公开(公告)号：US20240183799A1

公开(公告)日：2024-06-06

申请号：US18551707

申请日：2022-03-14

Applicant: GSI Electronique Inc ,  University of Manitoba

Inventor： Mohammad Asefi ,  Max Aaron Kelner Hughson ,  Hannah Claire Fogel ,  Ian Jeffrey ,  Joe LoVetri ,  Colin Gerald Gilmore

IPC: G01N22/04 ,  G01B15/00 ,  G01F23/284 ,  G06T7/00

CPC classification number: G01N22/04 ,  G01B15/00 ,  G01F23/284 ,  G06T7/0002 ,  G06T2207/10088 ,  G06T2207/20084

Abstract: In one embodiment, an electromagnetic imaging method, comprising: determining electromagnetic resonance data based on interrogating a stored commodity; and estimating features of the stored commodity based on the electromagnetic resonance data.

公开(公告)号：US20240183800A1

公开(公告)日：2024-06-06

申请号：US18551719

申请日：2022-03-16

Applicant: GSI Electronique Inc ,  University of Manitoba

Inventor： Mohammad Asefi ,  Ian Jeffrey ,  Joe LoVetri ,  Colin Gerald Gilmore ,  Eungjoo Kim

IPC: G01N22/04 ,  G01N33/02

CPC classification number: G01N22/04 ,  G01N33/02

Abstract: In one embodiment, a method, comprising: receiving measurement data of a container with contents stored within the container; performing a phaseless parametric inversion on the measurement data to provide a background model; determining calibration coefficients for each of a plurality of channels based on the measurement data and the background model; and determining calibrated scattered field measurements based on the background model and the calibration coefficients.

公开(公告)号：US20230280286A1

公开(公告)日：2023-09-07

申请号：US18042593

申请日：2021-07-27

Applicant: AGCO CORPORATION ,  University of Manitoba ,  GSI Electronique Inc

Inventor： Keeley Akiko Edwards ,  Ian Jeffrey ,  Colin Gerald Gilmore ,  Joe LoVetri ,  Mohammad Asefi ,  Nicholas Geddert ,  Kennedy Krakalovich ,  Ryan Kruk

IPC: G01N22/04 ,  G01N33/02 ,  G06N3/08

CPC classification number: G01N22/04 ,  G01N33/02 ,  G06N3/08

Abstract: In one embodiment, a system, comprising: one or more processors; and a memory comprising instructions, wherein the one or more processors are configured by the instructions to: receive first electromagnetic data at a plurality of frequencies; process the first electromagnetic data; and generate prediction parameters by passing the processed first electromagnetic data through a neural network trained on data corresponding to a synthetic training set, the prediction parameters corresponding to a container and contents located within the container.

公开(公告)号：US20240169716A1

公开(公告)日：2024-05-23

申请号：US18551688

申请日：2022-03-16

Applicant: GSI Electronique Inc ,  University of Manitoba

Inventor： Joe LoVetri ,  Vahab Khoshdel ,  Mohammad Asefi ,  Ahmed Bilal Ashraf

IPC: G06V10/82 ,  G06V10/25

CPC classification number: G06V10/82 ,  G06V10/25

Abstract: In one embodiment, a system, comprising: a neural network, configured to: receive electromagnetic field measurement data from an object of interest as input to the neural network, the neural network trained on labeled data; and reconstruct a three-dimensional (3D) distribution image of a physical property of the object of interest from the received electromagnetic field measurement data, the reconstruction implemented without performing a forward solve during the reconstruction.

公开(公告)号：US12105179B2

公开(公告)日：2024-10-01

申请号：US17767626

申请日：2020-10-08

Applicant: GSI Electronique Inc ,  University of Manitoba

Inventor： Ian Jeffrey ,  Colin Gerald Gilmore ,  Joe Lovetri ,  Jitendra Paliwal ,  Mohammad Asefi ,  William Kurt Hildebrand ,  Eric Conner Hawley

IPC: G01S13/04 ,  B65D88/08 ,  B65D90/00 ,  B65D90/22 ,  G01N22/00 ,  G01S7/41 ,  G06T7/62

CPC classification number: G01S13/04 ,  B65D88/08 ,  B65D90/008 ,  B65D90/22 ,  G01N22/00 ,  G01S7/41 ,  G06T7/62 ,  G06T2207/10028 ,  G06T2207/30188 ,  G06T2207/30196

Abstract: A system for detecting human entry into a container using electromagnetic imaging to generate image maps of the container. The system includes a door monitor configured to detect an entry door open event associated with the container. The system uses one or more processors and a memory with instructions to generate a baseline image map of the container, detect an entry door open event with the door monitor associated with the container, generate a post entry door open event image map of the container, and compare the baseline image map generated before the entry door open event with image map generated after the entry door open event.

公开(公告)号：US20220365002A1

公开(公告)日：2022-11-17

申请号：US17624382

申请日：2020-07-03

Applicant: GSI ELECTRONIQUE INC. ,  University of Manitoba

Inventor： Colin Gerald Gilmore ,  Ian Jeffrey ,  Joe LoVetri ,  Mohammad Asefi ,  Nicholas Geddert ,  Kevin Brown

IPC: G01N22/04 ,  G06T7/80

Abstract: A method for electromagnetic imaging of containers receives uncalibrated first data corresponding to signals of a first plurality of different frequencies associated with an antenna array residing in a container having contents. The method estimates of a second data based on a computer model and simulation of signals of a second plurality of different frequencies associated with the antenna array, the second plurality of different frequencies including a subset of the first plurality of different frequencies. The method compares magnitudes, without corresponding phase comparisons, of the first and second data at each frequency of the second plurality of different frequencies. The method updates the second data based on the comparing. The method provides information about the contents within the container based on the updated second data.