Item put and take detection using image recognition

• US 10,133,933 B1
• Filed: 02/27/2018
• Issued: 11/20/2018
• 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:
  US15/907,112
• Time in Patent Office: 266 Days
• CPC Class Codes: G06F 18/24143 Distances to neighbourhood prototypes, e.g. restricted Coulomb energy networks [RCEN]
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/20084 Artificial neural networks [ANN]
• CPC Class Codes: G06T 2210/12 Bounding box
• CPC Class Codes: G06V 10/454 Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 10/82 using neural networks
• CPC Class Codes: G06V 20/41 Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items segmenting video sequences G06V20/49
• 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: H04N 17/002 for television cameras
• CPC Class Codes: H04N 23/60 Control of cameras or camera modules
• CPC Class Codes: H04N 23/90 Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums

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. A processing system is coupled to the system. In one embodiment, the processing system comprises image recognition engines receiving corresponding sequences of images from the plurality of cameras. The image recognition engines process the images in the corresponding sequences to identify subjects represented in the images and generate classifications of the identified subjects. The system processes the classifications of identified subjects for sets of images in the sequences of images to detect takes and puts of inventory items on shelves by identified subjects.

Claims

1. A system for tracking puts and takes of inventory items by subjects 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 a plurality of image recognition engines, receiving corresponding sequences of images from the plurality of cameras, image recognition engines in the plurality of image recognition engines processing the images in the corresponding sequences to identify subjects represented in the images; and

logic to process sets of images in the sequences of images that include the identified subjects to detect takes of inventory items by identified subjects and puts of inventory items on shelves by identified subjects, wherein the logic to process sets of images includes;

for identified subjects, logic to process images to generate classifications of the images of the identified subjects, the classifications including whether the identified subject is holding an inventory item, a first nearness classification indicating a location of a hand of the identified subject relative to a shelf, a second nearness classification indicating a location a hand of the identified subject relative to the identified subject.

2. The system of claim 1, wherein the second nearness classification indicates a location of a hand of the identified subject relative to a body of the identified subject, and the generated classifications include a third nearness classification indicating a location of a hand of the identified subject relative to a basket associated with an identified subject.

3. The system of claim 1, including logic to perform time sequence analysis over the classifications of images to detect said takes and said puts by the identified subjects.

4. The system of claim 1, wherein the logic to process sets of images includes:

for identified subjects, logic to identify bounding boxes of data representing hands in images in the sets of images of the identified subjects, and to process data in the bounding boxes to generate classifications of data within the bounding boxes for the identified subjects.

5. The system of claim 3, wherein the classifications include whether the identified subject is holding an inventory item, a first nearness classification indicating a location of a hand of the identified subject relative to a shelf, a second nearness classification indicating a location a hand of the identified subject relative to a body of the identified subject, a third nearness classification indicating a location a hand of the identified subject relative to a basket associated with an identified subject, and an identifier of a likely inventory item.

6. The system of claim 3, including logic to perform time sequence analysis over the classifications of data within the bounding boxes in the sets of images to detect said takes and said puts by the identified subjects.

7. The system of claim 1, wherein the logic to process sets of images comprises convolutional neural networks.

8. The system of claim 1, wherein cameras in the plurality of cameras are configured to generate synchronized sequences of images.

9. The system of claim 1, wherein the plurality of cameras comprise cameras disposed over and having fields of view encompassing respective parts of the area in real space.

10. The system of claim 1, including logic responsive to the detected takes and puts, to generate log data structures including a list of inventory items for identified subjects.

11. A method for tracking puts and takes of inventory items by subjects in an area of real space, the method including:

using a plurality of cameras to produce 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;

receiving corresponding sequences of images from the plurality of cameras, processing the images in the corresponding sequences using image recognition engines in a plurality of image recognition engines and identifying subjects represented in the images wherein the plurality of image recognition engines are part of a processing system coupled to the plurality of cameras; and

processing sets of images in the sequences of images that include the identified subjects to detect takes of inventory items by identified subjects and puts of inventory items on shelves by identified subjects, wherein the processing sets of images includes;

for identified subjects, generating classifications of the images of the identified subjects, the classifications including whether the identified subject is holding an inventory item, a first nearness classification indicating a location of a hand of the identified subject relative to a shelf, a second nearness classification indicating a location of a hand of the identified subject relative to a body of the identified subject, a third nearness classification indicating a location a hand of the identified subject relative to a basket associated with an identified subject, and an identifier of a likely inventory item.

12. The method of claim 11, including performing time sequence analysis over the classifications of images to detect said takes and said puts by the identified subjects.

13. The method of claim 11, wherein the processing sets of images includes:

for identified subjects, identifying bounding boxes of data representing hands in images in the sets of images of the identified subjects, and processing data in the bounding boxes to generate classifications of data within the bounding boxes for the identified subjects.

14. The method of claim 13, including performing time sequence analysis over the classifications of data within the bounding boxes in the sets of images to detect said takes and said puts by the identified subjects.

15. The method of claim 11, including circular buffers coupled to cameras in the plurality of cameras to store sets of images in the sequences of images from the plurality of cameras.

16. The method of claim 11, including processing sets of images using convolutional neural networks.

17. The method of claim 11, wherein cameras in the plurality of cameras are configured to generate synchronized sequences of images.

18. The method of claim 11, wherein the plurality of cameras comprise cameras disposed over and having fields of view encompassing respective parts of the area in real space.

19. The method of claim 11, including responsive to the detected takes and puts, generating a log data structure including a list of inventory items for each identified subject.

20. A system for tracking puts and takes of inventory items by subjects 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 recognition engines, receiving the sequences of images from the plurality of cameras, which process images to generate first data sets that identify subjects and locations of the identified subjects in the real space;

logic to process the first data sets to specify bounding boxes which include images of hands of identified subjects in images in the sequences of images;

second image recognition engines, receiving the sequences of images from the plurality of cameras, which process the specified bounding boxes in the images to generate a classification of hands of the identified subjects, the classification including whether the identified subject is holding an inventory item, a first nearness classification indicating a location of a hand of the identified subject relative to a shelf, a second nearness classification indicating a location of a hand of the identified subject relative to the identified subject, and an identifier of a likely inventory item; and

logic to process the classifications of hands for sets of images in the sequences of images of identified subjects to detect takes of inventory items by identified subjects and puts of inventory items on shelves by identified subjects; and

logic to generate a log data structure including a list of inventory items for each identified subject.

21. The system of claim 20, including circular buffers coupled to cameras in the plurality of cameras to store sets of images in the sequences of images from the plurality of cameras for processing by corresponding ones of the first and second image recognition engines.

22. The system of claim 20, wherein the first data sets comprise for each identified subject sets of candidate joints having coordinates in real space.

23. The system of claim 20, wherein the logic to process the first data sets to specify bounding boxes specifies bounding boxes based on locations of joints in the sets of candidate joints for each subject.

24. The system of claim 20, wherein the second image recognition engines comprise convolutional neural networks.

25. The system of claim 20, wherein the logic to process the classifications of bounding boxes comprise convolutional neural networks.

26. The system of claim 20, wherein cameras in the plurality of cameras are configured to generate synchronized sequences of images.

27. The system of claim 20, wherein the plurality of cameras comprise cameras disposed over and having fields of view encompassing respective parts of the area in real space.