US 12,073,636 B2
Multi-sensor analysis of food
Cynthia Kuo, Mountain View, CA (US); Maher Matta, Sunnyvale, CA (US); and Avik Santra, Irvine, CA (US)
Assigned to Infineon Technologies AG, Neubiberg (DE)
Filed by Infineon Technologies AG, Neubiberg (DE)
Filed on May 30, 2023, as Appl. No. 18/325,575.
Application 18/325,575 is a continuation of application No. 17/368,570, filed on Jul. 6, 2021, granted, now 11,704,917.
Claims priority of provisional application 63/049,823, filed on Jul. 9, 2020.
Prior Publication US 2023/0306759 A1, Sep. 28, 2023
Int. Cl. G01S 13/86 (2006.01); G06T 7/00 (2017.01); G06V 10/82 (2022.01); G06V 20/64 (2022.01); G06V 20/68 (2022.01); G16H 20/60 (2018.01)
CPC G06V 20/647 (2022.01) [G01S 13/867 (2013.01); G06T 7/0004 (2013.01); G06V 10/82 (2022.01); G06T 2207/30128 (2013.01); G06V 20/68 (2022.01); G16H 20/60 (2018.01)] 24 Claims
OG exemplary drawing
 
1. A method for estimating a composition of a substance, the method comprising:
receiving a first 3D image;
identifying the substance in the first 3D image;
determining a volume of the identified substance based on the first 3D image; and
estimating the composition of the identified substance using a millimeter-wave radar, wherein estimating the composition of the identified substance comprises:
receiving radar data from an ADC of the millimeter-wave radar,
preprocessing the received radar data to generate a radar image, and
using a deep convolutional neural network (DCNN) to estimate the composition of the substance based on the radar image.