Method and system for detecting an object in relation to a surface
AssigneePoseidon
InventorsJerome Meniere, Christophe Migliorini
Life of this patent
Estimating the term…
Abstract
The invention relates to a method for detecting an object (1) in relation to a surface (2). A synthetic image (3c, 4c) is produced from at least two distinct viewpoints (3, 4), for each of said viewpoints, by means of a geometrical transformation comprising at least one perspective projection (3a, 4a) of the object on the surface (2), each synthetic image being associated with the viewpoint concerned. By discriminating between the synthetic images, it is possible to detect the presence of and determine the position of the object (1) in relation to the surface (2), by searching for contrast inversions. The invention can be used for surveying a swimming pool.
Claims24
A process for detecting an object in relation to a surface, said surface not necessarily being flat, said process comprising:
- realizing a computer-generated image associated to a viewpoint being considered for each viewpoint by a geometric conversion at least including a projection in perspective of said object on said surface from at least two distinct viewpoints;
- distinguishing between the computer-generated images for detecting a presence and determining a position of said object in relation to said surface, said distinguishing between the different computer-generated images including:
- breaking said surface down into a mosaic of fields each including a center;
- and
- associating a specific direction to each center and each viewpoint,
- wherein each computer-generated image is broken down in virtual fields each including as many specific virtual directions as there are viewpoints, said process further including, to distinguish between the computer-generated images:
- selecting at least two computer-generated images associated to at least two viewpoints;
- choosing zones situated according to each of the specific virtual directions of each virtual field on each of the two selected computer-generated images;
- and
- comparing said zones in searching for opposing differences from one computer-generated image to another,
- wherein to realize each of said computer-generated images associated to a viewpoint being considered, at least one of radioactive emissions, electromagnetic rays, and mechanical vibrations emitted by said object are captured from each viewpoint to produce a signal, said signal is digitized to obtain digitized data, and said computer-generated images are calculated based on the obtained digitized data, and
- wherein said computer-generated images show zones in different colors, said process searches for opposing differences on each of the two selected computer-generated images, and inversions of color contrasts between zones situated along each of the specific virtual directions of each field are sought.
A process for detecting an object in front of a bottom said bottom including a surface, said surface not necessarily being flat, said process comprising:
- realizing a computer-generated image associated to a viewpoint being considered for each viewpoint by a geometric conversion at least including a projection in perspective of said object on said surface from at least two distinct viewpoints;
- distinguishing between the computer-generated images for detecting a presence and determining a position of said object in relation to said surface, said distinguishing between the different computer-generated images including:
- breaking said surface down into a mosaic of fields each including a center;
- and
- associating a specific direction to each center and each viewpoint,
- wherein each computer-generated image is broken down in virtual fields each including as many specific virtual directions as there are viewpoints, said process further including, to distinguish between the computer-generated images:
- selecting at least two computer- generated images associated to at least two viewpoints;
- choosing zones situated according to each of the specific virtual directions of each virtual field on each of the two selected computer-generated images;
- and
- comparing said zones in searching for opposing differences from one computer-generated image to another;
- wherein said geometric conversion also includes a projection, on a reference surface associated to a viewpoint being considered, said projection in perspective of said object on said bottom based on said viewpoint being considered,
- said computer-generated image associated to the viewpoint being considered including:
- an image realized by application of said geometric conversion on said object, and in addition to superposition, on said reference surface, and
- an image realized through application of said geometric conversion on a virtual representation including sections of the bottom not masked by said projection in perspective of the object.
A system for detecting an object in relation to a surface, said surface not necessarily being flat, said system comprising:
- means for detecting and first means for calculating to realize a computer-generated image associated to a viewpoint being considered by a geometric conversion including at least one projection in perspective of said object on said surface from at least two distinct viewpoints and for each of the viewpoints;
- means for discrimination to distinguish between the computer-generated images to detect a presence and to determine a position of said object in relation to said surface;
- said means for discrimination including:
- means for partition for breaking said surface down into a mosaic of fields each including a center and as many specific directions as there are viewpoints,
- wherein each computer-generated image is broken down into virtual fields each including as many specific virtual directions as there are viewpoints, said means for discrimination also including, to distinguish between the computer-generated images:
- means for selection for selecting at least two computer-generated images associated to at least two viewpoints;
- means for choosing zones situated according to each of the specific virtual directions of each virtual field on each of the two selected computer-generated images;
- means for comparison for comparing said zones in searching for opposing differences from one computer-generated image to another,
- wherein to realize each of said computer-generated images associated to a viewpoint being considered, said system includes:
- sensors in each viewpoint, said sensors including means for capturing at least one of radioactive emissions, electromagnetic rays, and mechanical vibrations emitted from said object, to produce a signal,
- means for digitization to digitize said signal and to obtain digital data,
- means for calculation to calculate said computer-generated images based on the obtained digital data,
- wherein said computer-generated images show zones of different colors, said system searches out opposing differences on each of the two selected computer-generated images, and said means for discrimination includes means to search out inversions of contrasts of color between zones situated according to each of the specific virtual directions of each field.
A system for detecting an object in front of a bottom, said bottom including a surface, said surface not necessarily being flat, said system comprising:
- means for detecting and first means for calculating to realize a computer-generated image associated to a viewpoint being considered by a geometric conversion including at least one projection in perspective of said object on said surface from at least two distinct viewpoints and for each of the viewpoints;
- means for discrimination to distinguish between the computer-generated images to detect a presence and to determine a position of said object in relation to said surface;
- said means for discrimination including:
- means for partition for breaking said surface down into a mosaic of fields each including a center and as many specific directions as there are viewpoints,
- wherein each computer-generated image is broken down into virtual fields each including as many specific virtual directions as there are viewpoints;
- said means for discrimination also including, to distinguish between the computer-generated images:
- means for selection for selecting at least two computer-generated images associated to at least two viewpoints;
- means for choosing zones situated according to each of the specific virtual directions of each virtual field on each of the two selected computer-generated images;
- means for comparison for comparing said zones in searching for opposing differences from one computer-generated image to another,
- wherein said geometric conversion further includes a projection, on a reference surface associated with a viewpoint being considered, said projection in perspective of said object on said bottom based on said viewpoint being considered,
- said computer-generated image associated with the viewpoint being considered including:
- an image realized by application of said geometric conversion of said object and in addition to superposition on said reference surface,
- an image realized by application of said geometric conversion to a virtual representation including sections of the bottom not masked by said projection in perspective of the object.
Dependencies are inferred from the claim text.