Vehicle Exterior Recognition Using Relaxed Stereo Distance Blending
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle exterior environment recognition systems face errors in calculating the relative distance of three-dimensional objects when one imaging unit captures a blurred image, leading to accumulation of errors and potential unintended vehicle acceleration.
Innovation Solution
A vehicle exterior environment recognition apparatus that calculates a relaxation distance using a more lenient image matching threshold, combining it with a monocular distance at a predetermined ratio to generate an updated distance, thereby reducing error accumulation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a strict image matching threshold is used to calculate stereo distance, then measurement precision is improved, but reliability deteriorates when one imaging unit captures a blurred image
Solution Approach 1:
The patent applies parameter changes by introducing a relaxed threshold parameter for calculating relaxation distance when image quality deteriorates. The threshold is dynamically adjusted based on image quality assessment, allowing the system to switch between strict threshold (for clear images) and relaxed threshold (for blurred images), thereby maintaining reliability under varying conditions while preserving measurement precision when possible
Solution Approach 2:
The patent introduces an intermediary approach by calculating relaxation distance using a more lenient threshold as a supplementary measure. This relaxation distance acts as an intermediary calculation that can be combined with or substitute for the primary stereo distance calculation, providing a fallback mechanism that maintains system reliability when primary calculation fails due to blurred images
2Reliability
If monocular distance calculation is used when stereo calculation fails, then reliability is improved, but measurement precision deteriorates due to error accumulation
Solution Approach 1:
The patent implements feedback by continuously monitoring image quality and calculating both stereo distance and relaxation distance, then comparing and selecting the more reliable result. This feedback mechanism prevents error accumulation by detecting when monocular calculation errors are occurring and switching back to stereo-based calculation when conditions improve, thereby maintaining both reliability and precision
Solution Approach 2:
The patent applies partial action by performing both stereo distance calculation and relaxation distance calculation simultaneously, then selectively using the appropriate result. This excessive calculation approach ensures that precision is maintained by using stereo calculation when possible, while reliability is ensured by having the relaxation calculation available as a partial solution when stereo calculation fails
3Reliability
If a lenient threshold is used for relaxation distance calculation, then reliability under blurred conditions is improved, but measurement precision deteriorates
Solution Approach 1:
The patent dynamically changes the threshold parameter based on image quality conditions. When images are clear, a strict threshold is applied for high precision. When images are blurred, the threshold is relaxed to maintain reliability. This adaptive parameter adjustment resolves the contradiction by allowing the system to optimize for precision or reliability depending on current conditions
Solution Approach 2:
The patent introduces dynamics by making the threshold flexible rather than fixed. The threshold adapts in real-time based on image quality assessment, allowing the system to transition between precision-oriented and reliability-oriented operation modes. This dynamic adjustment enables the system to maintain both precision and reliability across varying operational conditions
Data Source
AI summary
A vehicle exterior environment recognition apparatus includes a monocular distance calculator, a relaxation distance calculator, and an updated distance calculator. The monocular distance calculator calculates a monocular distance of a three-dimensional object from a luminance image generated by an imaging unit. The relaxation distance calculator calculates a relaxation distance of the three-dimensional object from two luminance images generated by two imaging units based on a degree of image matching between the two luminance images determined using a threshold more lenient than another threshold used to determine the degree of image matching to generate a stereo distance of the three-dimensional object. The updated distance calculator calculates an updated distance of the three-dimensional object by mixing the monocular distance and the relaxation distance at a predetermined ratio.


