Orientation-based hashing for fast item orientation sensing

• US 9,969,514 B2
• Filed: 06/11/2015
• Issued: 05/15/2018
• Est. Priority Date: 06/11/2015
• Status: Active Grant

• Current Assignee: Empire Technology Development LLC (Allied Inventors Management, LLC)
• Original Assignee: Empire Technology Development LLC (Allied Inventors Management, LLC)
• Inventors: Kruglick, Ezekiel
• Primary Examiner(s): Logan, Kyle O
• Application Number:
  US14/737,416
• Publication Number:
  US 20160362211A1
• Time in Patent Office: 1,069 Days
• Field of Search: 700225
• CPC Class Codes: B65B 35/58 Turning articles by positively-acting means, e.g. to present labelled portions in uppermost position
• CPC Class Codes: B65B 57/02 responsive to absence, presence, abnormal feed, or misplacement of binding or wrapping material, containers, or packages
• CPC Class Codes: G05B 15/02 electric
• CPC Class Codes: G05B 19/4183 characterised by data acquisition, e.g. workpiece identification
• CPC Class Codes: G05B 2219/35084 Geometric feature extraction, concave and convex regions, object recognition
• CPC Class Codes: G05B 2219/40554 Object recognition to track object on conveyor
• CPC Class Codes: Y02P 90/02 Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Abstract

Technologies are generally described for orientation-based hashing to determine item orientation. In some examples, a conveyance system may be configured to adjust the orientations of various types of items before sorting. The conveyance system may include a computer vision system that determines whether the orientation of an item should be adjusted based on an item-feature hash table that relates item image features to item orientations or actuator signals. In other examples, the computer vision system may determine item image features associated with a particular item and perform an item-feature hash table lookup using the item image features to determine an item orientation or actuator action. The item-feature hash table may be separately trained, allowing the computer vision system to rapidly determine the appropriate item orientation or actuator action.

Claims

1. A system configured to adjust item orientation, the system comprising:

a memory configured to store an item-feature hash table;

an imager device configured to determine at least one feature associated with an item;

an actuator; and

a processor coupled to the memory, the imager device, and the actuator, wherein the processor is configured to;

determine a hash value based on the at least one feature determined by the imager device;

determine an actuation signal based on the hash value which is used as a key input into the item-feature hash table; and

provide the actuation signal to the actuator,

wherein the actuator is configured to adjust an orientation of the item based on the actuation signal that is determined based on the hash value.

2. The system of claim 1, wherein the at least one feature is associated with a particular orientation of the item.

3. The system of claim 1, wherein the imager device is configured to determine the at least one feature by use of at least one of:

a speeded-up robust features (SURF) process;

a scale-invariant feature transform (SIFT) process; and

a histogram of oriented gradients (HOG) process.

4. The system of claim 1, wherein the item-feature hash table is configured to group similar actuation signals into nearby hash buckets.

5. The system of claim 1, wherein the item-feature hash table is implemented by use of locality-sensitive hashing and/or parameter sketching.

6. The system of claim 1, wherein the item-feature hash table includes one of a single-entry hash table, a multiple-entry hash table, and a cuckoo hash table.

7. The system of claim 1, wherein the actuator is configured to adjust the orientation of the item through at least one of a tilt and a rotation of the item.

8. The system of claim 7, further comprising a conveyor module configured to transport the item, wherein the actuator is configured to adjust the orientation of the item with respect to the conveyor module.

9. A system configured to adjust item orientation, the system comprising:

a memory configured to store an item-feature hash table, wherein the item-feature hash table is configured to relate feature-hash values to item orientation parameters; and

a processor operatively coupled to the memory and configured to perform or control performance of;

collect multiple orientations associated with an item;

determine feature-hash value based on the collected multiple orientations associated with the item, wherein the multiple orientations include a vertical position of the item, a horizontal position of the item, or a tilted position of the item, with respect to a coordinate axis;

determine item orientation parameters associated with the feature-hash values from the item-feature hash table; and

adjust, based on the determined item orientation parameters, at least one of the multiple orientations associated with the item.

