Abstract: Described is a system for signal denoising. The system linearly maps a noisy input signal into a high-dimensional reservoir, where the noisy input signal is a time-series of data points from a mixture of waveforms. A high-dimensional state-space representation of the mixture of waveforms is created by combining the noisy input signal with reservoir states. A delay embedded state signal is generated from the reservoir states, and a denoised spectrogram of the noisy input signal is generated.

Abstract: Described is a system for synthetic aperture radar (SAR) imaging. The system is adapted to reconstruct a set of images to generate a set of reconstructed SAR images, wherein at least some of the reconstructed SIR images have noise and contain glint. The reconstructed SAR images are then stacked into a matrix D, in which each column of the matrix is a reconstructed SAR image. Using sparse and low-rank decomposition on the matrix D, the system then extracts a clean background from the reconstructed SAR images and separates the noise and glint. Based on that, the system is operable to detect moving targets in sparse part S and issuing a notification of such a moving target.

Abstract: A sensor system including a spectrometer with a light source having a plurality of selectable wavelengths, a controller for controlling the sensor system, for selecting wavelengths of illumination light produced by the light source, and for controlling the light source to illuminate a spatial location, a photodetector aligned to detect light received from the spatial location, a blind demixer coupled to the photodetector for separating received spectra in the detected light into a set of sample spectra associated with different demixed or partially demixed chemical components, a memory having a plurality of stored reference spectra, a non-blind demixer coupled to the blind demixer and to the memory for non-blind demixing of the sample spectra using the reference spectra, and a classifier coupled to the non-blind demixer for classifying the set of demixed sample spectra into chemical components using the reference spectra.

Abstract: Described is a system for detecting multiple salient objects in an image using low power hardware. From consecutive pair of image frames of a set of input image frames, image channels are generated. The image channels are resized into multiple image scales that specify a relative size of a salient object in the image frames. A patch-based spectral transform is applied to overlapping image patches in the resized image channel, generating salient patches. Saliency patches are combined into a saliency map for each resized image channel, resulting in multiple saliency maps. The saliency maps are combined into an aggregate saliency map. An adaptive threshold is applied to the aggregate saliency map to determine which pixels in the aggregate saliency map correspond to a detected salient object region including a salient object. An object bounding box is generated for each salient object and output to a display.

Abstract: Described is a system for remote analysis of spectral data. A set of measured spectral mixtures are separated using a blind demixing process, resulting in demixed outputs. A demixed output is selected for further processing, and a spectral library is selected from a set of spectral libraries that is specialized for the selected demixed output. Individual components in the selected demixed output are classified via a non-blind demixing process using the selected spectral library. Trace chemical residues are detected in the set of measured spectral mixtures.

Abstract: Described is a system for library-based spectral demixing. The system simultaneously separates and identifies spectral elements in a set of noisy, cluttered spectral elements using Sparse Representation-based Classification (SRC) by modeling the set of noisy, cluttered spectral elements. The spectral library models each spectral element in the set of noisy, cluttered spectral elements, each spectral element having a corresponding wavenumber measurement. Wavenumber measurements are classified, resulting in salient wavenumber measurements. Target spectral elements representing a target of interest are identified in the set of noisy, cluttered spectral elements using the salient wavenumber measurements.

Abstract: Described is a system for compensating for ego-motion during video processing. The system generates an initial estimate of camera ego-motion of a moving camera for consecutive image frame pairs of a video of a scene using a projected correlation method, the camera configured to capture the video from a moving platform. An optimal estimation of camera ego-motion is generated using the initial estimate as an input to a valley search method or an alternate line search method. All independent moving objects are detected in the scene using the described hybrid method at superior performance compared to existing methods while saving computational cost.

Abstract: Described is a neuromorphic processor for signal denoising and separation. The neuromorphic processor generates delay-embedded mixture signals from an input mixture of pulses. Using a reservoir computer, the delay-embedded mixture signals are mapped to reservoir states of a dynamical reservoir having output layer weights. The output layer weights are adapted based on short-time linear prediction, and a denoised output of the mixture of input signals us generated. The denoised output is filtered through a set of adaptable finite impulse response (FIR) filters to extract a set of separated narrowband pulses.

Abstract: Described is a cognitive signal processor that can denoise an input signal that contains a mixture of waveforms over a large bandwidth. Delay-embedded mixture signals are generated from a mixture of input signals. The delay-embedded mixture signals are mapped with a reservoir computer to reservoir states of a dynamical reservoir having output layer weights. The output layer weights are adapted based on short-time linear prediction. Finally, a denoised output of the mixture of input signals is generated.

Abstract: Described is a cognitive signal processor for signal denoising and blind source separation. During operation, the cognitive signal processor receives a mixture signal that comprises a plurality of source signals. A denoised reservoir state signal is generated by mapping the mixture signal to a dynamic reservoir to perform signal denoising. At least one separated source signal is identified by adaptively filtering the denoised reservoir state signal.

Abstract: Described is a system that can recognize novel objects that the system has never before seen. The system uses a training image set to learn a model that maps visual features from known images to semantic attributes. The learned model is used to map visual features of an unseen input image to semantic attributes. The unseen input image is classified as belonging to an image class with a class label. A device is controlled based on the class label.

