Techniques for target detection

Patent metadata

Field	Value
Publication number	US-10176378-B1
Application number	US-201615248983-A
Country	US
Kind code	B1
Filing date	Aug 26, 2016
Priority date	Aug 26, 2016
Publication date	Jan 8, 2019
Grant date	Jan 8, 2019

Abstract

Systems and methods are provided herein for detecting a marker (e.g., a marker that identifies a delivery location) utilizing an image captured by a camera of an unmanned aerial vehicle. A method may include obtaining marker information associated with a marker, the marker comprising a repetitive visual pattern, the marker being associated with delivery of an item by an unmanned aerial vehicle. Optical pattern information may be obtained that indicates a moiré pattern associated with the marker and the one or more cameras of the unmanned aerial vehicle. Image capture information that is associated with an image comprising the marker may be received. The marker may be detected in the image based at least in part on the image capture information and the moiré pattern associated with the marker.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
receiving, by a computing system of an unmanned aerial vehicle, instructions to deliver an item to a delivery location utilizing the unmanned aerial vehicle as a mode of transportation, the unmanned aerial vehicle comprising a camera;
obtaining, by the computing system, physical marker information associated with a physical marker, the physical marker comprising a repetitive visual pattern;
obtaining, by the computing system, optical pattern information associated with the physical marker and the camera, the optical pattern information indicating a moiré pattern associated with the physical marker and the camera, the moiré pattern being produced based at least in part on a spatial frequency associated with an image of the physical marker being within a threshold frequency range to a resolution associated with the camera;
receiving, by the computing system, from the unmanned aerial vehicle, image capture information associated with a captured image captured by the camera, the captured image comprising the physical marker;
comparing, by the computing system, the image capture information from the camera to the optical pattern information;
determining, by the computing system, that the physical marker exists in the image based at least in part on the comparison; and
in response to determining that the physical marker exists in the image, instructing the unmanned aerial vehicle to approach the physical marker for delivery.

2. The computer-implemented method of claim 1 , wherein the delivery location is associated with a user of an electronic marketplace, an order of the electronic marketplace, or a particular item of the electronic marketplace.

3. The computer-implemented method of claim 1 , wherein the physical marker is displayed by a light-emitting diode (LED) screen, a liquid crystal display (LCD), or a projector.

4. The computer-implemented method of claim 1 , further comprising adjusting an exposure of a portion of the image captured by the camera comprising the physical marker, wherein determining that the physical marker exists in the image is further based at least in part on the exposure of the portion of the image as adjusted.

5. A system, comprising:
a memory configured to store computer-executable instructions;
one or more cameras configured to capture one or more images; and
a processor configured to access the memory and execute the computer-executable instructions to at least:
obtain marker information associated with a marker, the marker comprising a repetitive visual pattern, the marker being associated with delivery of an item by an unmanned aerial vehicle;
obtain optical pattern information indicating a moiré pattern associated with the marker and one or more cameras systems of the unmanned aerial vehicle, the moiré pattern being produced based at least in part on a spatial frequency associated with an image of the marker being within a threshold frequency range to a resolution associated with at least one of the one or more cameras;
receive, from the one or more camera systems of the unmanned aerial vehicle, image capture information associated with a captured image comprising the marker; and
detect that the marker exists in the captured image based at least in part on the image capture information and the moiré pattern associated with the marker.

6. The system of claim 5 , wherein the marker is unique to the delivery of the item.

7. The system of claim 5 , the processor being further configured to execute the computer-executable instructions to at least:
identify the marker from a plurality of pre-defined markers; and
provide the marker information associated with the marker to a user device.

8. The system of claim 5 , the processor being further configured to execute the computer-executable instructions to at least:
receive order information associated with the delivery; and
identify the unmanned aerial vehicle as a mode of transportation based at least in part on the order information.

9. The system of claim 8 , wherein detecting that the marker exists in the captured image utilizes a portion of the captured image.

10. The system of claim 5 , wherein the image capture information comprises the moiré pattern and the moiré pattern is produced based at least in part on repetitive details of the marker and the resolution of the one or more cameras.

11. The system of claim 5 , the processor being further configured to execute the computer-executable instructions to at least:
obtain a secondary image from a plurality of images; and
superimpose the secondary image over the captured image, wherein the marker is detected in the captured image further based at least in part on the secondary image.

12. The system of claim 11 , wherein the moiré pattern comprises one of a line moiré pattern, a shape moiré pattern, or a moiré animation.

13. The system of claim 12 , wherein the moiré pattern enables the marker to be detected from a greater distance than detection could otherwise occur utilizing image capture alone.

14. A non-transitory computer-readable medium having stored thereon computer-executable instructions that, when executed by at least one processor, configure at least one computer to perform instructions comprising:
receiving instructions associated with delivery of an item, the delivery to be carried out utilizing an unmanned aerial vehicle as a mode of transportation, the unmanned aerial vehicle comprising one or more cameras;
generating an image of a delivery location marker for the delivery based at least in part with an attribute of the one or more cameras;
obtaining optical pattern information indicating a moiré pattern associated with the delivery location marker and the one or more cameras, the moiré pattern being produced based at least in part on a spatial frequency associated with an image of the delivery location marker being within a threshold frequency range to a resolution associated with at least one of the one or more cameras;
receiving, from the one or more cameras of the unmanned aerial vehicle, image capture information associated with a captured image captured by the one or more cameras comprising the delivery location marker; and
detecting the delivery location marker in the captured image based at least in part on the image capture information and the optical pattern information.

15. The non-transitory computer-readable medium of claim 14 , wherein the captured image is one of a plurality of images captured by the one or more cameras.

16. The non-transitory computer-readable medium of claim 14 , wherein the moiré pattern alters a contrast of an area of the captured image, and wherein altering the contrast enables the delivery location marker to be detected more frequently than if the contrast remained unaltered.

17. The non-transitory computer-readable medium of claim 14 , wherein the at least one computer is configured to perform further instructions comprising:
associating the image of the delivery location marker with a user of an electronic marketplace; and
storing the image of the delivery location marker.

18. The non-transitory computer-readable medium of claim 14 , wherein a replication of the delivery location marker is placed at a delivery location to enable the delivery location to be detected utilizing the one or more cameras.

19. The non-transitory computer-readable medium of claim 14 , wherein the at least one computer is configured to perform further instructions comprising, causing the

Assignees

• Amazon Tech Inc

Inventors

• Boyd Scott Patrick
• Cui Chengwu
• Watson Joshua John

Classifications

• G06V20/17

  taken from planes or by drones · CPC title

• G06V10/22

  by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition · CPC title

• G06V20/13

  Satellite images · CPC title

• G05D1/0676

  specially adapted for landing · CPC title

• G06K2209/03

  Physics · mapped topic