3D Geometry Change Detection for Geographic Imagery Ranking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing geographic imagery services fail to effectively showcase notable feature changes over time at specific locations, often returning images taken during optimal conditions without reflecting current changes in the landscape.
Innovation Solution
A computer-implemented method that generates first and second 3D geometries of a location based on sets of images captured over time, determines visual changes by comparing features in these geometries, ranks images based on change scores, and selects images that depict significant changes, which can be provided to users upon request.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Illumination intensity
If images are selected based on popular times and perfect conditions, then image quality is improved, but the ability to reflect landscape changes over time deteriorates
Solution Approach 1:
The system performs preliminary actions by generating 3D geometries from image sets captured at different times, comparing features between these geometries to determine visual changes, and ranking image sets based on change scores before user request, enabling the system to proactively identify and prepare images showing notable landscape changes
Solution Approach 2:
The system changes the selection parameter from image quality metrics (illumination, composition) to change detection metrics (visual change scores comparing 3D geometries across time), allowing images that capture significant landscape transformations to be selected regardless of whether they were taken during optimal conditions
2Measurement precision
If all image sets are processed and ranked, then change detection accuracy is improved, but processing time and computational resources increase
Solution Approach 1:
The system applies local quality by focusing computational resources on comparing specific corresponding areas between 3D geometries that are most likely to contain notable changes, rather than uniformly processing entire image sets, and by ranking image sets to prioritize those with highest change scores for detailed analysis
Data Source
AI summary
An exemplary method for surfacing feature changes occurring over time at a location is provided. The method includes identifying sets of images captured at a location over a period of time. The sets of images depict objects at the location. Visual changes at the location over the period of time are determined for a given physical feature of the objects depicted in images from the sets of images based on at least a comparison of features in corresponding areas of a first and a second 3D geometry of the location associated with the images. The first and second 3D geometries depict physical features of objects at the location at different times. The sets of images may be ranked based on the determined visual changes for each set. A given set of images from the sets of images may be selected for display on a user interface based on the ranking.