3D Coordinate Computing Apparatus for Accurate AR Feature Point Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The accuracy of computing three-dimensional coordinates for feature points in augmented reality applications is compromised due to the difficulty in capturing images at appropriate positions and directions, leading to low-quality feature point maps and decreased accuracy in superimposing virtual images.
Innovation Solution
A three-dimensional coordinate computing apparatus that automatically selects two appropriate images for computing three-dimensional coordinates using marker position information, distance, and the number of corresponding feature points, ensuring accurate positioning and direction for enhanced feature point map quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If images are captured manually at arbitrary positions and directions, then the capturing process is simple and quick, but the accuracy of three-dimensional coordinate computation deteriorates
Solution Approach 1:
The system automatically evaluates and selects image pairs suitable for three-dimensional coordinate computation by computing distances between capture positions and counting corresponding feature points, eliminating the need for manual selection and ensuring accurate image pair selection without requiring user expertise in stereo vision geometry
Solution Approach 2:
The system computes quantitative metrics (distance between capture positions and number of corresponding feature points) for each image pair and uses this feedback to automatically select the most suitable image pair, creating a closed-loop selection process that optimizes computation accuracy
2Measurement precision
If images are captured at appropriate positions and directions for accurate three-dimensional coordinate computation, then the accuracy improves, but the capturing process becomes more complex and time-consuming
Solution Approach 1:
The system pre-computes position information from marker detection in multiple captured images and stores this data, enabling rapid automatic selection of suitable image pairs without requiring manual positioning or real-time adjustment during the three-dimensional coordinate computation process
Solution Approach 2:
The system automatically evaluates image pairs using pre-computed position information and feature point matching, selecting the most suitable pair without human intervention, which eliminates the time required for manual image pair selection while ensuring accuracy
3Manufacturing precision
If manual image selection is used, then the system is easier to operate, but the quality of feature point maps deteriorates
Solution Approach 1:
The system computes the number of corresponding feature points between image pairs and uses this feedback to automatically select image pairs that will produce high-quality feature point maps, ensuring optimal mapping quality without requiring user knowledge of feature point distribution
Solution Approach 2:
The system autonomously evaluates and selects image pairs based on computed metrics, replacing manual selection with an automated process that consistently chooses optimal image pairs for high-quality feature point map generation
4Measurement precision
If automatic image selection based on distance and feature point count is implemented, then the accuracy of three-dimensional coordinate computation improves, but the computational complexity increases
Solution Approach 1:
The system extracts and utilizes marker position information from captured images to compute capture positions, leveraging this extracted information for automatic image pair selection without requiring complex full-image analysis or feature point extraction from all images
Data Source
AI summary
A three-dimensional coordinate computing apparatus includes an image selecting unit and a coordinate computing unit. The image selecting unit selects a first selected image from multiple captured images, and selects a second selected image from multiple subsequent images captured by the camera after the first selected image has been captured. The second selected image is selected based on a distance between a position of capture of the first selected image and a position of capture of each of the multiple subsequent images and the number of corresponding feature points, each of which corresponds to one of feature points extracted from the first selected image and one of feature points extracted from each of the multiple subsequent images. The coordinate computing unit computes three-dimensional coordinates of the multiple corresponding feature points based on two-dimensional coordinates of each corresponding feature point in the first and second selected images.