Predicting inventory events using semantic diffing

• US 10,127,438 B1
• Filed: 04/04/2018
• Issued: 11/13/2018
• Est. Priority Date: 08/07/2017
• Status: Active Grant

• Current Assignee: Standard Cognition Corp.
• Original Assignee: Standard Cognition Corp.
• Inventors: Fisher, Jordan E., Fischetti, Daniel L., Ogle, Brandon L., Novak, John F., Dorman, Kyle E., Kihara, Kenneth S., Lasheras, Juan C.
• Primary Examiner(s): Holder, Anner N
• Application Number:
  US15/945,466
• Time in Patent Office: 223 Days
• CPC Class Codes: G06F 18/241 relating to the classification model, e.g. parametric or non-parametric approaches
• CPC Class Codes: G06N 3/04 Architecture, e.g. interconnection topology
• CPC Class Codes: G06N 3/045 Combinations of networks
• CPC Class Codes: G06N 3/084 Backpropagation, e.g. using gradient descent
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 10/087 Inventory or stock management, e.g. order filling, procurement or balancing against orders
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/20084 Artificial neural networks [ANN]
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/254 involving subtraction of images
• CPC Class Codes: G06T 7/292 Multi-camera tracking
• CPC Class Codes: G06T 7/80 Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
• CPC Class Codes: G06V 10/147 Details of sensors, e.g. sensor lenses fingerprint or palmprint sensors G06V40/13; vascular sensors G06V40/145; eye sensors G06V40/19
• CPC Class Codes: G06V 10/454 Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]
• CPC Class Codes: G06V 10/82 using neural networks
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16

Abstract

Systems and techniques are provided for tracking puts and takes of inventory items by subjects in an area of real space. A plurality of cameras with overlapping fields of view produce respective sequences of images of corresponding fields of view in the real space. In one embodiment, the system includes first image processors, including subject image recognition engines, receiving corresponding sequences of images from the plurality of cameras. The first image processors process images to identify subjects represented in the images in the corresponding sequences of images. The system includes second image processors, including background image recognition engines, receiving corresponding sequences of images from the plurality of cameras. The second image processors mask the identified subjects to generate masked images. Following this, the second image processors process the masked images to identify and classify background changes represented in the images in the corresponding sequences of images.

Claims

1. A system for tracking changes in an area of real space, comprising:

a plurality of cameras, cameras in the plurality of cameras producing respective sequences of images of corresponding fields of view in the real space, the field of view of each camera overlapping with the field of view of at least one other camera in the plurality of cameras;

a processing system coupled to the plurality of cameras, the processing system including;

first image processors, including subject image recognition engines, receiving corresponding sequences of images from the plurality of cameras, which process images to identify subjects represented in the images in the corresponding sequences of images;

second image processors, including background image recognition engines, receiving corresponding sequences of images from the plurality of cameras, which mask the identified subjects to generate masked images, process the masked images to identify and classify background changes represented in the images in the corresponding sequences of images, wherein the second image processors include

a background image store to store background images for corresponding sequences of images; and

mask logic to process images in the sequences of images to replace foreground image data representing the identified subjects with background image data from the background images for the corresponding sequences of images to provide the masked images, wherein the mask logic combines sets of N masked images in the sequences of images to generate sequences of factored images for each camera, and the second image processors identify and classify background changes by processing the sequence of factored images.

2. The system of claim 1, wherein the background image recognition engines comprise convolutional neural networks.

3. The system of claim 1, including logic to associate identified background changes with identified subjects.

9. The system of claim 1, wherein the sequences of images from cameras in the plurality of cameras are synchronized.

4. A system for tracking changes in an area of real space, comprising:

a plurality of cameras, cameras in the plurality of cameras producing respective sequences of images of corresponding fields of view in the real space, the field of view of each camera overlapping with the field of view of at least one other camera in the plurality of cameras;

a processing system coupled to the plurality of cameras, the processing system including;

first image processors, including subject image recognition engines, receiving corresponding sequences of images from the plurality of cameras, which process images to identify subjects represented in the images in the corresponding sequences of images;

second image processors, including background image recognition engines, receiving corresponding sequences of images from the plurality of cameras, which mask the identified subjects to generate masked images, process the masked images to identify and classify background changes represented in the images in the corresponding sequences of images, wherein the second image processors include

logic to produce change data structures for the corresponding sequences of images, the change data structures including coordinates in the masked images of identified background changes, identifiers of an inventory item subject of the identified background changes and classifications of the identified background changes; and

coordination logic to process change data structures from sets of cameras having overlapping fields of view to locate the identified background changes in real space.

