Abstract-The undersea survey mission performed with a side scan sonar system can generate large volumes of data. Automating the detection and classification process using automated target recognition (ATR) is desirable to reduce post processing times and manning requirements. Traditionally ATR algorithms are trained using image exemplars representing the intended target, false targets and the expected operating environment. However, given the variability of the undersea environment, training a single ATR on all environments may degrade performance when operating in a specific environment, since operating thresholds are fixed. In this paper, we propose an ATR algorithm that changes its operating thresholds based on seabed texture parameter estimates of the sonar image statistics. A large set of sonar images with targets inserted at various ranges and orientations against various backgrounds was synthesized. The environmentally-adaptive ATR algorithm was trained on these specific environments and the optimal classification thresholds were stored in a look-up table (LUT). Upon encountering a novel test pattern, the environmental parameters of the sonar image texture are estimated and then used to index the LUT for the appropriate ATR operating threshold. Using this methodology, we show a performance increase for an adaptive ATR that encounters variable seabed environments versus an ATR algorithm with fixed operating thresholds trained with sonar images representative of a wide variety of environments.
There is a desire in the Mine Counter Measure community to develop a systematic method to predict and/or estimate the performance of Automatic Target Recognition (ATR) algorithms that are detecting and classifying mine-like objects within sonar data. Ideally, parameters exist that can be measured directly from the sonar data that correlate with ATR performance. In this effort, two metrics were analyzed for their predictive potential using high frequency synthetic aperture sonar (SAS) images. The first parameter is a measure of contrast. It is essentially the variance in pixel intensity over a fixed partition of relatively small size. An analysis was performed to determine the optimum block size for this contrast calculation. These blocks were then overlapped in the horizontal and vertical direction over the entire image. The second parameter is the one-dimensional K-shape parameter. The K-distribution is commonly used to describe sonar backscatter return from range cells that contain a finite number of scatterers. An Ada-Boosted Decision Tree classifier was used to calculate the probability of classification (Pc) and false alarm rate (FAR) for several types of targets in SAS images from three different data sets. ROC curves as a function of the measured parameters were generated and the correlation between the measured parameters in the vicinity of each of the contacts and the ATR performance was investigated. The contrast and K-shape parameters were considered separately. Additionally, the contrast and K-shape parameter were associated with background texture types using previously labeled high frequency SAS images.
A modeling tool for 3-D Forward-Look Sonar (3-D-FLS) or equivalent has been developed. The model replicates the entire process of a 3-D Forward-Look sonar generating a 3-D image of a target. The 3-D-FLS operates at a central frequency of 225 kHz and has a range of 100 m. The transmitted signal is a frequency-modulated chirp with 30 kHz of bandwidth. The source is a line array and the projector is a 64-element line array. Ray theory is used to calculate the trajectory of the rays. The model takes sound velocity profiles into account. The reverberation levels due to the sea bottom and sea surface are calculated using Kuos model. Targets of various shapes and sizes are modeled as a collection of reflecting data points. The target strengths of each point on a specific target are assumed equal. The final product is a modeling tool which can be used to define the sonar hardware and processing software necessary to achieve various operational needs. Simulated results are validated using 3-D-FLS data collected during several at-sea experiments.
Synthetic aperture sonar (SAS) provides the best opportunity for side-looking sonar mounted on unmanned underwater vehicles to achieve high-resolution images at longer ranges. However, SAS processing requires maintaining a coherent phase history over the entire synthetic aperture, driving strict constraints on resolvable platform motion. This has driven the development of motion estimation and compensation techniques that use the received ping data, in addition to the onboard navigation solution, to resolve ping-to-ping platform motion. The most common approach is to use the redundant phase center technique. Here the ping interval is set, such that a portion of the array is overlapped. The accuracy of the motion estimation depends on the accuracy of the time delay estimation between the data received on the overlapping channels. Given the stochastic nature of the operational environment some level of decorrelation between these two signals is likely, even without residual platform motion. This decorrelation results in inaccurate time delay estimation and image quality degradation. In this research various preprocessing techniques have been applied to the sonar data to reduce the influence of stochastic noise with the goal of improving the accuracy of the time delay estimates.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.