Michael Lee Bryant

Standard SAR ATR Evaluation Experiments using the MSTAR Public Release Data Set

The recent public release of high resolution Synthetic Aperture Radar (SAR) data collected by the DARPA/AFRL Moving and Stationary Target Acquisition and Recognition (MSTAR) program has provided a unique opportunity to promote and assess progress in SAR ATR algorithm development. This paper will suggest general principles to follow and report on a specific ATR performance experiment using these principles and this data. The principles and experiments are motivated by AFRL experience with the evaluation of the MSTAR ATR.

3-D E-CSAR imaging of a T-72 tank and synthesis of its SAR reconstructions

The results of three-dimensional (3-D) imaging of a T-72 tank using its angular azimuthal (turntable) and linear elevation synthetic aperture data at X band are presented. This is achieved using an accurate and computationally efficient wavefront (Fourier-based) reconstruction algorithm for elevation and circular (E-CSAR) data. The E-CSAR 3-D images are then used to synthesize 2-D spotlight and stripmap slant plane synthetic aperture radar (SAR) images of the target at a desired range and squint angle. For this purpose, a procedure is introduced that incorporates the spatially varying azimuthal and elevation Doppler signatures of individual reflectors on the target as well as the mean range, azimuth, and elevation of the flight path. Results using the E-CSAR images of the T-72 tank are provided.

A challenge problem for SAR-based GMTI in urban environments

This document describes a challenge problem whose scope is the detection, geolocation, tracking and ID of moving vehicles from a set of X-band SAR data collected in an urban environment. The purpose of releasing this Gotcha GMTI Data Set is to provide the community with X-band SAR data that supports the development of new algorithms for SAR-based GMTI. To focus research onto specific areas of interest to AFRL, a number of challenge problems are defined. The data set provided is phase history from an AFRL airborne X-band SAR sensor. Some key features of this data set are two-pass, three phase center, one-foot range resolution, and one polarization (HH). In the scene observed, multiple vehicles are driving on roads near buildings. Ground truth is provided for one of the vehicles.

SVM classifier applied to the MSTAR public data set

Support vector machines (SVM) are one of the most recent tools to be developed from research in statistical learning theory. The foundations of SVM were developed by Vapnik, and are gaining popularity within the learning theory community due to many attractive features and excellent demonstrated performance. However, SVM have not yet gained popularity within the synthetic aperture radar (SAR) automatic target recognition (ATR) community. The purpose of this paper is to introduce the concepts of SVM and to benchmark its performance on the Moving and Stationary Target Acquisition and Recognition (MSTAR) data set.

Class separability assessments and MSE algorithm robustness

Operational Synthetic Aperture Radar (SAR) based automatic target recognition (ATR) systems will encounter a wide range of target types, some of which will be variants of pre- mission training targets. Previous work measured classification performance when training and testing on different vehicle variants and assessed intra-class separability based on an empirical estimate of the mean square error (MSE) probability density function. This research showed a significant degree of intra-class signature variability for selective targets, resulting in a difficult ATR problem. The benefits of using mixture templates were demonstrated with respect to classification performance as well as pose prediction. This paper extends this analysis by considering the signature variability attributed to extended operating conditions such as depression angle and articulation. Furthermore, it demonstrates improved performance robustness is possible using an MSE classifier with appropriate normalization and segmentation. Additionally, a simple technique for minimizing the impact of localized error sources on MSE algorithms is discussed. Finally, error surfaces associated with missed classifications are shown to b similar in both space and amplitude, suggesting finer target discrimination may require improved feature sets and or adaptive refinement algorithms for handling both deterministic and random error sources associated with the observation to template.

Robust non-negative matrix factorization for joint spectrum sensing and primary user localization in cognitive radio networks

In this paper, a novel approach based on non-negative matrix factorization is applied for joint spectrum sensing and primary user localization in cognitive radio networks. This approach is robust and tolerant to sparse, yet strong interference caused by malicious attack or false data injection. Simulation results clearly indicate that the proposed method is highly effective in yielding low localization error for various strengths and degrees of sparsity of interferer. It is also shown that the localization performance significantly increases with the number of cognitive radios deployed.

Multisensor staring exploitation

The focus of this paper is on the exploitation of new staring sensors to address the urban surveillance challenge and help combat the war on terror. A staring sensor visualization environment, known as the Data Table, will be presented which integrates staring sensors with close-in sensors, such as small UAVs, building mounted sensors, and unattended ground sensors (UGS). There are several staring sensors in development, but two in particular will be highlighted in this paper - NightStare and the Gotcha Radar, both under development by the Air Force Research Laboratory (AFRL).

Target signature manifold methods applied to MSTAR dataset: preliminary results

The primary contribution of this paper is to demonstrate the application of signature manifold methods on the MSTAR data. Three manifold estimation methods (FIR, FFT, and Kalman smoothing) are compared to a baseline algorithm, MSE. The preliminary results show the manifold methods perform just as well as the baseline algorithm and have the potential for increased performance. In addition, both GLRT and Bayes hypothesis test algorithms are demonstrated for all of the manifold estimation algorithms.

Multi-path SAR change detection

Synthetic aperture radar (SAR) is a form of imaging radar. The defining characteristic of SAR is the usage of relative motion between an antenna and its target region to provide long-term coherent-signal variations that can be exploited to obtain fine spatial resolution for radar image. Due to the improvement of SAR data acquisition technique and the flexibility of SAR sensor deployment, multi-pass SAR imageries can be easily obtained. More information and intelligence can be extracted from SAR imageries. This paper will address one challenging issue for SAR data fusion, i.e. multi-pass SAR change detection. Two methods are proposed in this paper to perform multi-pass SAR change detection. One method is based on robust principal component analysis (PCA) and the other method uses template matching plus thresholding. Both methods explore the local statistics to indicate the change of each pixel in the SAR imageries. The visualization performances illustrate the potential of these two methods for the issue of SAR change detection.

Three-dimensional E-CSAR imaging of a T-72 tank and synthesis of its spotlight, stripmap and interferometric SAR reconstructions

This paper presents the results of three-dimensional imaging of a T-72 tank using its angular azimuthal (turntable) and linear elevation synthetic aperture data at X band. This is achieved using an accurate and computationally-efficient wavefront (Fourier-based) reconstruction algorithm for elevation and circular (E-CSAR) data. The E-CSAR 3D images are then used to synthesize 2D spotlight and stripmap slant plane SAR images of the target at a desired range and squint angle. For this purpose, a procedure is introduced that incorporates the spatially-varying azimuthal and elevation Doppler signatures of individual reflectors on the target as well as the mean range, azimuth and elevation of the flight path. Results using the E-CSAR images of the T-72 tank are provided.