Planar Surface Detection via Sub-Volume Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for processing planar surface information in large-scale physical environments are computationally intensive, leading to battery drain and delays in augmented reality experiences, especially for small mixed reality devices.
Innovation Solution
The environment is partitioned into virtual sub-volumes, with surface representations generated in each sub-volume, allowing for individual processing of planar regions and reducing computational load by only processing relevant sub-volumes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing methods process planar surface information in large-scale environments, then complete surface detection is achieved, but computational load and power consumption increase significantly
Solution Approach 1:
The patent divides the large-scale physical environment into multiple smaller sub-volumes or regions. Each sub-volume is processed independently for planar surface detection, reducing the computational burden on any single processing unit. This segmentation allows mobile devices to detect planar surfaces accurately within each region without being overwhelmed by the entire environment's data processing requirements, thereby reducing power consumption while maintaining detection accuracy.
2Measurement precision
If existing methods process all environment data for planar surface detection, then comprehensive surface information is obtained, but processing time and delays increase
Solution Approach 1:
By segmenting the environment into sub-volumes, the patent enables parallel processing of multiple regions simultaneously. This reduces the sequential processing time required to analyze the entire environment, as different sub-volumes can be processed concurrently. The system maintains comprehensive surface information by ensuring all sub-volumes are processed, but the overall processing time is reduced through this divide-and-conquer approach.
Solution Approach 2:
The patent implements a approach where initially only relevant or visible sub-volumes are processed for planar surface detection, rather than processing the entire environment data set. This partial action reduces processing time and delays, while still providing sufficient surface information for augmented reality experiences. Additional sub-volumes can be processed as needed based on user interaction or device capabilities.
3Measurement precision
If mobile devices process large-scale environment data, then accurate planar surface detection is achieved, but device performance and battery life deteriorate
Solution Approach 1:
The patent segments the processing task into manageable sub-volume units that can be handled by mobile device processors without causing performance degradation. Each sub-volume contains a limited amount of environment data that can be processed efficiently, maintaining detection accuracy while preventing the device from being overwhelmed by the computational demands of processing the entire large-scale environment at once.
Data Source
Figure 1A
Figure 1B
Figure 1C
AI summary
The described implementations relate to processing of an environment using a plurality of sub-volumes, and specifically to generating surface representations in the plurality of sub-volumes for individual processing. One example can identify planar fragments within the plurality of sub-volumes. The example can determine that various planar fragments constitute part of a contiguous planar surface and should be aggregated. The example can also output data representing the contiguous planar surface formed from the aggregated planar fragments.