LIOP based Feature Detection and Matching in SfM for 3D Object Reconstruction

Amit Banda¹ , Rajesh Patil²

¹ Dept. of Electrical Engineering, VJTI, Mumbai, India.
² Dept. of Electrical Engineering, VJTI, Mumbai, India.

Section:Research Paper, Product Type: Journal
Vol.5 , Issue.3 , pp.90-94, Jun-2017

Online published on Jun 30, 2017

Copyright © Amit Banda, Rajesh Patil . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
 

View this paper at   Google Scholar | DPI Digital Library

XML View     PDF Download

How to Cite this Paper

848 Views    361 Downloads    293 Downloads

Abstract :
3D object reconstruction is growing popular due to its various applications such as movie industry and research simulations. Multi-View Stereo (MVS) based reconstruction using camera without extra hardware helps in reducing the cost of the system. The process consists of solving correspondence problem between images cause by camera motion using feature detector and descriptor or the optical flow technique. We propose to use LIOP proposed recentlyas a feature descriptor algorithmin the SFM based method for 3D object reconstruction.Based on the feature descriptor, it is more robust to noise, rotation, translation and monotonic intensity changes. Use of such rich feature descriptors increases the accuracy of reconstruction.

Key-Words / Index Term :

References :
[1] Amit Banda, Rajesh A Patil, “Review on Feature Detection and Matching Algorithms for 3D Object Reconstruction�, IJRTER, Vol. 3, Jan 2017, pp. 219-225
[2] Seitz, Steven M., "A comparison and evaluation of multi-view stereo reconstruction algorithms" 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR06), USA, pp. 519-528 ,2006
[3] Soo Mi Choi, "Volumetric object reconstruction using the 3D-MRF model-based segmentation�, IEEE Transactions on Medical Imaging, Vol.16, Issue.6, pp.887-892, 1997.
[4] K. Kutulakos, S. Seitz., “A theory of shape by space carving�, IJCV, Vol.38, Issue.3, Issue.3, pp.199-218, 2000
[5] R. Szeliski, “A multi-view approach to motion and stereo�, In CVPR, Vol.1, Issue.4, pp.157-163, 1999.
[6] O. Faugeras, E. Bras-Mehlman, J.-D. Boissonnat, “Representingstereo data with the Delaunay triangulation�, Artificial Intelligence, Vol.44, Issue.1-2, pp.41-87, 1990.
[7] A. Manessis, A. Hilton, P. Palmer, P. McLauchlan, X. Shen, “Reconstruction of scene models from sparse 3D structure�, In CVPR, vol.1, Issue.3, pp.666-673, 2000.
[8] D. Morris, T. Kanade , “Image-consistent surface triangulation�, In CVPR, Vol.1, Issue.3, pp.332-338, 2000.
[9] C. J. Taylor, “Surface reconstruction from feature based stereo�, In ICCV, USA, pp. 184-190, 2003.
[10] Marius Muja, David G. Lowe, “Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration�, VISAPP, Vol.1, Issue.2, pp.331-340, 2009.
[11] DL Baggio, “Mastering OpenCV with practical computer vision projects�, Packt Publishing Ltd, UK, pp.1-134, 2012.
[12] RI. Hartley, “Triangulation", Computer vision and image understanding, Vol.68, Issue.2, pp.146-157, 1997.
[13] R. Hartley, Andrew Zisserman, “Multiple view geometry in computer vision�, Cambridge university press, UK, pp.34-57, 2003.
[14] E. Hildreth, "Recovering three-dimensional structure from motion with surface reconstruction", Vision research, Vol.35, Issue.1, pp.117-137, 1995.
[15] JL. Barron, “Performance of optical flow techniques", International journal of computer vision, Vol.12, Issue.1, pp.43-77, 1994.
[16] Berthold KP, Brian G. Schunck, "Determining optical flow", Artificial intelligence, Vol.17, Issue.1-3, pp.185-203, 1981.
[17] Kapila Sharma, "An Effective Approach of Thinning for Morphological Features An Effective Approach of Thinning for Morphological Features", International Journal of Computer Sciences and Engineering, Vol.3, Issue.10, pp.58-60, 2015.
[18] Zach Christopher, "Robust bundle adjustment revisited", European Conference on Computer Vision. Springer International Publishing, Europe, pp.12-19, 2014.
