Crowd-Sourced Visual Mapping for Mobile Device Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional visual mapping systems face delays and inaccuracies when a mobile device enters a new area, relying on time-consuming area learning processes or unreliable non-visual cues like GPS, especially in environments with poor reception or obstructions.
Innovation Solution
A cloud-based visual mapping system that leverages crowd-sourced data by mobile devices to create and update localization area description files (LADFs), allowing new devices to quickly localize using sparse point clouds of spatial features and associated data, while implementing privacy controls to protect sensitive information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a mobile device performs visual mapping to learn a new area, then localization accuracy is improved, but the time required for localization increases significantly
Solution Approach 1:
The system performs preliminary visual mapping and creates area description files in advance when the mobile device first explores an area. These pre-created maps and spatial feature data are stored and made available for rapid retrieval when the device returns to the same area, eliminating the need to perform time-consuming visual mapping again.
Solution Approach 2:
The system creates a digital copy of the area's spatial features, map data, and visual information and stores it in the area description file. When the mobile device needs localization, it retrieves this pre-created copy rather than performing new mapping operations, significantly reducing localization time.
2Device complexity
If a mobile device uses non-visual cues like GPS for localization, then the mapping process is simplified, but reliability and precision deteriorate in environments with poor reception or obstructions
Solution Approach 1:
The area description file serves as an intermediary that stores pre-processing results from visual mapping. It contains extracted spatial features, map data, and visual information that can be reliably used for localization without requiring real-time visual mapping or relying on unreliable non-visual cues like GPS.
Solution Approach 2:
The system replaces reliance on non-visual mechanical sensing systems (GPS, inertial sensors) with visual-based localization using pre-processed image data and spatial feature information stored in the area description file, providing more reliable localization in challenging environments.
3Measurement precision
If the system stores and processes detailed visual data for area mapping, then localization accuracy is improved, but privacy concerns and data security risks increase
Solution Approach 1:
The system extracts only the necessary spatial feature information, map data, and geometric relationships from the detailed visual data and stores these simplified representations in the area description file. This extraction process removes personally identifiable information and sensitive visual content while retaining the essential data needed for accurate localization.
Solution Approach 2:
The system transforms detailed visual data into abstracted spatial parameters and geometric representations. By changing the data from raw images to extracted spatial features and map coordinates, the system maintains localization accuracy while reducing the sensitivity and privacy risks associated with storing detailed visual information.
Data Source
AI summary
A computing system includes a network interface, a first datastore, a second datastore, and a merge module. The merge module is to receive a set of one or more area description files from a set of one or more first mobile devices. Each area description file represents a point cloud of spatial features detected by a corresponding first mobile device at an area. The computing system further includes a localization module and a query module. The localization generation module is to generate a localization area description file for the area from the set of one or more area description files and to store the localization area description file in the second datastore. The localization area description file represents a point cloud of spatial features for the area. The query module is to provide the localization area description file to a second mobile device via the network interface.