Image analysis for mapping objects in an arrangement
Image analysis is used to map objects in an arrangement. For example, images of a retail shelf are used to map items for sale on the retail shelf A first vector can used to identify a relative position of a first item on a shelf to a shelving diagram, and a second vector can be used to identify a relative position of a second on the shelf to the shelving diagram, using locations of optical codes (e.g., barcodes). Absolute positions can be calculated. In some configurations, multiple images having different fields of view are matched to an overview image.
1. A system for mapping objects on a shelving unit using image analysis, the system comprising:
a camera comprising an image sensor configured to acquire a plurality of image frames; and
one or more processors configured to:
receive a plurality of images acquired by the camera;
identify a first item code in the plurality of images;
identify a second item code in the plurality of images;
track a position of the first item code in the plurality of images without decoding the first item code in at least one or more of the plurality of images;
track a position of the second item code in the plurality of images without decoding the second item code in at least one or more of the plurality of images;
compute, using an image of the plurality of images that includes the first item code and the second item code, a distance and an orientation of the first item code with respect to the second item code;
calibrate the distance and the orientation to a shelving diagram; and
generate a first vector comprising the first item code and a relative position of the first item code to the shelving diagram;
generate a second vector comprising the second item code and a relative position of the second item code to the shelving diagram.
2. The system of claim 1 , wherein the one or more processors are configured to compute the distance and the orientation of the first item code with respect to the second item code based on the first item code and the second item code being in a two-dimensional, vertical plane.
3. The system of claim 1 , wherein the one or more processors are configured to compute the distance and the orientation of the first item code with respect to the second item code based on a width or height of the first item code.
4. The system of claim 1 , wherein the one or more processors are configured to compute the distance and the orientation of the first item code with respect to the second item code based on a width or height of a shelf label.
5. The system of claim 1 , wherein the one or more processors are configured to compute the distance and the orientation of the first item code with respect to the second item code based on a simultaneous location and mapping algorithm of a mobile device.
6. The system of claim 1 , wherein the one or more processors are configured to compute the distance and the orientation of the first item code with respect to the second item code based on two image sensors of a mobile device used to acquire the plurality of images and a known distance between the two image sensors.
7. The system of claim 1 , wherein the one or more processors are configured to compute the distance and the orientation of the first item code with respect to the second item code based on a depth sensor or three-dimensional image sensors of a mobile device used to acquire the plurality of images.
8. The system of claim 1 , wherein:
the shelving unit is part of an aisle of a store; and
the first vector comprises:
an aisle indicator, and
a relative position of the first item code with respect to the aisle.
9. The system of claim 8 , wherein the one or more processors are further configured to determine an item identified by the first item code is in a correct aisle based on comparing the aisle indicator of the first vector to a planned aisle location of the item from a planogram.
10. A method for mapping objects on a shelving unit using image analysis, the method comprising:
receiving a plurality of images;
identifying a first item code in the plurality of images;
identifying a second item code in the plurality of images;
tracking a position of the first item code in the plurality of images without decoding the first item code in at least one or more of the plurality of images;
tracking a position of the second item code in the plurality of images without decoding the second item code in at least one or more of the plurality of images;
computing, using an image of the plurality of images that includes the first item code and the second item code, a distance and an orientation of the first item code with respect to the second item code;
calibrating the distance and the orientation to a shelving diagram; and
generating a first vector comprising the first item code and a relative position of the first item code to the shelving diagram; and
generating a second vector comprising the second item code and a relative position of the second item code to the shelving diagram.
11. The method of claim 10 , wherein computing the distance and the orientation of the first item code with respect to the second item code is based on the first item code and the second item code being in a two-dimensional, vertical plane.
12. The method of claim 10 , wherein computing the distance and the orientation of the first item code with respect to the second item code is based on a width or height of the first item code.
13. The method of claim 10 , wherein computing the distance and the orientation of the first item code with respect to the second item code is based on a width or height of a shelf label.
14. The method of claim 10 , wherein computing the distance and the orientation of the first item code with respect to the second item code is based on a simultaneous location and mapping algorithm of a mobile device.
15. The method of claim 10 , wherein computing the distance and the orientation of the first item code with respect to the second item code is based on two image sensors of a mobile device used to acquire the plurality of images and a known distance between the two image sensors.
16. The method of claim 10 , wherein computing the distance and the orientation of the first item code with respect to the second item code is based on a depth sensor or three-dimensional image sensors of a mobile device used to acquire the plurality of images.
17. The method of claim 10 , wherein:
the shelving unit is part of an aisle of a store; and
the first vector comprises:
an aisle indicator, and
a relative position of the first item code with respect to the aisle.
18. The method of claim 17 , further comprising determining an item identified by the first item code is in a correct aisle based on comparing the aisle indicator of the first vector to a planned aisle location of the item from a planogram.
19. The method of claim 10 , further comprising:
ascertaining a first boundary of objects associated with the first item code, wherein the first vector comprises a value indicating the first boundary with respect to the shelving diagram; and
ascertaining a second boundary of objects associated with the second item code, wherein the second vector comprises a value indicating the second boundary with respect to the shelving diagram.
20. The method of claim 19 , further comprising:
comparing, using the value indicating the first boundary from the first vector, the first boundary to a planned location of a first item in a planogram;
determining the first boundary with respect to the shelving diagram complies with the planogram based on the first boundary with respect to the shelving diagram is similar to the planned location of the first item in the planogram;
comparing, using the value indicating the second boundary from the second vector, the second boundary to a planned location of a second item in the planogram; and
determining the second boundary with respect to the shelving diagram complies with the planogram based on the second boundary with respect to the shelving diagram is similar to the planned location of the second item in the planogram.