Overview of Total Least Squares Methods

Total least squares (TLS) is a basic estimation method to account for random errors in functional models and has found a wide variety of applications in different areas of science and engineering, including signal and image processing, computer vision, communication engineering and our own subject area (geodesy, photogrammetry, geomatics and GIS). The purpose of this paper is to briefly review TLS methods and algorithms, including a discussion of the accuracy of TLS estimates. Since reliability is of interest in our subject area, we will also briefly touch the reliability issue of TLS. Finally, we will outline some topics for further investigations in the future.