[19] Lindeberg Tony, "Scale invariant feature transform", Scholarpedia, Vol.7, Issue.5, pp.10491-10498, 2012.
[20] K. Mikolajczyk, C. Schmid, “A performance evaluation of local descriptors�, IEEE T-PAMI, Vol.27, Issue.10,pp.12-16, 2005
[21] Miksik Ondrej, Krystian Mikolajczyk, "Evaluation of local detectors and descriptors for fast feature matching", International Conference on Pattern Recognition (ICPR), Japan, pp.11-15, 2012.
[22] Wang Zhenhua, Bin Fan, Fuchao Wu, "Local intensity order pattern for feature description", 2011 IEEE International Conference on Computer Vision (ICCV), Spain, pp.603-610, 2011.
[1] Amit Banda, Rajesh A Patil, “Review on Feature Detection and Matching Algorithms for 3D Object Reconstruction�, IJRTER, Vol. 3, Jan 2017, pp. 219-225
[2] Seitz, Steven M., "A comparison and evaluation of multi-view stereo reconstruction algorithms" 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR06), USA, pp. 519-528 ,2006
[3] Soo Mi Choi, "Volumetric object reconstruction using the 3D-MRF model-based segmentation�, IEEE Transactions on Medical Imaging, Vol.16, Issue.6, pp.887-892, 1997.
[4] K. Kutulakos, S. Seitz., “A theory of shape by space carving�, IJCV, Vol.38, Issue.3, Issue.3, pp.199-218, 2000
[5] R. Szeliski, “A multi-view approach to motion and stereo�, In CVPR, Vol.1, Issue.4, pp.157-163, 1999.
[6] O. Faugeras, E. Bras-Mehlman, J.-D. Boissonnat, “Representingstereo data with the Delaunay triangulation�, Artificial Intelligence, Vol.44, Issue.1-2, pp.41-87, 1990.
[7] A. Manessis, A. Hilton, P. Palmer, P. McLauchlan, X. Shen, “Reconstruction of scene models from sparse 3D structure�, In CVPR, vol.1, Issue.3, pp.666-673, 2000.
[8] D. Morris, T. Kanade , “Image-consistent surface triangulation�, In CVPR, Vol.1, Issue.3, pp.332-338, 2000.
[9] C. J. Taylor, “Surface reconstruction from feature based stereo�, In ICCV, USA, pp. 184-190, 2003.
[10] Marius Muja, David G. Lowe, “Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration�, VISAPP, Vol.1, Issue.2, pp.331-340, 2009.
[11] DL Baggio, “Mastering OpenCV with practical computer vision projects�, Packt Publishing Ltd, UK, pp.1-134, 2012.
[12] RI. Hartley, “Triangulation", Computer vision and image understanding, Vol.68, Issue.2, pp.146-157, 1997.
[13] R. Hartley, Andrew Zisserman, “Multiple view geometry in computer vision�, Cambridge university press, UK, pp.34-57, 2003.
[14] E. Hildreth, "Recovering three-dimensional structure from motion with surface reconstruction", Vision research, Vol.35, Issue.1, pp.117-137, 1995.
[15] JL. Barron, “Performance of optical flow techniques", International journal of computer vision, Vol.12, Issue.1, pp.43-77, 1994.
[16] Berthold KP, Brian G. Schunck, "Determining optical flow", Artificial intelligence, Vol.17, Issue.1-3, pp.185-203, 1981.
[17] Kapila Sharma, "An Effective Approach of Thinning for Morphological Features An Effective Approach of Thinning for Morphological Features", International Journal of Computer Sciences and Engineering, Vol.3, Issue.10, pp.58-60, 2015.
[18] Zach Christopher, "Robust bundle adjustment revisited", European Conference on Computer Vision. Springer International Publishing, Europe, pp.12-19, 2014.
[19] Lindeberg Tony, "Scale invariant feature transform", Scholarpedia, Vol.7, Issue.5, pp.10491-10498, 2012.
[20] K. Mikolajczyk, C. Schmid, “A performance evaluation of local descriptors�, IEEE T-PAMI, Vol.27, Issue.10,pp.12-16, 2005
[21] Miksik Ondrej, Krystian Mikolajczyk, "Evaluation of local detectors and descriptors for fast feature matching", International Conference on Pattern Recognition (ICPR), Japan, pp.11-15, 2012.
[22] Wang Zhenhua, Bin Fan, Fuchao Wu, "Local intensity order pattern for feature description", 2011 IEEE International Conference on Computer Vision (ICCV), Spain, pp.603-610, 2011.