US 12,249,082 B2
Article identification and tracking
Sid Ryan, Montreal (CA)
Assigned to SITA Information Networking Computing UK Limited, Middlesex (GB)
Appl. No. 17/638,234
Filed by SITA Information Networking Computing UK Limited, Hayes Middlesex (GB)
PCT Filed Aug. 25, 2020, PCT No. PCT/GB2020/052037
§ 371(c)(1), (2) Date Feb. 25, 2022,
PCT Pub. No. WO2021/038218, PCT Pub. Date Mar. 4, 2021.
Claims priority of application No. 1912428 (GB), filed on Aug. 29, 2019; application No. 1918893 (GB), filed on Dec. 19, 2019; and application No. 20166042 (EP), filed on Mar. 26, 2020.
Prior Publication US 2023/0186509 A1, Jun. 15, 2023
Int. Cl. G06V 20/52 (2022.01); G06T 5/50 (2006.01); G06T 7/254 (2017.01); G06T 7/73 (2017.01); G06V 10/28 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 20/00 (2022.01); G06V 30/162 (2022.01); G06V 30/10 (2022.01)
CPC G06T 7/254 (2017.01) [G06T 5/50 (2013.01); G06T 7/73 (2017.01); G06V 10/28 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 20/00 (2022.01); G06V 20/52 (2022.01); G06V 30/162 (2022.01); G06V 30/10 (2022.01); G06V 2201/07 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method for identifying and tracking an article, the method comprising the steps of:
a. receiving a plurality of images of a first article following a path between an origin and a destination, wherein the plurality of images comprises a first set of images captured, by a first recording device, at a first location between the origin and destination and a second set of images captured, by a second recording device, at a second location between the origin and destination, wherein the first location is different from the second location and each of the first and second locations is associated with a list of expected articles that are predicted to pass each respective location, wherein the origin is a bag drop location and the destination is a bag collection location;
b. determining a first characteristic vector based on the received image wherein the first characteristic vector is defined by a plurality of characteristic features associated with the first article and a degree of similarity between the first characteristic vector and each of a plurality of predetermined characteristic vectors, wherein each predetermined characteristic vector is associated with a set of training images each corresponding to a previously identified article;
c. comparing the first characteristic vector with a set of predetermined characteristic vectors wherein each of the set of predetermined characteristic vectors is associated with an identifier; and
d. based on the comparison, associating the first article with the identifier associated with a corresponding one of the predetermined characteristic vectors or associating the first article with a new identifier.