Multi-angle object recognition

Patent metadata

Field	Value
Publication number	US-12347154-B2
Application number	US-202418601650-A
Country	US
Kind code	B2
Filing date	Mar 11, 2024
Priority date	Aug 8, 2018
Publication date	Jul 1, 2025
Grant date	Jul 1, 2025

Abstract

Methods, systems, and apparatus for controlling smart devices are described. In one aspect a method includes capturing, by a camera on a user device, a plurality of successive images for display in an application environment of an application executing on the user device, performing an object recognition process on the images, the object recognition process including determining that a plurality of images, each depicting a particular object, are required to perform object recognition on the particular object, and in response to the determination, generating a user interface element that indicates a camera operation to be performed, the camera option capturing two or more images, determining that a user, in response to the user interface element, has caused the indicated camera operation to be performed to capture the two or more images, and in response, determining whether a particular object is positively identified from the plurality of images.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
obtaining, by a user computing device comprising one or more processors, first image data captured in a first camera operation, wherein the first image data includes an object;
in response to a first object recognition process performed with respect to the first image data indicating a failure to recognize the object in the first image data, providing, for presentation to a user of the user computing device, a first user interface element indicating a second camera operation to be performed;
in response to the second camera operation being performed, obtaining, by the user computing device, second image data captured in the second camera operation, wherein the second image data includes the object; and
in response to a second object recognition process performed with respect to the second image data indicating a successful recognition of the object in the second image data, providing, for presentation to the user of the user computing device, a second user interface element indicating the successful recognition of the object.

2. The computer-implemented method of claim 1 , wherein
in the first camera operation the first image data is captured at a first frequency, and
in the second camera operation the second image data is captured at a second frequency, the second frequency being greater than the first frequency.

3. The computer-implemented method of claim 1 , wherein:
in the first camera operation an image of the object is captured from a first position, and
the first user interface element indicating the second camera operation to be performed includes an indication to perform the second camera operation by capturing one or more images of the object from one or more positions different than the first position.

4. The computer-implemented method of claim 1 , wherein:
in the first camera operation an image of the object is captured at a first zoom level, and
the first user interface element indicating the second camera operation to be performed includes an indication to perform the second camera operation by capturing one or more images of the object at one or more zoom levels different than the first zoom level.

5. The computer-implemented method of claim 1 , wherein:
in the first camera operation an image of a first side of the object is captured from a first position, and
the first user interface element indicating the second camera operation to be performed includes an indication to perform the second camera operation by adjusting a position of the object to capture one or more images of a second side of the object from the first position.

6. The computer-implemented method of claim 1 , wherein the object comprises a machine-readable code, a person, a vehicle, or a landmark.

7. The computer-implemented method of claim 1 , further comprising determining the first user interface element based on a type of the object.

8. The computer-implemented method of claim 1 , wherein the first user interface element is provided for presentation to the user on a user interface of the user computing device in real-time while the object is provided for presentation to the user on the user interface of the user computing device.

9. The computer-implemented method of claim 8 , wherein
the first user interface element comprises one or more of an icon, an animation, a video, an audio indication, or a descriptive text, and
the first user interface element is overlaid on the object on the user interface of the user computing device.

10. The computer-implemented method of claim 1 , further comprising determining the second camera operation to be performed and the first user interface element to be presented, based on determining images needed for the successful recognition of the object.

11. The computer-implemented method of claim 1 , further comprising:
transmitting, by the user computing device, the first image data to a server computing system; and
receiving, from the server computing system, a first indication indicating the failure to recognize the object in the first image data based on the first object recognition process.

12. The computer-implemented method of claim 11 , further comprising:
transmitting, by the user computing device, the second image data to the server computing system; and
receiving, from the server computing system, a second indication indicating the successful recognition of the object in the second image data based on the second object recognition process.

13. The computer-implemented method of claim 12 , wherein the second image data is transmitted to the server computing system at a second frequency which is greater than a first frequency at which the first image data is transmitted to the server computing system.

14. The computer-implemented method of claim 12 , further comprising suspending transmission of image data to the server computing system between completion of the first camera operation and performance of the second camera operation.

15. The computer-implemented method of claim 1 , wherein the second user interface element comprises one or more of an identification of the object or a hyperlink to another computing resource which provides content associated with the object.

16. The computer-implemented method of claim 1 , further comprising generating a composite image based on the second image data and the first image data, wherein the second object recognition process is performed with respect to the composite image.

17. The computer-implemented method of claim 1 , further comprising generating a panoramic image based on the second image data and the first image data, wherein the second object recognition process is performed with respect to the panoramic image.

18. The computer-implemented method of claim 1 , further comprising performing, by the user computing device, the second object recognition process with respect to the second image data,
wherein the second image data includes a plurality of image frames and each of the plurality of image frames includes the object,
wherein performing, by the user computing device, the second object recognition process with respect to the second image data comprises:
assigning a respective weight to the object in each of the plurality of image frames,
determining a weighted average for the object based on the respective weight assigned to the object in each of the plurality of image frames, and
determining the successful recognition of the object in the second image data when the weighted average is greater than a weighted average threshold value.

19. A user computing device, comprising:
a camera;
one or more processors; and
one or more non-transitory computer-readable media configured to store instructions that, when executed by the one or more processors, cause the user computing device to perform operations, the operations comprising:
capturing, by the camera in a first camera operation, a first plurality of images each including an object,
in response to a first object recognition process performed with respect to the first plurality of images indicating a failure to recognize the object in the first plurality of images, providing, for presentation to a user of the user computing device, a first user interface element indicating a second camera operation to be performed,
capturing, by the camera in the second camera operation, a second plurality of images each including the object, and
in response to a second object recognition process performed with respect to the

Assignees

• Google Llc

Inventors

• Badr Ibrahim

Classifications

• G06V10/16

  using multiple overlapping images; Image stitching · CPC title

• G06V10/24

  Aligning, centring, orientation detection or correction of the image · CPC title

• G06V10/776

  Validation; Performance evaluation · CPC title

• H04N23/698

  for achieving an enlarged field of view, e.g. panoramic image capture · CPC title

• H04N23/661

  Transmitting camera control signals through networks, e.g. control via the Internet · CPC title