Techniques and apparatuses are described that implement motion classification using low-level detections. In particular, a radar system identifies fused detections associated with an object and determines whether the fused detections indicate that the object is moving. If it is determined to be moving or moving perpendicular to the host vehicle, a current motion counter or perpendicular motion counter is incremented, respectively. A current motion flag and/or a perpendicular motion flag are set as true if the current motion counter or the perpendicular motion counter has a value greater than a threshold value, respectively. In response to setting either flag as true, the radar system increments a historical motion counter as true. The host vehicle is then operated based on the current motion flag, the perpendicular motion flag, and the historical motion counter. In this way, the radar system introduces hysteresis to improve the reliability and stability of motion classification.

A system can include a computer including a processor and a memory, the memory storing instructions executable by the processor to receive point cloud data. The instructions further include instructions to generate a plurality of feature maps based on the point cloud data, each feature map of the plurality of feature maps corresponding to a parameter of the point cloud data. The instructions further include instructions to aggregate the plurality of feature maps into an aggregated feature map. The instructions further include instructions to generate, via a feedforward neural network, at least one of a segmentation output or a classification output based on the aggregated feature map.

In implementations of systems for estimating three-dimensional trajectories of physical objects, a computing device implements a three-dimensional trajectory system to receive radar data describing millimeter wavelength radio waves directed within a physical environment using beamforming and reflected from physical objects in the physical environment. The three-dimensional trajectory system generates a cloud of three-dimensional points based on the radar, each of the three-dimensional points corresponds to a reflected millimeter wavelength radio wave within a sliding temporal window. The three-dimensional points are grouped into at least one group based on Euclidean distances between the three-dimensional points within the cloud. The three-dimensional trajectory system generates an indication of a three-dimensional trajectory of a physical object corresponding to the at least one group using a Kalman filter to track a position and a velocity a centroid of the at least one group in three-dimensions.

Disclosed is a method and system to provide protection for maritime vessels from multiple threat types including shoulder launched rocket propelled threats, ballistic (howitzer), and larger scale missile systems. According to an exemplary embodiment, the protection system is based on the ballistic launch (from the protected vessel) of an explosive charge(s) aimed ˜5 meters away from the vessel and ˜1 meter beneath the waterline followed by detonation to enable the formation of a water wall. Through the formation of a water wall, incident threats can be initiated (piezo fuze), and passivated through dynamic interaction with the water formation. In addition, the upward velocity of the water wall can enable an upwards rotation of the incident threat changing the orientation of the warhead jet formation (for shape charge warheads) above the vessel.

Sensors, including radar sensors, may be used to detect objects in an environment. In an example, a vehicle may include one or more radar sensors that sense objects around the vehicle, e.g., so the vehicle can navigate relative to the objects. A plurality of radar points from one or more radar scans are associated with a sensed object and a representation of the sensed object is determined from the plurality of radar points. The representation may be compared to track information of previously-identified, tracked objects. Based on the comparison, the sensed object may be associated with one of the tracked objects, and, alternatively, the track information may be updated based on the representation. Conversely, the comparison may indicate that the sensed object is not associated with any of the tracked objects. In this instance, the representation may be used to generate a new track, e.g., for the newly-sensed object.

Sensors, including radar sensors, may be used to detect objects in an environment. In an example, a vehicle may include one or more radar sensors that sense objects around the vehicle, e.g., so the vehicle can navigate relative to the objects. A plurality of radar points from one or more radar scans are associated with a sensed object and a representation of the sensed object is determined from the plurality of radar points. The representation may be compared to track information of previously-identified, tracked objects. Based on the comparison, the sensed object may be associated with one of the tracked objects, and, alternatively, the track information may be updated based on the representation. Conversely, the comparison may indicate that the sensed object is not associated with any of the tracked objects. In this instance, the representation may be used to generate a new track, e.g., for the newly-sensed object.

A radar system for monitoring shelves in a retail environment, where the system monitors the occupancy of the shelves and/or the dynamics of the customers in front of the shelves. The radar is preferably a wideband 3D imaging MIMO radar.

Techniques are disclosed for radar data denoising systems and methods. In one example, a method includes receiving radar data. The method further includes performing a first transform associated with the radar data to obtain transformed radar data. The transformed radar data is associated with a location parameter and a variance that is independent of the location parameter. The method further includes performing a second transform of the transformed radar data to obtain dimensionality-reduced radar data. The method further includes filtering the dimensionality-reduced radar data to obtain denoised dimensionality-reduced radar data. Related devices and systems are also provided.

Provided is an object recognition device including a temporary setting unit and an update processing unit. The temporary setting unit sets, based on specifications of an external information sensor that has detected an object, a position of at least one candidate point on the object. The update processing unit corrects a position of a detection point with respect to the external information sensor at a time when the external information sensor has detected the object based on the position of the candidate point on the object, and updates track data indicating a track of the object based on a position of the detection point with respect to the external information sensor after the correction.

A tracking device is configured to estimate a track for at least one possible target and is configured to receive incoming measurements and to process measurements and tracks. The tracking device includes a storage and a computational device. The tracking device is also configured to divide all measurements into a set of considered measurements and a set of unconsidered measurements for each passive track.