Occupancy estimation using nonparametric online change-point detection, and apparatuses, systems, and software for same
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current occupancy detection technologies, such as PIR sensors, ultrasonic sensors, thermal imaging cameras, and video cameras, face limitations in reliably detecting occupancy, including false positives, energy consumption, cost, and privacy concerns, especially when individuals are immobile or in complex environments.
Innovation Solution
The method employs nonparametric online change-point detection using radio frequency (RF) signals to determine changes in occupancy within a monitored space by analyzing RF signal strength, distinguishing between occupied and unoccupied states through statistical measures like mean and variance, and issuing a change-in-occupancy signal.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If thermal imaging cameras are used to detect immobile persons, then occupancy detection is improved, but cost and complexity increase
Solution Approach 1:
The patent employs inexpensive RF sensors and processors instead of expensive thermal imaging cameras. The RF sensing system uses commodity wireless communication hardware to detect occupancy, providing a cost-effective alternative that maintains detection capability for both moving and stationary persons without the high cost and complexity of thermal imaging technology.
2Reliability
If video cameras are used for occupancy detection, then detection reliability is high, but privacy concerns and computational requirements increase
Solution Approach 1:
The patent extracts only the essential occupancy detection function from video cameras by using RF sensing to detect presence/absence and motion states without capturing visual images. This extraction eliminates privacy concerns associated with video recording while maintaining occupancy detection reliability, as the system processes only RF signal characteristics rather than visual data.
3Use of energy by moving object
If PIR sensors are used with timers for lighting control, then energy is saved, but false positives occur when windows are in coverage area
Solution Approach 1:
The patent detects changes in RF signal characteristics (analogous to color changes in visual systems) to distinguish between thermal variations from windows and actual occupancy. By monitoring temporal patterns and signal feature changes rather than relying on simple threshold timers, the system can differentiate between false positive thermal signatures and genuine occupancy, maintaining energy efficiency while improving detection accuracy.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach provides a reliable, energy-efficient, and cost-effective means to detect occupancy changes, reducing false positives and addressing privacy concerns by using RF signals to accurately identify presence or absence of individuals within a space.
Implementation Method 1
receiving radio frequency (RF) energy within a monitored space, generating a time-series RF signal based on the RF energy received
Data Source
AI summary
Systems, methods, and software for determining whether or not a monitored space is occupied by one or more humans and/or animals. In some embodiments, one or more radio-frequency (RF) receivers monitor(s) one or more RF frequencies for changes in received signal strength that may be due to changes in occupancy of the space being monitored. The received signal strength is analyzed using nonparametric online change-point detection analysis to determine change-points in the received signal(s). One or more statistical measures of the received signal(s), such as mean and variance, are used in conjunction with the change-point detection to determine a probability that the occupancy of the monitored space has changed. In some embodiments, additional sensors and/or machine learning can be used to enhance the performance of the disclosed occupancy-detection methodologies.