Home Comparison of Total Least Squares and Least Squares for Four- and Seven-parameter Model Coordinate Transformation
Article
Licensed
Unlicensed Requires Authentication

Comparison of Total Least Squares and Least Squares for Four- and Seven-parameter Model Coordinate Transformation

  • You Wu EMAIL logo , Jun Liu and Hui Yong Ge
Published/Copyright: December 9, 2016
Become an author with De Gruyter Brill

Abstract

Total least squares (TLS) is a technique that solves the traditional least squares (LS) problem for an errors-in-variables (EIV) model, in which both the observation vector and the design matrix are contaminated by random errors. Four- and seven-parameter models of coordinate transformation are typical EIV model. To determine which one of TLS and LS is more effective, taking the four- and seven-parameter models of Global Navigation Satellite System (GNSS) coordinate transformation with different coincidence pointsas examples, the relative effectiveness of the two methods was compared through simulation experiments. The results showed that in the EIV model, the errors-in-variables-only (EIVO) model and the errors-in-observations-only (EIOO) model, TLS is slightly inferior to LS in the four-parameter model coordinate transformation, and TLS is equivalent to LS in the seven-parameter model coordinate transformation. Consequently, in the four- and seven-parameter model coordinate transformation, TLS has no obvious advantage over LS.

References

[1] Acar M, 00zlüdemir MT, Akyilmaz O, Celik RN, Ayan T (2006) Deformation analysis with Total Least Squares. Natural Hazards & Earth System Science 6(4):663–669. doi:10.5194/nhess-6-663-2006.Search in Google Scholar

[2] Akyilmaz O (2007) Total Least Squares solution of coordinate transformation. Survey Review 39(303):68–80(13). doi:10.1179/003962607X165005.Search in Google Scholar

[3] Bazlov YA, Galazin VF, Kaplan BL, Maksimov VG, Rogozin VP (1999) Propagating PZ 90 to WGS 84 transformation parameters. GPS Solutions 3(1):13–16.10.1007/PL00012773Search in Google Scholar

[4] Chen Y, Lu J, Zheng B (2008) Application of Total Least Squares to space resection. Geomatics and Information Science of Wuhan University (12):1271–1274. doi:10.13203/j.whugis2008.12.001.Search in Google Scholar

[5] Felus YA, Schaffrin B (2005) Performing similarity transformations using the error-in-variables model. Asprs Annual Conference.Search in Google Scholar

[6] Felus YA, Burtch RC (2009) On symmetrical three-dimensional datum conversion. GPS Solutions 13(1):65–74. doi:10.1007/s10291-008-0100-5.Search in Google Scholar

[7] Gallo PP (1982) Properties of estimators in errors-in-variables models. Applications of Mathematics 9(12):1309–1315.Search in Google Scholar

[8] Ge YH, Yuan Y, Jia NN (2013) More efficient methods among commonly used robust estimation methods for GPS coordinate transformation. Survey Review 45(330):229–234.10.1179/1752270612Y.0000000028Search in Google Scholar

[9] Golub GH, Van Loan CF (1980) An analysis of the Total Least Squares problem. Siam Journal on Numerical Analysis 17(6):883-893. doi:10.1137/0717073.Search in Google Scholar

[10] Van Huffel S, Vandewalle J (1989) Algebraic connections between the least squares and total least squares problems. Numerische Mathematik 55(4):431–449. doi: 10.1007/BF01396047.Search in Google Scholar

[11] Van Huffel S, Vandewalle J (1991) The total least squares problem: computational aspects and analysis. Mathematics of Computation.10.1137/1.9781611971002Search in Google Scholar

[12] Markovsky I, Van Huffel S (2007) Overview of total least-squares methods. Signal Processing 87(2):2283–2302.10.1016/j.sigpro.2007.04.004Search in Google Scholar

[13] Neitzel F (2010) Generalization of total least-squares on example of unweighted and weighted 2D similarity transformation. Journal of Geodesy 84(12):751–762. doi: 10.1007/s00190-010-0408-0.Search in Google Scholar

[14] Schaffrin B, Felus YA (2008) On the multivariate total least-squares approach to empirical coordinate transformations. Three algorithms. Journal of Geodesy 82(6):373–383. doi: 10.1007/s00190-007-0186-5.Search in Google Scholar

[15] Stoica P, Viberg M (1995) Weighted LS and TLS approaches yield asymptotically equivalent results. Signal Processing 45(2):255–259. doi:10.1016/0165-1684(95)00055-I.Search in Google Scholar

