/Patent Tracker
NvidiaGranted patentAI & softwareInterest 6/10

Nvidia patents image tracking that merges data to help machines navigate

Nvidia has been granted a patent for a method that helps autonomous systems track objects in video feeds. The system combines features tracked over time with new features detected in the current image, then filters out less important details like the sky to focus on objects near the ground.

Why it mattersThis improves how self-driving cars and robots understand their surroundings by prioritizing relevant visual data over background noise.

In the filing’s own words

In various examples, feature tracking for autonomous or semi-autonomous systems and applications is described herein. Systems and methods are disclosed that merge, using one or more processes, features detected using a feature tracker(s) and features detected using a feature detector(s) in order to track features between images. In some examples, the number of merged features and/or the locations of the merged features within the images are limited. This way, the systems and methods are able to identify merged features that are of greater importance for tracking while refraining from tracking merged features that are of less importance. For example, if the systems and methods are being used to identify features for autonomous driving, a greater number of merged features that are associated with objects located proximate to the driving surface may be tracked as compared to merged features that are associated with the sky.

What exactly they claim (claim 1)

1. A method comprising: determining, using one or more first machine learning models and based at least on image data representative of at least a first image associated with a first time and a second image associated with a second time that is after the first time, at least a tracked feature that is depicted by and tracked between the first image and the second image; determining, using one or more second machine learning models and based at least on at least a portion of the image data representative of the second image, at least a detected feature that is depicted by the second image, the one or more second machine learning models being different from the one or more first machine learning models; determining, based at least on a distance between the tracked feature and the detected feature within the second image, an association between the tracked feature depicted in the second image and the detected feature depicted in the second image; determining, based at least on the association and by at least merging the tracked feature depicted by the second image with the detected feature depicted by the second image, a merged feature that represents both the tracked feature and the detected feature; outputting data representative of at least a portion of merged features that includes at least the merged feature; and causing, based at least on the data representative of the at least the portion of the merged features, a machine to navigate within an environment.

Facts

Company
Nvidia (NVIDIA Corporation)
Official title
Feature tracking
Patent number
US12749292B2
Application number
18184071
Filed
Mar 15, 2023
Granted
Sep 29, 2026
Inventors
4
Claims
20

Classified under

G06V 10/771 Physics & computingG06V 10/7715 Physics & computing
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Nvidia 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.