IMPROVEMENT IN ROBUSTNESS OF THE STATISTICALLY INDEPENDENT REGION SNAKE-BASED SEGMENTATION METHOD OF TARGET-SHAPE TRACKING

We propose a technique to increase the robustness of a snake-based seg mentation method originally introduced to track the shape of a target with random white Gaussian intensity upon a random white Gaussian back ground. Because these statistical conditions are not always fulfilled with optronic images, we describe two improvements that increase the f ield of application of this approach. We first show that regularized w hitening preprocessing allows one to apply the original method success fully for a target with a correlated texture upon a correlated backgro und. We then introduce a simple multiscale approach that increases the robustness of the segmentation against the initialization of the snak e (i.e., the initial shape used for the segmentation). These results p rovide a robust and practical method for determination of the referenc e image for correlation techniques. (C) 1998 Optical Society of Americ a.