In this paper we present an algorithm to determine the location of an acoustic sensor array using the direction of arrival (DOA) estimates of a moving acoustic source whose ground truth is available. Determination of location and orientation of sensor array based on the statistics of errors in the DOA estimation is a nonlinear regression problem. We formulate and derive the necessary equations to solve this problem in terms of the bearing estimates of the acoustic source and its location. The algorithm is tested against helicopter data from three acoustic sensor arrays distributed over a field.
An automatic target recognition classifier is constructed that uses a set of dedicated vector quantizers (VQs). The background pixels in each input image are properly clipped out by a set of aspect windows. The extracted target area for each aspect window is then enlarged to a fixed size, after which a wavelet decomposition splits the enlarged extraction into several subbands. A dedicated VQ codebook is generated for each subband of a particular target class at a specific range of aspects. Thus, each codebook consists of a set of feature templates that are iteratively adapted to represent a particular subband of a given target class at a specific range of aspects. These templates are then further trained by a modified learning vector quantization (LVQ) algorithm that enhances their discriminatory characteristics. A recognition rate of 69.0 percent is achieved on a highly cluttered test set.
We present the design of an automatic target recognition (ATR) system that is part of a hybrid system incorporating some domain knowledge. This design obtains an adaptive trade-off between training performance and memorization capacity by decomposing the learning process with respect to a relevant hidden variable. The probability of correct classification over 10 target classes is 73.4%. The probability of correct classification between the target- class and the clutter-class (where clutters are the false alarms obtained from another ATR) is 95.1%. These performances can be improved by reducing the memorization capacity of this system because its estimation shows that it is too large.
This paper describes a model based approach to the detection of objects of known geometry in imagery. The algorithm is designed to be used as a front end to an automatic target recognizer. The algorithm uses probes to extract features from the neighborhood of the known boundary of the object. Neural nets are used to classify the probes as corresponding to background or an object/background boundary by estimating a posteriori probabilities. The paper investigates a number of probe geometries and nonparametric probe statistics. Experimental results demonstrate the utility of these methods in detecting ground vehicles in natural backgrounds.
We consider the problem of recognition of rigid, manufactured objects, each from a predefined set of possible object classes, from their images. We describe a parametric statistical approach to this problem that is a hybrid between statistical modeling using Bayes decision theory with a generative model of images and a case-based approach. Our method is a variant of the Gibbs sampling method, commonly used to compute posterior probabilities in complex statistical models, but unlike standard Gibbs sampling methods, our method is based directly on analysis of a library of previously analyzed images. We also propose a simple gradient descent method to optimize the parameters of the models to maximize effective object recognition.
In this paper, an adaptive neural network vector predictor is designed in order to improve the performance of the predictive component of the predictive vector quantizer (PVQ). The proposed vector predictor consists of a set of dedicated predictors (experts) where each predictor is optimized for a particular class of input vectors. In our simulations, we used five multi-layer perceptrons (MLP) to design our expert predictors. Each MLP predictor is separately trained by using a set of training vectors that belong to a particular class. The class identity of each training vector is determined by its directional variances. In our current implementation, one predictor is optimized for stationary blocks and four other predictors are designed for horizontal, vertical, 45 degree and 135 degree diagonally oriented edge blocks. The back-propagation algorithm is used for training each network. The directional variances of the neighboring blocks are used to select the appropriate expert predictor for the current input block. Therefore, no overhead information is transmitted in order to inform the receiver about the predictor selection. Our simulation shows that the proposed scheme gives an improvement of more than 1 dB over the predictor consisting of a single MLP predictor. The perceptual quality of the predicted images are also significantly improved.
In this paper a neural-network-based automatic target recognition (ATR) classifier is developed. The ATR classifier consists of a learning vector quantization (LVQ) algorithm followed by a multilayer perceptron (MLP). The LVQ is used as the feature extractor and the MLP as the classifier. The LVQ algorithm adaptively extracts a set of target templates (centroids) that are assumed to represent the target signatures. The Euclidean distances between the centroids and the input target are passed to an MLP. The MLP uses these distances as input and performs a classification. Experimental results are presented for two different test sets. The first test set has similar characteristics to those of the training set, and the ATR classifier does very well. However, the second test set has a different characteristics and the ATR classifier performance is poor.