Occluded Surface Reconstruction via Symmetry Computation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies are unable to effectively reconstruct 3D surfaces that are occluded from view, limiting applications such as robotic grasping and 3D modeling, as they rely on 2D image processing which distorts 3D symmetries and lacks methods for computing occluded surfaces from 3D data.
Innovation Solution
A system and method that acquire a 3D map of visible surfaces, identify symmetries, and compute probable occluded surfaces using symmetry features and domains, leveraging prior knowledge of object symmetries to infer occluded regions, even from limited viewpoints.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If multiple viewpoints are used to construct 3D model, then completeness of surface information is improved, but device complexity and cost increase
Solution Approach 1:
The system performs preliminary action by acquiring 3D range data of visible surfaces before the grasping operation, and uses symmetry computation to predict occluded surfaces in advance. This allows the robotic system to plan grasps without needing to physically move to multiple viewpoints, thereby reducing device complexity while maintaining information completeness.
Solution Approach 2:
The system creates a copy of the visible surface information and applies symmetry transformations to generate probable occluded surfaces. Instead of acquiring actual data from multiple viewpoints, the system synthesizes virtual copies of surface data through symmetry operations, achieving complete surface information with a single sensor.
2Ease of operation
If 2D image processing is used, then ease of operation is improved, but measurement precision of 3D surfaces deteriorates
Solution Approach 1:
The system transitions from 2D image processing to 3D range data processing. By acquiring depth information through time-of-flight cameras or structured light, the system operates in three dimensions while maintaining computational simplicity. The symmetry operations are performed on 3D point clouds rather than 2D images, preserving measurement precision while keeping the approach accessible.
3Productivity
If symmetry computation is used to predict occluded surfaces, then productivity is improved, but reliability of surface information may deteriorate
Solution Approach 1:
The system adjusts parameters such as symmetry score thresholds and confidence levels to balance productivity and reliability. By tuning these parameters, the system can quickly compute probable occluded surfaces when confidence is high, while being more conservative when uncertainty is greater, thus maintaining both speed and accuracy in grasp planning.
Data Source
AI summary
A system for obtaining a probable 3D map of an occluded surface of an object is provided. The system receives an initial 3D map of a visible surface of the object and identifies one or more symmetries of the initial 3D map. The system computes the probable 3D map of the occluded surface by projecting points of the initial 3D map into occluded regions of space according to the identified symmetries. The system can also comprise an imager for obtaining the initial 3D map. The actual occluded surface cannot be known with absolute certainly because it is occluded; however, the computed 3D map will closely resemble the actual occluded surface in many instances because most objects possess one or more symmetries and the computed 3D map is based on such symmetries that are identified in the initial 3D map of the object.