Nvidia patents method to stitch video clips into one track
Nvidia describes a system that uses neural networks to identify specific objects across multiple video feeds. It then automatically stitches these clips together into a single, continuous video based on the object's movement and timing.
In the filing’s own words
Apparatuses, systems, and techniques to concatenate multiple videos together to generate a single video. In at least one embodiment, an object is identified in two or more videos using metadata generated by one or more neural networks, and those videos are concatenated so that an object's movements are captured in a single video.
What exactly they claim (claim 1)
1. A processor, comprising: one or more circuits to: process two or more videos generated using sensor data from two or more different image sensors using one or more neural networks to identify one or more objects in the two or more videos and generate metadata for each video of the two or more videos, the metadata including respective unique object identifiers (IDs) for each object of the one or more objects and time information for when each object of the one or more objects appears in respective videos of the two or more videos; responsive to a request indicating a particular object ID of the respective unique object IDs, automatically combine two or more portions of the two or more videos in chronological order into a single video based, at least in part, on the metadata generated using the one or more neural networks; and provide input data, based at least in part on the single video, to another one or more neural networks to perform inferencing of one or more paths or one or more movements with respect to an object of the one or more objects corresponding to the particular object ID and that appears in the combined two or more portions of the two or more videos.
Facts
- Company
- Nvidia (NVIDIA Corporation)
- Official title
- Data combination techniques
- Patent number
- US12731616B1
- Application number
- 18213782
- Filed
- Jun 23, 2023
- Granted
- Sep 8, 2026
- Inventors
- 2
- Claims
- 20
Classified under
G11B 27/031 Physics & computingG06V 10/82 Physics & computingG06V 20/40 Physics & computingG11B 27/34 Physics & computingMore from Nvidia in AI & software
- Nvidia patents AI coach that analyzes your gameplay to suggest strategies Oct 13, 2026
- Nvidia patents AI system that writes and voices character conversations Sep 10, 2026
- Nvidia patents system that uses AI to find bugs in game videos Sep 17, 2026
- Nvidia patents AI method to make digital characters move realistically Sep 8, 2026
- Nvidia patents AI system that builds image generators from text prompts Sep 15, 2026
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.