Robust two-view reconstruction procedure for geometrical model retrieving

• Autorzy: Walczak J. , Wojciechowski A.
• Języki publikacji: EN

Abstrakty

EN

In this paper we present the enhancement of the standard two-view reconstruction procedure. An ordinary approach assumes determination of points’ correspondences followed by projection matrix estimation, to finally refine results with bundle adjustment taking as a cost function reprojection error. Our contribution is realized in two manners: introducing an additional step of outliers rejection, changing cost function of bundle adjustment process to Relative Reprojection Error (R) and applying central difference as a method for Jacobian matrix approximation. Tests revealed gain in average R with lower variance, for confidence level of 0.95. Besides accuracy improvement, the suggested modifications supply the final result in the time virtually independent on initial object’s complexity and, in most cases, shorter than the standard approach.

Słowa kluczowe

EN

3D reconstruction; epipolar geometry; photogrammetry; model refinement

PL

rekonstrukcja 3D; geometria dwubiegunowa; fotogrametria; doskonalenie modelu

• Wydawca: Wydawnictwo Politechniki Łódzkiej
• Czasopismo: Journal of Applied Computer Science
• Rocznik: 2018
• Tom: Vol. 26, nr 1
• Strony: 87--104
• Opis fizyczny: Bibliogr. 21 poz., il. kolor., rys., wykr.

Twórcy

autor

Walczak J.

• Lodz University of Technology, Institute of Information Technology, ul. Wólczańska 215, 90-924 Łódź, Poland, http://it.p.lodz.pl/

autor

Wojciechowski A.

• Lodz University of Technology, Institute of Information Technology, ul. Wólczańska 215, 90-924 Łódź, Poland, http://it.p.lodz.pl/

Bibliografia

• [1] Megyesi, Z., Dense Matching Methods for 3D Scene Reconstruction from Wide Baseline Images, Ph.D. thesis, Eotvos Lorand University, 2009.
• [2] Izadi, S., Kim, D., Hilliges, O., Molyneaux, D., Newcombe, R., Kohli, P., Shotton, J., Hodges, S., Freeman, D., Davison, A., and Fitzgibbon, A., KinectFusion: Real-time 3D Reconstruction and Interaction Using a Moving Depth Camera, In: Proceedings of the 24th Annual ACM Symposium on User Interface Software and Technology, UIST ’11, ACM, New York, NY, USA, 2011, pp. 559-568.
• [3] Mertz, C., Koppal, S. J., Sia, S., and Narasimhan, S. G., A low-power structured light sensor for outdoor scene reconstruction and dominant material identification, In: 9th IEEE International Workshop on Projector-Camera Systems, Pittsburgh, PA, June 2012.
• [4] Zhao, H. and Shibasaki, R., Reconstructing a textured CAD model of an urban environment using vehicle-borne laser range scanners and line cameras, Machine Vision and Applications, Vol. 14, No. 1, apr 2003, pp. 35-41.
• [5] Yang, Y. Q., Xiao, Q., and Song, Y. H., The investigation of 3D scene reconstruction algorithm based on laser scan data, In: 2010 International Conference on Machine Learning and Cybernetics, Vol. 2, July 2010, pp. 819-823.
• [6] Roman, Z., Evgeny, P., and Dmitry, S., Structured Light + Range Imaging. Lecture 17, 2012, Lecture notes.
• [7] Hartley, R. and Zisserman, A., Multiple View Geometry in Computer Vision, chap. 4, Cambridge University Press, 2nd ed., 2003, p. 108.
• [8] Westoby, M., Brasington, J., Glasser, N., Hambrey, M., and Reynolds, J., ‘Structure-from-Motion’ photogrammetry: A low-cost, effective tool for geoscience applications, Geomorphology, Vol. 179, No. Supplement C, 2012, pp. 300 - 314.
• [9] Micheletti, N., Chandler, J. H., and Lane, S. N., Structure from Motion (SfM) Photogrammetry, British Society for Geomorphology, 2015.
• [10] Zhang, C., Xue, B., and Zhou, F., Low-dimension local descriptor for dense stereo matching and scene reconstruction, Optical Engineering, Vol. 56, No. 08, aug 2017.
• [11] Kowalski, M. and Skarbek, W., Online 3D face reconstruction with incremental Structure From Motion and a regressor cascade, Vol. 9290, 2014, pp. 9290 - 9290 - 8.
• [12] Asif, U., Bennamoun, M., and Sohel, F., Simultaneous dense scene reconstruction and object labeling, In: 2016 IEEE International Conference on Robotics and Automation (ICRA), IEEE, Stockholm, Sweden, may 2016.
• [13] Lari, Z. and El-Sheimy, N., A new approach for progressive dense reconstruction from consecutive images based on prior low-density 3D point clouds, Vol. XLII-2/W7, Wuhan, China, sep 2017.
• [14] Kowalczyk, M., Fornalczyk, K., Napieralski, P., and Staniucha, R., Computer Game Innovations, chap. Disparity detection in three-dimensional scenes implementing virtual reality, LODZ UNIVERSITY OF TECHNOLOGY PRESS, 2016.
• [15] King, A. and Panchal, J., Analysis of Keypoint Detection Algorithm for Space - Based SFM, Tech. rep., Spring, 2017.
• [16] Bay, H., Tuytelaars, T., and Van Gool, L., SURF: Speeded Up Robust Features, Springer Berlin Heidelberg, Berlin, Heidelberg, 2006, pp. 404-417.
• [17] Gong, Y., Meng, D., and Seibel, E. J., Bound constrained bundle adjustment for reliable 3D reconstruction, Opt. Express, Vol. 23, No. 8, Apr 2015, pp. 10771-10785.
• [18] Agarwal, S., Snavely, N., Seitz, S. M., and Szeliski, R., Bundle Adjustment in the Large, In: Eleventh European Conference on Computer Vision (ECCV 2010), Springer Verlag, October 2010.
• [19] Little, T. D., The Oxford Handbook of Quantitative Methods: Foundations, Vol. 1, chap. Robust Statistical Estimators, Oxford University Press, 2013.
• [20] Madsen, K., Nielsen, H., and Tingle, O., METHODS FOR NON-LINEAR LEAST SQUARES PROBLEMS, Technical University of Denmark, 2nd ed., apr 2004.
• [21] Wilcox, R. R., Introduction to robust estimation and hypothesis testing, Elsevier Academic Press, 2005.

Uwagi

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019).