Industrial food processing using computer vision

1 . A method, comprising:

obtaining one or more images of an object;

thereafter identifying sub-objects, each of the sub-objects representing a respective sub-object physically separated from the object during food processing;

determining, using a set of one or more processors, an object location of respective sub-objects relative to the object; and

providing, using the set of one or more processors, an indicator, for the respective sub-objects, associated with the food processing and based on the object location of the respective sub-objects.

2 . The method of claim 1 , wherein the indicator comprises a tracked or predicted outcome of the food processing for the respective sub-objects.

3 . The method of claim 1 , comprising obtaining one or more images of the sub-objects after the sub-objects are physically separated from the object;

wherein:

the object exhibits a pattern;

the determining the object location occurs after the respective sub-objects are physically separated from the object; and

the object location is determined using the pattern.

4 . The method of claim 3 , comprising adjusting the food processing based on the indicator.

5 . The method of claim 1 , wherein the providing the indicator comprises visually identifying one or more of the sub-objects with respect to the object based on respective object locations.

6 . The method of claim 5 , wherein the visually identifying comprises generating a three-dimensional graphic of the object with one or more of the respective object locations of the sub-objects.

7 . The method of claim 6 , comprising associating the respective object locations with a tracked or predicted outcome of the food processing.

8 . The method of claim 7 , wherein the tracked or predicted outcome is associated with an adjustment of food processing equipment.

9 . The method of claim 7 , wherein the tracked or predicted outcome is a classification associated with a food processing step.

10 . The method of claim 9 , wherein the classification is formed using a trained model that acts to classify one or more of the images of the object and an image of a respective sub-object.

11 . A system, comprising:

one or more cameras;

a set of one or more processors; and

a non-transitory storage medium comprising code executable by the set of one or more processors to:

obtain, using the one or more cameras, one or more images of an object having a pattern;

thereafter identify sub-objects, each of the sub-objects representing a respective sub-object physically separated from the object during food processing;

determine an object location of respective sub-objects relative to the object based on the pattern; and

provide an indicator, for the respective sub-objects, associated with the food processing and based on the object location of the respective sub-objects.

12 . The system of claim 11 , wherein the indicator comprises a tracked or predicted outcome of the food processing for the respective sub-objects.

13 . The system of claim 11 , wherein the code is executable by the set of one or more processors to obtain one or more images, using the one or more cameras, of the sub-objects after the sub-objects are physically separated from the object;

wherein:

the object exhibits a pattern;

the determining the object location occurs after the respective sub-objects are physically separated from the object; and

the object location is determined using the pattern.

14 . The system of claim 13 , comprising one or more components, operatively coupled to the set of one or more processors, including a slicer operating on a respective sub-object;

wherein the code is executable by the set of one or more processors to adjust the one or more components based on the indicator.

15 . The system of claim 11 , comprising a display device, operatively coupled to the set of one or more processors;

wherein to provide the indicator comprises visually identifying, on the display device, one or more of the sub-objects with respect to the object based on respective object locations.

16 . The system of claim 15 , wherein the visually identifying comprises generating a three-dimensional graphic of the object with one or more of the respective object locations of the sub-objects.

17 . The system of claim 16 , wherein the code is executable by the set of one or more processors to associate the respective object locations with a tracked or predicted outcome of the food processing.

18 . The system of claim 17 , wherein the tracked or predicted outcome is associated with an adjustment of food processing equipment operatively coupled to the one or more processors.

19 . The system of claim 7 , wherein the tracked or predicted outcome is a classification associated with a food processing step.

20 . A computer program product, comprising:

a non-transitory computer readable medium comprising code executable by a set of one or more processors to:

obtain, using one or more cameras, one or more images of an object having a pattern;

thereafter identify sub-objects, each of the sub-objects representing a respective sub-object physically separated from the object during food processing;

determine an object location of respective sub-objects relative to the object based on the pattern; and

provide an indicator, for the respective sub-objects, associated with the food processing and based on the object location of the respective sub-objects.