Vehicular Vision System Occupancy Calibration Using Wavelet Transform
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for determining the occupancy of vehicle seats, such as those using image-based sensors, face challenges in reliably distinguishing between occupants and objects, especially under varying lighting conditions and environmental factors, which can lead to incorrect airbag deployment in vehicles.
Innovation Solution
A method and system that utilize an image capture device to acquire images of the vehicle interior, process them using a two-dimensional complex discrete wavelet transform to extract features, and statistically analyze these features with predefined classification weights to determine the most probable occupancy status, employing techniques like image subtraction and region of interest processing to mitigate dynamic range issues and improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If image-based sensor systems are used to determine seat occupancy, then the ability to distinguish occupants from objects is improved, but reliability under varying lighting conditions and environmental factors deteriorates
Solution Approach 1:
The system dynamically adapts to varying lighting conditions by capturing multiple images at different exposures and synthesizing them into a high dynamic range image. This allows the system to maintain measurement precision across different environmental conditions, resolving the contradiction between accuracy and reliability under varying conditions.
Solution Approach 2:
The system changes the parameter of image exposure by capturing images at multiple exposure levels and combining them. This parameter change enables the system to handle varying lighting conditions effectively, maintaining both measurement precision and reliability across different environmental factors.
2Reliability
If full image processing is performed to improve classification accuracy, then occupancy determination reliability is improved, but computational requirements and processing time increase
Solution Approach 1:
The system extracts only the necessary features from the image data by using wavelet transform to identify significant coefficients and eliminating redundant information. This extraction process maintains classification reliability while reducing computational requirements and improving processing speed.
Solution Approach 2:
The system performs partial processing by selectively processing only the most relevant image features rather than the entire image dataset. This partial action approach maintains sufficient reliability for occupancy determination while significantly reducing computational burden and processing time.
3Measurement precision
If high dynamic range image processing is used to handle varying lighting conditions, then measurement accuracy is improved, but device complexity and processing requirements increase
Solution Approach 1:
The system segments the image processing task into distinct stages: capturing multiple exposure images, synthesizing high dynamic range images, performing wavelet transform, and classifying occupancy. This segmentation manages device complexity by organizing complex processing into manageable, modular steps while maintaining measurement precision.
Data Source
AI summary
A method for calibrating a vehicular vision system includes providing a camera at a vehicle, with the camera having a field of view. Images are captured with the camera and a set of resultant images are acquired for a classification. Information is extracted related to image features in the set of resultant images, and an appropriate subset of coefficients is determined. For each classification, a classification vector of at least one appropriate weight is stored that corresponds to the determined subset of coefficients.