A sensor signal processing unit (100) arranged to detect a configuration of parking slots (1a,1b,1c,1d) based on radar detections received from a radar-based sensor system (120). The unit includes a histogram unit arranged to generate a representation of a spatial distribution of a set of radar detection coordinates, and a detection unit arranged to detect the configuration of parking slots. The detection unit is arranged to detect the configuration of parking slots based on a Fourier transform of the representation of spatial distribution.

An ultra-wideband-based system and method for detecting properties associated with a movable object in an environment such as an indoor environment. The method includes transmitting ultra-wideband radar signals to an environment, using an ultra-wideband transmitter, and receiving signals reflected from the environment as a result of the transmission of the first ultra-wideband radar signals using an ultra-wideband receiver. The method also includes processing the reflected signals and determining properties associated with a movable object in an environment based on the processed reflected signals, using the processor.

Systems and methods involve detecting objects using a radar system of a vehicle. Tracks of the objects are initiated in a track database. The tracks store data, respectively, for the objects and are updated based on additional detections of the objects. The tracks of the objects are initially unclassified tracks. Two tracks corresponding to two of the objects are selected as a candidate pair. Criteria are applied to the candidate pair to determine whether one track is of a ghost object and another track is of a true object corresponding with the ghost object. The ghost object represents detection of the true object in an incorrect location. The candidate pair is classified as tracks of a true object and ghost object pair based on determining that the one track is of the ghost object and the other track is of the true object corresponding with the ghost object.

A method for classification of ground conditions in the vicinity of a vehicle using a radar sensor, comprising: receiving reflected portions of a radar signal at a receiver unit of a radar system; calculating information derived from the received portions of the radar signal for discrete spatial regions by the radar system or a control unit connected thereto; assigning the information to data structure units associated with a geographical location and the assignment of the information taking into account movement of the vehicle; collecting pieces of information in the respective data structure units, the pieces of information being obtained from reflected portions of radar signals transmitted at different times; evaluating the information contained in the data structure using a classifier to obtain information regarding the ground condition; assigning ground condition types to the data structure units based on evaluation results obtained by the classifier.

An object detection method includes: obtaining a first offset value and a second offset value, setting a first detection threshold value by adding the first offset value to a first reference threshold value, setting a second detection threshold value by adding the second offset value to a second reference threshold value, obtaining a detection input, and performing target detection upon the detection input according to at least the first detection threshold value and the second detection threshold value. The first offset value is different from the second offset value. The first reference threshold value is determined for detecting if at least one object with a first value of an object characteristic exists. The second reference threshold value is determined for detecting if at least one object with a second value of the object characteristic exists. The second value is different from the first value.

A snapshot comprises a plurality of signals is received where each of the plurality of signals reflected from a respective source and received by an antenna array. A first DoA estimator determines, based on the received snapshot, a plurality of DoAs, the plurality of DoAs comprising a respective DoA for each of the plurality of signals. A reliability of the plurality of DoAs is measured. In response to the reliability of the plurality of the DoAs exceeding a threshold, at least one of the plurality of the DoAs determined by the first DoA estimator is output. In response to the reliability of the plurality of the DoAs not exceeding the threshold, a second DoA estimator determines based on the received snapshot a second plurality of DoAs comprising a respective DoA of each of the plurality of signals and outputs at least one of the second plurality of DoAs.

A system and method for detection of an aerial drone in an environment includes a baseline of geo-mapped sensor data in a temporal and location indexed database formed by (i) using at least one sensor to receive signals from the environment and converting into digital signals for further processing; (ii) deriving time delays, object signatures, Doppler shifts, reflectivity, and/or optical characteristics from the received signals; (iii) geo-mapping the environment using GNSS and the sensor data; and (iv) logging sensor data over a time interval, for example 24 hours to 7 days. Live sensor data can be then be monitored and signature data can be derived by computing at least one parameter such as direction and signal strength. The live data is continuously or periodically compared to the baseline data to identify a variance, if any, which may be indicative of a detection event.

A vehicle control device is mountable on a vehicle. The vehicle control device includes: a processor; and a memory storing instructions that, when executed by the processor, cause the vehicle control device to perform operations including: acquiring detection information obtained by detecting an obstacle around the vehicle; performing collision determination of evaluating a possibility of collision with the obstacle; generating, based on the detection information, information on an approaching object that is an obstacle approaching the vehicle and information on a detection point indicating an obstacle that does not move; estimating a position of a shielding object based on the information on the detection point; evaluating, based on the position of the shielding object and the information on the approaching object, a ghost likelihood indicating a possibility that the approaching object is a ghost; and excluding, based on the ghost likelihood, the approaching object from the collision determination.

This document describes techniques and systems related to a radar system using a machine-learned model for stationary object detection. The radar system includes a processor that can receive radar data as time-series frames associated with electromagnetic (EM) energy. The processor uses the radar data to generate a range-time map of the EM energy that is input to a machine-learned model. The machine-learned model can receive as inputs extracted features corresponding to the stationary objects from the range-time map for multiple range bins at each of the time-series frames. In this way, the described radar system and techniques can accurately detect stationary objects of various sizes and extract critical features corresponding to the stationary objects.

A deployment of sensors transmit radio frequency (RF) signals into an area of interest. The radar maps are generated from the reflected signals, including a static radar map and a dynamic radar map. Multipath and radar sidelobes are removed from the radar maps using a neural network to produce a density map. The neural network can be trained in two phases: a training phase that uses training data from a training site and a transfer learning phase that uses training data from the area of interest.