Mixed Reality Object Detection Using Depth-Based Point Cloud Partitioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mixed reality rendering engines require substantial memory and GPU resources due to complex layering operations and fail to enable effective segmentation based on image data, particularly in delicate settings like medical applications, leading to inefficient resource utilization and inaccurate modeling of physical environments.
Innovation Solution
The proposed solution employs depth-based partitioning and geometrically-aware object detection using point cloud partitions to reduce memory and GPU requirements, enabling accurate segmentation and direct object mapping, which reduces resource consumption and improves rendering efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If complex layering operations are used in mixed reality rendering engines, then rendering capability is improved, but memory and GPU resource requirements increase substantially
Solution Approach 1:
The patent segments the point cloud data into multiple depth-based partitions, where each partition contains points within a specific depth range. This segmentation allows the system to process and render only the necessary portions of the environment at any given time, reducing the memory and GPU resource requirements while maintaining comprehensive rendering capability across different depth planes.
2Adaptability or versatility
If existing mixed reality rendering engines use complex layering operations, then rendering capability is improved, but segmentation based on image data becomes ineffective
Solution Approach 1:
The patent introduces depth as an additional dimension for organizing and segmenting point cloud data. By creating depth-based partitions that organize points according to their distance from the camera, the system achieves effective segmentation based on image data while maintaining the rendering capabilities provided by the point cloud layering approach.
3Quantity of substance
If depth-based partitioning and object detection are implemented, then resource requirements are reduced, but processing complexity increases
Solution Approach 1:
The patent performs preliminary depth-based partitioning of the point cloud data before object detection and rendering operations. This preliminary organization of data into depth partitions reduces the complexity of subsequent processing by providing a pre-structured framework that guides object detection algorithms and rendering operations, thereby reducing overall resource requirements while managing processing complexity.
Data Source
AI summary
In general, embodiments of the present invention provide methods, apparatuses, systems, computing devices, computing entities, and/or the like for performing mixed reality processing using at least one of depth-based partitioning of a point cloud capture data object, object-based partitioning of a point cloud capture data object, mapping a partitioned point cloud capture data object to detected objects of a three-dimensional scan data object, performing noise filtering on point cloud capture data objects based at least in part on geometric inferences from three-dimensional scan data objects, and performing geometrically-aware object detection using point cloud capture data objects based at least in part on geometric inferences from three-dimensional scan data objects.