A scan matching and radar pose estimator for determining a final radar pose for an autonomous vehicle includes an automated driving controller that is instructed to determine a hyper-local submap based on a predefined number of consecutive aggregated filtered data point cloud scans and associated pose estimates. The automated driving controller determines an initial estimated pose by aligning a latest aggregated filtered data point cloud scan with the most recent hyper-local submap based on an iterative closest point (ICP) alignment algorithm. The automated driving controller determines a pose graph based on the most recent hyper-local submap and neighboring radar point cloud scans, and executes a multi-view non-linear ICP algorithm to adjust initial estimated poses corresponding to the neighboring radar point cloud scans in a moving window fashion to determine a locally adjusted pose.

Techniques are discussed herein for analyzing radar data to determine that radar noise from one or more target detections potentially conceals additional objects near the target detection. Determining whether an object may be concealed can be based at least in part on a radar noise level based on a target detection, as well as distributions of radar cross sections and/or doppler data associated with particular object types. For a location near a target detection, a radar system may determine estimated noise levels, and compare the estimated noise levels to radar cross section probabilities associated with object types to determine the likelihood that an object of the object type could be concealed at the location. Based on the analysis, the system may determine a vehicle trajectory or otherwise may control a vehicle based on the likelihood that an object may be concealed at the location.

A detection system and a detection method are provided. The detection method includes configuring a processing circuit to perform an initialization phase, which includes: executing a detection process to respectively accumulate numbers of times that objects are detected to be present in sub-areas, so as to generate initial count values; and configuring the processing circuit to perform a normal operation phase, which includes: executing the detection process to respectively accumulate numbers of times that the objects are detected to be present in the sub-areas, so as to generate current count values corresponding to the sub-areas; and comparing the current count value with the initial count value in a current sub-area of the sub-areas. In response to the current count value being greater than the initial count value plus a first count threshold, a new stationary object is determined to be present in the current sub-area.

This disclosure relates generally to method and system to track and monitor human using an array of radars. Human tracking is necessarily important in security, especially with the growth of threats and incidents. Conventional systems and method lack in tracking target subject being authenticated to move around the monitoring environment. The present invention provides a method of detect human continually based on radar signals from an array of radars to track the presence of one or more target subjects associated within the monitoring environment. Further, a height surface plot of each target subject present in a radar range is constructed for identification. Then, each target subject present in the radar range of the monitoring environment based on mapping the height surface plot with a predefined height map. The characteristics of each target subject helps in detecting the target subject accurately.

A method for optimizing the elevational pointing of an antenna of an airborne radar system at an altitude h includes an antenna and processing and calculation means, the method comprising: a. selecting an area of interest b. calculating atmospheric losses L.sub.ref at a reference altitude h.sub.ref at the reference range D.sub.ref and calculating a reference criterion K.sub.ref=−40 log.sub.10 (D.sub.ref); c. for each possible elevational pointing distance of the antenna D.sub.pt from the area of interest, calculating the antenna elevation S that makes it possible to target the distance D.sub.pt via the centre of the antenna; d. for each distance D from the region of interest, calculating the angle θ at which the antenna observes the point of the ground at the distance D and calculating a criterion; 1. K(D)=G.sub.e(θ)+G.sub.r(θ)−40 log.sub.10 D+L.sub.ref(h.sub.ref,D.sub.ref)−L.sub.atmo(h,D) 2. where G.sub.e(θ),G.sub.r(θ) are respectively the gains of the antenna that are normalized at emission and at reception; e. calculating all of the distances D that, for this pointing distance D.sub.pt, satisfy the relationship K(D)>K.sub.ref so as to obtain the start and the end of the sub-swath actually able to be used by the radar system; and calculating the actually usable sub-swaths that are to be juxtaposed (A, B, C) in order to cover the whole of the area of interest without discontinuities.

A device for estimating a distance based on object detection and a method thereof are provided. The device for estimating a distance based on object detection according to an embodiment of the present disclosure includes a fusion sensor including a first sensor configured to detect positions of a plurality of objects in front of a host vehicle and a second sensor configured to capture a front image of the host vehicle, and a controller communicatively connected to the fusion sensor and configured to recognize all radar tracks corresponding to distances detected by the first sensor and all vision tracks corresponding to distances detected by the second sensor, assign adjacent vision tracks for each of the radar tracks to one cluster, and correct distances of all the vision tracks assigned to the corresponding cluster based on the closest vision track from the radar track for each cluster.

The present invention provides a sensor recognition integration device capable of preventing a rapid change in coordinates of an integrated object and preventing, for example, an erroneous determination in an autonomous driving plan determination device, even when the combination of sensors that perform detection changes. In the present invention, since an object position is estimated in a state where information of a position detected by a sensor that recognizes an object in an external field is corrected or changed, the rapid change of coordinates of an integrated object is prevented even when the combination of sensors that perform detection changes.

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.

A gesture recognition method and a related apparatus are provided, to obtain a first point cloud data set by filtering an original point cloud data set collected by a radar apparatus. The first point cloud data set includes a plurality of frames of first point cloud subsets, the first point cloud subset includes a first cluster center, the first cluster center is a cluster center of a plurality of pieces of point cloud data in the first point cloud subset, a maximum horizontal distance between any two first cluster centers meets a first preset condition, and duration of the first point cloud data set meets the first preset condition. Point cloud data whose motion track does not match gesture motion can be effectively filtered out. Gesture recognition is performed by using the first point cloud data set obtained by filtering.

The techniques and systems herein enable target-velocity estimation using position variance. Specifically, a plurality of detections of a target are received for respective times as the target moves relative to a host vehicle. Based on the detections, two-dimensional positions of the target relative to the host vehicle are determined for the respective times. Based on the positions of the target at the respective times, a first variance is determined for a first dimension of the positions, and a second variance is determined for a second dimension of the positions. Based on the first and second variances, an estimated velocity of the target is calculated. By basing the estimated velocity on the variances of the positions, more-accurate estimated velocities may be generated sooner, thus enabling better performance of downstream operations.