Hrl Laboratories, LLC

The Boeing Company

Gm Global Technolgoy Operations, Inc.

Raytheon Company

Qin Jiang

Yuri Owechko

Tsai-Ching Lu

Narayan Srinivasa

Yang Chen

David W Payton

Swarup S Medasani

Praveen K Pilly

Kang-Yu Ni

Soheil Kolouri

Vincent De Sapio

Nigel D Stepp

Adour Vahe Kabakian

Brian N Limketkai

David L Allen

Jose Cruz-Albrecht

David J Huber

Leandro G Barajas

Franz David Betz

Shahriar Alam

Youngkwan Cho

Steven W Skorheim

John E Harrison

John L Ross

Deepak Khosla

Kyungnam Kim

Rajan Bhattacharyya

Sethu K Madhavan

Yilu Zhang

Michael J Daily

Hankyu Moon

Hyukseong Kwon

Shuoqin Wang

Kevin R Martin

Ryan M Uhlenbrock

David B Shu

Nick S Kapsokavathis

Troy Dean Rockwood

Matthew E Phillips

Shubha Kadambe

Yongqiang Cao

James Benvenuto

Richard Michael Kremer

Alex N Waagen

Jijun Yin

Patricia Ann Keaton

Darrel James Van Buer

Michael J O'Brien

Brian L Burns

Luan Vu

Cynthia E Daniell

Ruggero Scorcioni

Joshua Haug

Kangyu Ni

Rachel Millin

Fatih Porikli

Described is a system for anomaly detection from hyperspectral data. The system receives, from a hyperspectral sensor, input hyperspectral data cubes with input data bands for every pixel. Using an optimization technique, an optimized number of virtual bands is determined to use for combining the hyperspectral data cubes to achieve optimal anomaly detection performance. The optimized number of virtual bands is less than the input data bands, resulting in reduced hyperspectral data. The hyperspectral data cubes are combined into the optimized number of virtual bands with the optimal bandwidth for each virtual band, and a set of combined hyperspectral data is output. Anomalies are detected in the set of combined hyperspectral data using an anomaly detection technique. Based on the detected anomalies, single-pixel or subpixel targets of interest are detected in the combined hyperspectral data.

System and method for anomaly detection from hyperspectral data

Described is a method for extraction of a region of interest (ROI) from a composite synthetic aperture radar (SAR) phase history data. The method comprising receiving, with a system comprising a processor, the composite SAR phase history data of a plurality of backscattered return signals produced by a SAR system illuminating a scene with a SAR beam. The method also comprises obtaining a location of a first ROI within the scene and extracting from the composite SAR phase history data a first component SAR phase history data corresponding to the ROI at the location of the ROI.

System for extraction of a region of interest (ROI) from a composite synthetic aperture radar (SAR) system phase history

Disclosed is a synthetic aperture radar (SAR) system for target recognition with complex range profile. The SAR system comprising a memory, a recurrent neural network (RNN), a multi-layer linear network in signal communication the RNN, and a machine-readable medium on the memory. The machine-readable medium is configured to store instructions that, when executed by the RNN, cause the SAR system to perform various operations. The various operation comprise: receiving raw SAR data associated with observed views of a scene, wherein the raw SAR data comprises information captured via the SAR system; radio frequency (RF) preprocessing the received raw SAR data to produce a processed raw SAR data; converting the processed raw SAR data to a complex SAR range profile data; processing the complex SAR range profile data with the RNN having RNN states; and mapping the RNN states to a target class with the multi-layer linear network.

Complex recurrent neural network for Synthetic Aperture Radar (SAR) target recognition

A radar anti-spoofing system for an autonomous vehicle includes a plurality of radar sensors that generate a plurality of input detection points representing radio frequency (RF) signals reflected from objects and a controller in electronic communication with the plurality of radar sensors. The controller executes instructions to determine time-matched clusters that represent objects located in an environment surrounding the autonomous vehicle based on the input detection points from the plurality of radar sensors. The controller determines an adjusted signal to noise (SNR) measure for a specific time-matched cluster by dividing an SNR of the specific time-matched cluster by a range measurement of the specific time-matched cluster. The controller determines a velocity-ratio measure of the time-matched cluster by dividing a motion-based velocity by a Doppler-frequency velocity, and identifies the time-matched cluster as either a ghost object or a real object.

Radar anti-spoofing system for identifying ghost objects created by reciprocity-based sensor spoofing

A computing system including a processor configured to train a synthetic aperture radar (SAR) classifier neural network. The SAR classifier neural network is trained at least in part by, at a SAR encoder, receiving training SAR range profiles that are tagged with respective first training labels, and, at an image encoder, receiving training two-dimensional images that are tagged with respective second training labels. Training the SAR classifier neural network further includes, at a shared encoder, computing shared latent representations based on the SAR encoder outputs and the image encoder outputs, and, at a classifier, computing respective classification labels based on the shared latent representations. Training the SAR classifier neural network further includes computing a value of a loss function based on the plurality of first training labels, the plurality of second training labels, and the plurality of classification labels and performing backpropagation based on the value of the loss function.

Synthetic aperture radar classifier neural network

A radar anti-spoofing system for an autonomous vehicle includes a plurality of radar sensors that generate a plurality of input detection points representing radio frequency (RF) signals reflected from objects and a controller in electronic communication with the plurality of radar sensors. The one or more controllers execute instructions to determine a signal to noise ratio (SNR) distance ratio for the input detection points generated by the plurality of radar sensors, where a value of the SNR distance ratio is indicative of an object being a ghost vehicle. The one or more controllers also determine an effective particle number indicating a degree of particle degradation for the importance sampling for each variable that is part of the state variable. In response to determining the effective particle number is equal to or less than a predetermined threshold, the one or more controllers estimate a ghost position for the ghost vehicle.

