Point Cloud Map Skew Correction for Virtuality-Reality Overlap
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current virtuality-reality overlapping technologies face precision issues due to biased or skewed point cloud maps and inconsistent scales, leading to decreased efficiency and increased tracking miss rates.
Innovation Solution
A method and system that constructs a point cloud map of a real scene, performs 3D object detection to locate outline border vertexes, calculates proportion relationships, and projects the map to correct skewness, enabling accurate virtual content overlap with the real scene using a wearable device.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the constructed point cloud map has high degree of freedom for flexible mapping, then the adaptability of the mapping system is improved, but the precision of virtuality-reality overlapping drops and tracking miss rate increases due to map bias and skewness
Solution Approach 1:
The system performs preliminary actions by detecting outline border vertexes of objects in the scene before constructing the point cloud map. By identifying these key geometric features in advance and using them as reference points for map construction, the system ensures that the map is built with correct geometric constraints, preventing bias and skewness while maintaining mapping flexibility.
Solution Approach 2:
The system changes parameters by transforming the point cloud map using calculated proportion relationships and geometric constraints derived from outline border vertexes. This parameter transformation corrects map bias and skewness, ensuring consistent scale and orientation while preserving the flexible adaptive nature of the mapping system.
2Measurement precision
If additional space transformation is applied to correct inconsistent map scales, then the overlapping accuracy is improved, but the processing time and system efficiency decrease
Solution Approach 1:
The system performs scale correction as a preliminary action during the map construction phase rather than as a post-processing step. By calculating proportion relationships and applying scale transformations when building the point cloud map, the system ensures consistent scaling from the outset, avoiding the need for time-consuming additional transformations later.
Solution Approach 2:
The system achieves self-service efficiency by using outline border vertexes of objects as intrinsic reference points that automatically provide geometric constraints for scale normalization. These object-based references enable the system to self-correct scale inconsistencies without requiring external calibration data or complex multi-step transformation processes.
Data Source
AI summary
A virtuality-reality overlapping method is provided. A point cloud map related to a real scene is constructed. Respective outline border vertexes of a plurality of objects are located by using 3D object detection. According to the outline border vertexes of the objects, the point cloud coordinates of the final candidate outline border vertexes are located according to the screening result of a plurality of projected key frames. Then, the point cloud map is projected to the real scene for overlapping a virtual content with the real scene.