Get the newsletter
Nvidia · AI / ML · Filed Jul 16, 2025 · USPTO published Nov 19, 2026 · This week's release

Nvidia Files Patent for Locating Hundreds of Factory Cameras With One Walk-Through

Hundreds of cameras in a warehouse each need to be told exactly where they are and which way they point. Nvidia's patent application says one person with a roving camera could do it in a single walk.

A roving camera moves along a route to pinpoint the exact positions of fixed cameras mounted around a room. Drawing from patent filing US 2026/0368929 A1.
A roving camera moves along a route to pinpoint the exact positions of fixed cameras mounted around a room.All 18 drawings ↓
Publication number
US 2026/0368929 A1(US20260368929A1)
Applicant
NVIDIA Corporation
Filed · Published
Jul 16, 2025 · Nov 19, 2026
Inventors
Shuo Wang, Qunjie Zhou, Di Zeng, Sujit Biswas, Jun Liu, Kefei Ren, Chirag Ashokbhai Majithia, Vojtech Panek, Laura Leal-Taixe
Status when we published
Examiner raised objections; the company can respond
Document
20 claims
US classification
348/144
Examiner
BROWN JR, HOWARD D (Art Unit 2488)

What Nvidia's camera walk-through actually does

Imagine you run a warehouse with hundreds of cameras bolted to the walls and ceiling, and your software needs to know exactly where each one is and which way it faces. Today, someone sits at a screen and clicks matching landmarks, like a doorway corner, between each camera's view and a floor plan. Then they repeat it for the next camera, and the next.

Nvidia's patent application swaps that clicking for a walk-through. Someone carries a camera rig through the building (or flies it on a drone), stopping near each fixed camera to line up roughly with its view. Software stitches the footage into a 3D map of the space, then compares each fixed camera's picture to the walk-through frames to find the closest match.

Since the system knows where the roving camera was for that frame, it can work out where the fixed camera is and which way it points. The payoff is a location and direction for every camera with far less hand work.

From the filing · CLAIM 1
… determining a first image of the plurality of first images that corresponds with the second image of the camera; determining, based at least in part on a first pose of the movable camera system associated with the first image that corresponds with the second image, a second pose of the camera; …

Translation: The system matches a movable camera view with a fixed camera view to calculate the exact position of the fixed camera.

How a roving camera pins down fixed ones

The claims cover a method with four main steps, repeated for each fixed camera in the building:

  • Collect: a movable camera system (the filing says it can be a stereo pair, meaning two cameras mounted together) records images while it travels through the space.
  • Match: the software finds features (distinct spots like corners and edges) in every image and turns each into a descriptor (a numeric fingerprint of the pixels around it). It picks the walk-through image that shares the most matching features with the fixed camera's picture.
  • Locate: because the 2D points in that image are tied to 3D points in the map, a standard geometry calculation (called perspective-n-point) gives the fixed camera's position and orientation.
  • Store: rotation and translation values are saved as an extrinsic calibration matrix, the record of where a camera sits and where it points.

The 3D map comes from SLAM (simultaneous localization and mapping, which tracks a device's position while it builds a map) and structure from motion (rebuilding 3D scenes from flat photos). Nvidia names its own GPU-accelerated versions, cuVSLAM and cuSFM.

The walk-through only works if some frame was shot close to each fixed camera's viewpoint. The filing describes a field-of-view overlap of 70 to 90 percent as a match, and also describes skipping the image-matching step and comparing a camera's picture straight to the 3D map.

From the filing · THE ABSTRACT
A plurality of first images of an environment is captured using a movable camera system that traverses the environment. A second image of the environment is captured using a camera of the environment.

Translation: A walking camera records the space while fixed cameras take their own separate snapshots.

Why factories with hundreds of cameras care

If you run a site with hundreds of cameras, the practical gain is time. The filing says calibration has to be done for everything from basic object tracking to bird's-eye-view systems that merge many camera feeds, and the manual version scales badly. It also covers places where no floor plan exists, which is a harder case for today's methods.

