METHODS AND ARRANGEMENTS FOR IDENTIFYING OBJECTS
First Claim
1. A method comprising:
- moving an item to be purchased, along a path, the item having an irregular surface;
capturing first 2D image data from the irregular surface when it is at a first position along the path;
capturing second 2D image data from the irregular surface when it is at a second, different, location along said path;
processing the first and second 2D image data, in conjunction with information related to said path, to discern first 3D spatial orientation information for a first patch on the surface;
processing the first and second 2D image data, in conjunction with information related to said path, to discern second 3D spatial orientation information for a second patch on the surface, the second 3D spatial orientation information being different than the first 3D spatial orientation information; and
by reference to said discerned first and second 3D spatial orientation information, decoding a machine-readable identifier on the irregular surface, the identifier spanning at least a portion of the first patch and a portion of the second patch.
1 Assignment
0 Petitions
Accused Products
Abstract
In some arrangements, product packaging is digitally watermarked over most of its extent to facilitate high-throughput item identification at retail checkouts. Imagery captured by conventional or plenoptic cameras can be processed (e.g., by GPUs) to derive several different perspective-transformed views—further minimizing the need to manually reposition items for identification. Crinkles and other deformations in product packaging can be optically sensed, allowing such surfaces to be virtually flattened to aid identification. Piles of items can be 3D-modelled and virtually segmented into geometric primitives to aid identification, and to discover locations of obscured items. Other data (e.g., including data from sensors in aisles, shelves and carts, and gaze tracking for clues about visual saliency) can be used in assessing identification hypotheses about an item. A great variety of other features and arrangements are also detailed.
-
Citations
20 Claims
-
1. A method comprising:
-
moving an item to be purchased, along a path, the item having an irregular surface; capturing first 2D image data from the irregular surface when it is at a first position along the path; capturing second 2D image data from the irregular surface when it is at a second, different, location along said path; processing the first and second 2D image data, in conjunction with information related to said path, to discern first 3D spatial orientation information for a first patch on the surface; processing the first and second 2D image data, in conjunction with information related to said path, to discern second 3D spatial orientation information for a second patch on the surface, the second 3D spatial orientation information being different than the first 3D spatial orientation information; and by reference to said discerned first and second 3D spatial orientation information, decoding a machine-readable identifier on the irregular surface, the identifier spanning at least a portion of the first patch and a portion of the second patch.
-
-
2. A supermarket checkout apparatus including a processor coupled to a memory and to an output device, the memory storing instructions and rule data causing the processor to serve as a bagging expert system, the output device providing guidance to a human concerning a manner of packing items into bags, based on application of the rule data by the processor.
-
3. A method comprising
determining a volumetric configuration of a pile of objects presented at a checkout station by a shopper in a store; - and
determining data about each of plural objects in the pile, said determined data including identification data and orientation data; wherein said determining includes using collected sensor data to refine an identification hypothesis about a particular object in the pile. - View Dependent Claims (4, 5, 6, 7)
- and
-
8. A method comprising:
-
sensing first information from an object presented at a checkout station by a shopper in a store; and using said sensed first information—
in conjunction with sensed second information—
in identifying the object;wherein the sensed second information is of a different type that the first sensed information. - View Dependent Claims (9, 10, 11, 12, 13, 14, 15, 16)
-
-
17. A method comprising:
-
capturing imagery from a cylindrical object; detecting at least a section of an ellipse in the captured imagery, and determining therefrom an orientation of an axis of the cylindrical object; and attempting to decode a digital watermark from the captured imagery, based on a hypothesis that a watermark on the cylindrical object is aligned with said determined axis orientation.
-
-
18. A method comprising:
-
sensing identifying information from an item presented for sale on a shelf of a store, using a shelf-mounted unit; electronically presenting a price for said item using a display proximate to the item, by reference to the sensed identifying information.
-
-
19. A method comprising:
-
with a camera in a shopper'"'"'s mobile device, capturing imagery depicting plural product packages on a store shelf; processing the imagery to decode digital watermark data encoded in said product packages; and presenting an augmented reality display in which expiration date information for different of the packages is displayed as a graphical overlay on the captured imagery. - View Dependent Claims (20)
-
Specification