Image-based detection of planogram product spaces
This disclosure describes techniques for updating planogram data associated with a facility. The planogram may indicate inventory locations within the facility for various types of items supported by product fixtures. In particular an image of a product fixture is analyzed to identify image segments corresponding to product groups, where each product group consists of instances of the same product and each image segment corresponds to a group of image points. Image data is further analyzed to determine coordinates of the points of each image segment. A product space corresponding to the product group is then defined based on the coordinates of the points of the product group. In some cases, for example, a product space may be defined in terms of the coordinates of the corners of a rectangular bounding box or volume.
1 . A system comprising:
a first camera;
a second camera;
one or more processors;
one or more computer-readable media storing computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform actions comprising:
storing planogram data representing a planogram associated with a facility;
storing first location data representing a first location of the first camera within the facility;
storing second location data representing a second location of the second camera within the facility;
receiving first image data generated by the first camera;
determining that a portion of the first image data represents a contiguous group of item instances that have a common item identification;
receiving second image data generated by the second camera;
determining that a portion of the second image data represents the contiguous group of item instances that have the common item identification;
determining, based at least in part on the first location data, the second location data, the portion of the first image data, and the portion of the second image data, coordinates of a space within the facility are occupied by the contiguous group of item instances; and
causing the planogram to associate the common item identification with the coordinates.
2 . The system of claim 1 , wherein
the space comprises a volume containing the contiguous group of item instances; and
the coordinates are of the volume.
3 . The system of claim 1 , wherein the portion of the first image data is a first portion of the first image data, and wherein determining that the first portion of the first image data represents the contiguous group of item instances that have the common item identification comprises:
determining that a second portion of the first image data represents a first item that has a first identifier, the first portion of the first image data including the second portion of the first image data;
determining that the first identifier is associated with the common item identification;
determining that a third portion of the first image data represents a second item that has a second identifier, the first portion of the first image data also including the third portion of the first image data;
determining that the second identifier is associated with the common item identification; and
determining, based at least in part on the second portion of the first image data and the third portion of the first image data, that the first item is located proximate to the second item.
4 . A method comprising:
storing first data associated with a first camera located at a facility;
storing second data associated with a second camera located at the facility;
receiving first image data generated by the first camera;
receiving second image data generated by the second camera;
determining that the first image data represents an item;
determining that the first image data represents a second item;
determining that the item is associated with an item identification;
determining that the second item is also associated with the item identification;
identifying a contiguous group of items based at least in part on the first image data representing both the item and the second item;
determining that the second image data represents the item;
determining, based at least in part on the first image data and the second image data, coordinates of a facility that are associated with the contiguous group of items; and
generating planogram data that associates the item identification with the coordinates.
5 . The method of claim 4 , wherein at least one of receiving the first image data or receiving the second image data is performed during at least one of:
times that the item is being accessed by one or more persons;
once a day; or
multiple times per day when the facility is open.
6 . The method of claim 4 , further comprising:
performing image segmentation to identify a portion of the first image data that represents a group of items, the group of items including the item and being associated with the item identification; and
performing image segmentation to identify a portion of the second image data that represents the group of items,
wherein determining the coordinates is based at least in part on the portion of the first image data and the portion of the second image data.
7 . The method of claim 4 , wherein determining the coordinates comprises determining, based at least in part on the first image data and the second image data, volume coordinates of the facility that are associated with the item.
8 . The method of claim 4 , wherein determining coordinates comprises performing triangulating based at least in part on the first image data and the second image data.
9 . The method of claim 4 , further comprising:
receiving depth information generated by at least one of the first camera or a sensor,
wherein determining the coordinates is further based at least in part on the depth information.
10 . The method of claim 4 , wherein:
determining that the first image data represents the item comprises determining that a first portion of the first image data represents the item;
determining that the first image data represents the second item comprises determining that a second portion of the first image data represents the second item;
the method further comprises determining, based at least in part on the first portion of the first image data and the second portion of the first image data, that the item is located proximate to the second item; and
identifying the contiguous group of items is based at least in part on the item being located proximate to the second item.
11 . The method of claim 4 , further comprising:
determining that the item is located at an inventory location; and
determining that the second item is also located at the inventory location, wherein identifying the contiguous group of items is based at least in part on the item being located at the inventory location and the second item being located at the inventory location.
12 . The method of claim 4 , further comprising:
determining a characteristic associated within an inventory location, the characteristic including at least one of:
a type of inventory location; or
a location on the inventory location for which the item is located,
wherein determining the coordinates is further based at least in part on the characteristic.
13 . The method of claim 4 , wherein:
the first data comprises first location data associated with the first camera; and
the second data comprises second location data associated with the second camera; and
determining the coordinates is further based at least in part on the first location data and the second location data.
14 . The method of claim 4 , further comprising:
storing identifier data that associates the item identification with an identifier,
wherein determining that the item is associated with the item identification comprises:
determining that the first image data represents the identifier located on at least a portion of the item; and
determining, based at least in part on the identifier data, that the item is associated with the item identification.
15 . The method of claim 14 , wherein the identifier comprises at least one of:
a name;
a symbol; or
a code.
16 . The method of claim 4 , wherein:
the first data comprises indicates a first field-of-view of the first camera; and
the second data indicates a second field-of-view of the second camera; and
determining the coordinates is further based at least in part on the first data and the second data.
17 . A system comprising:
one or more processors; and
one or more computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform actions comprising:
storing first data associated with a first camera located at a facility;
storing second data associated with a second camera located at the facility;
receiving first image data generated by the first camera;
receiving second image data generated by the second camera;
determining that the first image data represents an item;
determining that the first image data represents a second item;
determining that the item is associated with an item identification;
determining that the second item is also associated with the item identification;
identifying a contiguous group of items based at least in part on the first image data representing both the item and the second item;
determining that the second image data represents the item;
determining, based at least in part on the first image data and the second image data, coordinates of a facility that are associated with the contiguous group of items; and
generating planogram data that associates the item identification with the coordinates.
18 . The system of claim 17 , the actions further comprising:
receiving depth information generated by at least one of the first camera or a sensor,
wherein determining the coordinates is further based at least in part on the depth information.