Automatic camera configuration using a fiducial marker

• US 10,453,216 B1
• Filed: 03/15/2017
• Issued: 10/22/2019
• Est. Priority Date: 03/15/2017
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Zelenskiy, Lev, Ducrou, Jon Robert, Edwards, Alexander, Li, Tony, Lin, Sheng-Wei, Waits, Stephen
• Primary Examiner(s): Le, Vu
• Assistant Examiner(s): Mangialaschi, Tracy
• Application Number:
  US15/459,583
• Time in Patent Office: 951 Days
• Field of Search: None
• CPC Class Codes: G06T 2207/30204 Marker
• CPC Class Codes: G06T 2207/30208 Marker matrix
• CPC Class Codes: G06T 2207/30232 Surveillance
• CPC Class Codes: G06T 2207/30244 Camera pose
• CPC Class Codes: G06T 7/74 involving reference images or patches
• 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: G06V 20/62 Text, e.g. of license plates, overlay texts or captions on TV images
• CPC Class Codes: G06V 20/625 License plates

Abstract

Systems and associated methods are disclosed for automatically configuring cameras to be associated with a known physical location in response to exposing the camera to a fiducial marker. In certain embodiments, boundaries for a zone of interest within images from the camera can be defined using the fiducial markers physically placed within the physical space.

Claims

1. A method of assigning a camera to a parking bay, the method comprising:

receiving, by a server, from a concierge tool implemented on a portable computing device, a command to enter a camera configuration mode;

instructing the concierge tool, by the server, to display a first fiducial marker on a display of the portable computing device;

receiving, by the server from a first camera of a plurality of cameras communicatively coupled with the server, a first image, the first image captured, with the first camera and showing at least a portion of the display;

detecting, by the server, that the first fiducial marker is shown within the first image;

selecting, by the server, the first camera from the plurality of cameras as a potential camera to be associated with a first parking bay based at least in part on the detecting;

receiving, by the server from the concierge tool, a selection of the first parking bay; and

automatically associating, by the server, the first camera with the first parking bay based at least in part on selecting the first camera and receiving the selection of the first parking bay from the concierge tool.

2. The method of claim 1 further comprising:

after automatically associating the first camera with the first parking bay;

receiving, by the server from the first camera, a second image captured with the first camera, the second image including a license plate;

performing, by the server, an automatic license plate recognition (ALPR) process on the second image to determine a license plate identification of the license plate; and

associating, by the server, the license plate identification with the first parking bay.

3. The method of claim 1 further comprising:

instructing the concierge tool, by the server, to display at least one of an augmented reality (AR) code or a quick response (QR) code on the display of the portable computing device as the first fiducial marker.

4. The method of claim 1 further comprising:

receiving, by the server from the first camera, a second image captured with the first camera, the second image including a border fiducial marker, the border fiducial marker comprising at least one of the first fiducial marker or a second fiducial marker;

determining, by the server, a physical location of the border fiducial marker within the second image;

defining, by the server, at least a portion of a zone of interest within a field of view of the first camera based on the physical location of the border fiducial marker within the second image; and

applying, by the server, the zone of interest to subsequent images received from the first camera such that the server identifies items within the zone of interest in the subsequent images and does not identify items outside of the zone of interest in the subsequent images.

5. A method of configuring a camera, the method comprising:

receiving, by a server, from a portable computing device, a command to enter a camera configuration mode;

instructing the portable computing device, by the server, to display a first fiducial marker on a display of the portable computing device;

receiving, by the server from a first camera of a plurality of cameras communicatively coupled with the server, a first image captured by the first camera, the first image showing at least a portion of a field of view of the first camera including a first known physical location and the first fiducial marker;

detecting, by the server, that the first fiducial marker is shown within the first image;

determining, by the server, the first known physical location from a plurality of known physical locations;

automatically associating, by the server, the first camera with the first known physical location based at least in part on the detecting of the first fiducial marker and the determining of the first known physical location; and

associating, by the server, subsequent images from the first camera with the first known physical location based at least in part on automatically associating the first camera with the first known physical location.

6. The method of claim 5

wherein determining the first known physical location of a plurality of known physical locations comprises receiving, by the server, from a concierge tool implemented on the portable computing device, a selection of the first known physical location.

7. The method of claim 5, further comprising:

determining the first known physical location of the plurality of known physical locations by extracting, by the server, an identification of the first known physical location embedded within the first fiducial marker within the first image.

8. The method of claim 5, further comprising:

after automatically associating the first camera with the first known physical location;

receiving, by the server from the first camera, a second image captured with the first camera, the second image including a license plate;

performing, by the server, an automatic license plate recognition (ALPR) process on the second image to determine a license plate identification of the license plate; and

associating, by the server, the license plate identification with the first known physical location.

9. The method of claim 5, further comprising:

receiving, by the server from a second camera of the plurality of cameras communicatively coupled with the server, a second image captured by the second camera, the second image including the first fiducial marker;

detecting, by the server, the first fiducial marker within the second image;

determining, by the server, a first position of the first fiducial marker in the first image and a second position of the first fiducial marker in the second image;

determining, by the server, that the first position is closer to a center of the first image than the second position is to the center of the second image; and

automatically associating, by the server, the first camera with the first known physical location in response to determining that the first position is closer to the center of the first image than the second position is to the center of the second image.

