Abstract: Various embodiments of the present technology generally relate to detecting and manipulating radar image data. More specifically, some embodiments relate to systems, methods, and computer-readable storage media for detecting, processing, viewing, and manipulating radar images in an image viewer application. Radar image data captured by a radar imaging system, such as a synthetic aperture radar (SAR) or other satellite-based equipment, comprises data unreadable by image viewers. In an implementation, an open-source plug-in for an image viewer application obtains SAR data, performs one or more algorithms on the SAR data to detect an image, and provides the detected image to an image viewer for display on a graphical user interface. Further, requests for manipulation of the detected image made by the image viewer application may be performed by the plug-in and exported in complex data formats for use downstream.

Abstract: In various examples, a sensor model may be learned to predict virtual sensor data for a given scene configuration. For example, a sensor model may include a deep neural network that supports generative learning—such as a generative adversarial network (GAN). The sensor model may accept an encoded representation of a scene configuration as an input using any number of data structures and/or channels (e.g., concatenated vectors, matrices, tensors, images, etc.), and may output virtual sensor data. Real-world data and/or virtual data may be collected and used to derive training data, which may be used to train the sensor model to predict virtual sensor data for a given scene configuration. As such, one or more sensor models may be used as virtual sensors in any of a variety of applications, such as in a simulated environment to test features and/or functionality of one or more autonomous or semi-autonomous driving software stacks.

Abstract: Systems, devices, and methods related to a radar and an artificial neural network are described. For example, the radar can have at least one processing unit configured to execute instructions implementing matrix computation of the artificial neural network. The artificial neural network is configured to identify features in the radar image in an output responsive to an input containing a radar image. Optionally, the radar can further include an image sensor to generate an optical image as part of the input to artificial neural network. Instead of outputting the radar images and/or the optical images, the radar may output a description of the features identified via the artificial neural network from the radar image.

Abstract: A radar system receives threat relevant data with pulses sufficiently separated to provide sufficient long-range imaging, analyzes the return data to identify features of the threat, and generate a second set of pulses to acquire more detailed, higher granularity data specific to the threat. The system may include an ESA that is configured for pulses in a higher frequency to acquire higher resolution data specific to the threat.

Abstract: A Global Navigation Satellite System (GNSS) receiver includes a wideband signal correlator and a multipath mitigator. The wideband signal correlator generates wideband correlation signals of at least one of a plurality of GNSS signals with respect to corresponding locally generated code replica signals in which a bandwidth of the wideband signal correlation module is at least about 20 MHz. The multipath mitigator determines a Line of Sight (LOS) signal from the wideband correlation signals. The GNNS receiver may include a narrowband signal correlator to generate narrowband correlation signals of the at least one GNSS signal with respect to corresponding locally generated code replica signals in which a bandwidth of the narrowband signal correlation module is less than about 6 MHz. The multipath mitigator further corrects a range and range-rate measurement generated from the narrowband correlation signals based on a code phase and a carrier estimated based on the LOS signal.

Abstract: A method of emulating echo signals reflected from an elongated target during radar testing includes identifying first and second end points do the target; acquiring a radar signal from a radar sensor that includes multiple receive elements; generating emulated echo signals, responsive to the acquired radar signal, corresponding to target points on the target, including the first and second end points and reference points located on a line connecting the first and second end points, by repeatedly identifying descriptive attributes corresponding to each of the target points during an integration period of the radar sensor, where the descriptive attributes are identified by interpolating between the corresponding descriptive attributes of the first and second end points; and applying the emulated echo signals to the receive elements of the radar sensor, respectively, during the integration period, where radar sensor calculates a relative position of the target using the descriptive attributes.

Abstract: 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.

Abstract: A method and apparatus for processing a transceiver signal (115) detected by a transceiver (110). The method includes obtaining (S1) a processed signal from the transceiver signal (115), the processed signal having frames (200, 300) corresponding to respective time intervals (t1, t2, t3, t4), wherein the frames define bins (210, 310) configured according to a quantized resolution (dr) of the transceiver signal (115). The method further includes obtaining (S2) data related to a relative motion of the transceiver (110) during a time interval (t1, t2, t3, t4) and initializing (S3) a residual distance to zero.

Abstract: A radar target simulator front end, configured to simulate at least one radar target for testing a radar device under test is provided. The radar target simulator front end comprises at least two antenna units, arranged along a first angle under investigation. The at least two antenna units are configured to be selectively activated and deactivated. Whereby each antenna unit of the at least two antenna units generates a simulated radar target along the first angle under investigation, when activated.

Abstract: In various examples, a deep neural network(s) (e.g., a convolutional neural network) may be trained to detect moving and stationary obstacles from RADAR data of a three dimensional (3D) space, in both highway and urban scenarios. RADAR detections may be accumulated, ego-motion-compensated, orthographically projected, and fed into a neural network(s). The neural network(s) may include a common trunk with a feature extractor and several heads that predict different outputs such as a class confidence head that predicts a confidence map and an instance regression head that predicts object instance data for detected objects. The outputs may be decoded, filtered, and/or clustered to form bounding shapes identifying the location, size, and/or orientation of detected object instances. The detected object instances may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.

