Vehicle Occupant Mass Estimation Using 2D/3D Skeleton Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mass estimation technologies for vehicle occupants are inaccurate, bulky, costly, and require excessive alignment, limiting their effectiveness in airbag deployment systems.
Innovation Solution
A method and system using a processor to analyze 2D and 3D images captured by an image sensor, applying a pose detection algorithm to generate skeleton representations, and extracting features to estimate occupant mass, integrated with airbag systems for tailored deployment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If prior mass estimation technologies (mechanical pressure pads or optical sensors) are used, then mass measurement function is provided, but measurement precision deteriorates due to vehicle acceleration interference
Solution Approach 1:
The patent replaces mechanical pressure sensors with an imaging system comprising multiple image sensors and a processor. The system captures images from different angles, generates 3D information through image processing, and estimates mass based on skeletal features and body volume. This substitution eliminates mechanical contact points that are sensitive to vehicle acceleration, providing more reliable measurements during dynamic conditions.
Solution Approach 2:
The patent introduces 3D image processing and skeletal feature extraction as intermediary steps between image capture and mass estimation. By generating depth maps, identifying skeletal keypoints, and calculating body volume through geometric modeling, the system creates a robust intermediate representation that is insensitive to vehicle acceleration, thereby improving measurement reliability.
2Measurement precision
If prior optical sensors or spectrometers are used, then mass estimation function is provided, but device complexity increases due to alignment requirements
Solution Approach 1:
The patent divides the imaging system into multiple independent image sensors positioned at different locations (front, rear, left, right) of the vehicle. Each sensor captures images from its own perspective without requiring precise alignment with others. The processor independently processes images from each sensor and integrates the results through 3D reconstruction, significantly reducing alignment complexity while maintaining measurement accuracy.
Solution Approach 2:
The patent uses multiple image sensors to create multiple copies of the occupant image from different viewpoints. Instead of relying on a single complex optical system requiring precise alignment, the system captures redundant image copies that can be processed independently and combined to generate accurate 3D information and mass estimates.
3Volume of moving object
If compact imaging systems are used, then device size is reduced, but manufacturing cost increases
Solution Approach 1:
The patent employs standard image sensors that can serve multiple functions: capturing 2D images for visual information, generating 3D depth maps through stereo processing, and extracting skeletal features for mass estimation. By using multi-functional sensors rather than specialized expensive equipment, the system achieves compactness while controlling manufacturing costs through component standardization.
Data Source
AI summary
There are provided methods and systems for estimating the mass of occupants in a vehicle cabin comprising obtaining multiple images of the occupants, comprising a sequence of two dimensional (2D) images and three dimensional (3D) 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 the occupants and combining the one or more 3D images of said sequence of 3D images with the skeleton representations of the occupants to yield skeleton models and analyze the skeleton models to extract one or more features of each of the occupants and further process the one or more extracted features of the skeleton models to estimate the mass of the occupants.