System and method for determining a 3D coordinate of a moving target are provided. The system may obtain 2D detection data of the moving target generated by a 2D detection device including two detection assemblies that are mounted at a known height above a horizontal plane along a first axis that forms a tilting angle with the horizontal plane. The system may determine a 2D coordinate of the moving target in a first coordinate system including the first axis and a second axis that is perpendicular to the first axis based on the 2D detection data. The 2D coordinate of the moving target may include a first value of the first axis and a second value of the second axis. The system may determine the 3D coordinate of the moving target in a second coordinate system based on the 2D coordinate, the tilting angle, and the known height.

In an embodiment, a method for generating a target set using a radar includes: generating, using the radar, a plurality of radar images; receiving the plurality of radar images with a convolutional encoder; and generating the target set using a plurality of fully-connected layers based on an output of the convolutional encoder, where each target of the target set has associated first and second coordinates.

A tracking device is provided, which may include a correction target area setting module configured to set an area in which an unnecessary echo tends to be generated based on a structure or behavior of a ship, as a correction target area, a correction target echo extracting module configured to extract a target object echo within the correction target area from a plurality of detected target object echoes, as a correction target echo, a scoring module configured to score a matching level between previous echo information on a target object echo and detected echo information on each of the target object echoes, based on the previous echo information, the detected echo information and the extraction result, and a determining module configured to determine a target object echo as a current tracking target by using the scored result.

A signal processing apparatus including a first position calculation unit that calculates a three-dimensional position of a target on a first coordinate system from a stereo image captured by a stereo camera, a second position calculation unit that calculates a three-dimensional position of the target on a second coordinate system from a sensor signal of a sensor capable of obtaining position information of at least one of a lateral direction and a longitudinal direction and position information of a depth direction, a correspondence detection unit that detects a correspondence relationship between the target on the first coordinate system and the target on the second coordinate system, and a positional relationship information estimating unit that estimates positional relationship information of the first coordinate system and the second coordinate system on the basis of the detected correspondence relationship.

In an embodiment, a method for generating a target set using a radar includes: generating, using the radar, a plurality of radar images; receiving the plurality of radar images with a convolutional encoder; and generating the target set using a plurality of fully-connected layers based on an output of the convolutional encoder, where each target of the target set has associated first and second coordinates.

A computer implemented method for detection of objects in a vicinity of a vehicle comprises the following steps carried out by computer hardware components: acquiring radar data from a radar sensor; determining a plurality of features based on the radar data; providing the plurality of features to a single detection head; and determining a plurality of properties of an object based on an output of the single detection head.

A system and method of conducting a vehicle by at least one processor may include: receiving sensor data from a plurality of sensor channels associated with the vehicle; for each sensor channel, calculating a three-dimensional (3D) reconstruction data element, representing real-world spatial information, based on said sensor data; for each sensor channel, calculating a channel score based on the 3D reconstruction data element; selecting a sensor channel of the plurality of sensor channels based on the channel score; and conducting the vehicle based on the 3D reconstruction data element of the selected sensor channel.

The present disclosure generally pertains to radar determination circuitry configured to: measure a first position of a radar source and a second position of the radar source with respect to a reference coordinate system of a vehicle, wherein the first position and the second position differ from each other for synchronizing the movement of the radar source with a measurement frame including multiple chirp sequences for distinguishing multiple targets; and determine, for each of the multiple targets, a target parameter based on the synchronized movement of the radar source with the measurement frame.

A method and system for enabling online perception performance evaluation for an ego-vehicle are disclosed. Method includes obtaining sensor data from a perception system of the ego-vehicle, where the sensor data includes information about at least one object in surrounding environment of ego-vehicle. Method includes obtaining communication data from an external vehicle in surrounding environment of ego-vehicle, where obtained communication data includes at least one physical attribute of external vehicle. Method includes comparing obtained at least one physical attribute of the external vehicle with information about at least one object in order to find an object of at least one object that matches at least one physical attribute. Then, if a match for at least one physical attribute is found, method further includes obtaining world view data indicative of world view of external vehicle, forming a common reference system between the ego-vehicle and external vehicle.

An information processing device according to one aspect of the present invention includes at least one memory storing instructions; and at least one processor coupled to the memory and configured to execute the instructions to: extract a candidate point which is a point contributing to a signal at a target point, based on a position of the target point in a three-dimensional space and a shape of an observed object, the target point being a point specified in an intensity map of the signal from the observed object, the intensity map being acquired by a radar; and generate an image indicating a position of the candidate point in a spatial image capturing the observed object.