Performance of region-based matching techniques to compute the ocean surface motion

The study of the ocean circulation is the central core of all dynamical oceanography. The routine derivation of sea surface temperature or infrared brightness temperatures has been used to estimate the surface circulation by calculating the motion of the thermal features (coastal upwellings, filaments and eddies) in successive images. To that respect, a number of authors have developed different methodologies to recover the motion field, but the most straightforward methods match patterns (points, borders or regions) in all possible subwindows of one image with those in the next image. The maximization of the normalized crosscorrelation coefficient, known as the Maximum Cross-Correlation (MCC) technique, is the most popular region-based matching metric applied to compute ocean circulation. In this paper a careful analysis of different region matching techniques has been conducted and the performance achieved for each approach is presented. The assessment methodology uses a database of synthetic sequences, real sequences and in-situ speed measurements. After the qualitative and quantitative analysis, we can conclude that the best performance is achieved by ZSAD, ZSSD, NZSSD and NCC metrics. These metrics achieve, when applied to synthetic sequences, mean angular errors around 30° and magnitude errors around 30% for the worst case. In general the flow field recovered by the 4 previous metrics, perfectly models the motion of the structures in real sequences. Finally, results obtained with comparison with ground-truth data suggest an underestimation in the computed velocity between 35%–45% but with a higher angular accuracy, achieving global errors around 30°–50°. To conclude, it is important to emphasize that the prevalent MCC method provides acceptable results but with more errors when compared with the four previous metrics over the three databases.