Vehicle Fisheye Camera Alignment for Road Condition Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The variability in vehicle builds and optical camera assemblies leads to misalignment of captured images, increasing computational demand and reducing the efficiency of camera-based advanced driver assistance systems (ADAS) in detecting road conditions.
Innovation Solution
A method and system for automatic image view alignment that transforms fisheye images into rectilinear images, aligning feature points like vanishing points and horizons by adjusting the center of projection using a pitch angle, ensuring consistent sky-to-ground ratios, and applying rectification transformations to achieve alignment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If images are captured using multiple vehicles with variable builds and camera assemblies, then image collection capability is improved, but image alignment accuracy deteriorates
Solution Approach 1:
The system changes the parameters of the rectification transformation based on detected feature point distances. When the vertical distance between corresponding feature points exceeds a threshold, the system adjusts the pitch angle parameter to realign the image, thereby adapting to variations in vehicle builds and camera assemblies while maintaining alignment accuracy
Solution Approach 2:
The system employs feedback by detecting the vertical distance between corresponding feature points in subject and reference images, comparing this distance against a threshold, and then adjusting the rectification transformation accordingly. This closed-loop approach ensures that images from vehicles with variable builds are properly aligned
2Manufacturing precision
If image alignment processing is performed to correct misalignment, then image alignment accuracy is improved, but computational demand increases
Solution Approach 1:
The system applies partial action by only performing rectification transformation when necessary - specifically when the vertical distance between corresponding feature points exceeds a predetermined threshold. This conditional approach avoids unnecessary computational overhead while maintaining alignment accuracy when needed
Solution Approach 2:
The system uses easily detectable feature points such as vanishing points and horizons that can be automatically identified without complex processing. By leveraging these self-evident geometric features, the system minimizes computational demand while achieving effective alignment
3Manufacturing precision
If feature point detection and distance calculation are performed, then image alignment precision is improved, but processing time increases
Solution Approach 1:
The system extracts only the essential information needed for alignment - specifically the vertical distance between corresponding feature points such as vanishing points and horizons. By focusing solely on this critical parameter rather than processing the entire image, the system achieves alignment precision with minimal processing time
Data Source
AI summary
A system and method of automatic image view alignment for a camera-based road condition detection on a vehicle. The method includes transforming a fisheye image into a non-distorted subject image, comparing the subject image with a reference image, aligning the subject image with the reference image, and analyzing the aligned subject image to detect and identify road conditions in real-time as the vehicle is in operation. The subject image is aligned with the reference image by determining a distance (d) between predetermined feature points of the subject and reference images, estimating a pitch of a projection center based on the distance d, and generating an aligned subject image by applying a rectification transformation on the fisheye image by relocating a center of projection of the fisheye image by the pitch angle .