Automated camera gimbal

Patent metadata

Field	Value
Publication number	US-12574639-B2
Application number	US-202318484294-A
Country	US
Kind code	B2
Filing date	Oct 10, 2023
Priority date	Oct 10, 2023
Publication date	Mar 10, 2026
Grant date	Mar 10, 2026

Abstract

The method includes capturing a first portion of a surround image using a camera; generating a bounding box using an image in the first portion of the surround image; estimating a center of an item in the image using the bounding box; and adjusting a position of a motorized gimbal such that the motorized gimbal focuses on the center of the item.

First claim

What is claimed is:

1 . A system comprising:
one or more processors; and one or more non-transitory computer-readable storage devices storing computing instructions configured to run on the one or more processors and cause the one or more processors to perform:
capturing a first portion of a surround image using a camera;
generating a bounding box using an image in the first portion of the surround image;
estimating a center of an item in the image using the bounding box;
determining a 3D position of the camera using metadata of the first portion of the surround image; and
adjusting a position of a motorized gimbal such that the motorized gimbal orients the camera towards the center of the item.

2 . The system of claim 1 , wherein the first portion of the surround image comprises approximately one quarter of the surround image.

3 . The system of claim 1 , wherein the capturing of the first portion of the surround image is at a higher frame rate than a remainder of the surround image.

4 . The system of claim 1 , wherein the generating the bounding box comprises using a predictive algorithm to generate the bounding box.

5 . The system of claim 1 , wherein the estimating the center of the item comprises using a weighted average of 3D points comprising the center of the bounding box.

6 . The system of claim 5 , further comprising determining a 3D point corresponding to the center of the bounding box using a 3D position of the camera.

7 . The system of claim 1 , wherein the computing instructions are further configured to cause the one or more processors to perform filtering a list of pairable peripherals by a vendor ID.

8 . A method comprising:
capturing a first portion of a surround image using a camera; generating a bounding box using an image in the first portion of the surround image; estimating a center of an item in the image using the bounding box; and determining a 3D position of the camera using metadata of the first portion of the surround image; and adjusting a position of a motorized gimbal such that the motorized gimbal orients the camera towards the center of the item.

9 . The method of claim 8 , wherein the first portion of the surround image comprises approximately one quarter of the surround image.

10 . The method of claim 8 , wherein the capturing of the first portion of the surround image is at a higher frame rate than a remainder of the surround image.

11 . The method of claim 8 , wherein the generating the bounding box comprises using a predictive algorithm to generate the bounding box.

12 . The method of claim 8 , wherein the estimating the center of the item comprises using a weighted average of 3D points comprising the center of the bounding box.

13 . The method of claim 12 , further comprising determining a 3D point corresponding to the center of the bounding box using a 3D position of the camera.

14 . The method of claim 8 , further comprising filtering a list of pairable peripherals by a vendor ID.

15 . An article of manufacture comprising a non-transitory, tangible computer readable storage medium having instructions stored thereon that, in response to execution by a computer based system, cause the computer based system to perform operations comprising:
capturing a first portion of a surround image using a camera; generating a bounding box using an image in the first portion of the surround image; estimating a center of an item in the image using the bounding box; and determining a 3D position of the camera using metadata of the first portion of the surround image; and adjusting a position of a motorized gimbal such that the motorized gimbal orients the camera towards the center of the item.

16 . The article of manufacture of claim 15 , wherein the first portion of the surround image comprises approximately one quarter of the surround image.

17 . The article of manufacture of claim 15 , wherein the capturing of the first portion of the surround image is at a higher frame rate than a remainder of the surround image.

18 . The article of manufacture of claim 15 , wherein the generating the bounding box comprises using a predictive algorithm to generate the bounding box.

19 . The article of manufacture of claim 15 , wherein the estimating the center of the item comprises using a weighted average of 3 D points comprising the center of the bounding box.

20 . The article of manufacture of claim 15 , wherein the instructions cause the computer based system to perform further operations comprising filtering a list of pairable peripherals by a vendor ID.

Assignees

• Carvana Llc

Inventors

• Wali Alexandre
• Francois Bruno
• Cilia Remy
• Melling Alan
• Vaucamps Antoine

Classifications

• H04N23/64

  Computer-aided capture of images, e.g. transfer from script file into camera, check of taken image quality, advice or proposal for image composition or decision on when to take image · CPC title

• G03B17/561

  Support related camera accessories · CPC title

• H04N23/68 Primary

  for stable pick-up of the scene, e.g. compensating for camera body vibrations · CPC title