[16] Nayak A, Trucco E, Thacker NA (2006) When are simple LS estimators enough? An empirical study of LS, TLS, and GTLS. International Journal of Computer Vision 68(2):203–216(14). doi: 10.1007/s11263-006-6486-z.Search in Google Scholar

[17] Wei MS (1992) Algebraic relations between the total least squares and least squares problems with more than one solution. Numerische Mathematik 62(1):123–148. doi:10.1007/BF01396223.Search in Google Scholar

[18] Wei EH, Yin ZX, Li GW, Li ZQ (2014) On 3D coordinate transformation with virtual observation method. Geomatics and Information Science of Wuhan University 39(2):152–156. doi: 10.13203/j.whugis20130178.Search in Google Scholar

[19] Yao YB, Huang CM, Li CC, Kong J (2012) A new algorithm for solution of transformation parameters of big rotation angle’s 3D coordinate. Geomatics and Information Science of Wuhan University 37(3):253–256. doi:10.13203/j.whugis2012.03.008.Search in Google Scholar

[20] Peiliang Xu, Yun Shi, Junhuan Peng, Jingnan Liu, Chuang Shi (2013) Adjustment of geodetic measurements with mixed multiplicative and additive random errors. Journal of Applied Geodesy 87:629–643. DOI 10.1007/s00190-013-0635-2.Search in Google Scholar

[21] Yun Shi, Peiliang Xu, Jingnan Liu, Chuang Shi (2015) Alternative formulae for parameter estimation in partial errors-in-variables models. Journal of Applied Geodesy 89:13–16. DOI 10.1007/s00190-014-0756-2.Search in Google Scholar

[22] Peiliang Xu, Jingnan Liu, Wenxian Zeng, Yunzhong Shen (2014) Effects of errors-in-variables on weighted least squares estimation. Journal of Applied Geodesy 88:705–716. DOI 10.1007/s00190-014-0716-x.Search in Google Scholar

[23] Xing Fang (2014) On non-combinatorial weighted total least squares with inequalityconstraints. Journal of Applied Geodesy 88:805–816. DOI 10.1007/s00190-014-0723-y.Search in Google Scholar

[24] Xing Fang (2014) A total least squares solution for geodetic datumtransformations. Journal of Applied Geodesy 49:189–207. DOI 10.1007/s40328-014-0046-8.Search in Google Scholar

[25] Xing Fang (2015) Weighted total least-squares with constraints: a universal formulafor geodetic symmetrical transformations. Journal of Applied Geodesy 89:459–469. DOI 10.1007/s00190-015-0790-8.Search in Google Scholar

[26] Xing Fang (2013) Weighted total least squares: necessary and sufficient conditions, fixed and random parameters. Journal of Applied Geodesy 87:733–749. DOI 10.1007/s00190-013-0643-2.Search in Google Scholar

[27] Peiliang Xu, Jingnan Liu, Chuang Shi (2012) Total least squares adjustment in partial errors-in-variablesmodels: algorithm and statistical analysis. Journal of Applied Geodesy 86:661–675. DOI 10.1007/s00190-012-0552-9.Search in Google Scholar

[28] Burkhard Schaffrin, Andreas Wieser (2008) On weighted total least-squares adjustment for linear regression. Journal of Applied Geodesy 82:415–421. DOI 10.1007/s00190-007-0190-9.Search in Google Scholar

[29] Yongjun Zhou, Xinjian Kou, Jonathan Li, and Xing Fang (2016) Comparison of Structured and Weighted Total Least-Squares Adjustment Methods for Linearly Structured Errors-in-Variables Models. Journal of Surveying Engineering. DOI 10.1061/(ASCE) SU.1943-5428.0000190.Search in Google Scholar

[30] Xing Fang (2014) A structured and constrained Total Least-Squares solutionwith cross-covariances. Studia Geophysica Et Geodaetica 58(1):1–16. DOI 10.1007/s11200-012-0671-z.Search in Google Scholar

[31] Peiliang Xu, Chuang Shi, Rongxin Fang, Jingnan Liu, Xiaoji Niu, Quan Zhang, Takashi Yanagidani (2013) High-rate precise point positioning (PPP) to measure seismic wavemotions: an experimental comparison of GPS PPP with inertial measurement units. Journal of Applied Geodesy 87:361–372. DOI 10.1007/s00190-012-0606-z.Search in Google Scholar

Received: 2016-6-6
Accepted: 2016-7-10
Published Online: 2016-12-9
Published in Print: 2016-12-1

© 2016 Walter de Gruyter GmbH, Berlin/Munich/Boston

Downloaded on 23.11.2025 from https://www.degruyterbrill.com/document/doi/10.1515/jag-2016-0015/html
Scroll to top button