Vehicle Occupant Mass Estimation Using 2D/3D Skeletal Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing airbag systems struggle with inaccurate mass estimation of vehicle occupants, particularly children, leading to potential fatal injuries, and prior solutions are bulky, costly, and require complex alignment.
Innovation Solution
A method and system using a processor to analyze 2D and 3D images of vehicle occupants, applying pose detection algorithms to extract skeletal features, filter valid poses, and estimate mass, integrated with airbag control units for tailored deployment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If prior mass estimation systems use mechanical solutions such as pressure pads or optical sensors, then mass measurement function is provided, but measurement precision deteriorates due to vehicle acceleration interference
Solution Approach 1:
The patent replaces mechanical pressure pads and optical sensors with image processing-based mass estimation. The system captures images of occupants and uses computer vision algorithms to estimate mass, eliminating the mechanical connection that causes measurement errors during vehicle acceleration. This substitution of mechanical measurement with optical/image-based measurement resolves the reliability issue under acceleration conditions.
2Measurement precision
If prior spectrometers are used for mass estimation, then measurement function is provided, but device complexity increases due to alignment requirements
Solution Approach 1:
The patent extracts the essential measurement function from complex spectrometer systems and implements it through simpler image capture and processing. By using standard imaging devices and algorithmic mass estimation rather than full spectrometer systems, the invention removes the alignment complexity while retaining mass estimation capability. The solution takes out only the necessary functional elements needed for mass estimation.
3Adaptability or versatility
If prior mass estimation technologies are implemented, then airbag control function is provided, but device size increases making the system bulky
Solution Approach 1:
The patent makes the imaging system multi-functional by using it for both occupant detection and mass estimation. The same image capture device that detects occupant presence is also used to extract mass information through image processing algorithms. This universality eliminates the need for separate dedicated mass measurement devices, reducing overall system volume while maintaining airbag control adaptability.
4Measurement precision
If prior mass estimation systems are used, then occupant detection function is provided, but cost increases beyond ideal levels
Solution Approach 1:
The patent employs inexpensive image capture devices and processing algorithms instead of expensive dedicated mass measurement sensors. By using standard imaging technology and computational methods that can be implemented with relatively low-cost hardware, the system achieves mass detection capability at a reduced cost profile compared to specialized mechanical or optical measurement systems.
Data Source
Figure 1A
Figure 1B
Figure 1C
AI summary
There are provided methods and systems for estimating the mass of one or more occupants in a vehicle cabin comprising obtaining multiple images of the one or more occupants, comprising a sequence of 2D (two dimensional) images and 3D (three dimensional) images of the vehicle cabin captured by an image sensor, applying a pose detection algorithm on each of the obtained sequences of 2D images to yield one or more skeleton representations of said one or more occupants and combining the one or more 3D images of said sequence of 3D images with said one or more skeleton representations of said one or more occupants to yield skeleton models and analyze the skeleton models to extract one or more features of each of the one or more occupants and further process the one or more extracted features of the skeleton models to estimate the mass of the one or more occupants.