US 12,146,945 B2
Detection and estimation of spin
Batuhan Okur, Singapore (SG); Roshan Gopalakrishnan, Singapore (SG); Saurabh Garg, Singapore (SG); and Lodiya Radhakrishnan Vijayanand, Singapore (SG)
Assigned to RAPSODO PTE. LTD., Singapore (SG)
Filed by RAPSODO PTE. LTD., Singapore (SG)
Filed on Feb. 15, 2024, as Appl. No. 18/442,392.
Application 18/442,392 is a continuation of application No. 17/462,276, filed on Aug. 31, 2021, granted, now 11,940,525.
Prior Publication US 2024/0192352 A1, Jun. 13, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G01S 13/58 (2006.01); G01S 7/04 (2006.01); G01S 7/295 (2006.01); G06N 3/02 (2006.01); G06N 3/08 (2023.01); G06N 20/00 (2019.01)
CPC G01S 13/589 (2013.01) [G01S 7/046 (2013.01); G01S 7/295 (2013.01); G06N 3/02 (2013.01); G06N 3/08 (2013.01); G06N 20/00 (2019.01)] 25 Claims
OG exemplary drawing
 
1. A method comprising:
training a neural network with a set of initial data that has been generated based on a plurality of initial radar signals of a plurality of initial objects in motion;
receiving a radar signal of an object in motion;
converting the radar signal into an input vector, the input vector including time and frequency information of the object in motion;
providing the input vector as input to the trained neural network; and
determining a spin rate of the object in motion based on an analysis performed by the trained neural network, said analysis comprising analyzing the input vector including time and frequency information of the object in motion in view of the set of initial data;
wherein training the neural network comprises converting the plurality of initial radar signals into a plurality of initial input vectors, the plurality of initial input vectors including time and frequency information of the respective plurality of initial objects in motion.