A method, apparatus and system for image processing

摘要

Embodiments of the present invention provide a device for superimposing a graphic on a second image generated from a cut-out of a first image of a scene that represents the field of view of a virtual camera. The device comprises receiver circuitry configured to receive the second image and a set of cut­out corner coordinates, each of which gives a position of a corner point of the cut-out in a first two-dimensional (2D) coordinate system defined for the first image. A homography determining circuit determines from the set of cut-out corner coordinates a homography between coordinates of the first 2D coordinate system defined within the cut-out and coordinates of a second 2D coordinate system defined for the second image. A feature determining circuit determines from the homography, a camera matrix representing a relationship between a three-dimensional (3D) coordinate system defined for the scene and the first 2D coordinate system defined for the first image and a virtual 3D map of the scene defining features of the scene in the 3D coordinate system of the scene, a feature of the virtual 3D map of the scene within the field of view of the virtual camera. A graphic generator circuit then generates the graphic from the determined feature of the virtual 3D map and a graphic superimposing circuit superimposes the generated graphic on the second image.