Environmentally-adaptive target recognition for SAS imagery

Characteristics of underwater targets displayed in synthetic aperture sonar (SAS) imagery vary depending on their environmental context. Discriminative features in sea grass may differ from the features that are discriminative in sand ripple, for example. Environmentally-adaptive target detection and classification systems that take into account environmental context, therefore, have the potential for improved results. This paper presents an end-to-end environmentally-adaptive target detection system for SAS imagery that performs target recognition while accounting for environmental context. First, locations of interest are identified in the imagery using the Reed-Xiaoli (RX) detector and a Non-Gaussian detector based on the multivariate Laplace distribution. Then, the Multiple Instance Learning via Embedded Instance Selection (MILES) approach is used to identify the environmental context of the targets. Finally, target features are extracted and a set of environmentally-specific k-Nearest Neighbors (k-NN) classifiers are applied. Experiments were conducted on a collection of both high and low frequency SAS imagery with a variety of environmental contexts and results show improved classification accuracy between target classes when compared with classification results with no environmental consideration.

[1]  Xiaoli Yu,et al.  Adaptive multiple-band CFAR detection of an optical pattern with unknown spectral distribution , 1990, IEEE Trans. Acoust. Speech Signal Process..

[2]  Leslie M. Collins,et al.  Exploiting Ground-Penetrating Radar Phenomenology in a Context-Dependent Framework for Landmine Detection and Discrimination , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[3]  Kpalma Kidiyo,et al.  A Survey of Shape Feature Extraction Techniques , 2008 .

[4]  Xiaoxiao Du,et al.  Possibilistic context identification for SAS imagery , 2015, Defense + Security Symposium.

[5]  Leslie M. Collins,et al.  Bayesian Context-Dependent Learning for Anomaly Classification in Hyperspectral Imagery , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[6]  Paul D. Gader,et al.  Adaptive edge histogram descriptor for landmine detection using GPR , 2009, Defense + Commercial Sensing.

[7]  James P. Egan,et al.  Signal detection theory and ROC analysis , 1975 .

[8]  Mahmood R. Azimi-Sadjadi,et al.  Non-Gaussian target detection in sonar imagery using the multivariate Laplace distribution , 2011 .

[9]  Paul D. Gader,et al.  Context dependent hyperspectral subpixel target detection , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[10]  Seniha Esen Yuksel,et al.  Comparison of RX-based anomaly detectors on synthetic and real hyperspectral data , 2015, WHISPERS.

[11]  N. Altman An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression , 1992 .

[12]  Yixin Chen,et al.  MILES: Multiple-Instance Learning via Embedded Instance Selection , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Thomas G. Dietterich,et al.  Solving the Multiple Instance Problem with Axis-Parallel Rectangles , 1997, Artif. Intell..

[14]  J Gazagnaire,et al.  Environmentally-adaptive automated target recognition algorithm using parametric characterization of seabed textures , 2010, OCEANS 2010 MTS/IEEE SEATTLE.

[15]  David P. Williams,et al.  Exploiting Environmental Information for Improved Underwater Target Classification in Sonar Imagery , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[16]  Paul D. Gader,et al.  Context-Dependent Multisensor Fusion and Its Application to Land Mine Detection , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[17]  Chee Sun Won,et al.  Efficient use of local edge histogram descriptor , 2000, MULTIMEDIA '00.

[18]  Chein-I Chang,et al.  Anomaly detection and classification for hyperspectral imagery , 2002, IEEE Trans. Geosci. Remote. Sens..