Abstract
Abstract. Least squares image matching (LSM) has been extensively applied and researched for high matching accuracy. However, it still suffers from some problems. Firstly, it needs the appropriate estimate of initial value. However, in practical applications, initial values may contain some biases from the inaccurate positions of keypoints. Such biases, if high enough, may lead to a divergent solution. If all the matching biases have exactly the same magnitude and direction, then they can be regarded as systematic errors. Secondly, malfunction of an imaging sensor may happen, which generates dead or stuck pixels on the image. This can be referred as outliers statistically. Because least squares estimation is well known for its inability to resist outliers, all these mentioned deviations from the model determined by LSM cause a matching failure. To solve these problems, with simulation data and real data, a series of experiments considering systematic errors and outliers are designed, and a variety of robust estimation methods including RANSACbased method, M estimator, S estimator and MM estimator is applied and compared in LSM. In addition, an evaluation criterion directly related to the ground truth is proposed for performance comparison of these robust estimators. It is found that robust estimators show the robustness for these deviations compared with LSM. Among these the robust estimators, M and MM estimator have the best performances.
Highlights
Image matching is an active research field in digital photogrammetry and computer vision
According to Taylor linearization based on the intensity in the patch, cannot appropriately fit the model determined by least squares image matching (LSM), LSM will not converge to a correct solution, causing mismatches in the end
It can be illustrated from the results that with the increase of systematic errors, the success rates of all the estimation methods generally have decreasing trends, it is interesting to find that the success rate slightly increases when the systematic error changes from 0.5 pixel to 1 pixel on M estimator in Table 6, which shows the robust estimators’ resistance for outliers
Summary
Image matching is an active research field in digital photogrammetry and computer vision. If the deviation is not large enough, there will be a tiny influence on the final result If it is sizable, it can be identified as an outlier, causing masking and swamping effect, it will affect the final solution for linear or nonlinear estimations. Knight and Wang (2009) made the comparison of robust estimators on simulated GPS measurements in terms of the ability of outlier exclusion They demonstrated that no method could correctly exclude all the outliers.
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
