Efficient model-based recognition of objects using a calibrated image system
A model-based object recognition system operates to recognize an object on a predetermined world surface within a world space. An image of the object is acquired. This image is a distorted projection of the world space. The acquired image is processed to locate one or more local features of the image, with respect to an image coordinate system of the image. These local features are mapped a world coordinate system of the world surface, and matched to a model defined in the world coordinate system. Annotations can be arranged as desired relative to the object in the world coordinate system, and then inverse-mapped into the image coordinate system for display on a monitor in conjunction with the acquired image. Because models are defined in world coordinates, and pattern matching is also performed in world coordinates, one model definition can be used by multiple independent object recognition systems.
1. A method of recognizing an object in an image with at least two independent image processing systems, the method comprising steps of:
defining a single model of the object with respect to a world coordinate system of a world space; and
for each one of the at least two image processing systems;
calibrating a respective image processing system to the world space comprising the world coordinate system by determining a respective transformation between coordinates in an image coordinate system and coordinates in the world coordinate system;
acquiring an image;
mapping the image into the world coordinate system of the world space using the respective transformation; and
matching in the world coordinate system of the world space at least one occurrence of the object in the mapped image with the single model of the object based on a geometric shape of the single model.
2. A method as claimed in claim 1 , wherein the single model is defined using a selected one of the at least two image processing systems.
3. A method as claimed in claim 1 , wherein the single model is defined independently of the at least two image processing systems.
4. A method as claimed in claim 1 , wherein a respective instance of the single model is provided for each image processing system.
5. A method as claimed in claim 1 , wherein a common instance of the model is provided for two or more image processing systems.
6. A method as claimed in claim 1 , further comprising, for each one of the at least two image processing systems, extracting local features from the image as acquired, and wherein mapping the image into a world coordinate system comprises mapping the local features into the world coordinate system.
7. A method as claimed in claim 6 , wherein matching in the world coordinate system of the world space at least one occurrence of the object comprises matching in the world coordinate system the local features as mapped with the single model based on the shape of the single model.