Abstract: Implementations provide denoising a signal. A plurality of reservoir state values are produced based on the signal and the plurality of reservoir state values are collected into a historical record. A plurality of reservoir state value weights are calculated based at least in part on the historical record to produce a plurality of output values. The plurality of reservoir state value weights are computed over multiple clock cycles of a clock for the cognitive signal processor system. The plurality of output values are output. A more accurate representation of a next of set of output layer weights is thereby obtained.

Abstract: Described is a stripmap SAR system on a vehicle comprising an antenna that is fixed and directed outward from the side of the vehicle, a SAR sensor, a storage, and a computing device. The computing device comprises a memory, one or more processing units, and a machine-readable medium on the memory. The machine-readable medium stores instructions that, when executed by the one or more processing units, cause the stripmap SAR system to perform various operations. The operations comprise: receiving stripmap range profile data associated with observed views of a scene; transforming the received stripmap range profile data into partial circular range profile data; comparing the partial circular range profile data to a template range profile data of the scene; and estimating registration parameters associated with the partial circular range profile data relative to the template range profile data to determine a deviation from the template range profile data.

Abstract: A system for real time bilinear interpolation includes a bilinear interpolation module capable of: generating pixel addresses for original image pixels of an original image needed for performing bilinear interpolation of the original image to form a resized image, wherein the generated pixel addresses assume all the original image pixels of the original image are accessible, and performing bilinear interpolation, and a pixel smart memory module capable: of sequentially receiving original image pixel rows of the original image an original image pixel row a time, predicting which original image pixel rows are needed for performing bilinear interpolation, storing only the needed sequentially received original image pixel rows in a memory, decoding the generated pixel addresses to form decoded addresses to access the needed original image pixel rows stored in the memory, and sending the needed original image pixel rows to the bilinear interpolation module for performing bilinear interpolation.

Abstract: A synthetic aperture radar (SAR) system is disclosed. The SAR comprises a memory, a convolutional neural network (CNN), a machine-readable medium on the memory, and a machine-readable medium on the memory. The machine-readable medium storing instructions that, when executed by the CNN, cause the SAR system to perform operations. The operation comprises: receiving range profile data associated with observed views of a scene; concatenating the range profile data with a template range profile data of the scene; and estimating registration parameters associated with the range profile data relative to the template range profile data to determine a deviation from the template range profile data.

Abstract: Systems and methods according to one or more embodiments are provided for registration of synthetic aperture range profile data to aid in SAR-based navigation. In one example, a SAR-based navigation system includes a memory comprising a plurality of executable instructions. The SAR-based navigation system further includes a processor adapted to receive range profile data associated with observed views of a scene, compare the range profile data to a template range profile data of the scene, and estimate registration parameters associated with the range profile data relative to the template range profile data to determine a deviation from the template range profile data.

Abstract: A synthetic aperture radar (SAR) system is disclosed. The SAR comprises a memory, a convolutional neural network (CNN), a machine-readable medium on the memory, and a machine-readable medium on the memory. The machine-readable medium storing instructions that, when executed by the CNN, cause the SAR system to perform operations. The operation comprises: receiving range profile data associated with observed views of a scene; concatenating the range profile data with a template range profile data of the scene; and estimating registration parameters associated with the range profile data relative to the template range profile data to determine a deviation from the template range profile data.

Abstract: Described is a cognitive signal processor that is implemented in a field programmable gate array (FPGA). During operation, the FGPA receives a continuous noisy signal. The continuous noisy signal is a time-series of data points from a mixture signal of waveforms having both noise and a desired waveform signal. The continuous noisy signal is linearly mapped to reservoir states of a dynamical reservoir. A high-dimensional state-space representation of the continuous noisy signal is generated by digitally combining the continuous noisy signal with the reservoir states. Notably, the continuous noisy signal is approximated over a time interval based on a linear basis function. One or more delay-embedded state signals are then generated based on the reservoir states. The continuous noisy signal is then denoised by removing the noise from the desired waveform signal, resulting in a denoised waveform signal.

Abstract: Described is a stripmap SAR system on a vehicle comprising an antenna that is fixed and directed outward from the side of the vehicle, a SAR sensor, a storage, and a computing device. The computing device comprises a memory, one or more processing units, and a machine-readable medium on the memory. The machine-readable medium stores instructions that, when executed by the one or more processing units, cause the stripmap SAR system to perform various operations. The operations comprise: receiving stripmap range profile data associated with observed views of a scene; transforming the received stripmap range profile data into partial circular range profile data; comparing the partial circular range profile data to a template range profile data of the scene; and estimating registration parameters associated with the partial circular range profile data relative to the template range profile data to determine a deviation from the template range profile data.

