- Number
- 12688732
- Published
- 2026-07-21
- Filed
- 2023-11-09
- Assignee
- Disney Enterprises, Inc.
- Inventors
- Hale; Gregory Brooks, Markowitz; Gary D., Wilkinson; Clifford Aron, Chen; Ching-Chien
- CPC
- G06V40/20; G06V40/28; G06V10/82; G06V20/41; G06V20/52; G06V40/10; G06V40/1365; G08B21/043; G08B21/245; G09B19/003; G08B29/186
- Verdict
- Low Notable software
- First reported
- 2026-W36 (2026-09-06)
- Source
- Google Patents · FreePatentsOnline
The keeper's note
Computer-vision system that watches pool/water areas and flags a person in distress — real-time CV/tracking, relevant to anyone doing camera-based safety detection.
Abstract
A guest assistance platform may analyze video data of an environment that includes a liquid substance. The video data is analyzed using a machine learning model trained to detect objects in the liquid substance. The guest assistance platform may detect an individual in the liquid substance based on analyzing the video data and may determine a measure of confidence associated with detecting the individual in the liquid substance. The guest assistance platform may determine one or more confidence factors associated with detecting the individual in the liquid substance. The guest assistance platform may modify the measure of confidence using the one or more confidence factors and may determine whether the modified measure of confidence satisfies a confidence threshold. The guest assistance platform may selectively cause assistance to be provided to the individual or continue analyzing the video data based on whether the modified measure of confidence satisfies the confidence threshold.
Background
BACKGROUND (1) Closed-circuit television (CCTV) is a system that includes video camera devices that provide signals (e.g., video feeds) to specified monitors located at a specified location. In this regard, a CCTV system differs from a broadcast television system that broadcasts signals to multiple monitors located at multiple locations. A CCTV system is typically used to perform surveillance of areas monitored by the video camera devices. SUMMARY (2) In some implementations, a method performed by a guest assistance platform includes analyzing video data of an environment that includes a liquid substance, wherein the video data is analyzed using a machine learning model trained to detect objects in the liquid substance; detecting an individual in the liquid substance based on analyzing the video data; determining a measure of confidence associated with detecting the individual in the liquid substance; determining one or more confidence factors associated with detecting the individual in the liquid substance; modifying the measure of confidence, using the one or more confidence factors, to obtain a modified measure of confidence; determining whether the modified measure of confidence satisfies a confidence threshold; and selectively causing assistance to be provided to the individual or continue analyzing the video data based on whether the modified measure of confidence satisfies the confidence threshold, wherein the assistance is provided based on the modified measure of con
Claims
1. A method comprising: receiving, by one or more processors, video data of an environment that includes a liquid substance; detecting, by the one or more processors using a machine learning model, in a first frame of the video data, a first individual within a distance threshold from the liquid substance; detecting, by the one or more processors using the machine learning model, in a second frame of the video data, the first individual in the liquid substance based at least partially on analyzing the video data; determining, by the one or more processors, a measure of confidence indicative of a likelihood of the machine learning model accurately detecting that the first individual is in the liquid substance; analyzing, by the one or more processors using the machine learning model, a frame of the video data to determine a behavior of one or more additional individuals; determining, by the one or more processors, one or more confidence factors based on at least the behavior; 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, wherein the behavior indicates that the one or more additional individuals are attempting to provide assistance to the first individual; comparing, by the one or more processors, the modified measure of confidence to a confidence threshold; and communicating assistance to be provided to the first individual to at least one of a client device or an assistance device in response to determining that the modified measure of confidence satisfies the confidence threshold. ||
7. A system, comprising: one or more cameras to capture video data of an environment including a liquid substance; and a guest assistance platform comprising a machine learning model, a response engine, and one or more processors, configured to: receive the video data from the one or more cameras; analyze, using the machine learning model, the video data; detect, using the machine learning model, that a first individual is in the liquid substance; determine a measure of confidence indicative of a likelihood of the machine learning model accurately detecting that the first individual has fallen into the liquid substance; analyze, using the machine learning model, a frame of the video data to determine a behavior of one or more additional individuals in response to determining the measure of confidence; determine one or more confidence factors associated with the measure of confidence based on at least the behavior; increase the measure of confidence, using the one or more confidence factors, to determine a modified measure of confidence, wherein the behavior indicates that the one or more additional individuals are attempting to provide assistance to the first individual; perform, by the response engine, a first action in response to determining that the modified measure of confidence is a first value that satisfies a first confidence threshold; and perform, by the response engine, a second action different than the first action in response to determining that the modified measure of confidence is a second value different than the first value and the second value satisfies a second confidence threshold; wherein the first action and the second action provide assistance to the first individual. ||
13. A non-transitory computer-readable medium comprising: one or more instructions that, when executed by one or more processors, cause the one or more processors to: update, using training data, a machine learning model; receive video data of an environment; analyze, using the machine learning model, a first portion of the video data; detect a first individual in the environment; analyze, using the machine learning model, a second portion of the video data; determine that the first individual is missing from the environment in the second portion of the video data; determine a measure of confidence indicative of a likelihood of the machine learning model accurately detecting that the first individual is missing from the environment by determining at least one of conditions of the environment, obstruction in the video data, or an amount of the training data used to update the machine learning model; analyze, using the machine learning model, a frame of the video data to determine a behavior of one or more additional individuals in response to determining the measure of confidence; determine one or more confidence factors associated with the measure of confidence based on at least the behavior; modify the measure of confidence using the one or more confidence factors to determine a modified measure of confidence, wherein the measure of confidence is increased in response to the behavior indicating that the one or more additional individuals are attempting to provide assistance to the first individual; and generate 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 a first confidence threshold.