Science Applications International Corporation

Leidos, Inc.

Hanna Elizabeth Witzgall

Jay Scott Goldstein

Timothy F Settle

Object detection architectures for detecting and classifying objects in an image are modified to incorporate an extending Rapid Class Augmentation (XRCA) progressive learning algorithm with its defining aspect of memory built into its optimizer which allows joint optimization over both the old and the classes using just the new class data and eliminates the issues associated with catastrophic forgetting.

Method and system for accelerating rapid class augmentation for object detection in deep neural networks

A system, method and apparatus is provided for calculating the position of a single receiver by receiving a signal from an emitter. Either the receiver or the emitter may be stationary relative to the surface of the Earth. The invention may use a particle filter to optimize the efficiency of the position calculation. The invention may further utilize a particle filter to estimate the frequency drift and bias of the emitter and/or receiver, and use the estimated frequency drift to improve the position calculation. In one embodiment, the invention may be used to calculate the position of a single GPS receiver given the position of, and a transmission from, a single GPS satellite.

Machine and process for self localization using doppler

The described invention allows for rapid geolocation of one or more RF emitters using a single moving collection platform. Inaccuracies of conventional frequency of arrival (FOA) geolocation methods are overcome by solving simultaneously for emitter location and a potential emitter drift associated with an observed emitter frequency. Certain embodiments may utilize particle filtering algorithms to recursively update multimodal state densities that are typical of solutions involving both unknown emitter location and nonstationary emitter carrier drift. Moreover, certain properties of particle filters may be exploited to provide a geolocation solution given a complex multimodal state space composed of emitter location and a non-stationary emitter frequency required for FOA.

Diversified doppler for single platform geolocation

Complex image data is transformed to a holographic representation of the image. A subset of the holographic representation is modeled. Model parameters constitute a compressed image representation. A two-dimensional Fourier transform can be applied to obtain the holographic image. Modeling includes applying an analysis portion of an adaptive analysis/synthesis linear prediction methodology to a subset of the holographic representation to obtain an autoregressive model. Prior to modeling, one-dimensional Fourier transform can be performed on the holographic representation and the linear prediction is one-dimensional. Model parameters are preferably quantized. Embodiments include determining error between the model and the model's input data. There the compressed image representation the error, which also can be quantized. The subset of the holographic representation can be less than all the representation. The subset can be a plurality of complete rows; preferably substantially symmetric about 0 Hz.

Complex image compression

Embodiments of the invention view image intensity data as a spectrum of underlying wave forms. The spectrum of these waves can be approximated using spectral estimation techniques where the spectrum parameters constitute the compressed image. The image's underlying wave forms can be recovered using an inverse Fourier transform. The original image can also be symmetrically extended prior to the transform to preserve real valued transformed data and model parameters. The modeling method is typically based on a linear predictive methodology to obtain the spectrum parameters. Other transforms include a 2-D Fourier transform that transforms the image into a holographic representation similar to synthetic aperture radar (SAR) phase history. This 2-D waveform holographic format can be decorrelated into 1-D planar waves by applying a 1D Fourier transform. This process enables 1-D linear predictive modeling to obtain the spectral parameters. For compression applications the model parameters are preferably quantized.

Magnitude image compression

Image pixel intensity data is transformed to a holographic representation of the image. A subset of the holographic representation is modeled. Model parameters constitute a compressed image representation. A two-dimensional Fourier transform can be applied to obtain the holographic image. Modeling includes applying an analysis portion of an adaptive analysis/synthesis prediction methodology to a subset of the holographic representation. Linear prediction can be the adaptive analysis/synthesis prediction methodology. Prior to modeling, one-dimensional Fourier transform can be performed on the holographic representation and the linear prediction is one-dimensional. Model parameters are preferably quantized. Embodiments include determining error between the model and the model's input data. There the compressed image representation the error, which also can be quantized. The subset of the holographic representation can be less than all the representation. The subset can be a plurality of complete rows; preferably substantially symmetric about 0 Hz.

Compression for holographic data and imagery

In a digital signal processor (DSP), input data is configured as a data matrix comprising data samples collected from an input signal. A weight vector is applied to the matrix, where the weight vector comprises three parts including (a) a rank reduction transformation produced by decomposition of data samples in a multistage Wiener filter having a plurality of stages, each stage comprising projection onto two subspaces. Each subsequent stage comprises projecting data transformed by the preceding second subspace onto each of a first subspace comprising a normalized cross-correlation vector at the previous stage and a second subspace comprising the null space of the normalized cross-correlation vector of the current stage, to form a reduced rank data matrix. Part (b) of the weight vector comprises minimizing mean squared error in the reduced rank data space. The output is a linear estimate of input data.

System and method for linear prediction

In a digital signal processor (DSP), input data is configured as a data matrix comprising data samples collected from an input signal. A weight vector is applied to the data matrix, where the weight vector comprises three parts including (a) a rank reduction transformation produced by decomposition of the data samples in a multistage Wiener filter having a plurality of stages, each stage comprising projection onto two subspaces. Each subsequent stage comprises projecting data transformed by the preceding second subspace onto each of a first subspace comprising a normalized cross-correlation vector at the previous stage and a second subspace comprising the null space of the normalized cross-correlation vector of the current stage, to form a reduced rank data matrix. Part (b) of the weight vector comprises minimizing the mean squared error in the reduced rank data space. The output is a linear estimate of the input data. In one embodiment, further processing produces an estimate of the power spectral density of the input signal.

Growing community of inventors

Chantilly, VA, United States of America

Hanna Elizabeth Witzgall