In-Vehicle FMCW Radar Occupant Classification Under Occlusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Camera-based solutions for preventing heatstroke deaths in vehicles are ineffective in situations with occlusions or lighting issues, failing to detect children when there is no line-of-sight or when they are covered.
Innovation Solution
A system utilizing frequency modulated continuous wave (FMCW) radar for in-vehicle sensing and classification, which transmits and receives radar signals to generate classification data, including point cloud data and Doppler features, to determine the presence and state of occupants inside the vehicle.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If camera-based solutions are used for occupancy detection, then the system can identify occupants visually, but the detection fails when there are occlusions or lighting issues inside the vehicle
Solution Approach 1:
The patent replaces the optical camera-based detection system with a radar-based detection system. Radar uses electromagnetic wave reflection principles to detect occupants, eliminating dependency on visible light and line-of-sight conditions. The radar signals can penetrate through blankets, clothing, and other occlusions that block camera views, thereby resolving the contradiction between detection reliability and susceptibility to occlusion/lighting interference.
Solution Approach 2:
The patent changes the detection parameter from optical characteristics (visible light reflection) to electromagnetic wave characteristics (radio wave reflection). By operating in the microwave frequency range, the system detects changes in dielectric properties and motion of occupants rather than visual appearance, making detection immune to lighting conditions and visual occlusions while maintaining high reliability.
2Measurement precision
If camera-based solutions are used, then the system can detect occupants with line-of-sight, but it fails to detect children when there is no line-of-sight or when they are covered
Solution Approach 1:
The patent substitutes optical line-of-sight detection with radar wave penetration detection. Radar waves at microwave frequencies can pass through non-metallic materials like blankets, car seats, and clothing, allowing the system to detect occupants even when they are covered or positioned in areas blocked from camera view, thereby improving detection accuracy without increasing difficulty.
Solution Approach 2:
The radar system provides universal detection capability across all vehicle interior conditions - whether occupants are visible or covered, in direct line-of-sight or obscured positions. The same radar hardware and processing algorithm effectively detect all types of occupants (adults, children, infants) regardless of their position or coverage state, eliminating the need for multiple specialized detection systems.
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 FMCW radar system effectively classifies occupants regardless of occlusions or lighting conditions, providing accurate detection and enabling timely responses to prevent heatstroke by generating alerts or system responses when animate subjects are present.
Implementation Method 1
transmitting, via a FMCW radar sensor, radar transmission signals. The method includes receiving, via the FMCW radar sensor, radar reflection signals based on the radar transmission signals
Implementation Method 2
generating first range data by performing a fast Fourier transform (FFT) on a first set of chirps of a first frame using the digital signals
Implementation Method 3
generating Doppler data by performing the FFT on at least the first range data and the second range data. The method includes extracting Doppler features from the Doppler data. The Doppler features include a velocity of the radar subject
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A system and method relate to in-vehicle sensing and classification via frequency modulated continuous wave (FMCW) radar. Radar reflection signals are received based on the radar transmission signals. The radar reflection signals include a plurality of chirps across a plurality of frames. The radar reflection signals are converted into digital signals. Range-FFT data is generated by performing a fast Fourier transform (FFT) on each chirp of a particular frame using the digital signals. Doppler-FFT data is generated by performing the FFT on the range-FFT data. Point cloud data of a radar subject is generated using the Doppler-FFT data. The point cloud data includes location data of the radar subject. Doppler features are extracted from the Doppler-FFT data. The Doppler features include a velocity of the radar subject. Classification data is generated to indicate a sensing state inside a vehicle based on the point cloud data and the Doppler features. The classification data includes class data that classifies the radar subject. A system response is generated to provide an action concerning the sensing state inside the vehicle based on the classification data.