Indoor Positioning Using Structure Line Descriptors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current indoor positioning methods in complex environments like shopping malls are unstable due to dynamic objects and illumination changes, relying heavily on textured images such as billboards, which are not static and frequently updated.
Innovation Solution
The method involves extracting descriptors of structure lines from images collected indoors and matching them with a pre-established indoor image database to acquire pose information using a 3D structure line map, independent of texture and illumination changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If textured images such as billboards are used for indoor positioning, then positioning can be performed in complex indoor environments, but positioning stability deteriorates due to dynamic objects and illumination changes
Solution Approach 1:
The patent extracts and utilizes structure lines (edges, contours, geometric features) from images while discarding texture information. This extraction of structural elements provides stable positioning features that are independent of illumination changes and dynamic objects, resolving the contradiction between environment adaptability and positioning stability
Solution Approach 2:
The patent changes the feature parameter from texture-based to structure-line-based. By transforming the positioning approach from relying on texture information (billboards, decorations) to relying on structural information (edges, lines, geometric shapes), the system achieves both environment adaptability and positioning stability
2Adaptability or versatility
If texture-based features are used for positioning, then positioning can be achieved in various indoor scenes, but positioning accuracy deteriorates due to frequent updates of dynamic images
Solution Approach 1:
The patent extracts structure lines as the primary positioning feature, separating structural information from texture information. This extraction ensures that positioning accuracy is not affected by frequent updates of dynamic texture elements like billboards and decorations
Solution Approach 2:
Instead of using texture information to achieve positioning, the patent inverts the approach by using structure line information. This inversion makes positioning accuracy independent of texture updates while maintaining versatility across different indoor scenes
Data Source
AI summary
The present application relates to a method for indoor positioning, and an apparatus, an electronic device and a storage medium, which relates to the fields of positioning technologies and deep learning technologies. A specific implementation solution is: extracting descriptors of structure lines in a specified image collected by a terminal indoors; based on the descriptors of the structure lines in the specified image and descriptors of structure lines of images included in a pre-established indoor image database, acquiring, from the indoor image database, target structure line descriptors closest to the descriptors of the structure lines in the specified image; and acquiring pose information of the terminal based on a pre-established indoor 3D structure line map and the target structure line descriptors corresponding to the descriptors of the structure lines in the specified image. The present application can position a terminal based on structure lines in a specified image collected by the terminal indoors, without being affected by texture information such as a billboard in the image, as well as illumination and appearance changes, which has higher robustness and can effectively improve the stability and accuracy of indoor positioning.