Buried Underwater Object Classification Using a Collaborative Multi-Aspect Classifier

2009

IEEE J. Oceanic Eng.

Abstract-In this paper, a new collaborative multiaspect classification system (CMAC) is introduced, which utilizes a group of collaborative decision-making agents capable of producing a highconfidence final decision based on features obtained over multiple aspects. It is also shown how CMAC can be modified to perform multiaspect classification using a decision feedback (DF) strategy. The system is then applied to a buried underwater target classification problem. The results show that CMAC provides excellent multiple-ping classification of mine-like objects while reducing the number of false alarms compared to other multiple-ping classification fusion systems such as nonlinear decision-level fusion (DLF).

Section: Discussionmentioning

confidence: 99%

Buried Underwater Object Classification Using a Collaborative Multiaspect Classifier

Cartmill

Wachowski

2009

IEEE J. Oceanic Eng.

“…The problem of underwater object classification in sonar imagery has recently attracted a substantial amount of attention [1][2][3][4][5][6]. This problem is rather complicated due to the numerous factors which inhibit repeatable and reliable ATR.…”

Section: Problem Statement and Motivationsmentioning

confidence: 99%

“…Moreover, it was shown that under fixed operating conditions, canonical correlation features are relatively invariant to changes in aspect angle. New feature and decision-level fusion algorithms were also developed in [12] and [3] using a hidden Markov model (HMM) and a Collaborative…”

Section: Literature Review On Underwater Target Classificationmentioning

confidence: 99%

“…This is due to the fact that the multi-aspect processing yields substantial improvements in performance, resolution, and sensing of the properties of the object in a non-isotropic environment. Inspired by these desired properties, two different general frameworks were developed in [2,5,12,43]. The framework in [2,43] is based upon the idea of multi-aspect feature extraction that uses the two-channel canonical coordinate decomposition method [11] to extract robust features with maximum coherence (or mutual information) from pairs of sonar pings with certain separation.…”

Section: Future Workmentioning

confidence: 99%

“…Inspired by these desired properties, two different general frameworks were developed in [2,5,12,43]. The framework in [2,43] is based upon the idea of multi-aspect feature extraction that uses the two-channel canonical coordinate decomposition method [11] to extract robust features with maximum coherence (or mutual information) from pairs of sonar pings with certain separation. The idea is that the coherence pattern extracted from the UXO objects differ from those of the non-UXO objects, hence aiding the overall classification process.…”

Section: Future Workmentioning

confidence: 99%

See 2 more Smart Citations

Underwater UXO classification using Matched Subspace Classifier with synthetic sparse dictionaries

Hall

OCEANS 2016 MTS/IEEE Monterey

Kargl

2016

Self Cite

UNDERWATER UXO CLASSIFICATION USING MATCHED SUBSPACE CLASSIFIER WITH SYNTHETIC SPARSE DICTIONARIESClassification of underwater objects such as unexploded ordnances (UXO) and mines from sonar datasets poses a difficult problem. Among factors that complicate classification of these objects are: variations in the operating and environmental conditions, presence of spatially varying clutter, variations in target shape, composition, orientation and burial conditions. Furthermore, collection of large quantities of real and representative data for training and testing in various background conditions is very difficult and impractical in many cases. In order to remedy the lack of data availability, physical models of varying computational complexity are often used to supplement training databases with synthetically created samples which predict the response of known target models.In this thesis, we try to address several key questions for designing robust classifiers for UXO and munitions classification from low frequency sonar. These include: (1) "How can we form discriminative and highly separable features for describing UXO and non-UXO objects in a given dataset?", (2) "When do we reach a point of diminishing returns when utilizing synthetic models in a classifier's training?", and more importantly (3) "Which types of object variations cannot be modeled well by synthetic data?". Although, it may be somewhat ambitious to expect model data to capture all the essential features of proud or buried underwater objects for target characterization, these models can nevertheless provide us with clues on how to augment the training datasets to improve the robustness in different environmental conditions.ii Using empirically validated scattering models developed by University of Washington's Applied Physics Laboratory (APL-UW), fast ray models were acquired to generate the required synthetic training dataset for various UXO and non-UXO objects. A comprehensive analysis is then carried out on the classification performance of two subspace matching classifiers, trained on the synthetic data generated from this physical model, and tested on three real underwater sonar datasets. Both single and multi-aspect classification were considered using a combination of linear subspace models. Our classification hypothesis is that the spectral content of sonar backscatter display unique signatures providing good discrimination between different classes of objects. To develop a robust target classification method that can be applied to discriminate munitions from non-hostile man-made objects and competing natural clutter, the Matched Subspace Classifier (MSC) framework was adopted in conjunction with multidimensional Acoustic Color (AC) feature data extracted from raw sonar returns.Classification results of the MSC system constructed using two different signal subspace learning methods, namely K-SVD and locality preserving (LP) K-SVD are presented and benchmarked against each other. Additionally, a non-linear version of MSC using the...

A likelihood-based decision feedback system for multi-aspect classification of underwater targets

Wachowski

2009 International Joint Conference on Neural Networks

2009

Self Cite

This paper presents a new method for multiaspect/ping classification of underwater objects using sonar data. This system uses decision feedback to form a likelihood ratio for making a high confidence final decision based not only upon the data of the current ping but also the final decisions made at several previous pings. The system is then applied to an underwater target classification problem. Test results on a buried object scanning sonar (BOSS) database collected for different objects and in different conditions show the promise of the proposed method for multi-aspect underwater target discrimination.