Imagery Graph Navigation for Multi-Source Visual Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems fail to effectively navigate and integrate multiple types of visual data associated with a point of interest, such as landmarks, as different imagery sets like street view panoramas, aerial images, and user images from photograph sharing services are often disjointed, making it difficult for users to understand the three-dimensional relationships between them.
Innovation Solution
A computer-implemented method and system that utilizes an imagery graph to connect image nodes from various imagery types based on geospatial data, allowing users to select regions within an image and seamlessly transition between different imagery sets, such as from street view to user images, by providing a unified three-dimensional representation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple imagery sets (street view, aerial, user images) are stored separately in different data stores, then each imagery type can be managed independently, but users cannot easily navigate between different imagery types or understand their three-dimensional relationships
Solution Approach 1:
The patent merges multiple separate imagery data stores into a unified imagery graph data structure. This graph integrates street view panoramas, aerial images, satellite images, and user images from photograph sharing services into a single cohesive system where all imagery types are interconnected through shared geospatial references, enabling seamless navigation between different imagery types while maintaining their individual characteristics
2Device complexity
If imagery data is organized by separate data stores for each imagery type, then data management is simplified, but the three-dimensional spatial relationships between images from different sources cannot be effectively represented
Solution Approach 1:
The patent introduces a new dimensional organization based on geospatial coordinates and camera parameters. By organizing imagery nodes in a graph structure with explicit spatial relationships (latitude, longitude, heading, pitch, roll), the system preserves three-dimensional spatial information while maintaining manageable data organization. This allows users to navigate between imagery types based on their spatial relationships rather than treating them as separate categories
3Measurement precision
If users view images from different imagery sets separately, then each image can be displayed in full detail, but users cannot understand how images from different sets relate to each other in three-dimensional space
Solution Approach 1:
The patent introduces geospatial coordinates and camera parameters as intermediary elements that connect different imagery nodes. These intermediaries serve as reference points that allow the system to maintain full detail of individual images while simultaneously establishing their spatial relationships. The imagery graph uses these intermediaries to enable navigation between images based on their three-dimensional positions, preserving both detail and context
Data Source
AI summary
Systems and methods for navigating an imagery graph are provided. In some aspects, a first image is provided for display, where the first image corresponds to a first image node within an imagery graph, where the imagery graph comprises image nodes corresponding to images from a plurality of different imagery types, and where each image node in the imagery graph is associated with geospatial data. An indication of a selection of a predetermined region within the first image is received, where the predetermined region is associated with a position in the first image that corresponds to geospatial data associated a second image node within the imagery graph. A second image corresponding to the second image node is provided for display in response to the indication of the selection of the predetermined region.