Disney patents video system to detect when guests need help
Disney describes a system that uses cameras and machine learning to spot if a visitor is in trouble, such as falling or getting separated from their group. The software checks for changes in the person's position, the number of people nearby, or sounds like screaming to confirm the event before sending an alert to staff.
In the filing’s own words
Methods, systems, and non-transitory computer-readable media are described for providing assistance based on video analysis. One or more processors are configured to receive and analyze video data using a machine learning model to detect an individual in a first portion of the video data and detect an event involving the individual in a subsequent portion, determine a measure of confidence indicative of a likelihood of accurately detecting the event, determine one or more confidence factors based on detecting a change, difference, or audio data, increase the measure of confidence using the confidence factors to determine a modified measure of confidence, which is compared to a confidence threshold, and generate a notification to cause assistance to be provided to the individual when the modified measure of confidence satisfies the confidence threshold.
What exactly they claim (claim 1)
1. A method comprising: receiving, by one or more processors, video data of an environment; detecting, by the one or more processors using a machine learning model, a first individual in a first portion of the video data; detecting, by the one or more processors using the machine learning model, an event involving the first individual in a second portion of the video data following the first portion; determining, by the one or more processors, a measure of confidence indicative of a likelihood of the machine learning model accurately detecting the event; determining, by the one or more processors, one or more confidence factors based on detecting at least one of: (i) a change, between the first portion of the video data and the second portion of the video data, in a position of an item belonging to the first individual relative to the first individual; (ii) a difference, between the first portion of the video data and the second portion of the video data, in a number of individuals within a region of the environment; or (iii) audio data associated with the event; increasing, by the one or more processors, the measure of confidence using the one or more confidence factors to determine a modified measure of confidence; comparing, by the one or more processors, the modified measure of confidence to a confidence threshold; and generating, by the one or more processors, a notification to a client device to cause assistance to be provided to the first individual in response to determining that the modified measure of confidence satisfies the confidence threshold.
Facts
- Company
- Disney (DISNEY ENTERPRISES, INC.)
- Official title
- EVENT DETECTION BASED ON ANALYSIS OF VIDEO DATA
- Publication number
- US20260321061A1
- Application number
- 19720600
- Filed
- Jun 25, 2026
- Published
- Oct 15, 2026
- Inventors
- 4
- Claims
- 20
Classified under
G06V 40/20 Physics & computingG06V 20/41 Physics & computingG06V 40/10 Physics & computingG06V 40/1365 Physics & computingG09B 19/003 Physics & computingMore from Disney in AI & software
- Disney patents AI character that creates art from your shared memories Sep 8, 2026
- Disney patents video compression using generative models to cut file sizes Sep 3, 2026
- Disney patents AI characters that create art from shared memories Oct 22, 2026
- Disney patents tech to sync translated speech with body gestures Sep 17, 2026
- Disney patents AI characters that pause and react when you interrupt them Sep 24, 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.
