Static Object Reconstruction Using 2D Feature Points for Depth Data Loss
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing static object reconstruction systems fail when depth data collected by depth cameras is lost or damaged, limiting their application due to the reliance on expensive devices and complex user interfaces.
Innovation Solution
A method and system that calculates the extrinsic camera parameter using two-dimensional feature points when depth data is missing, allowing for the alignment of point clouds and successful reconstruction of static objects by mixing two-dimensional and three-dimensional feature points.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If depth data is collected by a depth camera for static object reconstruction, then the reconstruction precision is improved, but the system fails when depth data is lost or damaged
Solution Approach 1:
The system dynamically changes the parameter type used for extrinsic camera parameter calculation based on data availability. When depth data is available, it uses three-dimensional feature points; when depth data is lost or damaged, it switches to using two-dimensional feature points. This parameter switching mechanism ensures continuous operation and reconstruction capability despite depth data loss, resolving the contradiction between reconstruction precision and system reliability.
2Measurement precision
If multiple synchronous cameras or three-dimensional scanning devices are used for object reconstruction, then the reconstruction detail is improved, but the device cost and complexity increase
Solution Approach 1:
The patent makes the RGB-D camera universal by enabling it to perform both standard depth-based reconstruction and alternative 2D feature-based reconstruction. The system can adaptively switch between different reconstruction modes (3D feature points with depth data, or 2D feature points without depth data), making a single device capable of multiple reconstruction approaches. This eliminates the need for expensive multiple synchronous cameras or dedicated 3D scanning devices while maintaining reconstruction capability.
3Measurement precision
If three-dimensional feature points are used for calculating extrinsic camera parameters, then the alignment accuracy is improved, but the calculation fails when depth data is lost
Solution Approach 1:
The system implements dynamic adaptability by making the feature point selection process variable rather than fixed. The choice between three-dimensional feature points and two-dimensional feature points is dynamically determined based on the availability and quality of depth data. This dynamic switching mechanism allows the system to maintain alignment accuracy when depth data is available while adapting to handle depth data loss scenarios, thereby improving both alignment accuracy and data loss handling capability.
Data Source
Figure 1
Figure 2
Figure 3(a)~3(b)
AI summary
Embodiments of the present invention disclose a static object reconstruction method and system that are applied to the field of graph and image processing technologies. In the embodiments of the present invention, when a static object reconstruction system does not obtain, by means of calculation, an extrinsic camera parameter in a preset time when calculating the extrinsic camera parameter based on a three-dimensional feature point, it indicates that depth data collected by a depth camera is lost or damaged, and a two-dimensional feature point is used to calculate the extrinsic camera parameter, so as to implement alignment of point clouds of a frame of image according to the extrinsic camera parameter. In this way, a two-dimensional feature point and a three-dimensional feature point are mixed, which can implement that a static object can also be successfully reconstructed when depth data collected by a depth camera is lost or damaged.