Abstract
Abstract. Rational function models (RFMs) are known as one of the most appealing models which are extensively applied in geometric correction of satellite images and map production. Overfitting is a common issue, in the case of terrain dependent RFMs, that degrades the accuracy of RFMs-derived geospatial products. This issue, resulting from the high number of RFMs’ parameters, leads to ill-posedness of the RFMs. To tackle this problem, in this study, a fast and robust statistical approach is proposed and compared to Tikhonov regularization (TR) method, as a frequently-used solution to RFMs’ overfitting. In the proposed method, a statistical test, namely, significance test is applied to search for the RFMs’ parameters that are resistant against overfitting issue. The performance of the proposed method was evaluated for two real data sets of Cartosat-1 satellite images. The obtained results demonstrate the efficiency of the proposed method in term of the achievable level of accuracy. This technique, indeed, shows an improvement of 50–80% over the TR.
Highlights
Since 1999, High-Resolution Satellite Images have paved the way for extracting detailed and accurate information from our planet and nowadays, with no contest, remotely-sensed images are the main source of information
These methods, which are conceptually similar to Variable Selection, determine the optimum set of parameters which minimize the RMSE over Dependent Control Points (DCPs)
To the best of our knowledge, capability of statistical tests for the prevention of the overfitting issue, in the context of the Rational Function Models (RFMs) has not been addressed in the literature
Summary
Since 1999, High-Resolution Satellite Images have paved the way for extracting detailed and accurate information from our planet and nowadays, with no contest, remotely-sensed images are the main source of information. In addition to the Variable selection and Regularization techniques , methods based on artificial intelligence such as Genetic Algorithm (GA) have been successfully applied to address the overfitting problem (Zoej et al, 2007). These methods, which are conceptually similar to Variable Selection, determine the optimum set of parameters which minimize the RMSE over Dependent Control Points (DCPs). That has a simple concept and low computational burden, uses t-test in a recursive mode to remove those coefficients which are statistically insignificance
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
