US 12,216,229 B2
Parametric CNN for radar processing
Avik Santra, Irvine, CA (US); and Thomas Reinhold Stadelmayer, Wenzenbach (DE)
Assigned to Infineon Technologies AG, Neubiberg (DE)
Filed by Infineon Technologies AG, Neubiberg (DE)
Filed on Aug. 29, 2023, as Appl. No. 18/239,521.
Application 18/239,521 is a continuation of application No. 16/905,335, filed on Jun. 18, 2020, granted, now 11,774,553.
Prior Publication US 2023/0408649 A1, Dec. 21, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G01S 7/41 (2006.01); G01S 13/89 (2006.01); G01S 7/285 (2006.01); G01S 7/35 (2006.01); G01S 13/02 (2006.01); G01S 13/06 (2006.01); G01S 13/32 (2006.01); G01S 13/34 (2006.01); G06N 3/045 (2023.01); G06N 3/08 (2023.01)
CPC G01S 7/417 (2013.01) [G01S 7/412 (2013.01); G01S 7/415 (2013.01); G01S 13/89 (2013.01); G01S 7/285 (2013.01); G01S 7/352 (2013.01); G01S 2013/0245 (2013.01); G01S 13/06 (2013.01); G01S 13/32 (2013.01); G01S 13/34 (2013.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
transmitting a plurality of sensor signals towards a target;
receiving a plurality of reflected sensor signals that correspond to the plurality of transmitted sensor signals;
producing raw digital data representing the reflected sensor signals;
processing the raw digital data using a constrained L dimensional convolutional layer of a neural network to generate intermediate digital data, wherein L is a positive integer greater than or equal to 2, and wherein the neural network comprises a plurality of additional layers, and wherein processing the raw digital data comprises using a time-domain two-dimensional (2D) filter to filter the raw digital data in a fast time dimension and in a slow time dimension; and
processing the intermediate digital data using the plurality of additional layers to generate information about the target.