 2008)
Fadili, M.J., Starck, J.-L.: EM Algorithm for Sparse Representation-Based on Image Inpainting. In: ICIP, pp. II61–II64 (2005)
Ghoniem, M., Chahir, Y., Elmoataz, A.: Geometric and texture inpainting based on discrete regularization on graphs. In: ICIP, pp. 1349–1352 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hirose, N., Yasunobe, T., Kawanaka, A. (2013). 3D Shape Estimation Based on Sparsity in Stereo Matching. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2013. Lecture Notes in Computer Science, vol 8034. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41939-3_55
Download citation
DOI: https://doi.org/10.1007/978-3-642-41939-3_55
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-41938-6
Online ISBN: 978-3-642-41939-3
eBook Packages: Computer ScienceComputer Science (R0)