Wi-Fi Human Detection via Sub-Carrier Correlation and Distance Metrics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current non-contact human behavior recognition methods using Wi-Fi signals face challenges in stability, accuracy, and scalability due to the need for extensive professional knowledge and domain experience in establishing the mapping relationship between Wi-Fi signal disturbances and human behavior, limiting their practicality and reliability.
Innovation Solution
A Wi-Fi based human body detection method that utilizes sub-carrier channel frequency responses to detect human presence and activity by calculating correlation coefficients and Mahalanobis distances, employing principal component analysis to filter out invalid data and automatically calibrate thresholds, allowing for robust and accurate detection with minimal human intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If Wi-Fi signal disturbance mapping methods are used to detect human behavior, then sensing capability is provided, but system stability and accuracy deteriorate due to requiring extensive professional knowledge and domain experience
Solution Approach 1:
The system automatically selects sub-carriers and calibrates thresholds without requiring manual professional knowledge or domain experience. The device performs self-service by autonomously adapting to different environments and optimizing detection parameters, thereby improving reliability while maintaining sensing capability.
Solution Approach 2:
The system dynamically changes detection parameters (sub-carrier selection, thresholds) based on environmental conditions. By automatically adjusting these parameters rather than using fixed mappings, the system achieves both high reliability and adaptability across different scenarios.
2Adaptability or versatility
If Wi-Fi signal disturbance mapping methods are used to detect human behavior, then sensing capability is provided, but ease of operation deteriorates due to requiring extensive professional knowledge
Solution Approach 1:
The system performs automatic sub-carrier selection and threshold calibration without requiring user intervention or professional knowledge. This self-service approach makes the system easy to operate while maintaining its sensing capability through automated adaptation.
Solution Approach 2:
The system performs preliminary automatic calibration and selection of detection parameters before actual human behavior detection begins. This preliminary action eliminates the need for users to have domain knowledge, thereby improving ease of operation while preserving sensing capability.
3Measurement precision
If sub-carrier channel frequency responses are used for detection, then measurement precision is improved, but device complexity increases due to additional processing requirements
Solution Approach 1:
The system extracts only the necessary sub-carrier channel frequency response data and relevant features from the Wi-Fi signals, rather than processing all available data. This extraction approach maintains high detection accuracy while reducing processing complexity by focusing only on essential information.
Solution Approach 2:
The system dynamically selects specific sub-carriers and adjusts processing parameters based on environmental conditions. By changing parameters adaptively rather than using fixed complex processing pipelines, the system achieves high precision with reduced overall complexity.
4Ease of operation
If automatic sub-carrier selection and threshold calibration are implemented, then ease of operation is improved, but processing time increases due to additional calibration steps
Solution Approach 1:
The system performs sub-carrier selection and threshold calibration as preliminary actions during initialization or when environmental changes are detected. By consolidating these operations rather than performing them continuously, the system improves ease of operation while minimizing time loss during actual detection phases.
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 method enhances the accuracy and reliability of human behavior recognition, improves system stability, and expands application scope by enabling detection in various environments with reduced CPU performance and cost, while integrating seamlessly with existing smart devices.
Implementation Method 1
uses a change of the sub-carrier channel frequency responses in the channel state information of a Wi-Fi connection
Implementation Method 2
CSI can describe the multipath link changes caused by a sensed target
Data Source
AI summary
The present disclosure provides a Wi-Fi based human body detection method, which includes selecting a sub-carrier data source device by a smart device, acquiring sub-carrier channel frequency responses, checking and filtering out invalid sub-carrier channel frequency responses, obtaining sub-carrier amplitudes, and grouping to obtain a plurality of datasets. Each data set is divided into multiple sub-datasets according to different parts of the sub-carrier channel frequency responses, and then for each sub-dataset, a correlation coefficient between the sub-carrier amplitudes is calculated, to obtain a human body presence detection value; a Mahalanobis distance or a Euclidean distance between the sub-carrier amplitudes is calculated to obtain a human activity detection value; in conjunction of a human activity threshold and a human presence threshold, a state of a human body sign is determined and reported to a cloud server. The present disclosure also includes a smart device for implementing the above method.