Seafloor Description in Sonar Images Using the Monogenic Signal and the Intrinsic Dimensionality

In a mine warfare context, the performance of automatic target recognition (ATR) algorithms depends on the environment. Globally, minelike textures and regions with high clutter density increase the false alarm rate. Thus, the environment must be considered as information that can be used to define robust ATR or at least to give a level of confidence in the results according to the seafloor environment. Previous works dealing with this objective have led to the description of the seafloor in terms of anisotropy and complexity. Following these approaches, in this paper, we propose a new definition of these features for describing the seafloor in sonar images. It is based on the monogenic representation of the images and the continuous intrinsic dimensionality (ciD). The monogenic signal, which is the multidimensional extension of the analytic signal, provides an orthogonal separation between energetic, geometric, and structural information of the image in a multiscale framework. The ciD provides information on 2-D geometric structures in the image. The resulting method leads to continuous values giving a confidence degree in relation to three features: the homogeneity, the anisotropy, and the complexity. Several data sets from different sonar systems are used to show the potential of our approach. They also show the ability of the method to deal with different image sources without changing or recalibrating the number of parameters.