Incremental AR Landmarker Mapping Across Lighting Changes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing AR systems face challenges in providing consistent augmented reality experiences across varying lighting conditions and environmental changes, requiring separate custom landmarkers for different scenarios, which is inconvenient for creators and can lead to map size issues, latency, and duplicate data.
Innovation Solution
A method for incrementally updating a custom AR landmarker by adding keyframes and 3D points under different conditions, purging frames to maintain map size, and aligning coordinate systems to ensure a single landmarker functions across lighting and environmental changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the localizer map is continuously updated with new keyframes and 3D points under different lighting conditions, then the adaptability of the custom landmarker improves, but the map size increases leading to latency and performance degradation
Solution Approach 1:
The patent extracts and removes duplicate or redundant keyframes and 3D points from the localizer map during incremental updates. By identifying and eliminating redundant data that does not contribute new information about the reference scene, the system maintains adaptability to different lighting conditions while preventing map bloat that would cause latency.
Solution Approach 2:
The system discards redundant or obsolete keyframes and 3D points that no longer provide unique value to the localizer map. This selective discarding allows the map to maintain an optimal size for real-time performance while retaining essential data needed for accurate localization across varying environmental conditions.
2Reliability
If the localizer map includes data from multiple lighting conditions and environmental changes, then the reliability of AR tracking improves, but the complexity of map management increases
Solution Approach 1:
The patent implements dynamic keyframe selection and map update mechanisms that automatically adjust which keyframes and 3D points are retained based on current lighting conditions and environmental context. This dynamic approach maintains reliable tracking across changing conditions while the system autonomously manages map complexity through intelligent selection algorithms.
Solution Approach 2:
The system changes parameters such as keyframe selection criteria and map update frequency based on environmental conditions. By adapting these parameters dynamically, the system maintains reliable AR tracking across different lighting scenarios while managing map complexity through condition-dependent parameter adjustment rather than fixed complex management rules.
3Adaptability or versatility
If the custom landmarker is designed to work across multiple lighting conditions, then the versatility improves, but the initial map creation time and processing increase
Solution Approach 1:
The patent performs preliminary keyframe selection and redundancy identification during the map creation process. By pre-processing and organizing keyframes with selection criteria in mind before full map construction, the system reduces the overall map creation time while still achieving versatile multi-lighting condition support through strategically selected keyframes.
Solution Approach 2:
The system initially creates a map with a subset of essential keyframes that cover multiple lighting conditions, rather than including all possible keyframes from the beginning. This partial action approach enables faster initial map creation with multi-lighting versatility, allowing the map to be progressively enhanced later if needed.
Data Source
AI summary
A method for generating an updated localizer map of a reference scene is provided. The method may include: acquiring a preliminary localizer map of the reference scene, the preliminary localizer map including a preliminary frame that each is associated with a set of preliminary data points; capturing a plurality of new data points on the reference scene; determining poses of the capture device related to the capture of the plurality of new data points; creating at least one new frame; selecting one or more target frames from the preliminary frame and the new frame; and generating the updated localizer map based on the one or more target frames.