Abstract: Described is a system for detecting salient objects in images. During operation, the system maps an input image into a frequency domain having a spectral magnitude. The spectral magnitude is replaced with weights from a weight matrix W. The frequency domain is then transformed with the weights to a saliency map in the image domain, the saliency map having pixels with pixel values. A squaring operation is then performed on the saliency map by squaring the pixel values to generate a pixel-value altered saliency map. A final saliency map is generated by filtering the pixel-value altered saliency map. A number of devices may then be operated based on the saliency map.

Abstract: Described is a system for compensating for ego-motion during video processing. The system generates an initial estimate of camera ego-motion of a moving camera for consecutive image frame pairs of a video of a scene using a projected correlation method, the camera configured to capture the video from a moving platform. An optimal estimation of camera ego-motion is generated using the initial estimate as an input to a valley search method or an alternate line search method. All independent moving objects are detected in the scene using the described hybrid method at superior performance compared to existing methods while saving computational cost.

Abstract: A method of processing a plurality of time-varying signals received at a sensor communicatively coupled to a signal data processor to identify at least one parameter of at least one of the plurality of time-varying signals is provided. The method includes receiving, at a plurality of blind source separation (BSS) modules of the signal data processor, signals derived from the plurality of time-varying signals, each BSS module of the plurality of BSS modules including a filtering subsystem having a pipelined architecture and a parallelized architecture. The method also includes generating a plurality of blind source separated signals, and transmitting at least one pulse descriptor word (PDW) parameter vector signal to a computing device of the signal data processor. The method further includes identifying the at least one parameter from the at least one PDW parameter vector signal, and outputting the at least one parameter from the signal data processor.

Abstract: A method for removing an extracted RF signal to examine a spectrum of at least one other RF signal includes receiving a mixture signal by an ADC. The mixture signal includes a plurality of separate signals from different signal sources. The mixture signal is digitized by the ADC. A first digitized signal and a second digitized signal are generated that are the same. The first digitized signal is delayed a predetermined time delay and the second digitized signal is processed in a neuromorphic signal processor to extract an extracted signal. The predetermined time delay corresponds to a delay embedding in the neuromorphic signal processor. A phase delay and amplitude of the extracted signal is adjusted based on a phase delay and amplitude of the first digitized signal. An adjusted extracted signal is cancelled from the first digitized signal to provide an input examination signal for examination.

Abstract: Described is a cognitive signal processor for signal denoising and blind source separation. During operation, the cognitive signal processor receives a mixture signal that comprises a plurality of source signals. A denoised reservoir state signal is generated by mapping the mixture signal to a dynamic reservoir to perform signal denoising. At least one separated source signal is identified by adaptively filtering the denoised reservoir state signal.

Abstract: A method of processing a plurality of time-varying signals received at a sensor communicatively coupled to a signal data processor to identify at least one parameter of at least one of the plurality of time-varying signals is provided. The method includes receiving, at a plurality of blind source separation (BSS) modules of the signal data processor, signals derived from the plurality of time-varying signals, each BSS module of the plurality of BSS modules including a filtering subsystem having a pipelined architecture and a parallelized architecture. The method also includes generating a plurality of blind source separated signals, and transmitting at least one pulse descriptor word (PDW) parameter vector signal to a computing device of the signal data processor. The method further includes identifying the at least one parameter from the at least one PDW parameter vector signal, and outputting the at least one parameter from the signal data processor.

Abstract: A method for generating pulse descriptor words (PDWs) including frequency and/or bandwidth data from time-varying signals received by a sensor includes filtering, at a plurality of blind source separation (BSS) modules, signals derived from the time-varying signals, each BSS module including a filtering subsystem having a plurality of filter modules. Each filter module has a frequency filter coefficient (?) and is parameterized by a center frequency (f). The method also includes transmitting at least one blind source separated signal from the BSS modules to a PDW generation module communicatively coupled to the filtering subsystem. The method further includes generating, using the PDW generation module and based on the blind source separated signal, at least one PDW parameter vector signal containing the frequency data. The method also includes updating, upon generating and based on the PDW parameter vector signal, values of ? and/or f for each filter module.

Abstract: Described is a cognitive blind source separator (CBSS). The CBSS includes a delay embedding module that receives a mixture signal (the mixture signal being a time-series of data points from one or more mixtures of source signals) and time-lags the signal to generate a delay embedded mixture signal. The delay embedded mixture signal is then linearly mapped into a reservoir to create a high-dimensional state-space representation of the mixture signal. The state-space representations are then linearly mapped to one or more output nodes in an output layer to generate pre-filtered signals. The pre-filtered signals are passed through a bank of adaptable finite impulse response (FIR) filters to generate separate source signals that collectively formed the mixture signal.

Abstract: A spatio-temporal signal monitoring system includes a sampler configured to receive a radio frequency signal and obtain first compressive sensing measurements of said received signal at a first resolution level, and a signal detector configured to identify at least one signal of interest based on said first compressive sensing measurements and perform second compressive sensing measurements on said at least one signal of interest at a second resolution level, said second resolution level being higher than said first resolution level. The received signal may be analyzed as an array or image having two or more dimensions, based on frequency and on at least one other parameter, such as angle-of arrival, and may be analyzed at a higher level of resolution at the frequencies and angles corresponding to a signal of interest (SOI). Estimates of the frequency and/or the at least one other parameter may be generated by the system.