Depth-Based Object Dimensioning With Adaptive Ray Error Bounds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing sample consensus model fitting methods for dimensioning target objects do not adequately account for the inaccuracies of depth sensors, particularly near the edges of their field of view, leading to incorrect classification of data points as inliers or outliers.
Innovation Solution
A method and device that determine errors for each data point along a ray defined from the sensor to the data point, with stricter error thresholds near the edges of the field of view to reflect decreasing sensor accuracy, allowing for accurate classification and selection of object models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a fixed error bound is used to classify data points as inliers or outliers, then the model fitting process is simple and fast, but the classification accuracy deteriorates near the edges of the sensor's field of view due to sensor inaccuracies
Solution Approach 1:
The patent applies local quality by making the error bound adaptive rather than fixed. The error bound varies locally across the field of view, being stricter near the center where sensor accuracy is high and more lenient near the edges where sensor accuracy deteriorates. This allows the system to maintain high classification accuracy across different spatial regions while preserving computational efficiency through a unified adaptive error calculation approach.
2Measurement precision
If stricter error thresholds are applied near the edges of the field of view to account for sensor inaccuracies, then the classification accuracy improves, but the complexity of the error calculation increases
Solution Approach 1:
The patent implements parameter changes by dynamically adjusting the error bound parameter based on the spatial position of each data point within the field of view. The error bound is calculated as a function of the distance from the center of the field of view, automatically adapting the classification threshold to the local sensor accuracy characteristics. This approach achieves accurate classification without requiring complex manual calibration or multiple error models.
Data Source
AI summary
A method comprising obtaining, from a sensor, depth data representing a target object; selecting a model to fit to the depth data; for each data point in the depth data: defining a ray from a location of the sensor to the data point; and determining an error based on a distance from the data point to the model along the ray; when the depth data does not meet a similarity threshold for the model based on the determined errors, selecting a new model and repeating the error determination for the depth data based on the new model; when the depth data meets the similarity threshold for the model, selecting the model as representing the target object; and outputting the selected model representing the target object.