Radar anti-spoofing systems for an autonomous vehicle that identify ghost vehicles

A method, system, and computer program product for predicting abnormal operation of at least one component of a machine is provided. Real time monitoring data from an operating machine is received and monitoring features that are informative of likely abnormal operation are extracted and/or calculated. The monitoring features are applied to a prediction matrix that outputs probabilities of abnormal operation within one or more prediction time horizons. If the output probabilities exceed a threshold probability, then an alert can be output. Maintenance can be automatically scheduled in response to the alert.

Monitored machine performance as a maintenance predictor

A method is disclosed. The method models a plurality of visual cortex neurons, models one or more connections between at least two visual cortex neurons in the plurality of visual cortex neurons, assigns synaptic weight value to at least one of the one or more connections, simulates application of one or more electrical signals to at least one visual cortex neuron in the plurality of visual cortex neurons, adjusts the synaptic weight value assigned to at least one of the one or more connection based on the one or more electrical signals, and generates an orientation map of the plurality of visual cortex neurons based on the adjusted synaptic weight values.

Method of modeling functions of orientation and adaptation on visual cortex

A method of identifying a target from synthetic aperture radar (SAR) data without incurring the computational load associated with generating an SAR image. The method includes receiving SAR data collected by a radar system including RF phase history data associated with reflected RF pulses from a target in a scene, but excluding an SAR image. Range profile data is determined from the SAR data by converting the RF phase history data into a structured temporal array that can be applied as input to a classifier incorporating a recurrent neural network, such as a recurrent neural network made up of long short-term memory (LSTM) cells that are configured to recognize temporal or spatial characteristics associated with a target, and provide an identification of a target based on the recognized temporal or spatial characteristic.

Target recognition from SAR data using range profiles and a long short-term memory (LSTM) network

Described is a system for online vehicle recognition in an autonomous driving environment. Using a learning network comprising an unsupervised learning component and a supervised learning component, images of moving vehicles extracted from videos captured in the autonomous driving environment are learned and classified. Vehicle feature data is extracted from input moving vehicle images. The extracted vehicle feature data is clustered into different vehicle classes using the unsupervised learning component. Vehicle class labels for the different vehicle classes are generated using the supervised learning component. Based on a vehicle class label for a moving vehicle in the autonomous driving environment, the system selects an action to be performed by the autonomous vehicle, and causes the selected action to be performed by the autonomous vehicle in the autonomous driving environment.

Method of real time vehicle recognition with neuromorphic computing network for autonomous driving

Described is a system for predicting future social activity. The system extracts social activities from spatial-temporal social network data collected in a first time period ranging from hours to days to capture spatial structures of social activities in a graph network representation. A graph matching technique is applied over a set of spatial-temporal social network data collected in a second time period ranging from weeks to months to capture temporal structures of the social activities. A spatial-temporal structure of each social activity is represented as an activity core, where each activity core is defined as active nodes that participate in the social activity with a frequency over a predetermined threshold over the second time period. For each activity core, the system computes statistics of the social activity and uses the statistics to generate a prediction of future behaviors of the social activity.

Method of malicious social activity prediction using spatial-temporal social network data

A system configured to identify a target in a synthetic aperture radar signal includes: a feature extractor configured to extract a plurality of features from the synthetic aperture radar signal; an input spiking neural network configured to encode the features as a first plurality of spiking signals; a multi-layer recurrent neural network configured to compute a second plurality of spiking signals based on the first plurality of spiking signals; a readout neural layer configured to compute a signal identifier based on the second plurality of spiking signals; and an output configured to output the signal identifier, the signal identifier identifying the target.

System and method for synthetic aperture radar target recognition using multi-layer, recurrent spiking neuromorphic networks

A system to detect a feature in an input image comprising a processor to evaluate a model including: four layers including: a supragranular layer, a granular layer, a first infragranular layer, and a second infragranular layer, each of the layers including a base connection structure including: an excitatory layer including a excitatory neurons arranged in a two dimensional grid; and an inhibitory layer including a inhibitory neurons arranged in a two dimensional grid; within-layer connections between the neurons of each layer in accordance with a Gaussian distribution; between-layer connections between the neurons of different layers, the probability of a neuron of a first layer of the different layers to a neuron of a second layer of the different layers in accordance with a uniform distribution; and input connections from lateral geniculate nucleus (LGN) neurons of an input LGN layer to the granular layer in accordance with a uniform distribution.

System and method of modeling visual perception V1 area

A system configured to identify a target in a synthetic aperture radar signal includes: a feature extractor configured to extract a plurality of features from the synthetic aperture radar signal; a spiking neural network configured to encode the features as a plurality of spiking signals; a readout neural layer configured to compute a signal identifier based on the spiking signals; and an output configured to output the signal identifier, the signal identifier identifying the target.

System and method for synthetic aperture radar target recognition utilizing spiking neuromorphic networks

Described herein is a method of enhancing an image includes determining a level of environmental artifacts at a plurality of positions on an image frame of image data. The method also includes adjusting local area processing of the image frame, to generate an adjusted image frame of image data, based on the level of environmental artifacts at each position of the plurality of positions. The method includes displaying the adjusted image frame.

Apparatus, system, and method for enhancing an image

Growing community of inventors

Oak Park, CA, United States of America

Qin Jiang