Abstract: The present application discloses a new form of ?-STAP, referred to herein as post ?-STAP or P?-STAP, which overcomes the drawbacks associated with existing ?-STAP techniques. The P?-STAP techniques described herein facilitate the generation of additional training data and homogenization after pulse compression. For example, P?-STAP techniques may apply a plurality of homogenization filters to a pulse compressed datacube generated from an input radar waveform, which produces a plurality of new pulse compressed datacubes with improved characteristics. Unlike existing ?-STAP techniques described above, which require pre-pulse compressed data to operate, the P?-STAP techniques disclosed in the present application are designed to utilize pulse compressed data, and therefore may be readily applied to legacy radar systems.

Abstract: Examples disclosed herein relate to generating continuous visualizations of beam steering vehicle radar scans by acquiring data for a beam steering radar scan, generating a Range Doppler Map (“RDM”) corresponding to the acquired radar data, displaying a visualization of the RDM showing a plurality of identified objects, shifting each identified object by its velocity to generate a shifted RDM, and updating the visualization at a display rate that is higher than a radar scan rate to display continuous movement. The display may be part of an augmented reality system presented to a driver on a windshield or dashboard.

Abstract: A radar sensor for measuring a fill level and/or a point level of a product in a container is described, including a sensor configured to emit and/or to receive a radar signal; evaluation circuitry configured to determine a measurement signal; a housing having at least one housing region configured such that the radar signal can be transmitted through the housing region; an adhesive surface including an adhesive material, configured to attach the radar sensor to the container wall, is disposed on the outside of the housing at least along a portion of an outer circumference of the housing region, and a sealing surface including a sealing material configured to at least partially seal the housing region when the radar sensor is attached to the container wall, the sealing surface being disposed on the outside of the housing at least along a portion of the outer circumference of the housing region.

Abstract: Techniques and apparatuses are described that implement electromagnetic vector sensors (EMVS) for a smart-device-based radar system. Instead of including an antenna array of similar antenna elements, the radar system includes two or more electromagnetic vector sensors. At least one of the electromagnetic vector sensors is used for transmission and at least another of the electromagnetic vector sensors is used for reception. Each electromagnetic vector sensor includes a group of antennas with different antenna patterns, orientations, and/or polarizations. An overall footprint of the two electromagnetic vector sensors (e.g., one for transmission and one for reception) can be smaller than antenna arrays used by other radar systems, thereby enabling the radar system to be implemented within space-constrained devices.

Abstract: A vehicular radar sensing system includes a radar sensor disposed at a vehicle so as to sense exterior of the vehicle and having at least one transmitter that transmits radio signals and at least one receiver that receives radio signals. The radar sensor includes a transmitting wave guide antenna and a receiving wave guide antenna, a PCB, and a processor operable to process radio signals transmitted by the at least one transmitter and received by the at least one receiver. Each of the wave guide elements includes a respective wave guide slot disposed at the inboard side of the PCB, and another respective wave guide slot that guides the radio signals to or from the environment, and a respective air wave guide that guides the radio signals between the respective wave guide slots.

Abstract: Herein disclosed is a method for radar detection of a valid target within a monitored zone with disturbing elements passing therethrough, e.g. process scraps of a machine on which the radar system is installed. The method includes transmitting, receiving and processing radar signals to locate and track the movement of a moving potential target. The method discriminates whether the potential target is valid or not, by checking whether the potential target has an initial position within a disturbance zone and whether it is detected for an overall detection time period that is less than the assessment time interval. If a target is not valid, it will be assimilated to background after it stops.

Abstract: A synthetic aperture radar image analysis system 20 includes: a phase correlation determination means 21 which determines a strength of the phase correlation between a plurality of pixels in an image selected from among a plurality of images on the basis of the plurality of images that have been photographed by a synthetic aperture radar and show the same point; a shape determination means 22 which determines a degree of similarity between the shape of the distribution of the plurality of pixels and an object shape indicated by geospatial information; and an association means 23 which associates the plurality of pixels with the object on the basis of the determined strength of the phase correlation and the determined degree of similarity.

Abstract: A narrowband AJ signaling system includes an AJ processor placed between a high precision analog-to-digital (ADC) converter and a narrowband digital receiver. In another example, the AJ processor is placed between the high precision ADC and a digital-to-analog converter (DAC). The AJ processor of either example may suppress the jammer power down to the level of the noise floor of the system.

Abstract: A system and method for detection and identification of an Unmanned Aircraft Systems (UAS) employs a radar system to detect and identify the UAS based on the rich Doppler spectrum generated by one or more rotors and associated motors onboard the UAS. UAS have a low radar cross sections (RCS), relatively low speed, and possess a unique Doppler signature providing data for the system to discriminate once the system detects the quadcopter UAS. The system and method functions as a traditional radar, yet analyzes the micro-Doppler signature, including the RCS and radial speed, to detect and identify the UAS. Based on the signature analysis, the system and method are able to distinguish one model from other types of UAS.

Abstract: In imaging radar, examples are directed to uses of multiple sets of transmit antenna included with transceiver circuitry, for transmitting in a plurality of modes. Transmissions may involve having at least one transmit antenna, from each of at least two of the multiple sets, to transmit continuous-wave energy concurrently (simultaneously) in one or more of the plurality of different modes. Transceiver circuitry may include multiple receive antennas which may be receiving reflections of the continuous-wave energy from various targets. Signals from the multiple receive antennas may route to signal processing circuitry. The signal processing circuitry may respond to the received reflections of the continuous-wave energy by assessing differences in antenna gain and/or phase due to transmit antenna position associated with the received reflections.