3D Model-Based AR Coordinate Transformation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Marker-less type augmented reality (AR) systems face difficulties in accurately displaying AR images at desired positions, especially in large or distant locations where feature points are hard to acquire, such as sport venues.
Innovation Solution
An information processing apparatus that includes model-space storage, object-information acquisition, relation specifying, transformation, and coordinate notification means to transform 3D model coordinates into real-space coordinates, enabling precise AR image placement by comparing camera images with stored 3D models and specifying correspondence relations between model and real-space coordinate systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If marker-less type AR is used to avoid markers, then ease of operation is improved, but measurement precision deteriorates in large or distant locations
Solution Approach 1:
The patent introduces a 3D model of the specific object as an intermediary between the camera image and the coordinate system. By comparing the camera image with the pre-stored 3D model, the system can accurately determine the position and orientation of the specific object even in large or distant locations where feature points are sparse. This intermediary 3D model enables precise measurement without requiring markers or dense feature points.
2Measurement precision
If feature points are acquired for object recognition, then measurement precision is improved, but ease of operation deteriorates in locations where feature points are difficult to acquire
Solution Approach 1:
The patent performs preliminary action by pre-storing 3D models of specific objects before the actual AR operation. These 3D models contain comprehensive geometric information that will be used later for accurate position and orientation determination. By preparing the 3D model in advance, the system eliminates the need to acquire and process numerous feature points during real-time operation, making the process easier while maintaining high measurement precision.
3Measurement precision
If 3D model comparison is performed for coordinate transformation, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent uses a 3D model as a digital copy of the specific object, which stores all necessary geometric information. Instead of performing complex real-time feature point extraction and matching, the system compares the camera image with this pre-existing digital copy. This copying approach simplifies the device complexity while maintaining high measurement precision, as the 3D model can be efficiently stored and compared using standard computer vision techniques.
Data Source
AI summary
An information processing apparatus includes a model-space storage unit that stores a 3D (three-dimensional) model of a predetermined object present in a real space, an object-information acquisition unit that acquires an image of the object taken by a camera of an augmented-reality display apparatus, a relation specifying unit that specifies a correspondence relation between a model coordinate system and a real-space coordinate system based on a result of a comparison between the image and the 3D model, a transformation unit that transforms coordinates in the model coordinate system for specifying a position at which a predetermined image is displayed into coordinates in the real-space coordinate system by using the correspondence relation, and a coordinate notification unit that notifies the augmented-reality display apparatus of the coordinates transformed by the transformation means.