Planar Surface Reconstruction with User-Added Feature Points
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing 3D reconstruction methods face challenges in determining the position and orientation of planar surfaces, especially those with weak or no texture, as they often lack sufficient feature points for accurate reconstruction.
Innovation Solution
A method and apparatus that prompt users to add feature points when the initial number is below a threshold, using algorithms like Least Squares, Random Sample Consensus, or 3-D Kernel-based Hough Transform to reconstruct the planar surface based on 3D coordinates and image acquisition apparatus pose, employing Visual Inertial Odometry for accurate positioning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If automatic feature point detection is used for planar surface reconstruction, then the process is automated and efficient, but weakly-textured or texture-less surfaces lack sufficient feature points for accurate reconstruction
Solution Approach 1:
The system automatically detects when feature points are insufficient and prompts the user to add them, then automatically proceeds with reconstruction when the threshold is met, minimizing manual intervention while ensuring accuracy
Solution Approach 2:
The system provides feedback to the user about the number of detected feature points and prompts them to add more when necessary, creating a closed-loop process that ensures sufficient feature points for accurate reconstruction
2Measurement precision
If manual feature point addition is required to ensure sufficient points for reconstruction, then reconstruction accuracy improves, but the operation becomes more complex and time-consuming
Solution Approach 1:
The system automatically counts feature points and determines whether user intervention is needed, reducing the cognitive load on users and making the process easier to operate
Solution Approach 2:
The system performs preliminary feature point detection and evaluation before requiring user action, so users only need to add points when necessary rather than always manually specifying all points
3Measurement precision
If the system waits for sufficient feature points before reconstruction, then reconstruction accuracy is ensured, but the processing time increases due to iterative point collection
Solution Approach 1:
The system performs preliminary detection of feature points and evaluates whether the threshold is met before initiating the full reconstruction process, avoiding unnecessary iterative cycles
Solution Approach 2:
The system provides immediate feedback to users about feature point sufficiency, enabling quick user response and minimizing the time spent in iterative point collection
Data Source
AI summary
Embodiments of the present disclosure disclose a method and an apparatus for determining a planar surface. A specific embodiment of the method comprises: determining, from obtained images of the environment that include a to-be-determined planar surface, feature points belonging to the to-be-determined planar surface; judging whether the number of the feature points belonging to the to-be-determined planar surface is smaller than a preset number threshold; if yes, generating first prompt information for prompting a user to add feature points on the to-be-determined planar surface; obtaining at least two first images including the added feature points; and in response to the number of the feature points belonging to the to-be-determined planar surface in the first images being no less than the preset number threshold, reconstructing the to-be-determined planar surface based on the first images so as to determine a location and an orientation of the to-be-determined planar surface. This embodiment implements reconstruction of a weakly-textured or texture-less planar surface.