David H. Kil

Integrated approach to bandwidth reduction and mine detection in shallow water with reduced-dimension image compression and automatic target recognition algorithms

In distributed underwater signal processing for area surveillance and sanitization during regional conflicts, it is often necessary to transmit raw imagery data to a remote processing station for detection-report confirmation and more sophisticated automatic target recognition (ATR) processing. Because of he limited bandwidth available for transmission, image compression is of paramount importance. At the same time, preservation of useful information that contains essential signal attributes is crucial for effective mine detection and classification in shallow water. In this paper, we present an integrated processing strategy that combines image compression and ATR algorithms for superior detection performance while achieving maximal bandwidth reduction. Our reduced-dimension image compression algorithm comprises image-content classification for the subimage-specific transformation, principal component analysis for further dimension reduction, and vector quantization to obtain minimal information state. Next, using an integrated pattern recognition paradigm, our ATR algorithm optimally combines low-dimensional features and an appropriate classifier topology to extract maximum recognition performance from reconstructed images. Instead of assessing performance of the image compression algorithm in terms of commonly used peak signal-to-noise ratio or normalized mean-squared error criteria, we quantify our algorithm performance using a metric that reflects human and operational factors - ATR performance. Our preliminary analysis based on high-frequency sonar real data indicates that we can achieve a compression ratio of up to 57:1 with minimal sacrifice in PD and PFA. Furthermore, we discuss the concept of the classification Cramer-Rao bound in terms of data compression, sufficient statistics, and class separability to quantify the extent to which a classifier approximates the Bayes classifier.

Target characterization using hidden Markov models and classifiers

Abstract : We investigate various projection spaces and extract key parameters or features from each space to characterize low-frequency active (LFA) target returns in a low-dimensional space. The projection spaces encompass (1) time embedded phase map, (2) segmented matched filter output, (3) various time frequency distribution functions, such as Reduced Interference Distribution, to capture time-varying echo signatures, and (4) principal component inversion for signal cleaning and characterization. We utilize both dynamic and static features and parameterize them with a hybrid classification methodology consisting of hidden Markov models, classifiers, and data fusion. This clue identification and evaluation process is complemented by concurrent work on target physics to enhance our understanding of the target echo formation process. As a function of target aspect, we can observe (1) back scatter dominated by axial n=O modes propagating back and forth along the length of the shell, (2) direct scatter from shell discontinuities, (3) helical or creeping waves from phase matching between the acoustic waves and membrane waves (both shear and compressional), and (4) the array response of the shell, with coherent super- position of elemental scattering sites along the shell leading to a peak response near broadside. As a function of target structures (the empty shell and the ribbed/complex shells), we see considerable complexity brought about by multiple reflections of the membrane waves between the rings. We show the merit of fusing parameters estimated from these projection spaces in characterizing LFA target returns using the MIT/NRL scaled model data. Our hybrid classifiers outperform the matched filter-based recognizer by an average of 5 to 25%.

Bandwidth reduction of high-frequency sonar imagery in shallow water using content-adaptive hybrid image coding

One of the biggest challenges in distributed underwater mine warfare for area sanitization and safe power projection during regional conflicts is transmission of compressed raw imagery data to a central processing station via a limited bandwidth channel while preserving crucial target information for further detection and automatic target recognition processing. Moreover, operating in an extremely shallow water with fluctuating channels and numerous interfering sources makes it imperative that image compression algorithms effectively deal with background nonstationarity within an image as well as content variation between images. In this paper, we present a novel approach to lossy image compression that combines image- content classification, content-adaptive bit allocation, and hybrid wavelet tree-based coding for over 100:1 bandwidth reduction with little sacrifice in signal-to-noise ratio (SNR). Our algorithm comprises (1) content-adaptive coding that takes advantage of a classify-before-coding strategy to reduce data mismatch, (2) subimage transformation for energy compaction, and (3) a wavelet tree-based coding for efficient encoding of significant wavelet coefficients. Furthermore, instead of using the embedded zerotree coding with scalar quantization (SQ), we investigate the use of a hybrid coding strategy that combines SQ for high-magnitude outlier transform coefficients and classified vector quantization (CVQ) for compactly clustered coefficients. This approach helps us achieve reduced distortion error and robustness while achieving high compression ratio. Our analysis based on the high-frequency sonar real data that exhibit severe content variability and contain both mines and mine-like clutter indicates that we can achieve over 100:1 compression ratio without losing crucial signal attributes. In comparison, benchmarking of the same data set with the best still-picture compression algorithm called the set partitioning in hierarchical trees (SPIHT) reveals that some weak targets can completely disappear in certain situations because SPIHT is not content adaptive.

Development of a web-centric virtual prototyping environment for shallow-water mine countermeasures using the Internet paradigm

In shallow-water mine countermeasure, the objective is to find underwater mines with consistently high PD and low PFA in diverse environmental conditions. In order to achieve this goal in a cost-effective manner, we are developing a Web-centric virtual prototyping environment that consists of various tools to make algorithm development and performance analysis as seamless as possible. Furthermore, by making algorihrtm toolboxes available for download at the project Web site, we are involving end users in the development cycle in an attempt to improve the utility and functionality of the toolboxes. This approach focuses on community collaboration and uses the Internet as a communications medium, i.e., open-source software development paradigm. We envision the virtual prototyping environment to eventually address the entire operating spectrum form algorithm development to real-time implementation by concatenating complementary toolboxes and hosting various services at a Web data center. The advantages of this approach are more cost-effective algorithm development, facilitation of accurate performance comparison between existing and new algorithms, and minimization of performance ambiguity through the use of tap points and visual information presentation. Perhaps the biggest advantage is that the environment allows researchers to spend more time on creative aspects of algorithm development and less time on mundane parts.

Sonar Target Recognition

The sections in this article are n n n1 nIntegrated Sonar ATR Processing n n2 nReal-World Experiments n n3 nEmerging Technologies in Sonar Target Recognition n n4 nAcknowledgment