Camera Pose Determination Without Initialization Movement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing pose determination methods for cameras in augmented reality (AR) systems, such as those using ARkit development components, require cumbersome system initialization involving camera movement, leading to poor timeliness and high computational demands.
Innovation Solution
A pose determining method that allows for the determination of a camera's pose in the world coordinate system without the need for system initialization movement, by selecting a user-defined two-dimensional plane point in a video frame, obtaining camera orientation information, and calculating three-dimensional space point coordinates to establish the camera's pose.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If visual inertial odometry (VIO) technology is used to determine camera pose, then the pose can be tracked in the real world, but system initialization requiring camera movement is needed, leading to poor timeliness
Solution Approach 1:
The patent extracts the essential function of pose determination from the complex VIO system initialization process. By selecting a specific point on a horizontal plane in the video frame and using its coordinates directly to establish the camera pose, the method removes the time-consuming camera movement requirement while maintaining pose determination capability
Solution Approach 2:
The patent performs preliminary action by pre-establishing the relationship between the horizontal plane point coordinates and the camera pose. The method prepares the pose determination by using the selected point's coordinates to directly calculate the camera position and orientation, eliminating the need for subsequent initialization movements
2Reliability
If VIO technology with point cloud reconstruction is used, then comprehensive environment mapping is achieved, but computational complexity and resource requirements increase significantly
Solution Approach 1:
The patent extracts only the essential information needed for pose determination - the coordinates of a single point on the horizontal plane - from the complex point cloud reconstruction process. This extraction approach maintains sufficient reliability for AR applications while dramatically reducing computational complexity by avoiding full environment mapping
Solution Approach 2:
The patent applies partial action by using only the necessary portion of environment information (one horizontal plane point) rather than performing complete point cloud reconstruction. This partial approach provides sufficient data for pose determination without the excessive computational burden of comprehensive mapping
Data Source
AI summary
This application provides a pose determining method performed by an electronic device. The method includes: determining a first two-dimensional plane point in a first video frame captured by a camera, in response to a user-selected point within a display region of a target horizontal plane in a real world captured in the first video frame; obtaining first orientation information of the camera when acquiring the first video frame; determining a first three-dimensional space point corresponding to the first two-dimensional plane point in the real world and first coordinates of the first three-dimensional space point in a camera coordinate system; and determining a pose of the camera when acquiring the first video frame in the world coordinate system, according to the first orientation information of the camera and the first coordinates of the first three-dimensional space point in the real world.