This is a patent application, and the examiner's first review rejected the claims as filed, which is routine at this stage and usually followed by amendments. Nothing here says Nvidia is selling a calibration product. It does show the company working on the setup layer that camera-based factory and warehouse systems depend on.

That makes this Nvidia's 48th filing in Enterprise AI we've tracked since May, following one on frames sharing static and one on merging AI steps.

Source: US 2026/0368929 A1 at the USPTO (PDF). Full patent text and figures are in the official publication.

Get our take in your Top Stories

Liked this breakdown? Add Patentlyze as a preferred source on Google, and our plain-English take shows up more often in your Top Stories the next time Nvidia patent news breaks.

There are more where this came from

We read every patent application Big Tech publishes and send you the ones worth knowing. Plain English, free, every week.

The drawings · 18 sheets

18 drawing sheets from US 2026/0368929 A1 · click any drawing to enlarge

Connecting fixed factory cameras to a mobile cart, drawing sheet 1 from US 2026/0368929 A1
Sheet 1 Connecting fixed factory cameras to a mobile cart
Software tools for building 3D room maps, drawing sheet 2 from US 2026/0368929 A1
Sheet 2 Software tools for building 3D room maps
Walking a portable rig past stationary sensors, drawing sheet 3 from US 2026/0368929 A1
Sheet 3 Walking a portable rig past stationary sensors
Matching mobile video against wall-mounted shots, drawing sheet 4 from US 2026/0368929 A1
Sheet 4 Matching mobile video against wall-mounted shots
Converting walk-through footage into camera positions, drawing sheet 5 from US 2026/0368929 A1
Sheet 5 Converting walk-through footage into camera positions
Processor circuits optimized for AI math, drawing sheet 6 from US 2026/0368929 A1
Sheet 6 Processor circuits optimized for AI math
Cloud servers orchestrating site-wide vision data, drawing sheet 7 from US 2026/0368929 A1
Sheet 7 Cloud servers orchestrating site-wide vision data
Computer chips that calculate camera coordinates, drawing sheet 8 from US 2026/0368929 A1
Sheet 8 Computer chips that calculate camera coordinates
Show the other 10 sheets
Internal parts of a computer running the camera tracking software, drawing sheet 9 from US 2026/0368929 A1
Sheet 9 Internal parts of a computer running the camera tracking software
Connecting sensors and displays to the central processor, drawing sheet 10 from US 2026/0368929 A1
Sheet 10 Connecting sensors and displays to the central processor
Inside a processor with graphics cores that handle image math, drawing sheet 11 from US 2026/0368929 A1
Sheet 11 Inside a processor with graphics cores that handle image math
Using factory images to build and deploy vision models, drawing sheet 12 from US 2026/0368929 A1
Sheet 12 Using factory images to build and deploy vision models
Cloud services and graphics chips that power the software, drawing sheet 13 from US 2026/0368929 A1
Sheet 13 Cloud services and graphics chips that power the software
Helping a human label images to train better vision models, drawing sheet 14 from US 2026/0368929 A1
Sheet 14 Helping a human label images to train better vision models
Labeling server feeding ready-made AI models into training tools, drawing sheet 15 from US 2026/0368929 A1
Sheet 15 Labeling server feeding ready-made AI models into training tools
Linking high-power chips across networks for heavy factory computing, drawing sheet 16 from US 2026/0368929 A1
Sheet 16 Linking high-power chips across networks for heavy factory computing
Connecting processors to share memory for fast visual mapping, drawing sheet 17 from US 2026/0368929 A1
Sheet 17 Connecting processors to share memory for fast visual mapping
Server chips wired together to handle factory mapping data, drawing sheet 18 from US 2026/0368929 A1
Sheet 18 Server chips wired together to handle factory mapping data
Patent filing page

Reader comments

No comments yet

Start the discussion

Real name or a handle, either is fine. Comments are read by a person before they appear, so allow a little time. Keep it about the filing.