Ship recognition via its radiated sound: The fractal based approaches

Abstract

Due to the complexity of its radiated sound, ship recognition is difficult. Fractal approaches are proposed in this study, including fractal Brownian motion based analysis, fractal dimension analysis, and wavelet analysis, to augment existing feature extraction methods that are based on spectrum analysis. Experimental results show that fractal approaches are effective. When used to augment two traditional features, line and average spectra, fractal approaches led to better classification results. This implies that fractal approaches can capture some information not detected by traditional approaches alone.

A detailed investigation into low-level feature detection in spectrogram images

“…In practical terms, the problem forms a critical stage in the detection and classification of sources in passive sonar systems, the analysis of speech data and the analysis of vibration data-the outputs of which could be the detection of a hostile torpedo or of an aeroplane engine which is malfunctioning. Applications within these areas are wide and include identifying and tracking marine mammals via their calls [39,36], identifying ships, torpedoes or submarines via the noise radiated by their mechanical movements such as propeller blades and machinery [52,7], distinguishing underwater events such as ice cracking [16] and earth quakes [20] from different types of source, meteor detection, speech formant tracking [47] and so on. Recent advances in torpedo technology has fuelled the need for more robust, reliable and sensitive algorithms to detect ever quieter engines in real time and in short time frames.…”

An active contour algorithm for spectrogram track detection

“…Existing applications cover a wide range and include meteor detection, identifying and tracking marine mammals via their calls (Urazghildiiev and Clark, 2007), identifying noise radiated by mechanical devices (Yang et al, 2002;Chen et al, 2000) and distinguishing events such as ice cracking (Ghosh et al, 1996) and earth quakes (Howell et al, 2003). In the broad sense this "problem arises in any area of science where periodic phenomena are evident and in particular signal processing" (Quinn, 1994).…”

A Multi-scale Piecewise-Linear Feature Detector for Spectrogram Tracks

“…This problem is a critical stage in the detection and classification of sources in passive sonar systems and the analysis of vibration data. Applications are wide ranging and include identifying and tracking marine mammals via their calls [11,10], identifying ships, torpedoes or submarines via the noise radiated by their mechanics [15,2], distinguishing underwater events such as ice cracking [4] and earth quakes [6] from different types of source, meteor detection and speech formant tracking [14].…”