Scene Parameterization via Surface Geometry Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for estimating object size and distance in images from cameras are prone to errors due to reliance on assumed surface geometry, leading to inaccurate scene geometry assessments in vehicle assistance systems.
Innovation Solution
A method that calculates object size and distance using a parameter characterizing surface geometry, employing image recognition to assign objects to classes and using probability distributions to determine the most accurate surface geometry by maximizing scene probability through iterative parameter variation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional methods use assumed surface geometry to estimate object size and distance, then the estimation process is simple, but the accuracy of geometry assessment deteriorates
Solution Approach 1:
The invention changes the approach from using fixed assumed surface geometry parameters to iteratively optimizing surface parameters by calculating scene probability for different parameter values. The system varies surface parameters (such as inclination angle) and selects the values that maximize scene probability, thereby improving measurement precision without requiring complex additional hardware
Solution Approach 2:
The invention replaces direct mechanical/geometric measurement methods with a probabilistic calculation approach. Instead of relying on physical assumptions about surface geometry, the system uses image recognition data and probability distributions to computationally determine the most likely surface parameters, substituting physical measurement assumptions with statistical analysis
2Measurement precision
If iterative parameter variation is used to maximize scene probability, then measurement precision improves, but computing effort increases
Solution Approach 1:
The invention applies partial action by performing iterative parameter optimization only for the critical surface parameters that most affect measurement accuracy (such as inclination angle), rather than optimizing all possible parameters. This selective approach achieves sufficient measurement precision while limiting the increase in computing effort to only what is necessary for the most impactful parameters
Data Source
AI summary
A method for parameterizing a scene having a surface, on which at least two objects are disposed, using a camera disposed at a distance from the objects. The method includes: a) using the camera, producing an image of the scene, the image containing image data regarding the objects; b) recognizing at least two objects in the image by evaluation of the image data and assigning each recognized object to a specific object class; c) estimating an object size of each of the at least two recognized objects in accordance with at least one surface parameter characterizing the surface; d) for each of the at least two objects: calculating an individual probability that the object has the object size estimated in measure c); e) calculating a scene probability from the at least two calculated individual probabilities.