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.

This document describes apparatuses and techniques for radar-enabled sensor fusion. In some aspects, a radar field is provided and reflection signals that correspond to a target in the radar field are received. The reflection signals are transformed to provide radar data, from which a radar feature indicating a physical characteristic of the target is extracted. Based on the radar features, a sensor is activated to provide supplemental sensor data associated with the physical characteristic. The radar feature is then augmented with the supplemental sensor data to enhance the radar feature, such as by increasing an accuracy or resolution of the radar feature. By so doing, performance of sensor-based applications, which rely on the enhanced radar features, can be improved.

The methods and device disclosed herein provide an array such as a Radio Frequency (FR) antenna array for measuring the array movement or displacement of the array relative to a reference location. In some cases the array may be attached to or in communication with the device. The array comprises at least two transducers (e.g. RF antennas), wherein at least one of the at least two transducers is configured to transmit a signal towards the object, and at least one transceiver attached to said at least two transducers, the at least one transceiver is configured to repetitively transmit at least one signal toward an object and receive a plurality of signals affected or reflected while the array is moved in proximity to the object/medium or scene; and at least one processor unit, configured to: process the affected signals to yield a plurality of signal measurements and compare said signal measurements obtained at different locations over time of said second object and calculate a movement of the object relative to a reference location.

This document describes apparatuses and techniques for radar-enabled sensor fusion. In some aspects, a radar field is provided and reflection signals that correspond to a target in the radar field are received. The reflection signals are transformed to provide radar data, from which a radar feature indicating a physical characteristic of the target is extracted. Based on the radar features, a sensor is activated to provide supplemental sensor data associated with the physical characteristic. The radar feature is then augmented with the supplemental sensor data to enhance the radar feature, such as by increasing an accuracy or resolution of the radar feature. By so doing, performance of sensor-based applications, which rely on the enhanced radar features, can be improved.

Various embodiments dynamically learn user-customizable input gestures. A user can transition a radar-based gesture detection system into a gesture-learning mode. In turn, the radar-based gesture detection system emits a radar field configured to detect a gesture new to the radar-based gesture detection system. The radar-based gesture detection system receives incoming radio frequency (RF) signals generated by the outgoing RF signal reflecting off the gesture, and analyzes the incoming RF signals to learn one or more identifying characteristics about the gesture. Upon learning the identifying characteristics, the radar-based gesture detection system reconfigures a corresponding input identification system to detect the gesture when the one or more identifying characteristics are next identified, and transitions out of the gesture-learning mode.

The presently disclosed subject matter includes a UAV surveillance system and method which enables quick and convenient activation of an on-board radar (e.g., in SAR or GMTI mode) without having predefined suitable flight instructions. It enables ad-hoc operation of radar data acquisition devices allowing to switch from EO data acquisition to radar data acquisition or activate a radar side-by-side with an EO sensing device.

Aspects of the disclosure are directed towards obstacle position and extent measurement. In accordance with one aspect, obstacle detection includes creating one or more interferometric measurements to generate a flow of response position locations using a flow of range/Doppler detections by fitting a parametric expression; and deriving one or more scatterer positions and obstacle position and extent measurements from the flow of response position locations.

Embodiments provide for a portable imager by capturing several radar readings related to an object in an environment over several times from several of Points of View (POV), wherein each radar reading indicates a distance to and reflectivity of the object relative to the imager; capturing several camera images of the environment over the several of times from the several POVs; determining positional shifts of the imager over the several times based on photogrammetrical differences between subsequent camera images of the several camera images; determining, based on accelerometer data, a trajectory that the imager moves in the environment over the several times; determining positions of the imager in the environment over the several times based on the positional shifts and the trajectory; combining the several radar readings based on the positions to produce a synthetic aperture radar image of the object; and outputting the synthetic aperture radar image.

A method for reconstructing elevation information from measured data that were recorded with the aid of at least one radar device and include a two-dimensional spatial distribution of at least one physical measured variable. The measured data are fed as input variables to at least one generator module that is designed as a neural network. At least one output variable is retrieved from the generator module that represents a measure of the elevation angles from which radar radiation was reflected to the radar device from at least one object. A method for training a generator module, and a method including a complete active chain up to activating a vehicle, are also described.

The signal processing device includes an interference processing unit which generates an interferogram from a plurality of SAR images, a coherence calculation unit which calculates coherence of the SAR images, a singular point processing unit which performs an operation for resolving singular points in the interferogram, a phase unwrapping unit which executes a phase unwrapping process using operation result of the singular point processing unit, and an SBAS analysis unit which performs displacement analysis by SBAS, using processing result of the phase unwrapping unit.