System for generating 3D images for image recognition based positioning

A method of positioning a user equipment located in an environment, the user equipment comprising a camera for acquiring digital images, the method comprising:

• defining a three-dimensional model of the environment through a cloud of points, each point being defined by a set of coordinates and a color information;
• having the user equipment acquire a query image by capturing, by the camera, a portion of the environment;
• estimating an initial camera parameters configuration of the camera of the user equipment;
• evaluating similarities between the query image and each of a plurality of three-dimensional images to determine an initial three-dimensional image, the initial three-dimensional image being obtained from the three-dimensional model of the environment as seen by a virtual camera having said initial camera parameters configuration;
• modifying a camera parameters configuration of the virtual camera associated with the initial three-dimensional image to increase a similarity between the initial three-dimensional image and the query image up to a predetermined value;
• and
• generating an additional three-dimensional image based on the three-dimensional model of the environment, the additional three-dimensional image being obtained from the three-dimensional model of the environment as seen by a modified virtual camera having the modified camera parameters configuration.