A method for detecting objects and labeling the objects with distances in an image includes steps of: obtaining a thermal image from a thermal camera, an RGB image from an RGB camera, and radar information from an mmWave radar; adjusting the thermal image based on the RGB image to generate an adjusted thermal image, and generating a fused image based on the RGB image and the adjusted thermal image; generating a second fused image based on the fused image and the radar information; detecting objects in the images, and generating, based on the fused image, another fused image including bounding boxes marking the objects; and determining motion parameters of the objects.

A method for converting measured data of at least one source measurement modality into realistic measured data of at least one target measurement modality. The method includes: the measured data of the source measurement modality are mapped onto representations in a latent space using an encoder of a trained encoder-decoder arrangement, and the representations are mapped onto the realistic measured data of the target measurement modality using the decoder of the encoder-decoder arrangement, the amount of information of the representations of measured data in the latent space being smaller than the amount of information of the measured data.

A vehicle radar sensor unit (2) arranged to acquire a plurality of radar detections, and including an antenna arrangement (3), a transmitter unit (4), a receiver unit (5) and a processing unit (6). The antenna arrangement (3) has at least two transmitter antennas (7, 8) and at least two receiver antennas (9, 10, 11, 12), where two transmitter antennas (7, 8) have a vertical spacing (h) between their respective phase centers (17, 18) that exceeds half the free-space wavelength of the transmitted signal. The processing unit (5) is arranged to determine a first radial velocity of each radar detection by tracking the change of radial distance (r) to each radar detection for a plurality of radar cycles; determine a second radial velocity that best matches the first radial velocity; track a plurality of measured heights (z) as a function of radial distance (r); and to choose a measured height (z.sub.GT) among the tracked measured heights (z) that has a minimal change from radar cycle to radar cycle.

A method for determining the validity of radar measured values in order to determine an occupancy state of a parking space. A device that includes at least one radar sensor and a processing unit, the processing unit being configured to carry out the method. A parking area that includes at least one parking space, the parking space including the device.

A system for localization includes a radar, a database, a simulator, a registrar, and a filter. The radar is positioned at a disposed location requiring localization. The radar generates a radar image scanning a proximity around the disposed location. The database stores features of a landmass. The simulator generates synthesized images of the features that the radar is predicted to generate from corresponding viewpoints. The registrar calculates respective correlation indicators between the radar image and each synthesized image. The filter sets a pose estimate of the disposed location to an average of those viewpoints from which correspond the synthesized images having the best or better ones of the correlation indicators.

Methods and systems are described that enable radar reference map generation. A high-definition (HD) map is received and one or more HD map objects within the HD map are determined. Attributes of the respective HD map objects are determined, and, for each HD map object, one or more occupancy cells of a radar occupancy grid are indicated as occupied space based on the attributes of the respective HD map object. By doing so, a radar reference map may be generated without a vehicle traversing through an area corresponding to the radar reference map.

This document describes methods and systems for vehicle localization based on radar detections. Radar localization starts with building a radar reference map. The radar reference map may be generated and updated using different techniques as described herein. Once a radar reference map is available, real-time localization may be achieved with inexpensive radar sensors and navigation systems. Using the techniques described in this document, the data from the radar sensors and the navigation systems may be processed to identify stationary localization objects, or landmarks, in the vicinity of the vehicle. Comparing the landmark data originating from the onboard sensors and systems of the vehicle with landmark data detailed in the radar reference map may generate an accurate pose of the vehicle in its environment. By using inexpensive radar systems and lower quality navigation systems, a highly accurate vehicle pose may be obtained in a cost-effective manner.

Methods and systems are described that enable radar reference map generation. A radar occupancy grid is received, and radar attributes are determined from occupancy probabilities within the radar occupancy grid. Radar reference map cells are formed, and the radar attributes are used to determine Gaussians for the radar reference map cells that contain a plurality of the radar attributes. A radar reference map is then generated that includes the Gaussians determined for the radar referenced map cells that contain the plurality of radar attributes. By doing so, the generated radar reference map is accurate while being spatially efficient.

In one embodiment, a method includes, by a computing system associated with a vehicle, receiving sensor data from one or more sensors of the vehicle, wherein the sensor data is based on an environment of the vehicle, identifying, based on the sensor data, one or more objects in the environment, generating, based on the one or more objects, a set of points that represent the environment, wherein each object has one or more corresponding points in the set of points, and each of the points is associated with one or more features associated with the corresponding object, generating a prediction for at least one of the objects in the environment or the vehicle by processing the set of points using a machine-learning model, and causing the vehicle to perform one or more operations based on the prediction.

The present disclosure provides a ship monitoring system capable of appropriately evaluating risks of collisions for a plurality of other ships which constitute a convoy. The ship monitoring system includes a first data generator, a second data generator, and processing circuitry. The first data generator generates first ship data indicative of a position and a velocity of a first ship. The second data generator generates a plurality of second ship data indicative of positions and velocities of a plurality of second ships. The processing circuitry calculates a risk value indicative of a risk of a collision between the first ship and each of the plurality of second ships based on the first ship data and the plurality of second ship data. The processing circuitry determines whether the plurality of second ships are a convoy based on the plurality of second ship data. The processing circuitry selects a representative value from the risk values calculated for the plurality of second ships determined to be the convoy.