US 12,443,813 B2
Computer vision system and method of label detection, reading, and registration of labels on objects
Narasimhachary Nallana Chakravarty, Rollinsford, NH (US); Guohua Min, Exeter, NH (US); and Edward L. Hill, Conway, NH (US)
Assigned to Position Imaging, Inc., Portsmouth, NH (US)
Filed by Position Imaging, Inc., Portsmouth, NH (US)
Filed on Jan. 3, 2024, as Appl. No. 18/403,296.
Application 18/403,296 is a continuation of application No. 17/227,931, filed on Apr. 12, 2021, granted, now 11,886,953.
Claims priority of provisional application 63/009,143, filed on Apr. 13, 2020.
Prior Publication US 2024/0135124 A1, Apr. 25, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06K 7/14 (2006.01); G06Q 10/087 (2023.01)
CPC G06K 7/1417 (2013.01) [G06K 7/1413 (2013.01); G06K 7/1447 (2013.01); G06Q 10/087 (2013.01)] 14 Claims
OG exemplary drawing
 
1. A computer vision system for automatic identification, tracking and management of inventory and/or assets, wherein:
the computer vision system is programmed to identify and capture movements and changes of interest;
the computer vision system is programmed to trigger a process of identifying all objects and extracting label information from objects present in a field of view of one or more sensors if a set of rules for capturing the movements and changes of interest are fulfilled;
the computer vision system processes the image data with one or more object detection algorithms and label detection algorithms and generates correspondences between objects and labels identified; and
the computer vision system running change detection algorithms and semantic analysis to detect if any object was moved, removed, occluded and if any new objects were added to the system.