Item identification using digital image processing

An item tracking method, comprising:

• detecting a triggering event at a platform, wherein the triggering event corresponds with a user placing items on the platform;
• capturing an overhead depth image a first item and a second item on the platform using a three-dimensional (3D) sensor, wherein the overhead depth image is configured to capture upward-facing surfaces of items placed on the platform;
• determining a first object pose for the first item based at least in part upon the overhead depth image, wherein determining the first object pose comprises determining a first orientation for the first item with respect to the platform;
• determining a second object pose for the second item based at least in part upon the overhead depth image, wherein determining the second object pose comprises determining a second orientation for the second item with respect to the platform;
• identifying a first camera from among a plurality of cameras based at least in part upon the first object pose for the first item;
• identifying a second camera from among the plurality of cameras base at least in part upon the second object pose for the second camera, wherein the second camera is different from the first camera;
• capturing a first image of the first item using the first camera, wherein:
• the first image comprises one or more features of the first item;
• and
• each feature corresponds with a physical attribute of the first item;
• capturing a second image of the second item using the second camera, wherein:
• the second image comprises one or more features of the second item;
• and
• each feature corresponds with a physical attribute of the second item;
• identifying the first item within the first image based at least in part upon features of the first items;
• identifying the second item within the second image based at least in part upon the features of the second item;
• identifying the user associated with the first item and the second item;
• identifying an account that is associated with the user;
• and
• associate the first item and the second item with the account of the user.

A computer program product comprising executable instructions stored in a non-transitory computer-readable medium that when executed by a processor causes the processor to:

• detect a triggering event at a platform, wherein the triggering event corresponds with a user placing items on the platform;
• capture an overhead depth image a first item and a second item on the platform using a three-dimensional (3D) sensor, wherein the overhead depth image is configured to capture upward-facing surfaces of items placed on the platform;
• determine a first object pose for the first item based at least in part upon the overhead depth image, wherein determining the first object pose comprises determining a first orientation for the first item with respect to the platform;
• determine a second object pose for the second item based at least in part upon the overhead depth image, wherein determining the second object pose comprises determining a second orientation for the second item with respect to the platform;
• identify a first camera from among a plurality of cameras based at least in part upon the first object pose for the first item;
• identify a second camera from among the plurality of camera based at least in part upon the second object pose for the second item, wherein the second camera is different from the first camera;
• capture a first image of the first item using the first camera, wherein:
• the first image comprises one or more features of the first item;
• and
• each feature corresponds with a physical attribute of the first item;
• capture a second image of the second item using the second camera, wherein:
• the second image comprises one or more features of the second item;
• and
• each feature corresponds with a physical attribute of the second item;
• identify the first item within the first image based at least in part upon features of the first items;
• identify a second item within the second image based at least in part upon the features of the second item;
• identify the user associated with the first item and the second item on the platform;
• identify an account that is associated with the user;
• and
• associate the first item and the second item with the account of the user.