Model-based recognition of objects using a calibrated image system

A method of recognizing an object within a predetermined world space, the method comprising:

• acquiring an image of the object, the image comprising a distorted projection of the world space;
• analyzing the acquired image to locate one or more local features of the image, with respect to an image coordinate system of the image;
• mapping the local features into a world coordinate system of the world space;
• and
• matching the mapped local features to a model defined in the world-coordinate system.

A method of annotating an image of an object located in a predetermined world space of an image processing system adapted to estimate at least a location of the object in the world space, the image processing system including a monitor for displaying the image, the method comprising the steps of:

• defining an annotation of the object relative to at least the estimated location of the object, the annotation being defined in a world coordinate system of the world space;
• piece-wise mapping the annotation into an image space corresponding to the image of the object;
• and
• displaying the annotation on the monitor in conjunction with the image.

A method of generating a model for identifying an object within a predetermined world space, the method comprising steps of:

• providing an archetype of the object in the world space;
• acquiring an image of the archetype, the image comprising a distorted projection of the world space;
• analyzing the acquired image to locate one or more local features of the image, with respect to an image coordinate system of the image;
• mapping the local features into a world coordinate system of the world space;
• and
• deriving model data from the mapped local features.

A method of managing at least two independent image processing systems, each image processing system being adapted for model-based recognition of an object within a respective world space, the method comprising steps of:

• defining a model of the object with respect to a predetermined world coordinate system;
• and
• at each image processing system;
• calibrating the image processing system to a respective world space comprising the predetermined world coordinate system;
• and
• performing model-based recognition of objects within the respective world space using the model.