Reconfigurable computing obtains its performance advantage over fixed processors by creating hardware configurations specialized for a particular application. In some cases this advantage can be pushed even further, by creating hardware specialized to a particular instance of an application. For many problems where this approach is applicable, such as automatic target recognition, template matc...

The implementation of computational systems to perform challenging operations often involves balancing the performance specification, system throughput, and available system resources. For problems of automatic target recognition (ATR), these three quantities of interest are the probability of classification error, the rate at which regions of interest are processed, and the capabilities of the...

We present a method for estimating classi cation performance of a model-based synthetic aperture radar (SAR) automatic target recognition (ATR) system. Target classi cation is performed by comparing a feature vector extracted from a measured SAR image chip with a feature vector predicted from a hypothesized target class and pose. The feature vectors are matched using a Bayes likelihood metric t...

A phenomenon of thermal radiation of real objects is used in systems of automatic target recognition (ATR). To develop effective algorithms, it is essential to know both radiation characteristics of the detected objects and characteristics of their surroundings. The paper presents a method of numerical modeling of clouds radiation and their environment in IR range. Experimental data registered ...

The ladar range image has received considerable attentions in the automatic target recognition field. However, previous research does not cover target recognition using log-polar ladar range images. Therefore, we construct a target recognition system based on log-polar ladar range images in this paper. In this system combined moment invariants and backpropagation neural network are selected as ...

Correlation tracking is used in civilian and military automatic target recognition and surveillance systems, to track objects based on their 2-dimensional shape. However traditional correlation-tracking systems have difficulty robustly detecting an object when the object is partially obscured by clutter. This paper describes one of the main problems of image-based correlation tracking systems, ...

Mechanical systems or robots to assist landmine detection are expected to greatly improve quality of humanitarian demining tasks. These new systems could provide: i) safer operation; ii) advanced methods for automatic target recognition and discrimination; iii) consistent performance with less influence of “human-factors”; iv) better detection performance, i.e., higher probability of detection ...

Recognition of occluded objects in synthetic aperture radar SAR images is a signi cant problem for automatic target recognition Stochastic models provide some attractive features for pattern matching and recognition under partial occlusion and noise In this paper we present a discrete hidden Markov modeling HMM based approach for recognizing objects in synthetic aperture radar SAR images We ide...

In this paper we present a fuzzy system based hyperspectral classi®er for automatic target identi®cation. The system is based on partitioning the spectral band space into clusters using a modi®ed fuzzy C-Means clustering algorithm. Classi®cation of each pixel is then carried out by calculating its fuzzy membership in each cluster. The results showed that the fuzzy hyperspectral classi®er is suc...

Target class measurements, if available from automatic target recognition systems, can be incorporated into multiple target tracking algorithms to improve measurement-to-track association accuracy. In this work, the performance of the classifier is modeled as a confusion matrix, whose entries are target class likelihood functions that are used to modify the update equations of the recently deri...