Radar Movement Detection Using Acoustic Domain Transformation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current surveillance and automotive systems struggle to accurately distinguish between human and non-human movements using radar signals, leading to false alarms and inefficiencies, as existing methods are not effective in discriminating between specific types of objects or animals and other moving entities.
Innovation Solution
A method utilizing radar signals to differentiate between specific and non-specific movements by extracting acoustic and spectral features, combined with machine learning techniques like MLP and SVM, and employing a frame-level joint decision strategy to improve detection accuracy and reduce false alarms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If motion detectors are used to detect human activity, then detection coverage is improved, but false alarms increase due to inability to distinguish between human and non-human movements
Solution Approach 1:
The patent applies local quality by analyzing specific local features of movement patterns rather than treating all movements uniformly. It extracts and analyzes local characteristics such as velocity, acceleration, and movement trajectories of specific body parts to distinguish human movements from non-human movements, thereby improving detection accuracy while reducing false alarms
Solution Approach 2:
The patent employs parameter changes by monitoring and analyzing multiple dynamic parameters of movement including velocity, acceleration, and movement patterns over time. By tracking changes in these parameters and comparing them against learned human movement profiles, the system can distinguish human activities from non-human movements, resolving the contradiction between detection coverage and false alarm reduction
2Duration of action of moving object
If radar sensing technology is used for human detection, then continuous covert detection is improved, but output interpretability deteriorates
Solution Approach 1:
The patent introduces an intermediary processing layer that translates raw radar signals into interpretable movement patterns and characteristics. This intermediary layer extracts meaningful features from the radar data and presents them in a form that is both continuous for monitoring and interpretable for analysis, bridging the gap between continuous detection capability and output interpretability
3Measurement precision
If ideal action models are used for human detection, then normal human detection is improved, but detection of unusual human behavior deteriorates
Solution Approach 1:
The patent applies dynamics by implementing a learning system that adapts its detection models based on observed movements. Rather than relying on static ideal action models, the system dynamically learns and updates its understanding of human movement patterns, enabling it to detect both normal and unusual human behaviors by comparing against evolving reference profiles
Solution Approach 2:
The patent employs preliminary action by pre-learning normal human movement patterns to establish reference profiles before actual detection begins. These pre-learned models serve as baselines for comparison, enabling the system to identify deviations that indicate unusual behavior while maintaining high accuracy for normal human detection
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 achieves robust and accurate detection of specific movements, enhancing the ability to identify predetermined objects or animals, thereby reducing false alarms and improving system performance in surveillance and automotive applications.
Implementation Method 1
using a radar sensor to monitor a space
Implementation Method 2
A Fourier transform is performed on the output signal to produce a frequency domain signal spectrum
Data Source
AI summary
A method of detecting movement includes using a radar sensor to monitor a space, and receiving an output signal from the radar sensor. A Fourier transform is performed on the output signal to produce a frequency domain signal spectrum. The frequency domain signal spectrum is transformed into an acoustic domain signal. It is decided whether the output signal is indicative of movement of a predetermined object or a non-human animal dependent upon at least one feature of the acoustic domain signal and at least one spectral feature of the signal spectrum.