Autonomous image acquisition systems for production and environment monitoring and event detection

Patent metadata

Field	Value
Publication number	US-12347109-B2
Application number	US-202217722060-A
Country	US
Kind code	B2
Filing date	Apr 15, 2022
Priority date	Apr 15, 2022
Publication date	Jul 1, 2025
Grant date	Jul 1, 2025

Abstract

Certain aspects of the present disclosure provide techniques for autonomous image acquisition. This includes determining a plurality of two-dimensional image perspectives for a plurality of image capture devices, and comparing the plurality of two-dimensional image perspectives with a generated two-dimensional representation of a target object, where the two-dimensional representation is generated based on a three-dimensional model of the target object. This further includes automatically moving at least one of the plurality of image capture devices, based on the comparing, to increase a portion of the target object captured by the plurality of image capture devices.

First claim

What is claimed is:

1. A method, comprising:
determining a plurality of two-dimensional image perspectives for a plurality of image capture devices, wherein one or more of the plurality of image capture devices is moveable relative to other image capture devices of the plurality of image capture devices;
generating a two-dimensional representation of a target object based on a three-dimensional model of the target object;
comparing the plurality of two-dimensional image perspectives with the two-dimensional representation of the target object to generate a coverage map indicating a number of pixels of the plurality of the two-dimensional image perspectives that correspond to the target object in the two-dimensional representation of the target object;
automatically moving at least one of the plurality of image capture devices relative to the other image capture devices of the plurality of image capture devices to increase the number of pixels of the plurality of the two-dimensional image perspectives that correspond to the target object included in the coverage map; and
capturing a plurality of images of the target object with the plurality of image capture devices based on automatically moving the at least one of the plurality of image capture devices relative to the other image capture devices.

2. The method of claim 1 , wherein:
the target object comprises an object undergoing manufacturing, and
the plurality of image capture devices are configured to capture images to monitor the target object during manufacturing.

3. The method of claim 1 , wherein the comparing the plurality of two-dimensional image perspectives with the generated two-dimensional representation of a target object comprises:
generating a plurality of enclosing bounding boxes or semantically segmented regions, each of the bounding boxes or semantically segmented regions corresponding with at least one of the plurality of two-dimensional image perspectives; and
comparing the plurality of enclosing bounding boxes or semantically segmented regions with the two-dimensional representation of the target object to generate the coverage map.

4. The method of claim 3 , wherein the comparing the plurality of two-dimensional image perspectives with the generated two-dimensional representation of the target object further comprises:
excluding a portion of the three-dimensional model of the target object from the comparing the plurality of enclosing bounding boxes or semantically segmented regions with the two-dimensional representation of the target object,
wherein the excluded portion is not captured by the plurality of image capture devices.

5. The method of claim 1 , wherein the at least one of the plurality of image capture devices comprises an automated guided vehicle (AVG) mounted camera.

6. The method of claim 1 , wherein the at least one of the plurality of image capture devices comprises a crane-mounted camera.

7. The method of claim 1 , wherein the automatically moving the at least one of the plurality of image capture devices is performed to and to reduce image overlap between the plurality of two-dimensional image perspectives.

8. The method of claim 1 , wherein the automatically moving the at least one of the plurality of image capture devices is performed to avoid collisions between image capture devices of the plurality of image capture devices.

9. The method of claim 1 , further comprising:
identifying at least a portion of the target object as static during a first time period,
wherein the at least one of the plurality of image capture device is automatically moved to omit capturing images of the portion of the target object during the first time period.

10. The method of claim 1 , further comprising:
generating a network graph reflecting an environment for the target object,
wherein the network graph comprises a node representing the target object and a plurality of edges representing distances from the target object to a plurality of other objects in the environment represented as respective nodes in the network graph.

11. The method of claim 10 , further comprising: identifying one or more static objects in the environment and one or more dynamic objects in the environment, using a deep neural network (DNN).

12. A non-transitory computer-readable medium containing computer program code that, when executed by operation of one or more computer processors, performs operations comprising:
determining a plurality of two-dimensional image perspectives for a plurality of image capture devices, wherein one or more of the plurality of image capture devices is moveable relative to other image capture devices of the plurality of image capture devices;
generating a two-dimensional representation of a target object based on a three-dimensional model of the target object;
comparing the plurality of two-dimensional image perspectives with the two-dimensional representation of the target object to generate a coverage map indicating a number of pixels of the plurality of the two-dimensional image perspectives that correspond to the target object in the two-dimensional representation of the target object;
automatically moving at least one of the plurality of image capture devices relative to the other image capture devices of the plurality of image capture devices, to increase the number of pixels of the plurality of the two-dimensional image perspectives that correspond to the target object; and
capturing a plurality of images of the target object with the plurality of image capture devices based on automatically moving the at least one of the plurality of image capture devices relative to the other image capture devices.

13. The non-transitory computer-readable medium of claim 12 , wherein:
the target object comprises an object undergoing manufacturing, and
the plurality of image capture devices are configured to capture images to monitor the target object during manufacturing.

14. The non-transitory computer-readable medium of claim 12 , wherein the comparing the plurality of two-dimensional image perspectives with the generated two-dimensional representation of the target object comprises:
generating a plurality of enclosing bounding boxes or semantically segmented regions, each of the bounding boxes or semantically segmented regions corresponding with at least one of the plurality of two-dimensional image perspectives; and
comparing the plurality of enclosing bounding boxes or semantically segmented regions with the two-dimensional representation of the target object to generate the coverage map.

15. The non-transitory computer-readable medium of claim 14 , wherein the comparing the plurality of two-dimensional image perspectives with the generated two-dimensional representation of a target object further comprises:
excluding a portion of the three-dimensional model of the target object from the comparing the plurality of enclosing bounding boxes or semantically segmented regions with the two-dimensional representation of the target object,
wherein the excluded portion is not captured by the plurality of image capture devices.

16. The non-transitory computer-readable medium of claim 12 , wherein the at least one of the plurality of image capture devices comprises an automated guided vehicle (AVG) mounted camera or a crane-mounted camera.

17. A system, comprising:
a computer processor; and
a memory having instructions stored thereon which, when executed on the computer processor, performs operations comprising:
determining a plurality of two-dimensional image perspectives for a

Assignees

• Boeing Co

Inventors

• Afrasiabi Amir
• Evans Nick S

Classifications

• G06T2210/12

  Bounding box · CPC title

• G06T7/0004

  Industrial image inspection · CPC title

• G05B19/41895

  using automatic guided vehicles [AGV] (control of position or course of AGV's G05D1/00) · CPC title

• G06T2207/30244

  Camera pose · CPC title

• G06T7/62

  of area, perimeter, diameter or volume · CPC title