US 11,669,714 B1
Models for stop sign database creation
Muhammad Ali Akhtar, Oakland, CA (US); Abhishyant Khare, San Francisco, CA (US); Brian Tuan, Cupertino, CA (US); and John Charles Bicket, Burlingame, CA (US)
Assigned to SAMSARA INC., San Francisco, CA (US)
Filed by Samsara Inc., San Francisco, CA (US)
Filed on Aug. 24, 2021, as Appl. No. 17/410,295.
Application 17/410,295 is a continuation of application No. 17/197,557, filed on Mar. 10, 2021, granted, now 11,126,910.
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 3/02 (2006.01); G06F 16/29 (2019.01); G06N 7/01 (2023.01)
CPC G06N 3/02 (2013.01) [G06F 16/29 (2019.01); G06N 7/01 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A method performed by a computing system having one or more hardware computer processors and one or more non-transitory computer readable storage device storing software instructions executable by the computing system, the method comprising:
accessing map data including indications of points of interest within a geographic region;
accessing a plurality of trip stills data points each indicating at least a trip stills image obtained from a vehicle camera and an associated point of interest in the map data;
accessing a plurality of telemetry data points each indicating at least a speed of a vehicle and an associated point of interest in the map data; and
for individual points of interest:
evaluating a neural network based on the telemetry data points associated with the individual point of interest to determine a telemetry probability for the individual point of interest;
evaluating an object detection model for one or more trip stills data points associated with the individual point of interest to determine a corresponding one or more trip stills probabilities indicating likelihood of an object of interest in the trip stills image of the trip stills data point; and
determining a likelihood of the object of interest being present at the individual point of interest based on at least the telemetry probability for the individual point of interest and the one or more trip stills probabilities associated with the point of interest.