10. The method of claim 5, further comprising:

partitioning, by the server, the field of view of the first camera into a first zone of interest and a second zone of interest;

associating, by the server, the first zone of interest with the first known physical location; and

associating, by the server, the second zone of interest with a second known physical location of the plurality of known physical locations.

11. The method of claim 5, further comprising:

receiving, by the server from the first camera, a second image captured by the first camera, the second image including a border fiducial marker, the border fiducial marker comprising at least one of the first fiducial marker or a second fiducial marker;

determining, by the server, a position of the border fiducial marker within the second image;

defining, by the server, at least a portion of a zone of interest within a field of view of the first camera based on the position of the border fiducial marker within the second image; and

applying, by the server, the zone of interest to subsequent images received from the first camera such that the server identifies items within the zone of interest in the subsequent images and does not identify items outside of the zone of interest in the subsequent images.

12. The method of claim 11, further comprising:

receiving, by the server from the first camera, a third image captured by the first camera, the third image including a depth fiducial marker, the depth fiducial marker comprising at least one of the first fiducial marker, the border fiducial marker, or a different fiducial marker;

determining, by the server, a perceived depth of the depth fiducial marker within the third image; and

defining, by the server, at least another portion of the zone of interest within the field of view of the first camera based on the perceived depth of the depth fiducial marker within the third image.

13. A system, comprising:

a portable computing device comprising a display and configured to present a first fiducial marker on the display based at least in part on instructions to display the first fiducial marker;

a first camera configured to capture a first image, the first image showing at least a portion of a field of view of the first camera including a first known physical location;

fiducial detection circuitry coupled to the first camera, the fiducial detection circuitry configured to detect that the first fiducial marker is shown within the first image;

device registration circuitry coupled to the fiducial detection circuitry, the device registration circuitry configured to;

determine the first known physical location from a plurality of known physical locations;

automatically associate the first camera with the first known physical location in response to the fiducial detection circuitry detecting that the first fiducial marker is shown within the first image and determining the first known physical location; and

associate subsequent images from the first camera with the first known physical location.

14. The system of claim 13, further comprising:

receiving from a concierge tool implemented on the portable computing device, a selection of the first known physical location,

wherein the device registration circuitry is further configured to determine the first known physical location from the selection of the first known physical location received from the concierge tool.

15. The system of claim 13, wherein the fiducial detection circuitry is further configured to extract an identification of the first known physical location embedded within the first fiducial marker within the first image, and wherein the device registration circuitry is further configured to determine the first known physical location from the identification of the first known physical location extracted from the first fiducial marker.

16. The system of claim 13, wherein the first camera is further configured to capture a second image including a license plate,

wherein the system further comprises automatic license plate recognition (ALPR) circuitry coupled to the first camera, the ALPR circuitry configured to:

perform an automatic license plate recognition (ALPR) process on the second image to determine a license plate identification of the license plate, and

wherein the device registration circuitry is further configured to, after automatically associating the first camera with the first known physical location, associate the license plate identification with the first known physical location.

17. The system of claim 13, further comprising:

a second camera coupled to the fiducial detection circuitry, the second camera configured to capture a second image, the second image including the first fiducial marker,

wherein the fiducial detection circuitry is further configured to;

detect the first fiducial marker within the second image;

determine a first position of the first fiducial marker in the first image and a second position of the first fiducial marker in the second image; and

determine that the first position is closer to a center of the first image than the second position is to a center of the second image, and

wherein the device registration circuitry is further configured to automatically associate the first camera with the first known physical location in response to the fiducial detection circuitry determining that the first position is closer to the center of the first image than the second position is to the center of the second image.

18. The system of claim 13, wherein the fiducial detection circuitry is further configured to partition the field of view of the first camera into a first zone of interest and a second zone of interest, and

wherein the device registration circuitry is further configured to:

associate the first zone of interest with the first known physical location;

and associate the second zone of interest with a second known physical location of the plurality of known physical locations.

19. The system of claim 13, wherein the first camera is further configured to capture a second image including a border fiducial marker, the border fiducial marker comprising at least one of the first fiducial marker or a second fiducial marker,

wherein the fiducial detection circuitry is further configured to:

determine a position of the border fiducial marker within the second image;

define at least a portion of a zone of interest within a field of view of the first camera based on the position of the border fiducial marker within the second image; and

apply the zone of interest to subsequent images received from the first camera such that items within the zone of interest in the subsequent images are identified and items outside of the zone of interest in the subsequent images are not identified.

20. The system of claim 19, wherein the first camera is further configured to capture a third image including a depth fiducial marker, the depth fiducial marker comprising at least one of the first fiducial marker, the border fiducial marker, or a different fiducial marker,

wherein the fiducial detection circuitry is further configured to:

determine a perceived depth of the depth fiducial marker within the third image; and

define at least another portion of the zone of interest within the field of view of the first camera based on the perceived depth of the depth fiducial marker within the third image.