Vehicle Camera-Ground Alignment Using Reduced Image Frames
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The navigation of autonomous vehicles is hindered by errors introduced by the difference between camera-centered and ground coordinate systems, affecting the accurate determination of object locations and trajectory planning.
Innovation Solution
A method and system that reduce image data files from cameras on vehicles to determine alignment between camera-centered and ground coordinate systems by selecting and processing temporally spaced frames, forming and filtering feature pairs, and generating a road mask using a processor, which adjusts for vehicle velocity and quality thresholds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the original image data file is processed without reduction, then the alignment accuracy between camera and ground coordinate systems is improved, but the computational time and processing resources increase
Solution Approach 1:
The patent segments the original image data file into multiple individual frames, allowing selective processing of only necessary frames rather than processing the entire data file. This segmentation enables the system to divide computational work into manageable units and process only temporally relevant frames for alignment calculation.
Solution Approach 2:
The patent extracts and processes only the essential features and key frames from the original image data file, removing redundant information. By extracting only the necessary temporal and spatial features required for alignment computation, the system maintains accuracy while reducing computational burden.
2Productivity
If frames are selected based on vehicle velocity with larger temporal spacing, then the processing speed is improved, but the alignment precision deteriorates
Solution Approach 1:
The patent dynamically adjusts the temporal spacing between selected frames based on the vehicle's velocity. When the vehicle moves faster, larger temporal spacing is used to maintain processing speed; when moving slower, smaller spacing is used to maintain precision. This dynamic adaptation allows the system to optimize the trade-off between processing speed and alignment precision according to real-time operating conditions.
3Productivity
If feature pairs are filtered using quality scores and metrics, then the computational efficiency is improved, but the measurement accuracy may deteriorate
Solution Approach 1:
The patent changes the quality parameters and thresholds used for filtering feature pairs based on operating conditions. By adjusting the stringency of quality scores and metrics dynamically, the system can be more lenient when computational efficiency is prioritized and more stringent when measurement precision is critical, thus balancing the trade-off between efficiency and accuracy.
Data Source
AI summary
A vehicle, a system and a method of navigating the vehicle. The system includes a camera conveyed by the vehicle and a processor. The camera is configured to obtain an original image data file of an environment. The processor is configured to reduce the original image data file to obtain a reduced image data file and determine an alignment between a camera-centered coordinate system and a ground coordinate system using the reduced image data file.