International Business Machines Corporation

University of Illinois

Nokia Solutions and Networks Oy

Junfeng Guan

Alberto Valdes Garcia

Harish Viswanathan

Bodhisatwa Sadhu

Arun Paidimarri

Asaf Tzadok

Saeed Reza Khosravirad

Haitham Al Hassanieh

Suraj S Jog

Seyedsohrab Madani

Jakub Sapis

Saurabh Gupta

Disclosed is a method including transmitting one or more reference signals to one or more user devices; performing preliminary sensing over a sensing area of interest based at least partly on the one or more reference signals; allocating, based at least partly on the preliminary sensing, radio resources for performing sensing with a higher resolution than a resolution of the preliminary sensing; and performing the sensing with the higher resolution over the sensing area of interest by using the allocated radio resources.

Resource allocation in joint communication and sensing

Methods and systems for estimating a distance to an object are described. In an example, a device can receive a reflected signal of a modulated signal being used in a wireless transmission of data. The reflected signal can be a reflection of the modulated signal from at least one object. The device can estimate a distance to the at least one object based on the modulated signal and the reflected signal. Further, the device can use the estimated distance to image a scenery including the at least one object.

Imaging with wireless communication signals

A method includes receiving data including a plurality of data items, each data item of the plurality of data items including a three-dimensional (3D) radar heat map of an object and a corresponding two-dimensional (2D) image of the object captured by a stereo camera, inputting the training dataset into a machine learning model including a neural network (NN) that generates, from the 3D radar heat map, a 2D depth map for the object and outputs a probability that the 2D depth map is the corresponding 2D image of the object, and training the machine learning model based on a training dataset to generate a trained machine learning model that iteratively learns to generate an updated 2D depth map that approximates the corresponding 2D image. The training dataset includes the plurality of data items, the 2D depth map and the probability.

Neural network-based millimeter-wave imaging system

Growing community of inventors

Champaign, IL, United States of America

Junfeng Guan