High-Resolution Sonars: What Resolution Do We Need for Target Recognition?

Abstract

Target recognition in sonar imagery has long been an active research area in the maritime domain, especially in the mine-counter measure context. Recently it has received even more attention as new sensors with increased resolution have been developed; new threats to critical maritime assets and a new paradigm for target recognition based on autonomous platforms have emerged. With the recent introduction of Synthetic Aperture Sonar systems and high-frequency sonars, sonar resolution has dramatically increased and noise levels decreased. Sonar images are distance images but at high resolution they tend to appear visually as optical images. Traditionally algorithms have been developed specifically for imaging sonars because of their limited resolution and high noise levels. With high-resolution sonars, algorithms developed in the image processing field for natural images become applicable. However, the lack of large datasets has hampered the development of such algorithms. Here we present a fast and realistic sonar simulator enabling development and evaluation of such algorithms. We develop a classifier and then analyse its performances using our simulated synthetic sonar images. Finally, we discuss sensor resolution requirements to achieve effective classification of various targets and demonstrate that with high resolution sonars target highlight analysis is the key for target recognition.

Best practices in convolutional networks for forward-looking sonar image recognition

“…A more comprehensive evaluation is provided by Yosinski et al [5]. An evaluation of object size versus recognition accuracy in high-resolution sonars is done by Pailhas et al [6]. Their work uses a sonar image simulator and a simple PCA classifier and the authors conclude that only the highlight of the object is required to obtain low misclassification performance, but their analysis only considers simple mine-like objects, while our dataset contains real world marine debris, which is much more complex in their shape (and often has no shadow).…”

Seafloor identification in sonar imagery via simulations of Helmholtz equations and discrete optimization

“…The source and receiver locations are colocated near the surface of the water, and the strength of the acoustic source is a constant and given by the sonar manufacturer. For sidescan sonars this is typically between 200 − 230 decibels [35]. High frequency signals produce strong scattering from artifacts in the seabed that have variations on the scale of the acoustic wavelength.…”

Dolphin-inspired sonar system and its performance

“…9 displays an example of seabed elevation using a fractal generator based on pink noise. The reader can refer to [37] for more details on the fractal generator where a similar seafloor elevation has been successfully used for synthetic sidescan simulation. The roughness on the seafloor introduces speckle in the reverberation noise.…”