System and method for processing video images

摘要

Embodiments use point clouds to form a three dimensional image of an object. The point cloud of the object may be formed from analysis of two dimensional images of the object. Various techniques may be used on the point cloud to form a three dimensional model of the object which is then used to create a stereoscopic representation of the object.

主权项

1. A method for forming a three dimensional image of an object, the method comprising:
providing, to a processor, at least two images of the object, wherein a first image has a different view of the object than a second image, wherein the first and second images are two dimensional images of a scene; forming a point cloud for the object using the first image and the second image, wherein the point cloud comprises virtual tracking markers, wherein the virtual tracking markers are associated with movement data of particular pixels of features of the scene; creating, by said processor, the three dimensional image of the object using the point cloud, wherein the point cloud comprises points that comprise X, Y, Z coordinates and wherein the point cloud comprises points from each of said first and second images; and placing the three dimensional image of the object into an image of the scene such that the three dimensional image of the object is located in the scene at a different location or where it did not exist in the two dimensional images of the scene.