Mapping optical-code images to an overview image
Images of optical codes are mapped to an overview image to localize optical codes within a space. By localizing optical codes, information about locations of various products can be ascertained. One or more techniques can be used to map the images of optical codes to the overview image. The overview image can be a composite image formed by stitching together several images.
1. A system for mapping optical-code images to an overview image, the system comprising:
an image sensor configured to acquire a first image, a second image, and a third image of a scene; and
one or more processors configured to:
receive the first image, wherein the first image includes a first optical code but not a second optical code;
decode the first optical code using the first image;
receive the second image, wherein the second image is acquired after the first image and includes the second optical code but not the first optical code;
decode the second optical code using the second image;
receive the third image, wherein the third image includes both the first optical code and the second optical code, without decoding the first optical code or the second optical code using the third image;
generate a first map of the probability of a location of the first optical code in the third image;
generate a second map of the probability of a location of the second optical code in the third image;
correlate the first optical code with a first location in the third image, based on the first map; and
correlate the second optical code with a second location in the third image, based on the second map.
2. The system of claim 1 , wherein the first map is based on:
a convolution of one or more features in the first image with the third image;
an assumed scan order of the first optical code and the second optical code; and
identifying label positions in the third image.
3. The system of claim 1 , wherein the first map is further based on:
an estimated device position at a time the first image is acquired;
identifying characters in the first image and in the third image;
image recognition of a product in the third image identified by the first optical code;
data from the second map;
data of phone translation; and
matching interest points and texture features in the first image to the third image.
4. A method for mapping optical-code images to an overview image, the method comprising:
receiving a first image, wherein the first image includes a first optical code but not a second optical code;
decoding the first optical code using the first image;
receiving a second image, wherein the second image includes the second optical code but not the first optical code;
decoding the second optical code using the second image;
receiving a third image, wherein the third image includes both the first optical code and the second optical code, without decoding the first optical code or the second optical code using the third image;
generating a first map of the probability of a location of the first optical code in the third image;
generating a second map of the probability of a location of the second optical code in the third image;
identifying a first location in the third image of the first optical code, based on the first map; and
identifying a second location in the third image of the second optical code, based on the second map.
5. The method of claim 4 , wherein the first map is based on a convolution of one or more features in the first image with the third image.
6. The method of claim 5 , wherein the one or more features includes the first optical code.
7. The method of claim 4 , wherein the first map and the second map are based on a known scan order.
8. The method of claim 4 , wherein the first map and the second map are based on an estimated device position at a time the first image is acquired.
9. The method of claim 4 , wherein the first map and the second map are based on identifying label positions in the third image.
10. The method of claim 4 , wherein the first map is based on identifying characters in the first image and in the third image.
11. The method of claim 4 , wherein the first map is based on image recognition of a product in the third image identified by the first optical code.
12. The method of claim 4 , wherein the first map is based on data from the second map.
13. The method of claim 4 , further comprising searching for a scale of the first image compared to the third image.
14. The method of claim 4 , wherein the first map is based on data of phone translation between the first image and the second image.
15. The method of claim 4 , wherein the first map is based on matching texture features in the first image to the third image.
16. The method of claim 4 , wherein there is less than 25 degrees rotation between the first image and the third image.
17. The method of claim 4 , further comprising stitching images together to form the third image.
18. The method of claim 4 , wherein the first map is based on:
a convolution of one or more features in the first image with the third image;
a known scan order of the first optical code and the second optical code;
identifying label positions in the third image;
an estimated device position at a time the first image is acquired;
identifying characters in the first image and in the third image;
image recognition of a product in the third image identified by the first optical code;
data from the second map;
data of phone translation; and/or
matching texture features in the first image to the third image.
19. A memory device containing instructions that, when executed, cause one or more processors to perform the following steps for mapping optical-code images to an overview image:
receiving a first image, wherein the first image includes a first optical code but not a second optical code;
decoding the first optical code using the first image;
receiving a second image, wherein the second image includes the second optical code but not the first optical code;
decoding the second optical code using the second image;
receiving a third image, wherein the third image includes both the first optical code and the second optical code, without decoding the first optical code or the second optical code using the third image;
generating a first map of the probability of a location of the first optical code in the third image;
generating a second map of the probability of a location of the second optical code in the third image;
identifying a first location in the third image of the first optical code, based on the first map; and
identifying a second location in the third image of the second optical code, based on the second map.
20. The memory device of claim 19 , wherein the first map is based on:
a convolution of one or more features in the first image with the third image; and
identifying label positions in the third image.