Infant Monitoring With Two-Time-Scale Sleep Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing infant monitoring systems struggle to accurately determine sleep stages in real-time using video analysis, often leading to unreliable results due to reliance on short-term data and requiring cloud processing or wearable devices.

Innovation Solution

A method utilizing two-time scale motion detection algorithms to analyze infant activity levels over a shorter and longer period, enabling real-time determination of sleep status without cloud processing or wearable devices.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If only short-term video data is analyzed for sleep stage determination, then real-time responsiveness is improved, but measurement precision deteriorates

Engineering Contradiction:

Improvereal-time responsivenessVSAvoidsleep stage determination accuracy

Core Design Contradiction:

SpeedVSMeasurement precision

Solution Approach 1:

The patent segments the analysis time into two distinct periods: a first time period for calculating recent activity level (real-time responsiveness) and a second time period for calculating longer-term activity level (measurement precision). This segmentation allows the system to simultaneously achieve both real-time responsiveness and accurate sleep stage determination by comparing activity levels across different time scales.

Inventive Principle:

Principle #1Segmentation

2Power

If cloud processing is used for sleep analysis, then computational power is improved, but device complexity and loss of time are worsened

Engineering Contradiction:

Improvecomputational powerVSAvoidsystem complexity

Core Design Contradiction:

PowerVSDevice complexity

Solution Approach 1:

The monitoring device performs sleep stage determination autonomously using local processing. The processor calculates activity levels from video data using the two-time period method and determines sleep stages without requiring cloud connectivity. This self-service approach eliminates the need for complex cloud infrastructure while maintaining accurate real-time analysis.

Inventive Principle:

Principle #25Self-service

3Measurement precision

If wearable tracking devices are used for infant monitoring, then measurement precision is improved, but ease of operation and object-generated harmful factors are worsened

Engineering Contradiction:

Improvesleep tracking accuracyVSAvoidcomfort and interference with sleep

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The patent replaces wearable mechanical tracking devices with a video-based optical monitoring system. The processor analyzes video data of the infant's movements to determine activity levels and sleep stages, eliminating the need for physical contact with the infant. This substitution maintains measurement precision while improving ease of operation and eliminating discomfort or sleep interference caused by wearable devices.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentEP4625380A1Infant monitoring

Publication Date: 2025.10.01 KONINKLIJKE PHILIPS NV

Figure 1
Figure 2
Figure 3

AI summary

Proposed concepts pertain to determining a sleep status of an infant in a monitored area. In particular, embodiments aim to provide a method for determining the sleep status of a monitored infant by monitoring the infant's level of activity over both a first time period and a second, longer, time period.