US 11,727,668 B2
Using captured video data to identify pose of a vehicle
Rotem Littman, Hod Hasharon (IL); Gilad Saban, Rehovot (IL); Noam Presman, Ramat Gan (IL); Dana Berman, Tel Aviv (IL); and Asaf Kagan, Herzliya (IL)
Assigned to ARGO AI, LLC, Pittsburgh, PA (US)
Filed by Argo AI, LLC, Pittsburgh, PA (US)
Filed on Nov. 7, 2022, as Appl. No. 18/53,069.
Application 18/053,069 is a continuation of application No. 17/216,848, filed on Mar. 30, 2021, granted, now 11,527,078.
Application 17/216,848 is a continuation of application No. 16/535,335, filed on Aug. 8, 2019, granted, now 11,003,928, issued on May 11, 2021.
Prior Publication US 2023/0091928 A1, Mar. 23, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 11/20 (2006.01); G06V 10/44 (2022.01); G06T 7/70 (2017.01); G06T 7/20 (2017.01); G06T 7/00 (2017.01); G06T 7/90 (2017.01); G05D 1/02 (2020.01); G05D 1/00 (2006.01); G06V 20/58 (2022.01); G06V 20/40 (2022.01); G06F 18/24 (2023.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 10/75 (2022.01)
CPC G06V 10/454 (2022.01) [G05D 1/0088 (2013.01); G05D 1/0231 (2013.01); G06F 18/24 (2023.01); G06T 7/20 (2013.01); G06T 7/70 (2017.01); G06T 7/90 (2017.01); G06T 7/97 (2017.01); G06T 11/20 (2013.01); G06V 10/758 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/41 (2022.01); G06V 20/58 (2022.01); G06V 20/584 (2022.01); G05D 2201/0213 (2013.01); G06T 2207/10016 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30244 (2013.01); G06T 2207/30252 (2013.01); G06T 2210/12 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method for predicting movement of an object in a real-world environment, comprising:
obtaining, by a processor, a plurality of image frames captured in a sequence during a period of time;
identifying, by the processor, first image frames of the plurality of image frames that contain an image of at least one object with one or more turn signals;
analyzing, by the processor, the first image frames to obtain a classification for a pose of the at least one object;
using, by the processor, the classification of the pose of the at least one object to further obtain a type classification for at least one of the turn signals and a state classification for a state of at least one of the turn signals; and
predicting, by the processor, movement of the at least one object based at least on the type and state classifications obtained for at least one of the turn signals;
wherein the first image frames are associated with bounding box intersection values which are higher than bounding box intersection values associated with all other ones of the plurality of image frames.