US 12,416,720 B2
Scintillation-based neural network for radar target classification
Daniel Flores Tapia, Fairfield, CA (US); and Kotung Lin, San Carlos, CA (US)
Assigned to GM CRUISE HOLDINGS LLC, San Francisco, CA (US)
Filed by GM CRUISE HOLDINGS LLC, San Francisco, CA (US)
Filed on Oct. 12, 2022, as Appl. No. 17/964,208.
Prior Publication US 2024/0125919 A1, Apr. 18, 2024
Int. Cl. G01S 13/89 (2006.01); G01S 7/02 (2006.01); G01S 13/931 (2020.01); G06N 3/047 (2023.01)
CPC G01S 13/89 (2013.01) [G01S 7/02 (2013.01); G01S 13/931 (2013.01); G06N 3/047 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
generating a point cloud from radio frequency (RF) scene responses received from a radio detection and ranging (RADAR) sensor for a scanned scene;
populating a rolling buffer with frame data from the point cloud, the frame data including radar cross section (RCS) values, RCS scintillation measurements corresponding to the RCS values, and velocity values for objects in the scanned scene;
inputting the RCS scintillation measurements and velocity values for an object of the objects in the scanned scene to a convolutional neural network (CNN); and
receiving a classification of the object from the CNN, wherein the CNN is to utilize a probability density function (PDF) estimate of the RCS scintillation measurements and the velocity values to determine fits with one or more reference PDFs based on a Neyman-Pearson evaluation, and wherein the fits are assessed to classify the object.