Abstract
Detection of buried underwater objects, and especially mines, is a current crucial strategic task. Images provided by sonar systems allowing to penetrate in the sea floor, such as the synthetic aperture sonars (SASs), are of great interest for the detection and classification of such objects. However, the signal-to-noise ratio is fairly low and advanced information processing is required for a correct and reliable detection of the echoes generated by the objects. The detection method proposed in this paper is based on a data-fusion architecture using the belief theory. The input data of this architecture are local statistical characteristics extracted from SAS data corresponding to the first-, second-, third-, and fourth-order statistical properties of the sonar images, respectively. The interest of these parameters is derived from a statistical model of the sonar data. Numerical criteria are also proposed to estimate the detection performances and to validate the method.
Highlights
Detection and classification of different kinds of underwater mines are crucial strategic tasks
It basically consists in locally estimating the higher-order statistics (HOSs) on a square sliding window (Figure 4(b) where all the objects of interests are framed by high values of the kurtosis, the size of the frame being linked to the size of the computation window)
These images are combined using the orthogonal rule in order to obtain the mass images associated to each proposition (Figure 16)
Summary
Detection and classification of different kinds of underwater mines are crucial strategic tasks. Many methods have been proposed to reach this goal: filters enhancing echoes before a selection of the pixels of high value [3], making use of several parameters (mean, variance, lacunarity, etc.) that are locally estimated on the image [4, 5], or searching for outlines including one or several echoes [6, 7]. After this location, the second step consists in extracting several statistical or morphological parameters from the selected regions.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have