Sequencing products recognized in a shelf image
A method for sequencing products on a retail shelf, or other objects, recognized in an image of the retail shelf includes detecting products in the received image and calculating a final sequence position for each detected product. The final sequence position is calculated by generating a region of interest for each detected product in the received image, generating a plurality of unique raster numbers for each region of interest using a raster number equation by varying parameters of the raster number equation based on pixel coordinates of each region of interest, determining a plurality of sequence positions for each region of interest using the plurality of unique raster numbers, and determining the final sequence position for each region of interest using the plurality of sequence positions for each region of interest. The disclosure also includes systems for implementing the method.
1. A method comprising:
receiving an image of a plurality of objects;
detecting objects in the received image;
generating a region of interest for each detected object in the received image;
generating a plurality of unique raster numbers for each region of interest using a raster number equation by varying parameters of the raster number equation based on pixel coordinates of each region of interest;
determining a plurality of sequence positions for each region of interest using the plurality of unique raster numbers; and
determining a final sequence position for each region of interest using the plurality of sequence positions for each region of interest.
2. The method of claim 1 , wherein the raster number equation includes a normalization factor.
3. The method of claim 1 , wherein the parameters of the raster number equation are selected from the group consisting of: a row and column number of a pixel corresponding to a center of the region of interest; a row and column number of a pixel corresponding to a left-top of the region of interest; a row and column number of a pixel corresponding to a right-top of the region of interest; a row and column number of a pixel corresponding to a left-bottom of the region of interest; and a row and column number of a pixel corresponding to a right-bottom of the region of interest.
4. The method of claim 2 , wherein the normalization factor comprises an average height of the regions of interest, an average length of diagonal of the regions of interest, or an average width of the regions of interest.
5. The method of claim 1 , wherein determining a final sequence position for each region of interest comprises calculating one of a mean, median, or mode of the plurality of sequence positions for each region of interest.
6. The method of claim 1 , further comprising presenting the image for display with the final sequence position for each region of interest indicated in the image.
7. The method of claim 1 , wherein the final sequence position for each region of interest orders the plurality of objects in the image in a zig-zag fashion from a top-left corner of the image to a bottom-right corner of the image.
8. A computer program product comprising a non-transitory computer usable medium including a computer readable program, wherein the computer readable program when executed on a computer causes the computer to:
receive an image of a plurality of objects;
detect objects in the received image;
generate a region of interest for each detected object in the received image;
generate a plurality of unique raster numbers for each region of interest using a raster number equation by varying parameters of the raster number equation based on pixel coordinates of each region of interest;
determine a plurality of sequence positions for each region of interest using the plurality of unique raster numbers; and
determine a final sequence position for each region of interest using the plurality of sequence positions for each region of interest.
9. The computer program product of claim 8 , wherein the raster number equation includes a normalization factor.
10. The computer program product of claim 8 , wherein the parameters of the raster number equation are selected from the group consisting of: a row and column number of a pixel corresponding to a center of the region of interest; a row and column number of a pixel corresponding to a left-top of the region of interest; a row and column number of a pixel corresponding to a right-top of the region of interest; a row and column number of a pixel corresponding to a left-bottom of the region of interest; and a row and column number of a pixel corresponding to a right-bottom of the region of interest.
11. The computer program product of claim 9 , wherein the normalization factor comprises an average height of the regions of interest, an average length of diagonal of the regions of interest, or an average width of the regions of interest.
12. The computer program product of claim 8 , wherein to determine a final sequence position for each region of interest the computer readable program causes the computer to calculate one of a mean, median, or mode of the plurality of sequence positions for each region of interest.
13. The computer program product of claim 8 , wherein the computer readable program causes the computer to present the image for display with the final sequence position for each region of interest indicated in the image.
14. The computer program product of claim 8 , wherein the final sequence position for each region of interest orders the plurality of objects in the image in a zig-zag fashion from a top-left corner of the image to a bottom-right corner of the image.
15. A system comprising:
a communication unit configured to receive an image of a plurality of objects;
an object detection engine to:
detect objects in a received image; and
generate a region of interest for each detected object in the received image;
a raster number engine to generate a plurality of unique raster numbers for each region of interest by varying parameters of a raster number equation based on pixel coordinates of each region of interest;
a sequencing engine to:
determine a plurality of sequence positions for each region of interest using the plurality of unique raster numbers; and
determine a final sequence position for each region of interest using the plurality of sequence positions for each region of interest.
16. The system of claim 15 , wherein the raster number equation includes a normalization factor.
17. The system of claim 15 , wherein the parameters of the raster number equation are selected from the group consisting of: a row and column number of a pixel corresponding to a center of the region of interest; a row and column number of a pixel corresponding to a left-top of the region of interest; a row and column number of a pixel corresponding to a right-top of the region of interest; a row and column number of a pixel corresponding to a left-bottom of the region of interest; and a row and column number of a pixel corresponding to a right-bottom of the region of interest.
18. The system of claim 16 , wherein the normalization factor comprises an average height of the regions of interest, an average length of diagonal of the regions of interest, or an average width of the regions of interest.
19. The system of claim 15 , wherein, to determine the final sequence position, the sequencing engine calculates one of a mean, median, or mode of the plurality of sequence positions for each region of interest.
20. The system of claim 15 , wherein the final sequence position for each region of interest orders the plurality of objects in the image in a zig-zag fashion from a top-left corner of the image to a bottom-right corner of the image.