US 11,790,664 B2
Estimating object properties using visual image data
James Anthony Musk, San Francisco, CA (US); Swupnil Kumar Sahai, Saratoga, CA (US); and Ashok Kumar Elluswamy, Sunnyvale, CA (US)
Assigned to Tesla, Inc., Austin, TX (US)
Filed by Tesla, Inc., Austin, TX (US)
Filed on Mar. 23, 2022, as Appl. No. 17/656,183.
Application 17/656,183 is a continuation of application No. 17/249,110, filed on Feb. 19, 2021, granted, now 11,288,524.
Application 17/249,110 is a continuation of application No. 16/279,657, filed on Feb. 19, 2019, granted, now 10,956,755, issued on Mar. 23, 2021.
Prior Publication US 2022/0284712 A1, Sep. 8, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06V 20/58 (2022.01); G06T 7/70 (2017.01); G06N 20/00 (2019.01); G06V 10/80 (2022.01)
CPC G06V 20/58 (2022.01) [G06N 20/00 (2019.01); G06T 7/70 (2017.01); G06V 10/803 (2022.01); G06V 20/584 (2022.01); G06T 2207/20081 (2013.01); G06T 2207/30261 (2013.01)] 15 Claims
OG exemplary drawing
 
1. A method implemented by a processor included in a vehicle, the method comprising:
receiving a time series training set comprising a plurality of images captured over a period of time, the images depicting an object proximate to a vehicle and being associated with respective timestamps, wherein the time series training set is associated with label information indicating, at least, respective distances of the object with respect to the vehicle and auxiliary data associated with the vehicle;
training a machine learning model based on the time series training set; and
providing the machine learning model for execution by one or more other vehicles, wherein the machine learning model is configured to output distance information associated with objects.