Plane Detection in VR Using RANSAC and Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for plane detection in VR, AR, and MR environments suffer from insufficient or excessive detection, affecting accuracy and stability due to diverse physical environments.
Innovation Solution
A method and system that involves obtaining point cloud information, performing iterative regressing using the RANSAC algorithm, merging plane information based on preset rules, and filtering with a pre-trained plane segmentation model to determine target plane information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If plane detection is performed based on point cloud data in diverse physical environments, then the applicability of plane detection is improved, but the accuracy and stability of plane detection deteriorate
Solution Approach 1:
The patent segments the plane detection process into multiple stages: initial plane detection using RANSAC algorithm, plane merging based on spatial relationships, and iterative refinement. This segmentation allows the system to handle diverse environments by breaking down the complex detection task into manageable steps, each optimized for specific conditions.
Solution Approach 2:
The patent performs preliminary plane detection and merging operations before final accuracy refinement. By pre-identifying candidate planes and merging overlapping detections, the system reduces the complexity of subsequent refinement steps and improves overall detection accuracy across different environments.
2Measurement precision
If iterative regressing operation is performed on point cloud information to fit all plane information, then the extraction precision of plane information is improved, but the time consumption increases
Solution Approach 1:
The patent employs iterative regressing operations that periodically refine plane fitting results. Instead of continuous refinement, the system performs discrete iteration cycles with convergence criteria, achieving high precision while limiting time consumption through controlled iteration counts and early termination conditions.
Solution Approach 2:
The iterative regressing operation uses feedback from previous iteration results to guide subsequent refinement steps. The system monitors convergence metrics and adjusts refinement intensity accordingly, reducing unnecessary computation when precision thresholds are met and maintaining efficiency while achieving high extraction precision.
3Stability of the object's composition
If plane merging is performed according to preset rules, then the stability of plane detection is improved, but the device complexity increases
Solution Approach 1:
The patent uses parameter-based merging rules that compare plane characteristics (normal vectors, positions, dimensions) with preset thresholds. By transforming the merging decision into parameter comparison operations, the system achieves stable and reproducible results while keeping the complexity manageable through clear mathematical criteria.
Data Source
AI summary
A method and system for detecting plane information are provided. The method includes: obtaining point cloud information of a physical environment of a user; performing an iterative regressing operation on the point cloud information to fit all plane information corresponding to the physical environment; merging all the plane information according to a preset rule to obtain a merged plane information set; performing plane segmentation on the plane information set based on a pre-trained plane segmentation model to obtain segmented plane information; and filtering the segmented plane information to determine all target plane information corresponding to the physical environment.