Abstract: Systems and methods according to one or more embodiments are provided for registration of synthetic aperture range profile data to aid in SAR-based navigation. In one example, a SAR-based navigation system includes a memory comprising a plurality of executable instructions. The SAR-based navigation system further includes a processor adapted to receive range profile data associated with observed views of a scene, compare the range profile data to a template range profile data of the scene, and estimate registration parameters associated with the range profile data relative to the template range profile data to determine a deviation from the template range profile data.

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 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 multi-input cognitive signal processor (CSP) for estimating time-difference-of-arrival (TDOA) of incoming signals. The multi-input CSP receives a mixture of input signals from an antenna a and an antenna b. The multi-input CSP predicts and temporally de-noises input signals a and b received from antennas a and b, respectively, using an input corresponding to each input signal, resulting in de-noised state vectors for input signals a and b. Using the de-noised state vectors for input signals a and b, cross-predicting and spatially de-noising the other of the de-noised state vectors for input signals a and b. TDOA values of signal pulses to each of antennas a and b are estimated and converted into estimated angles of arrival for each signal pulse.

Abstract: Described is a system for signal denoising using a cognitive signal processor having a time-varying reservoir. The system receives a noisy input signal of a time-series of data points from a mixture of waveform signals. The noisy input signal is linearly mapped into the time-varying reservoir. A high-dimensional state-space representation of the mixture of waveform signals is generated by combining the noisy input signal with a plurality of reservoir states. The system then generates a denoised signal corresponding to the noisy input signal.

Abstract: Described is a video scene analysis system. The system includes a salience module that receives a video stream having one more pairs of frames (each frame having a background and a foreground) and detects salient regions in the video stream to generate salient motion estimates. The salient regions are regions that move differently than dominant motion in the pairs of video frames. A scene modeling module generates a sparse foreground model based on salient motion estimates from a plurality of consecutive frames. A foreground refinement module then generates a Task-Aware Foreground by refining the sparse foreground model based on task knowledge. The Task-Aware Foreground can then be used for further processing such as object detection, tracking or recognition.

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 adaptive blind source separation. A time-series of data points from one or more mixtures of source signals is continuously passed through adaptable filters, where each filter has a corresponding output signal. An error of each output signal is determined, and a filter state of each filter is determined using the error signals. A set of filter center frequencies are adapted using the set of error signals and the filter states, resulting in new filter center frequencies. The set of filter center frequencies are updated with the new filter center frequencies. Finally, separated source signals are extracted from the mixture of signals.

Abstract: A system and method for low power surveillance. The system receives a series of frames from a camera, each frame having a background and a foreground. A background template is generated. Thereafter, the system receives a new image frame of the scene, the new image frame having a background and a foreground. Potential regions of interest (ROI) are detected in the new image frame. Initial region descriptors are determined in the potential ROI in the foreground. The initial region descriptors are segmented to generate a segmented region. Region descriptors are re-determined from the segmented region. A contiguous sparse foreground is determined from the re-determined region descriptors, the contiguous sparse foreground being a contiguous ROI. The ROI is reconstructed using foveated compressive sensing to generate an image of an interesting object. Finally, the interesting object image is combined with the background template to reconstruct the foreground.

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 signal processor (CSP) for signal denoising. In operation, the CSP receives a noisy signal as a time-series of data points from a mixture of both noise and one or more desired waveform signals. The noisy signal is linearly mapped to reservoir states of a dynamical reservoir. A high-dimensional state-space representation is then generated of the noisy signal by combining the noisy signal with the reservoir states. A delay-embedded state signal is generated from the reservoir states. The reservoir states are denoised by removing noise from each reservoir state signal, resulting in a real-time denoised spectrogram of the noisy signal. A denoised waveform signal is generated combining the denoised reservoir states. Additionally, the signal denoising process is implemented in software or digital hardware by converting the state-space representation of the dynamical reservoir to a system of delay difference equations and then applying a linear basis approximation.

Abstract: Described is a system for bounding box generation. The system operates on an image comprised of pixels having a one-bit value per pixel. Bounding boxes are generated around connected components in the image, the connected components having pixel coordinate and pixel count information. A ranking score is generated for each bounding box based on the pixel coordinate and pixel count information. The bounding boxes are filtered to remove bounding boxes that exceed a predetermined size and pixel count based on the pixel coordinate and pixel count information. The bounding boxes are further filtered to remove bounding boxes that fall below a predetermined ranking score, resulting in remaining bounding boxes. Finally, a device can be controlled or otherwise operated based on the remaining bounding boxes.