3D Environment Model Generation with VIO-SLAM Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing spatial modeling technologies face challenges in accurately simulating real environments due to errors in sensing data, leading to distortions in the simulated environment.
Innovation Solution
A computing apparatus and method that fuse multiple sensing data, including image and inertial measurement data, using VIO and SLAM algorithms to track pixel trajectories and map sensing points into a coordinate system, thereby generating an accurate three-dimensional environment model.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If sensing data is used to generate a simulated environment, then the simulated environment can be created for applications such as games, home furnishing, and robot movement, but errors in the sensing data cause distortion of the simulated environment
Solution Approach 1:
The patent combines multiple sensing data sources (image data from cameras and inertial measurement data from IMU sensors) to compensate for errors in individual sensors. By fusing these diverse data sources through VIO and SLAM algorithms, the system achieves more reliable depth information and position estimation, thereby improving the fidelity of the simulated environment while accounting for measurement uncertainties
Solution Approach 2:
The patent implements feedback mechanisms through the VIO algorithm that continuously tracks pixel trajectories and adjusts position estimates based on inertial measurement data. This feedback loop allows the system to detect and compensate for sensing errors in real-time, correcting distortions in the simulated environment by comparing expected versus actual sensor readings and adjusting the model accordingly
2Measurement precision
If VIO and SLAM algorithms are used to estimate positions of sensing points and generate a three-dimensional model, then the accuracy of position estimation and fidelity of the model are improved, but the computational complexity increases
Solution Approach 1:
The patent divides the complex modeling task into separate functional modules: image data acquisition, inertial measurement data acquisition, VIO algorithm processing for trajectory tracking, SLAM algorithm processing for mapping, and 3D model generation. This segmentation allows each algorithm to specialize in specific computations, improving position estimation accuracy while managing overall system complexity through modular architecture
Solution Approach 2:
The patent performs preliminary processing of sensing data before full 3D modeling, including pre-tracking of pixel trajectories using VIO algorithms and pre-mapping of sensing points using SLAM. These preliminary actions prepare refined position estimates and depth information in advance, reducing the computational burden during final model generation and optimizing the balance between accuracy and complexity
Data Source
AI summary
A computing apparatus and a model generation method are provided. In the method, multiple sensing data are fused to determine depth information of multiple sensing points, moving trajectories of one or more pixels in the image data are tracked according to the image data and the inertial measurement data through the visual inertial odometry (VIO) algorithm, and those sensing points are mapped into a coordinate system according to the depth information and the moving trajectories through the simultaneous localization and mapping (SLAM) algorithm, to generate a three-dimensional environment model. An object is set on the three-dimensional environment model through a setting operation. The shopping information of the object is provided.