Dan E. Dudgeon

Use of persistent scatterers for model-based recognition

The signature of a target imaged by a millimeter-wave SAR is highly variable. Various viewing angles will cause different scattering centers to be illuminated, the returns from which can vary greatly with minor changes in viewing angle, and the coherence of the radiation induces speckle noise. Using fully polarimetric turntable (inverse SAR) data, we have undertaken some basic investigations of the persistence of scatterers as a function of azimuth for a number of depression angles from 15 degrees to 32 degrees. Although many scatterers persist for only a few degrees of azimuth, enough persist for 10 to 20 degrees to make model-based recognition feasible. Based on these results, we have developed an experimental system for target recognition. The system uses the functional template approach for detection, pose estimation, and initial hypothesis ranking. The best-matching template defines an area where so-called bright-points are extracted, resulting in a binary feature map that shows the location of strong scatterers. Back-end recognition consists of matching these feature maps to target appearance models that capture the location of scatterers that produce strong returns and are sufficiently persistent with changes in viewing angle. The performance of the hypothesis generation via functional templates is briefly reviewed, both for ISAR data and for SAR data. Recognition results obtained with the new back-end recognition system are also presented for the case of ISAR data.

The existence of cepstra for two-dimensional rational polynomials

The use of cepstral analysis is helpful for some problems where two one-dimensional signals are combined by convolution [1]. In such problems it is important to ensure that the phase function associated with the resultant signal may be defined so that it is a continuous, odd, and periodic function of frequency [2], [3]. One class of one-dimensional signals which have this property is the class whose z-transforms are rational polynomials [2]. In this correspondence, we shall show that these results are extendible to two dimensions, and that 2-D cepstra can be defined for 2-D rational polynomials.

Model-based system for automatic target recognition from forward-looking laser-radar imagery

We describe an experimental model-based automatic target recognition (ATR) system, called XTRS, for recognizing 3-D vehicles in real or synthetic, ground-based or airborne, 2-D laser-radar range and intensity images. The key to recognition is a new generic matching engine that compares image events (e.g., silhouettes) and their constituent primitives to some appearance-model (AM) hierarchy , which describes how 3-D, possibly articulated, objects appear in the imagery. We describe each of the systems components, i.e., the event characterization (for extracting events from images and decomposing the events into primitives), the models, the matching, and the control. XTRS may also perform low-level information fusion by constructing feature-indicating interest images and combining them into an overall interest image used for locating an event. Examples of processing and performance results are given for real CO 2 ground-based laser-radar imagery. We also report on a performance evaluation of XTRS based on synthetic data where important parameters (e.g., range to target) are systematically varied. Overall, more than 1500 range and intensity image pairs have been used throughout the development of XTRS.

Functional templates and their application to 3-D object recognition

A new approach to shape matching and knowledge-based signal processing, called functional template correlation (FTC), is presented in the context of 3D object recognition. Incorporating aspects of fuzzy set theory, functional templates (FTs) define, for each template point, arbitrarily complex tolerances of input image values. With this approach, object- and sensor-dependent knowledge is easily encoded in FTs, making it possible to effectively deal with uncertain or variable object appearance noise occlusion, and articulation. The output of FTC is a map of match scores, reflecting pixel-by-pixel belief of whether or not an encoded shape is present. Such maps can be combined using simple rules of arithmetic and are used to guide selective attention. The use of FTC is illustrated with examples from work in automatic recognition.<<ETX>>

ATR Performance Modeling and Estimation

Dudgeon, Dan E., ATR Performance Modeling and Estimation, Digital Signal Processing10 (2000), 269?285.This paper provides an overview of approaches and issues in modeling the performance of automatic target recognition (ATR) systems. The need to understand ATR performance capability is important under circumstances in which significant testing is not possible, for example, because of the amount of data required to be collected to accurately assess performance and its associated cost or because of denied targets and ground environments. One would like to have a “theory” to extrapolate ATR performance from a well-characterized set of data to situations likely to be confronted in real military operations. Unfortunately no such theory exists, in part because of the difficulty of characterizing and representing in a computational model the inherent variability of target signatures and the backgrounds in which they are embedded.

Wideband Array Processing For Acoustic Detection and Tracking Of Aircraft/sup */

The Distributed Sensor Network Program, sponsored by DAFPA, has as its goal the development of technology to enable the construction of defensive systems of geographically separated sensors and distributed computational resources. In general such a system would consist of autonomous nodes that would work cooperatively to detect and track targets of interest and would report interesthg situations to a user (or set of users) through some interface. Each node would consist of appropriate sensors and processors (hardware and software) to permit it to perform some tasks independently of other nodes and communications to permit it t o work cooperatively with other nodes to form a viable distributed system.

An experimental target recognition system for airborne laser radar imagery

An experimental target recognition system (XTRS) for detecting and recognizing target vehicles in laser radar imagery is discussed. XTRS is a model-based system with four major processing stages; detection, extraction, decomposition, and matching. Recognition decisions are made by comparing image features and their spatial relationships to a hierarchical library of target appearance models. Laser radar sensors and the imagery they produce are briefly described. XTRS and its processing stages are described. System performance on several data sets is discussed

New Technique For Blind Deconvolution

Frequently an image may be blurred by a point spread function whose details are not known exactly. In such a case, it is necessary to estimate the point spread function before deconvolving the blurred image. This paper presents a new technique for estimating a zero phase blurring function when its optical transfer function is smooth. The estimate is obtained by smoothing the spectral magnitude of the image and comparing it to an average magnitude that is also smoothed. The average magnitude is obtained by averaging over an ensemble of similar images. The estimate can be extended to degradations such as a defocused lens by thresholding the estimation magnitude to obtain zero crossings and adjusting the phase accordingly. In particular, this technique can be applied to a circularly symmetric Gaussian blur or a defocused lens with a circular aperture.

Model-based system for automatic target recognition

An experimental model-based automatic target recognition (ATR) system, XTRS, for recognizing 3-D vehicles in real or synthetic, groundbased or airborne, 2-D laser-radar range and intensity images is discussed. The key to recognition is a new generic matching engine that compares image events (e.g., silhouettes) and their constituent primitives to some appearance-model (AM) hierarchy, which describes how 3-D--possibly articulated--objects appear in the imagery. The authors describe each of the systems components; i.e., the even characterization (for extracting events from images and decomposing the events into primitives), the models, the matching, and the control. XTRS may also perform low-level information fusion by constructing feature-indicating interest images and combining them into an overall interest image used for locating an event. Examples of processing and performance results are given for real CO2 groundbased laser-radar imagery. The authors also report on a performance evaluation of XTRS based on synthetic data where importance parameters (e.g., range to target) are systematically varied. Overall, more than 1500 range and intensity image pairs have been used throughout XTRSs development.

Silhouette understanding system

Range images obtained from infrared ranging sensors often provide detailed silhouettes of objects in the field of view. Elements of a system for extracting and analyzing such range silhouettes are proposed. The effectiveness of the system implemented so far is demonstrated on real data. The other elements of the ultimate system are also discussed, but, only at a conceptual level.