5. The system of claim 4, wherein the classifications of identified background changes in the change data structures indicate whether the identified inventory item has been added or removed relative to the background image.

6. The system of claim 4, wherein the classifications of identified background changes in the change data structures indicate whether the identified inventory item has been added or removed relative to the background image, and including logic to associate background changes with identified subjects, and to make detections of takes of inventory items by the identified subjects and of puts of inventory items on inventory display structures by the identified subjects.

7. A system for tracking changes in an area of real space, comprising:

a plurality of cameras, cameras in the plurality of cameras producing respective sequences of images of corresponding fields of view in the real space, the field of view of each camera overlapping with the field of view of at least one other camera in the plurality of cameras;

a processing system coupled to the plurality of cameras, the processing system including;

first image processors, including subject image recognition engines, receiving corresponding sequences of images from the plurality of cameras, which process images to identify subjects represented in the images in the corresponding sequences of images;

second image processors, including background image recognition engines, receiving corresponding sequences of images from the plurality of cameras, which mask the identified subjects to generate masked images, process the masked images to identify and classify background changes represented in the images in the corresponding sequences of images; and

logic to associate background changes with identified subjects, and to make detections of takes of inventory items by the identified subjects and of puts of inventory items on inventory display structures by the identified subjects.

8. A system for tracking changes in an area of real space, comprising:

a plurality of cameras, cameras in the plurality of cameras producing respective sequences of images of corresponding fields of view in the real space, the field of view of each camera overlapping with the field of view of at least one other camera in the plurality of cameras;

a processing system coupled to the plurality of cameras, the processing system including;

first image processors, including subject image recognition engines, receiving corresponding sequences of images from the plurality of cameras, which process images to identify subjects represented in the images in the corresponding sequences of images, wherein the first image processors identify locations of hands of identified subjects;

second image processors, including background image recognition engines, receiving corresponding sequences of images from the plurality of cameras, which mask the identified subjects to generate masked images, process the masked images to identify and classify background changes represented in the images in the corresponding sequences of images; and

logic to associate background changes with identified subjects by comparing the locations of the changes with the locations of hands of identified subjects, and to make detections of takes of inventory items by the identified subjects and of puts of inventory items on inventory display structures by the identified subjects.

10. A method for tracking put and takes of inventory items by subjects in an area of real space including inventory display structures, comprising:

using a plurality of cameras disposed above the inventory display structures to produce respective sequences of images of inventory display structures in corresponding fields of view in the real space, the field of view of each camera overlapping with the field of view of at least one other camera in the plurality of cameras; and

detecting puts and takes of inventory items by identifying semantically significant changes in the sequences of images relating to inventory items on inventory display structures and associating the semantically significant changes with subjects represented in the sequences of images, wherein said detecting puts and takes includes

using first image processors, including subject image recognition engines, to process images to identify subjects represented in the images in the corresponding sequences of images;

using second image processors, including background image recognition engines, to mask identified subjects in images in the sequences of images, to generate masked images, to process the masked images to identify and to classify background changes represented in the images in the corresponding sequences of images; and

associating identified background changes with identified subjects.

11. The method of claim 10, wherein the background image recognition engines comprise convolutional neural networks.

12. The method of claim 10, wherein using the second image processors includes

storing background images for corresponding sequences of images;

processing images in the sequences of images to replace foreground image data representing the identified subjects with background image data from the background images for the corresponding sequences of images to provide the masked images.

13. The method of claim 12, wherein processing images in the sequences of images includes combining sets of N masked images in the sequences of images to generate sequences of factored images for each camera, and the second image processors identify and classify background changes by processing the sequence of factored images.

19. The method of claim 10, including synchronizing the sequences of images from cameras in the plurality of cameras.

14. A method for tracking put and takes of inventory items by subjects in an area of real space including inventory display structures, comprising:

using a plurality of cameras disposed above the inventory display structures to produce respective sequences of images of inventory display structures in corresponding fields of view in the real space, the field of view of each camera overlapping with the field of view of at least one other camera in the plurality of cameras; and

detecting puts and takes of inventory items by identifying semantically significant changes in the sequences of images relating to inventory items on inventory display structures and associating the semantically significant changes with subjects represented in the sequences of images, wherein said detecting puts and takes includes

using first image processors, including subject image recognition engines, to process images to identify subjects represented in the images in the corresponding sequences of images;

using second image processors, including background image recognition engines, to mask identified subjects in images in the sequences of images, to generate masked images, to process the masked images to identify and to classify background changes represented in the images in the corresponding sequences of images, wherein using the second image processors includes

producing change data structures for the corresponding sequences of images, the change data structures including coordinates in the masked images of identified background changes, identifiers of an inventory item subject of the identified background changes and classifications of the identified background changes; and

processing change data structures from sets of cameras having overlapping fields of view to locate the identified background changes in real space.

