banner image
No data available.
Please log in to see this content.
You have no subscription access to this content.
No metrics data to plot.
The attempt to load metrics for this article has failed.
The attempt to plot a graph for these metrics has failed.
Acoustic identification of buried underwater unexploded ordnance using a numerically trained classifier (L)
Rent this article for
View: Figures


Image of FIG. 1.
FIG. 1.

Diagram of the experimental setup used for the measurements in the sediment pool facility. A broadband, spherical source is positioned directly above, and 1.25 m from, the target buried 10 cm into the sediment. A 2D receive array is generated synthetically by scanning a single hydrophone over a 1 m × 1 m patch 20 cm above the sediment surface in 3 cm steps. The six targets shown are buried one at a time below the array center.

Image of FIG. 2.
FIG. 2.

The computed broadband plan view local scattering strength images (center column) and the narrowband nearfield target strength maps (right column) for the four depicted rocket burial angles (left column). The two dashed lines are separated by 10 cm.

Image of FIG. 3.
FIG. 3.

The probability color map for the RVM algorithm generatively trained using the features derived from the STARS3D simulations for the 90 rocket burial angles. The contours are the various decision boundaries: 0.5 probability (black) and 0.8 and 0.2 probabilities (dashed gray). The inset depicts the range (not the step) of target burial angles for the simulations.

Image of FIG. 4.
FIG. 4.

RVM testing using the sediment pool buried target measurements. The target features are derived from the measured time signals for the six buried targets as depicted by the inset: rocket buried 90° (dark blue); rocket buried 120° (light blue); rocket buried 150° (green); cinder block buried 90° (fuchsia); rock (yellow); cinder block rolled 45° buried 90° (orange).


Article metrics loading...


Full text loading...

This is a required field
Please enter a valid email address
752b84549af89a08dbdd7fdb8b9568b5 journal.articlezxybnytfddd
Scitation: Acoustic identification of buried underwater unexploded ordnance using a numerically trained classifier (L)