/Patent Tracker
AppleGranted patentAI & softwareInterest 6/10

Apple patents method to estimate 3D size and position of objects

Apple has patented a method for devices to estimate the three-dimensional size and position of objects in a physical environment. The system uses sensor data, including images and depth information, to calculate these metrics, relying on previous estimates when depth data is unavailable.

Why it mattersThis technology could improve how devices perceive their surroundings, potentially enhancing augmented reality experiences or robotic navigation.

In the filing’s own words

Various implementations of the systems, methods, and electronic devices described herein estimate three-dimensional (3D) size and position of objects. An example process may include obtaining sensor data for a sequence of frames, determining a representation of an object, and determining 3D positions and size estimates. For each frame that includes image data and depth data, the 3D position is determined based on the device pose data and the depth data for each corresponding frame, and the size estimate is determined based on the image data and the depth data. For each frame of the sequence of frames that includes image data and excludes depth data, the size estimate is determined based on a prior size estimate from a prior frame, and the 3D position is determined based on the size estimate of the representation of the object and a portion of the image data.

What exactly they claim (claim 1)

1. A method comprising: at a device having a processor and one or more sensors: obtaining sensor data for a sequence of frames by the one or more sensors in a physical environment, wherein the physical environment comprises an object, the sensor data comprising image data, depth data, device pose data, or a combination thereof, for each frame of the sequence of frames; determining a representation of the object; and determining three-dimensional (3D) positions and size estimates of the representation of the object for each frame of the sequence of frames, wherein: for each frame of the sequence of frames that includes image data and depth data, (i) the 3D position of the representation of the object is determined based on the device pose data and the depth data for each corresponding frame, and (ii) the size estimate of the representation of the object is determined based on the image data and the depth data; and for each frame of the sequence of frames that includes image data and excludes depth data, (i) the size estimate of the representation of the object is determined based on a prior size estimate from a prior frame of the sequence of frames that included image data and depth data, and (ii) the 3D position of the representation of the object is determined based on the size estimate of the representation of the object and a portion of the image data.

Facts

Company
Apple (Apple Inc.)
Official title
Size and position estimation determination of 3D objects
Patent number
US12743808B1
Application number
18743459
Filed
Jun 14, 2024
Granted
Sep 22, 2026
Inventors
6
Claims
20

Classified under

G06T 7/70 Physics & computingG06T 7/20 Physics & computingG06T 7/62 Physics & computingG06T 17/00 Physics & computing

More from Apple in AI & software

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.