Multiple Camera System for Inventory Tracking

• US 20180005176A1
• Filed: 06/26/2017
• Published: 01/04/2018
• Est. Priority Date: 06/30/2016
• Status: Active Grant

• Current Assignee: Shanghai Hanshi Information Technology Company Limited (Hanshow Technology Co., Ltd.)
• Original Assignee: Bossa Nova Robotics IP, Inc.
• Inventors: Williams, Stephen, Gonzalez, Juan Pablo, Skaff, Sarjoun
• Granted Patent: US 10,769,582 B2
• Time in Patent Office: Days
• CPC Class Codes: G06Q 10/08 Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
• CPC Class Codes: G06Q 10/087 Inventory or stock management, e.g. order filling, procurement or balancing against orders
• 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 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69

Abstract

A camera system for inventory monitoring includes a movable base that supports multiple cameras. The multiple cameras are directed toward inventory to take a series of pictures along aisle of a retail store or warehouse. A processing module connected to the multiple cameras is used to stitch together the pictures, and along with depth information and product identification information, construct a real time or near real time inventory mapping of products positioned on aisle shelves. This information can be transferred to remote locations to simplify and speed product ordering, and assist in maintenance of appropriate product stock levels.

Claims

1. A camera system for inventory monitoring, comprising:

a movable base;

multiple cameras supported by the movable base, the multiple cameras being directable toward inventory;

a processing module connected to the multiple cameras and able to construct inventory related information;

a data storage module connected to the processing module and able to store inventory related information; and

a communication module connected to the processing module to transfer inventory related information to remote locations.

2. The camera system of claim 1, wherein inventory related information further comprises a realogram.

3. The camera system of claim 1, wherein the movable base further comprises an autonomous robot.

4. The camera system of claim 1, wherein the multiple cameras are linearly mounted on a camera support.

5. The camera system of claim 1, wherein at least one of the multiple cameras is fixedly mounted on a camera support.

6. The camera system of claim 1, wherein at least one of the multiple cameras is a zoom camera.

7. The camera system of claim 1, wherein at least one of the multiple cameras is directed downward and at least one of the multiple cameras is directed upward.

8. The camera system of claim 1, further comprising a plurality of lights directable toward inventory.

9. The camera system of claim 1, wherein the multiple cameras include at least one of a wide field camera, a fixed camera, and a movable camera having a resolution sufficient to read shelf attached inventory information.

10. The camera system of claim 1, wherein the multiple cameras include an infrared camera.

11. A inventory monitoring method, comprising the steps of:

allowing an autonomous robot to move along a shelf lined aisle holding inventory, with the autonomous robot acting as a movable base for multiple cameras;

directing the multiple cameras toward inventory and shelf labels on the shelf lined aisle;

defining bounding boxes around potential inventory related information in an image taken with the multiple cameras;

associating selected bounding boxes in the image to selected shelf labels;

transferring inventory related information to remote locations using a communication module; and

receiving inventory related information from remote locations.

12. A inventory monitoring method, comprising the steps of:

allowing an autonomous robot to move along a shelf lined aisle holding inventory, with the autonomous robot acting as a movable base for multiple cameras;

maintaining a substantially constant distance from the shelf lined aisle holding inventory while moving in a forward direction;

directing the multiple cameras toward inventory on the shelf lined aisle;

determining inventory related information from multiple camera images of inventory positioned along the shelf lined aisle holding inventory, using a processing module contained in the autonomous robot; and

pausing, reversing, or marking for further multiple camera inspection if inventory related information for a portion of the shelf lined aisle is incomplete.

13. The camera system of claim 12, wherein the multiple cameras are linearly mounted on a camera support.

14. The camera system of claim 12, wherein at least one of the multiple cameras is fixedly mounted on a camera support.

15. A inventory monitoring method, comprising the steps of:

allowing an autonomous robot to move along a shelf lined aisle holding inventory, with the autonomous robot acting as a movable base for multiple cameras;

directing the multiple cameras toward inventory on the shelf lined aisle;

determining inventory related information from camera images of inventory positioned along the shelf lined aisle using a processing module contained in the autonomous robot;

detecting and reading shelf labels;

detecting distance from at least one the multiple cameras to the shelf lined aisle using at least one distance ranging system;

defining bounding boxes around potential inventory in an image taken with at least one of the multiple cameras; and

associating selected bounding boxes in the image to selected shelf labels to build at least one of a product classifier or a product library.

16. The inventory monitoring method of claim 15, wherein the inventory related information further comprises realograms.

17. The inventory monitoring method of claim 15, further comprising the step of using the distance ranging system to capture a depth map.

18. The inventory monitoring method of claim 15, further comprising the step of using the distance ranging system to capture a depth map including both shelves and products positioned on shelves.

19. The inventory monitoring method of claim 15, further comprising the step of building a product library.

20. The inventory monitoring method of claim 15, further comprising the step of building a product library using manual input to identify potential inventory designated in the multiple bounding boxes in the image taken with at least one camera

21. The inventory monitoring method of claim 15, wherein the bounding boxes can surround gaps between potential inventory.

22. The inventory monitoring method of claim 15, further comprising the step of building the product library without use of an initial planogram.