Tracking an object included in a reflective surface by detecting the reflective surface included in one or more images included in a plurality of images by determining a location of the reflective surface in pixel coordinates and tracking the location of the reflective surface in the plurality of images. Real world locations of the object can be determined based on attributes of the reflective surface including a geometric class, extrinsic properties that relate the reflective surface to an environment, intrinsic properties describing the reflective surface without referring to the environment and calibration properties of the sensor.

In an aspect, a wireless node may transmit one or more messages to a reconfigurable intelligence surface (RIS), the one or more messages indicating a sensing beam sweeping mode for a sensing operation, an incident angle of a forward path of the sensing operation with respect to the RIS, a redirected angle of the forward path of the sensing operation with respect to the RIS, or any combination thereof. The wireless node may transmit a sensing signal for the sensing operation to the RIS, the RIS being configured based on the sensing beam sweeping mode, the incident angle of the forward path, the redirected angle of the forward path, or any combination thereof.

This document describes techniques and systems to enable a radar system to jointly detect DoA and DoD angles in multipath scenarios. In some examples, an automotive radar system includes one or more processors. The processors obtain electromagnetic (EM) energy reflected by objects and generate, based on the reflected EM energy, a two-dimensional (2D) data matrix. The 2D data matrix has a number of rows corresponding to the number of antenna elements in a transmitter array and a number of columns corresponding to the number of antenna elements in a receiver array. Using the 2D data matrix, the processors can determine DoA estimates and DoD estimates in both monostatic and bistatic reflection scenarios. By comparing the DoA estimates to the DoD estimates, the processors determine angles associated with the objects with improved angular resolution and reduced cost.

The present invention provides an obstacle detection method, an obstacle detection system and a vehicle. An original range profile is separated to obtain a first range profile of a first target according to echo signal models, therefore a two-dimensional position coordinate of the first target is determined. The first target is in front of or beside a second target and is in an invisible line of sight of the mmWave radar, and the second target is in a direct line of sight of the mmWave radar. By adopting a signal separation method in the present invention, the first range profile can be effectively separated from an original range profile, thereby reducing interference of a range profile of the second target, and obtaining an accurate position of the first target.