Geo-registration of Digital Images Using 3D Landmark Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods fail to accurately and efficiently organize and summarize large collections of digital images and videos in social networking systems, particularly in determining the geo-location of images captured by users and their connections, due to inaccuracies in GPS tagging and reliance on manual entry.
Innovation Solution
A system that uses geo-registration by comparing digital images with a database of 3D models of landmarks to determine precise locations, allowing images to be mapped and users to explore their connections' travels, with features like user travel scores and intuitive map navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If GPS tagging is used to determine image locations, then the process is simple and automated, but the location accuracy deteriorates especially in urban canyons
Solution Approach 1:
The patent introduces image content analysis as an intermediary between the image and its location. Instead of directly using GPS coordinates, the system extracts visual features from the image (buildings, landmarks, streets) and matches them with map data to determine location. This intermediary process overcomes GPS inaccuracies in urban canyons by relying on visual evidence rather than satellite signals.
Solution Approach 2:
The patent replaces the mechanical GPS satellite-based positioning system with a computer vision-based location determination system. Instead of relying on electromagnetic signals from satellites, the system uses image processing algorithms to identify visual features and match them with geographic data, providing accurate location determination where GPS fails.
2Measurement precision
If manual entry of visited cities is required, then location information can be accurate, but user participation deteriorates due to busy schedules
Solution Approach 1:
The patent implements self-service by enabling the system to automatically determine image locations without requiring user input. The computer vision system autonomously analyzes image content, extracts features, matches them with map data, and generates location information. This eliminates the need for users to manually enter visited cities while maintaining accurate location data.
Solution Approach 2:
The patent replaces the manual data entry process with an automated computer vision system. Instead of users typing in location information, the system uses image processing and feature matching algorithms to automatically determine and tag locations, making the process both accurate and convenient.
3Loss of information
If all images from contacts are analyzed for geo-location, then comprehensive travel information is obtained, but processing time and computational resources increase
Solution Approach 1:
The patent applies partial action by selectively processing images based on their potential to provide useful travel information. The system likely prioritizes images that show distinctive features or are taken in locations of interest, rather than uniformly processing every single image. This approach maintains comprehensive travel information while reducing unnecessary processing of redundant or low-value images.
Solution Approach 2:
The patent segments the large collection of images into manageable groups or batches for processing. Instead of analyzing all images simultaneously, the system divides them into smaller sets that can be processed independently and in parallel, reducing overall processing time while still achieving comprehensive coverage of travel information.
Data Source
AI summary
Aspects of the disclosure relate to identifying visited travel destinations from a set of digital images associated with users of a social networking system. For example, one or more computing devices provide access to an individual user's account, including the individual user and other users affiliated with the individual user via the social networking system. One or more digital images are received from a computing device associated with the individual user and from one or more second computing devices associated with the other users of the social networking system. From each digital image, a geo-location is determined for each digital image. The one or more computing devices display each geo-located image on a map at a position corresponding to the determined geo-location for the geo-located image.