Nec Corporation

Nec Laboratories America, Inc.

Valorisation-recherche, Limited Partnership

Suometry, Inc.

Sebastien Roy

Warren Smith

Vincent Chapdelaine-Couture

Albert Peter Blicher

The present disclosure relates to omnipolar imaging for generating a substantially 360 degree by 180 degree stereo spherical view. The omnipolar imaging device comprises at least three wide angle lenses facing in a first direction and at least three wide angle lenses facing in a second direction opposite to the first direction, each lens connected to an image sensor. The lens are positioned so as to capture the substantially 360 degree by 180 degree view. The method of rendering the view comprises, for each pixel in an output image, selecting one set of lenses, i.e. the first set of lenses or the second set of lenses, selecting one lens from the selected set of lenses, and rendering the pixel in an output image from a corresponding point in an input image of the selected lens.

Spherical omnipolar imaging

There is described a camera setup for capturing omnistereo images using a minimum of three cameras with ultra wide angle lenses and a method for generating a substantially 360 degree view from images taken from the cameras. The field of view covered in stereo may be a dome. The baseline between pairs of cameras defines epipoles which can be used for stitching without any horizontal misalignments due to parallax. The method comprises capturing the images from a plurality of cameras fixed at a baseline height substantially equidistantly about a circle; and stitching together portions of the images from each one of the plurality of cameras along first and second borders corresponding at least in part to lines joining center points of neighboring ones of the plurality of cameras.

Omnistereo imaging

The present invention is a system and method for three dimensional machine vision including a projector and camera. The projector casts a structured light Quadratic Residue Bar Code on the surface to be mapped. The camera then images the surface. The projected image is shifted, and the process is repeated a number of times, according to the particular arrangement selected for the structured light Quadratic Residue Bar Code. The image data collected from this series of images is then processed by relatively simple matrix operations to determine the location of each camera pixel in three dimensional space.

Three dimensional vision device and method, and structured light bar-code patterns for use in the same

A method for matching a two dimensional image to one of a plurality of three dimensional candidate models. The method including the steps of: determining the position and orientation of the two dimensional image; for each three dimensional model, computing a histogram-like table having a computed brightness coefficient for each surface normal of the model based on the corresponding value in the two dimensional image, each brightness coefficient depending only on the corresponding surface normal; and either successively rendering each three dimensional model in the determined position and orientation using the surface normals in conjunction with the corresponding computed brightness histogram-like table; and comparing the two dimensional image with each of the rendered three dimensional models or computing the variance of the brightness coefficients that are used to create each bucket of the histogram-like table, a bucket being a set of similar normal values that are lumped together to form a single argument value in the histogram-like table; computing the sum of the variances of the histogram-like table buckets; and ranking the three dimensional models using its computed sum as an error function, the ranking indicating the likelihood that the corresponding three dimensional model matches the two dimensional image. Also provided is a program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform the method steps of the present invention and a computer program product embodied in a computer-readable medium for carrying out the methods of the present invention.

Method for matching a two dimensional image to one of a plurality of three dimensional candidate models contained in a database

A method for computing the location and orientation of an object in three-dimensional space. The method comprises the steps of: (a) marking a plurality of feature points on a three-dimensional model and corresponding feature points on a two-dimensional query image; (b) for all possible subsets of three two-dimensional feature points marked in step (a), computing the four possible three-dimensional rigid motion solutions of a set of three points in three-dimensional space such that after each of the four rigid motions, under a fixed perspective projection, the three three-dimensional points are mapped precisely to the three corresponding two-dimensional points; (c) for each solution found in step (b), computing an error measure derived from the errors in the projections of all three-dimensional marked points in the three-dimensional model which were not among the three points used in the solution, but which did have corresponding marked points in the two-dimensional query image; (d) ranking the solutions from step (c) based on the computed error measure; and (e) selecting the best solution based on the ranking in step (d). Also provided is a program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform the method steps of the present invention and a computer program product embodied in a computer-readable medium for carrying out the methods of the present invention.

Growing community of inventors

Montreal, Canada

Sebastien Roy