US 11,756,216 B2
Object re-identification during image tracking
Shahmeer Ali Mirza, Celina, TX (US); Sailesh Bharathwaaj Krishnamurthy, Irving, TX (US); Madan Mohan Chinnam, Irving, TX (US); and Crystal Maung, Dallas, TX (US)
Assigned to 7-ELEVEN, INC., Irving, TX (US)
Filed by 7-Eleven, Inc., Irving, TX (US)
Filed on May 21, 2021, as Appl. No. 17/326,630.
Application 17/326,630 is a continuation of application No. 16/664,219, filed on Oct. 25, 2019, granted, now 11,107,226.
Prior Publication US 2021/0272296 A1, Sep. 2, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 7/292 (2017.01); G06T 7/246 (2017.01); G06T 7/285 (2017.01); G06T 7/73 (2017.01); G06T 7/40 (2017.01); G06T 7/60 (2017.01); G06T 7/13 (2017.01); G06F 18/22 (2023.01); G06V 20/52 (2022.01); G06V 40/20 (2022.01)
CPC G06T 7/292 (2017.01) [G06F 18/22 (2023.01); G06T 7/13 (2017.01); G06T 7/248 (2017.01); G06T 7/285 (2017.01); G06T 7/40 (2013.01); G06T 7/60 (2013.01); G06T 7/74 (2017.01); G06V 20/52 (2022.01); G06V 40/23 (2022.01); G06T 2207/20084 (2013.01)] 15 Claims
OG exemplary drawing
 
1. A system, comprising:
a plurality of sensors, each sensor configured to generate top-view images of at least a portion of a space; and
a processor communicatively coupled to the plurality of sensors, the processor configured to:
track, using top-view images generated by at least one of the plurality of sensors, a first position of a first object in the space, wherein the first object is associated with a first contour;
track, using top-view images generated by at least one of the plurality of sensors, a second position of a second object in the space, wherein the second object is associated with a second contour;
detect that the first tracked position is within a threshold distance of the second tracked position;
receive a first top-view image of the first object;
determine, based on the first top-view image, a first descriptor for the first object, the first descriptor comprising at least one value associated with an observable characteristic of the first contour;
identify the first object based at least in part upon the first descriptor;
wherein a collision event corresponds to the first contour merging with the second contour in a first top-view image frame; and
the processor is further configured to:
in response to detecting the collision event, receive the top-view image frames at least until the first contour and the second contour are no longer merged; and
after the first and second contours are no longer merged, determine the first descriptor for the first object.