Electronic Device Positioning via Pre-Extracted Feature Point Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic devices face challenges in providing accurate position information using images, as the calculation of feature points from captured images is time-consuming and can be inaccurate due to differences in camera settings or capture environments.
Innovation Solution
An electronic device equipped with a camera module, communication circuit, memory, and processor, which obtains position information, stores feature point data, recognizes objects in images, extracts feature points, and calculates more accurate position information by comparing feature points from actual images with those from a three-dimensional virtual map.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If feature points are extracted from captured images to provide position information, then position information can be provided, but the calculation time increases and user waiting time increases
Solution Approach 1:
The patent pre-extracts feature points from images captured at different locations and stores them in advance. When position information is needed, the system directly compares pre-extracted feature points rather than extracting them in real-time, significantly reducing calculation time and user waiting time while maintaining position accuracy.
2Measurement precision
If feature points are extracted from captured images to determine position, then position information can be obtained, but the calculation complexity and processing time increase
Solution Approach 1:
The system performs feature point extraction in advance during map construction or image capture phases, storing extracted feature points with their corresponding location information. This preliminary processing shifts the computational burden away from real-time operation, reducing calculation complexity when position information is actually needed.
3Measurement precision
If feature point comparison is performed between captured images to provide position information, then position information can be provided, but accuracy decreases when camera settings or capture environments differ
Solution Approach 1:
The patent creates a virtual map by capturing images at various locations and extracting feature points from these images to construct a reference database. When determining position, the system compares feature points from the current captured image against this pre-built virtual map, allowing accurate position identification even when camera settings or environmental conditions differ, as the comparison is based on distinctive feature point patterns rather than exact image matching.
Data Source
AI summary
An electronic device is provided. The electronic device includes a camera that collects image data, a communication circuit that performs communication with an external device, a memory, and a processor. The processor obtains first position information about the electronic device, stores first feature point information based on the first position information, obtains an image via the camera, recognizes an object from the image, extracts second feature point information about the recognized object, and calculates second position information of higher accuracy than the first position information based on comparing the first feature point information with the second feature point information.