Measuring people-flow through doorways using easy-to-install IR array sensors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional people counting solutions in buildings lack accuracy, privacy, scalability, and installation flexibility while being costly, with break-beam sensors having restrictive placement requirements, high-cost thermal imagers raising privacy concerns, and ultrasonic sensors requiring extensive training and not being pet-friendly.
Innovation Solution
A method and system using an infrared array sensor system with a processor to read and process temperature data frames from a doorway, employing filtering techniques to identify and track individuals across frames, providing accurate people flow measurement with flexibility in sensor placement and low cost, leveraging Otsu's thresholding and thermal noise modeling for improved accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If break-beam sensors are used for people counting, then cost is reduced, but installation flexibility and accuracy deteriorate due to restrictive placement requirements and inability to handle multiple simultaneous people
Solution Approach 1:
The patent divides the doorway monitoring task into multiple infrared sensor elements arranged in an array, where each sensor captures thermal data from a specific portion of the doorway. This segmentation allows the system to accurately detect and count multiple people simultaneously while providing flexible installation options, as the distributed sensor array can adapt to various doorway configurations without requiring precise alignment like break-beam sensors.
2Reliability
If ceiling mounted high-resolution thermal imagers are used, then people counting accuracy is improved, but cost increases prohibitively for large scale deployments
Solution Approach 1:
The patent employs low-cost infrared sensor array elements instead of expensive high-resolution thermal imagers. Each sensor in the array is a relatively inexpensive component that can be deployed at scale. The system achieves accurate people counting by processing data from multiple low-cost sensors rather than relying on a single expensive high-resolution imager, enabling large-scale commercial and residential deployments.
3Measurement precision
If RGB cameras are used for occupancy estimation, then accuracy is improved, but privacy concerns prevent deployment in many settings
Solution Approach 1:
The patent replaces visible light-based RGB cameras with infrared thermal sensing technology. Infrared sensors detect thermal radiation from human bodies rather than capturing visual images, thereby providing accurate occupancy estimation without compromising privacy. This substitution allows the system to maintain measurement precision while eliminating the privacy concerns associated with visible light cameras in residential and commercial settings.
4Quantity of substance
If ultrasonic sensors are used, then cost is reduced, but occupancy estimation accuracy deteriorates and pet-friendly capability is lost
Solution Approach 1:
The patent replaces ultrasonic acoustic sensing with infrared thermal sensing. Infrared sensors detect the thermal signature of occupants, providing superior occupancy estimation accuracy compared to ultrasonic methods. Additionally, thermal sensing is inherently pet-friendly as it can distinguish between humans and pets based on temperature differences and detection patterns, while maintaining cost-effectiveness for large-scale deployments.
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
Achieves high accuracy (93%) in estimating the number of occupants with real-time processing, privacy preservation, and reduced deployment constraints, making it suitable for large-scale commercial and residential applications.
Implementation Method 1
reading, with a processor, a sequence of sensor data frames from an infrared array that views the doorway, each sensor data frame having a grid of pixels, each pixel having a temperature value
Data Source
AI summary
A method of measuring people flow through a doorway using a low-resolution, low-cost infrared array is disclosed. The method includes reading a sequence of sensor data frames from the infrared array; determining a background temperature frame; determining whether sensor data frames include at least one person using noise filtering techniques; identifying at least one group of adjacent pixels corresponding to the at least one person; determining at least one location corresponding to the at least one person; and determining whether the at least one person is a same person as a person in a previous sensor data frame. Based on the matching of a same person through multiple sensor data frames, direction of movement and entry/exit events can be determined. The entry/exit events can advantageously be used to operate and HVAC system, security system, or other such system more efficiently and effectively.