10. The system of claim 9, wherein to determine the feature-hash values, the processor is configured to perform or control performance of:

determine at least one feature associated with a particular orientation of the item, wherein the at least one feature includes at least one of a speeded-up robust feature (SURF) feature, a scale-invariant feature transform (SIFT) feature, and a histogram of oriented gradients (HOG) feature.

11. The system of claim 9, wherein the item-feature hash table includes one of a single-entry hash table, a multiple-entry hash table, and a cuckoo hash table.

12. The system of claim 9, wherein the item orientation parameters indicate at least one of an orientation of the item and an actuation signal associated with the item.

13. A system configured to determine item orientation, the system comprising:

a memory configured to store an item-feature hash table, wherein the item-feature hash table is configured to relate feature-hash values to item orientation parameters; and

a processor operatively coupled to the memory and configured to perform or control performance of;

determine a feature-hash value based on at least one feature associated with an item;

determine, from the item-feature hash table, an item orientation parameter associated with the feature-hash value, wherein the item orientation parameters, which are similar, are grouped into nearby hash buckets within the item-feature hash table; and

determine an actuation signal based on the item orientation parameter associated with the feature-hash value.

14. A system configured to determine an item orientation, the system comprising:

a memory configured to store an item-feature hash table, wherein the item-feature hash table is configured to relate feature-hash values to item orientation parameters;

an imager device operatively coupled to the memory and configured to determine at least one feature associated with an orientation of an item; and

a processor operatively coupled to the memory and the imager device, and configured to perform or control performance of;

determine a feature-hash value based on the at least one feature associated with the orientation of the item;

determine an orientation signal by use of the feature-hash value as a key for the item-feature hash table;

provide the orientation signal to an actuator; and

adjust, via the actuator and based on the determined orientation signal, the orientation of the item.

15. A method to adjust item orientation, the method comprising:

determining, by an imager device, at least one feature associated with an orientation of an item;

determining, by an orientation controller operatively coupled to the imager device, a hash value based on the at least one feature;

determining, by the orientation controller, an orientation signal by use of the hash value as a key for an item-feature hash table, wherein the item-feature hash table is configured to relate feature-hash values to item orientation parameters, and wherein the item-feature hash table is generated based on locality-sensitive hashing and/or parameter sketching;

providing, by the orientation controller, the orientation signal to an actuator; and

adjusting, by the actuator based on the orientation signal, the orientation of the item, wherein the adjustment of the orientation of the item facilitates the item being fitted into an output chute of a system that is configured for at least one of a distribution, packaging, and inspection of the item.

16. The method of claim 15, wherein determining the at least one feature includes determining at least one of a speeded-up robust feature (SURF) feature, a scale-invariant feature transform (SIFT) feature, and a histogram of oriented gradients (HOG) feature.

17. The method of claim 15, wherein the generation of the item-feature hash table is further based on sparse matrices.

18. The method of claim 15, wherein the item-feature hash table includes one of a single-entry hash table, a multiple-entry hash table, and a cuckoo hash table.

19. The method of claim 15, wherein determining the orientation signal includes determining an orientation signal that indicates at least one of the orientation of the item and an actuation signal associated with the item.

20. The method of claim 15, wherein the generation of the item-feature hash table comprises:

collecting, for at least one item, a plurality of orientations and associated features; and

determining at least one hash transformation configured to collapse multiple similar orientations in the plurality of orientations together into nearby hash buckets.

21. The method of claim 20, wherein determining the at least one hash transformation comprises:

determining at least one hash metric based on a type of the item;

performing a decomposition based on the at least one hash metric to form at least one eigenvector; and

using the at least one eigenvector to collapse the multiple similar orientations of the plurality of orientations together.