Predicting inventory events using foreground/background processing

Patent metadata

Field	Value
Publication number	US-2019043003-A1
Application number	US-201815945473-A
Country	US
Kind code	A1
Filing date	Apr 4, 2018
Priority date	Aug 7, 2017
Publication date	Feb 7, 2019
Grant date	—

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.

First claim

What is claimed is:

1 . A system for tracking puts and takes of inventory items by subjects in an area of real space including inventory display structures, comprising:
a plurality of cameras disposed above the inventory display structures, cameras in the plurality of cameras producing 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 a processing system coupled to the plurality of cameras, the processing system including logic that processes the sequences of images produced by the plurality of cameras to detect puts and takes of inventory items by identifying in the sequences of images gestures of subjects and by identifying in the sequences of images inventory items associated with the gestures.

2 . The system of claim 1 , wherein the logic to detect puts and takes of inventory items by identifying gestures of subjects and inventory items associated with the gestures comprises a foreground image recognition engine which recognizes gestures by processing foreground data in the sequences of images, and further including
logic to detect puts and takes of inventory items by identifying semantically significant changes in inventory items on inventory display structures comprising a background image recognition engine which recognizes changes by processing background data in the sequences of images.

3 . 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
third image processors, including foreground image recognition engines, receiving corresponding sequences of images from the plurality of cameras, which process images to identify and classify foreground changes represented in the images in the corresponding sequences of images.

4 . The system of claim 3 , wherein the foreground image recognition engines and the background image recognition engines comprise convolutional neural networks.

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

6 . The system of claim 3 , wherein the second image processors include:
a background image store to store background images for corresponding sequences of images; 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.

7 . The system of claim 6 , 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.

8 . The system of claim 3 , 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.

9 . The system of claim 8 , 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.

10 . The system of claim 8 , 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.

11 . The system of claim 3 , including:
logic to associate background changes and identified foreground 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.

12 . The system of claim 3 , wherein the first image processors identify locations of hands of identified subjects; and including:
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.

13 . The system of claim 3 , including
logic to associate background changes with identified subjects, and to make a first set of detections of takes of inventory items by the identified subjects and of puts of inventory items on inventory display structures by the identified subjects; logic to associate foreground changes with identified subjects, and to make a second set of detections of takes of inventory items by the identified subjects and of puts of inventory items on inventory display structures by the identified subjects; and selection logic to process the first and second sets of detections to generate log data structures including lists of inventory items for identified subjects.

14 . The system of claim 3 , wherein the sequences of images from cameras in the plurality of cameras are synchronized.

15 . A method for tracking puts and takes of inventory items by subjects in an area of real space, 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; detecting puts and takes of inventory items by identifying gestures of subjects and inventory items associated with the gestures by processing foreground data in the sequences of images.

16 . The method of claim 15 , including
detecting puts and takes of inventory items by identifying semantically significant changes in inventory items on inventory display structures by processing background data in the sequences of images.

1

Assignees

• 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

Classifications

• G06V10/82

  using neural networks · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G01S3/00

  Direction-finders for determining the direction from which infrasonic, sonic, ultrasonic or electromagnetic waves, or particle emission, not having a directional significance, are being received (position-fixing by co-ordinating a plurality of determinations of direction or position lines G01S5/00) · CPC title

• G06T7/85

  Stereo camera calibration · CPC title

• G06N3/084

  Backpropagation, e.g. using gradient descent · CPC title