Interior Location Identification via Visual Object Parsing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
GPS signals are often unavailable in interior spaces such as buildings, preventing users from determining their location or using navigation functions on electronic devices.
Innovation Solution
A method and apparatus for interior location identification that parses objects from images of interior spaces, compares them with stored objects, and indexes location descriptions in a location record, using a computer-readable storage medium and parse module to differentiate and identify unique objects within the space.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If GPS signals are used for location identification, then location accuracy in exterior spaces is improved, but location identification fails in interior spaces where GPS signals cannot be received
Solution Approach 1:
The patent introduces visual objects (landmarks, signs, decorations) as intermediary elements that can be detected in both exterior and interior spaces. These objects serve as mediators between the device and the location, allowing the system to identify locations through image recognition of these objects rather than relying solely on GPS signals that fail indoors.
Solution Approach 2:
The patent replaces the GPS satellite-based electromagnetic signal system with a local image recognition system using cameras and computer vision algorithms. This substitution enables location identification to function independently of external satellite signals, thereby working effectively in interior spaces where GPS is unavailable.
2Measurement precision
If object parsing and comparison algorithms are implemented, then interior location identification accuracy is improved, but computational complexity and processing time increase
Solution Approach 1:
The patent pre-processes and stores reference images of visual objects (landmarks, signs, decorations) in a database before actual location identification occurs. This preliminary action allows the system to quickly compare captured images against pre-existing templates, reducing real-time computational complexity while maintaining high identification precision.
Solution Approach 2:
The patent divides the complex task of location identification into separate modules: image capture, object detection/parsing, feature extraction, comparison with reference database, and location determination. This segmentation allows each module to be optimized independently, managing overall system complexity while achieving accurate results.
Data Source
AI summary
A parse module calibrates an interior space by parsing objects and words out of an image of the scene and comparing each parsed object with a plurality of stored objects. The parse module further selects a parsed object that is differentiated from the stored objects as the first object and stores the first object with a location description. A search module can detect the same objects from the scene and use them to determine the location of the scene.