15. The method of claim 14, wherein the classifications of identified background changes in the change data structures indicate whether the identified inventory item has been added or removed relative to the background image.

16. The method of claim 14, wherein the classifications of identified background changes in the change data structures indicate whether the identified inventory item has been added or removed relative to the background image, and including associating background changes with identified subjects, and making detections of takes of inventory items by the identified subjects and of puts of inventory items on inventory display structures by the identified subjects.

17. A method for tracking put and takes of inventory items by subjects in an area of real space including inventory display structures, comprising:

using a plurality of cameras disposed above the inventory display structures to produce respective sequences of images of inventory display structures in corresponding fields of view in the real space, the field of view of each camera overlapping with the field of view of at least one other camera in the plurality of cameras; and

detecting puts and takes of inventory items by identifying semantically significant changes in the sequences of images relating to inventory items on inventory display structures and associating the semantically significant changes with subjects represented in the sequences of images, wherein said detecting puts and takes includes

using first image processors, including subject image recognition engines, to process images to identify subjects represented in the images in the corresponding sequences of images;

using second image processors, including background image recognition engines, to mask identified subjects in images in the sequences of images, to generate masked images, to process the masked images to identify and to classify background changes represented in the images in the corresponding sequences of images, including

associating background changes with identified subjects, and making detections of takes of inventory items by the identified subjects and of puts of inventory items on inventory display structures by the identified subjects.

18. A method for tracking put and takes of inventory items by subjects in an area of real space including inventory display structures, comprising:

using a plurality of cameras disposed above the inventory display structures to produce respective sequences of images of inventory display structures in corresponding fields of view in the real space, the field of view of each camera overlapping with the field of view of at least one other camera in the plurality of cameras; and

detecting puts and takes of inventory items by identifying semantically significant changes in the sequences of images relating to inventory items on inventory display structures and associating the semantically significant changes with subjects represented in the sequences of images, wherein said detecting puts and takes includes

using first image processors, including subject image recognition engines, to process images to identify subjects represented in the images in the corresponding sequences of images;

using second image processors, including background image recognition engines, to mask identified subjects in images in the sequences of images, to generate masked images, to process the masked images to identify and to classify background changes represented in the images in the corresponding sequences of images, wherein using the first image processors includes identifying locations of hands of identified subjects; and

including

associating background changes with identified subjects by comparing the locations of the changes with the locations of hands of identified subjects, and making detections of takes of inventory items by the identified subjects and of puts of inventory items on inventory display structures by the identified subjects.

20. A computer program product, comprising:

a computer readable memory comprising a non-transitory data storage medium;

computer instructions stored in the non-transitory data storage medium executable by a computer to track multi-joint subjects in an area of real space by a process including;

using sequences of images from a plurality of cameras having corresponding fields of view in the real space, the field of view of each camera overlapping with the field of view of at least one other camera in the plurality of cameras;

using first image processors, including subject image recognition engines, to process images to identify subjects represented in the images in the corresponding sequences of images;

using second image processors, including background image recognition engines, to mask identified subjects in images in the sequences of images, to generate masked images, to process the masked images to identify and to classify background changes represented in the images in the corresponding sequences of images; and

associating background changes with identified subjects, and making detections of takes of inventory items by the identified subjects and of puts of inventory items on inventory display structures by the identified subjects.

21. The computer program product of claim 20, wherein the background image recognition engines comprise convolutional neural networks.

22. The computer program product of claim 20, including associating identified background changes with identified subjects.

23. The computer program product of claim 20, wherein using the second image processors includes

storing background images for corresponding sequences of images;

processing images in the sequences of images to replace foreground image data representing the identified subjects with background image data from the background images for the corresponding sequences of images to provide the masked images.

24. The computer program product of claim 20, wherein processing images in the sequences of images includes combining sets of N masked images in the sequences of images to generate sequences of factored images for each camera, and the second image processors identify and classify background changes by processing the sequence of factored images.