A DCV & USIR Method implemented for Reconstructed of Un-calibrated captured MVS Images

  Gorikapudi Usha Rani,  G. Madhusudhana Rao,  P.Jayababu

This paper presents a Detail-Storing and Content-aware difference (DCV) multi-view stereo method and a novel algorithm for un-calibrated stereo image pair rectification under the constraint of geometric distortion, called USIR is presented in this work. Although it is straightforward to define a rectifying transformation given the epipolar geometry. Preserve boundaries details of the reconstructed surface and builds a connection between guided image filtering and image registration. To obtain rectified images with reduced geometric distortions while maintaining a neutralized rectification error. We analyse the homographs by considering the effects of various kinds of geometric distortions. Next, we propose several geometric measures and incorporate them into a new cost function for description optimization. A content-aware Lp-minimization algorithm by adaptively estimating the p-value and regularization parameters based on the current input . Finally, we propose a constrained adaptive optimization scheme to allow a balanced performance between the rectification error and the geometric error. Extensive experimental results are provided to demonstrate the data Storing and rectifying of image by DCV&USIR method.

Keywords- Projective rectification, homographs, epipolar geometry, fundamental matrix, geometric distortion, constrained optimization, Multi-view stereo,L0 Minimization.

Unique Identification Number - IJEDR1704137
Page Number(s) - 842-847
Pubished in - Volume 5 | Issue 4 | November 2017
DOI (Digital Object Identifier) -    http://doi.one/10.8/ijedr.17495
Publisher - IJEDR (ISSN - 2321-9939)

  Gorikapudi Usha Rani,  G. Madhusudhana Rao,  P.Jayababu,   "A DCV & USIR Method implemented for Reconstructed of Un-calibrated captured MVS Images", International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.5, Issue 4, pp.842-847, November 2017, Available at :http://www.ijedr.org/papers/IJEDR1704137.pdf