Motion Sensor Person Counting Using Transition Matrix Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing person count estimation systems face challenges in accurately estimating the number of persons in areas due to assumptions about single person passage and the need for additional sensors, leading to inefficiencies and increased costs.
Innovation Solution
A person count estimation apparatus utilizing a plurality of motion sensors, a collection unit, a transition matrix generation unit, an instance prediction unit, a likelihood calculation unit, an instance selection unit, and an output unit to accurately estimate person counts in areas by predicting and calculating transition probabilities and likelihoods of person movement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a pyroelectric sensor and person count sensor are combined to estimate the number of persons, then the estimation function is provided, but the cost increases and the estimation accuracy is insufficient when multiple persons pass through simultaneously
Solution Approach 1:
The motion sensor performs multiple functions: it detects both the presence of persons and their movement patterns (entry/exit). By analyzing movement patterns over time, the system estimates person counts without requiring dedicated person count sensors, thus reducing device complexity and cost while maintaining estimation capability
Solution Approach 2:
The patent replaces the need for additional person count sensors with a computational approach using transition matrices and probability calculations. Instead of using more physical sensors to directly count persons, the system uses mathematical modeling to infer person counts from motion detection data, substituting mechanical sensing with information processing
2Measurement precision
If motion sensors are used to detect person presence, then the sensing function is provided, but the sensing areas may overlap causing difficulty in accurate counting
Solution Approach 1:
The system divides the monitoring space into multiple distinct sensing areas, each with its own motion sensor. By segmenting the space and tracking which specific sensing area each motion event occurs in, the system can accurately track person movement between areas and estimate total person counts even when sensing areas overlap, as each sensor independently monitors its designated zone
Solution Approach 2:
The system uses feedback from multiple motion sensors to continuously update the person count estimation. By collecting motion detection data from all sensing areas and processing it through transition matrix calculations, the system refines its estimation of actual person counts, using the feedback loop to compensate for any individual sensor limitations or overlapping detection issues
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
The apparatus effectively estimates person counts in areas with high accuracy at a lower cost, enabling efficient device control and reducing energy consumption by providing reliable output information for controlling devices such as lighting and air conditioning.
Implementation Method 1
The motion sensors each sense presence or absence of a human or a human motion in a corresponding sensing area to generate a sensing signal
Data Source
AI summary
According to one embodiment, an existent person count estimation apparatus includes motion sensors and following units. The collection unit generates human sensing information. The instance prediction unit predicts second instances from the first instances by using the transition matrix. The likelihood calculation unit calculates likelihoods of the second instances using the time information items. The instance selection unit selects one or more third instances having likelihoods higher than a threshold. The output unit generates output information including estimate values of existent person counts for the first areas included in the third instances.