Vehicle Surround View Disparity Correction for Depth Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional surround view monitoring systems face challenges in accurately monitoring targets around a vehicle due to calculation errors in disparity data, leading to potential collisions when deviations in disparity values result in exceeding tolerances, especially when near-side and far-side deviations have unequal impacts on depth distance calculations.
Innovation Solution
The system synchronously captures base and reference images, calculates disparities, and corrects these disparities using a predetermined tolerable disparity range to ensure accurate depth distance calculations, thereby reducing the difference between near-side and far-side deviations and enhancing collision avoidance capabilities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If disparity data is calculated using triangulation theory from stereo images, then distance information about target objects can be obtained, but calculation errors occur due to deviations in disparity values from true values
Solution Approach 1:
The system pre-calculates first and second tolerances for disparity data before actual measurement occurs. These tolerances are stored as reference values that account for potential calculation errors. When measuring distance, the system compares actual disparity values against these pre-established tolerances to determine if measurements are reliable, preventing false collision avoidance activations.
Solution Approach 2:
The system changes the parameter of disparity tolerance by establishing asymmetric first and second tolerances based on the specific geometric relationship between cameras and target objects. Instead of using a fixed symmetric tolerance, the system adjusts tolerance parameters dynamically according to object distance and camera baseline, optimizing measurement precision while maintaining reliability.
2Device complexity
If identical near-side and far-side tolerances are set for distance, then simplicity is maintained, but asymmetric deviations in disparity data cause actual distance to exceed tolerance ranges
Solution Approach 1:
The system applies asymmetry by setting different first and second tolerances for disparity data corresponding to near-side and far-side deviations. This asymmetric tolerance structure matches the asymmetric nature of triangulation errors, where positive and negative disparities have different impacts on calculated distance. The asymmetric tolerances ensure that measurement accuracy is maintained across the full range of possible deviations.
3Reliability
If disparity tolerance range is set to cover all possible deviations, then measurement reliability is improved, but the range becomes excessively wide reducing measurement precision
Solution Approach 1:
The system applies local quality by setting different tolerance values for different regions of the measurement space. Specifically, first tolerances apply to disparity values with positive deviations while second tolerances apply to disparity values with negative deviations. This localized approach allows each tolerance to be optimized for its specific deviation direction, maintaining precision while ensuring comprehensive coverage of all possible errors.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach allows for more accurate monitoring of targets around the vehicle by ensuring that the negative deviation range of disparities has a margin, preventing collisions by maintaining the actual depth distance within tolerable limits, even when disparities deviate from true values.
Implementation Method 1
a first imaging device to capture a first image of the target object... a second imaging device to capture a second image of the target object
Data Source
AI summary
In a monitoring apparatus, a disparity calculator obtains, for each point of a target object, a pair of matched pixel regions in respective base image and reference image corresponding to the point of the target object. The disparity calculator calculates a disparity of each of the matched pixel regions of the base image relative to the corresponding matched pixel region of the reference image. A distance calculator corrects the calculated disparity of each of the matched pixel regions of the base image in accordance with a tolerable disparity range for the disparity to thereby increase the calculated disparity of the corresponding one of the matched pixel regions of the base image. The distance calculator calculates the depth distance of each point of the target object relative to the vehicle as a function of the corrected disparity of the corresponding one of the matched pixel regions.