Rejecting False Positives in Point Cloud Extrusion Objects
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated algorithms for extracting objects of extrusion from point cloud data often produce 'false positives', which require manual detection and removal, increasing costs and labor in creating accurate 3D models for civil and mechanical engineering projects.
Innovation Solution
A method and apparatus that analyze nearby points in a point cloud to classify them as on-surface or off-surface and reject hypothesized objects of extrusion based on a threshold ratio of off-surface to on-surface points, automatically identifying and correcting false positives.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated algorithms are used to extract objects of extrusion from point cloud data, then productivity and cost savings are improved, but false positives increase requiring manual detection and removal
Solution Approach 1:
The system uses feedback by analyzing the spatial distribution of points relative to the hypothesized object surface. It calculates the ratio of off-surface points to on-surface points within a defined region, and uses this feedback to confirm or reject the object extraction hypothesis, thereby reducing false positives while maintaining automation
Solution Approach 2:
The patent replaces manual mechanical inspection with an automated computational system that uses mathematical calculations to determine point classifications and ratio thresholds, substituting human labor with algorithmic processing to maintain reliability while preserving productivity
2Measurement precision
If manual detection and removal of false positives is performed, then measurement precision is improved, but loss of time and productivity decrease
Solution Approach 1:
The system performs self-service by automatically detecting and rejecting false positives through its own computational processes. The algorithm independently analyzes point distributions, calculates ratios, and makes rejection decisions without requiring external manual intervention, thereby maintaining precision while eliminating time loss
3Ease of manufacture
If simple cylinder fitting algorithms are used, then ease of manufacture is improved, but object-generated harmful factors increase due to false positives from rounded edges
Solution Approach 1:
The patent applies segmentation by dividing the point cloud into distinct categories: on-surface points and off-surface points. This segmentation allows the system to analyze the spatial distribution of points relative to the hypothesized object, enabling simple algorithms to distinguish true objects from false positives caused by rounded edges without increasing complexity
Data Source
AI summary
A method of rejecting the presence of an object of extrusion within a point cloud. The method comprising receiving, through a data interface, data describing a set of measurements of observed portions of the one or more objects in the scene. The method further comprising receiving data describing an extruded object that is hypothesized to exist in the scene. The method further comprising finding a set of near measurement points comprising measurement points wherein each measurement point is within a predefined distance of the hypothesized extruded object. The method further comprising classifying points within the set of near measurement points associated with the hypothesized extruded object as on-surface or off-surface. The method further comprising rejecting the hypothesized extruded object whose off-surface measurement points exceed an allowable threshold.