Visual Geo-Localization Using Remotely Sensed Feature Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current location-based applications, especially in augmented reality and autonomous devices, face inaccuracies with GPS-based location information, requiring more precise geo-location and orientation measurements to interpret surroundings effectively.
Innovation Solution
The system uses visual data from camera images and videos to determine location and orientation by matching remotely sensed visual features with simulated image signatures, enabling devices to access and provide information about places directly through a camera view, integrating GPS, LIDAR, and computer-generated imagery for enhanced accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS sensors are used to measure device location, then location information can be obtained, but the measurement precision is insufficient for augmented reality and autonomous devices
Solution Approach 1:
The patent uses visual features from camera images as an intermediary to determine device location and orientation. Instead of relying solely on GPS signals, the system extracts visual features from the camera view, compares them with pre-stored images from known locations, and uses the matching results to calculate precise location and orientation data. This intermediary approach bridges the gap between simple GPS sensing and the need for high-precision location information.
Solution Approach 2:
The patent replaces the traditional GPS-based mechanical/electromagnetic sensing system with a visual-based system. By substituting GPS signal processing with image feature extraction and matching, the system achieves higher measurement precision for location and orientation without being constrained by GPS accuracy limitations.
2Measurement precision
If visual feature matching is used to improve location precision, then measurement precision increases, but the device complexity and processing requirements increase
Solution Approach 1:
The patent applies preliminary action by pre-collecting and storing images from known locations with their corresponding coordinate information before actual use. This pre-processing creates a reference database that can be quickly queried during runtime, avoiding the need for complex real-time image capture and analysis at the moment location determination is needed.
Solution Approach 2:
The patent segments the complex task of location determination into distinct components: visual feature extraction from camera images, feature matching with pre-stored reference images, and coordinate calculation based on match results. This segmentation allows each component to be optimized independently and processed efficiently.
3Measurement precision
If multiple sensors and processing methods are integrated to improve location accuracy, then measurement precision improves, but the device complexity increases
Solution Approach 1:
The patent makes the camera serve multiple functions: it acts as both the primary sensing device for capturing visual features and as a reference for determining device orientation. The same camera images used for location determination also provide orientation information, eliminating the need for separate sensors and reducing overall system complexity.
Solution Approach 2:
The patent merges location determination and orientation determination into a single integrated process using visual feature matching. By combining these functions into one unified system that processes camera images simultaneously for both purposes, the patent reduces the complexity that would arise from separate systems while maintaining high precision for both measurements.
Data Source
AI summary
Visual data is used to locate a device in the real world. The location and orientation of the device is detected by matching the camera view of the device to a computer-generated view of an area surrounding the location. The computer-generated view of the area is constructed by combining various remotely sensed geospatial data including satellite imagery, aerial LIDAR, map data, GIS inventory data, and/or the like. In various embodiments, the disclosed system can not only locate the device but can also provide measurements regarding where the user is looking and 3D measurement of the scene in the device camera view. In various embodiments, the presented invention enables devices to have a system that provides spatial intelligence to any camera.