Abstract: A method for estimating motion of each of a plurality of tessels in an intermediate image relative to a reference image, which includes searching the reference image to find points that lie along epipolar lines in the reference image corresponding to upper-left and lower-right vertices of the tessel, respectively, that result in a best-matching shape; estimating a depth of each of at least two of the vertices of the tessel; and using the depth estimates of the at least two vertices of the tessel to estimate the motion of the tessel relative to the best-matching shape.

Abstract: Systems and methods of multiframe image processing are described. In one aspect, correspondence mappings from one or more anchor views of a scene to a common reference anchor view are computed, and anchor views are interpolated based on the computed correspondence mappings to generate a synthetic view of the scene.

Abstract: Systems and methods of multiframe correspondence estimation are described. Light patterns reflected from the scene are captured at one or more capture planes. In one aspect, a sequence of patterns of light symbols that temporally encode two-dimensional position information in a projection plane with unique light symbol sequence codes is projected onto a scene. A correspondence mapping between multipixel regions in the capture plane and corresponding regions in the projection plane is computed based at least in part on correspondence between light symbol sequence codes captured at the capture plane and light symbol sequence codes projected from the projection plane. In another aspect, the patterns consist of a single plane of light that is swept across the scene. Correspondence is determined based at least in part on exploiting the epipolar constraint associated with any pair of cameras.

Abstract: An image capture and viewing system is disclosed. In one embodiment, the present invention provides an image capture system for providing an image of a subject. The image capture system includes a planar surface, a first camera, a second camera and a control module. The first camera is positioned to capture a first subject image of a subject positioned between the planar surface and the first camera. The second camera is spaced from the first camera. The second camera is positioned to capture a second subject image of the subject. The control module is configured to generate a synthesized image of the subject from a virtual view point using the relative positioning of the first camera, the second camera, and a planar surface.

Abstract: A system and method of locating a selected point in a bounded area of a three-dimensional graphical environment is described in which boundary points are assigned to boundaries of the area wherein boundary axes are formed (20), a selected boundary is determined by determining the consecutive boundary axes that the viewing orientation vector lies between (21), and a selected point on the selected boundary is determined dependent on angles formed by the selected boundary, the first and second boundary axes, and the viewing orientation vector (22). The selected point coordinate is compared and matched to image object coordinates (23) to determine the selected image object.

Abstract: An apparatus and method for partitioning a three-dimensional graphical environment for displaying representative images of objects in a database dependent on the database of objects and their associated metadata is described. According to the apparatus and method, the database of objects is represented by a hierarchical tree derived from the object metadata. The tree includes parent nodes, their associated child nodes, and data object nodes, where every node has an associated weight. A predetermined parent node is pre-assigned an area corresponding to the undivided graphical environment. Then, for each parent node having at least two associated child nodes in the tree, the area is recursively divided into a plurality of areas corresponding to each of the associated child nodes such that the areas are proportional to the child node weights.

Abstract: An apparatus and method for browsing a plurality of data objects represented by images displayed within a three-dimensional graphical environment is described. A plurality of data object arrangement schemes are provided for arranging corresponding represented images of the data objects within the three-dimensional environment dependent on a selected one of the schemes. The data objects are then automatically arranged within the three-dimensional environment according to the selected schemes. Schemes can be user selected such that by selecting a new scheme, the objects are rearranged according to the newly selected scheme. The environment is partitioned into three-dimensional areas and representative images of the data objects are arranged within the partitioned environment such that representative images of related groups of data objects with respect to the selected scheme are displayed within the same areas.

Abstract: An apparatus and method for distributing representative images of a plurality of data objects within a database within a partitioned three-dimensional graphical environment is described. According to the apparatus and method an environment is divided into areas bounded by partitions, and groups of representative images are distributed and displayed upon these partitions. In general, distribution of the representative images is achieved by determining weight factors for each partition bounding a given area and determining weight factors for representative images that are to be displayed within the areas upon the partitions and then distributing the images dependent on the comparison of the image weight factors to partition weight factors.

Abstract: A user interface and method for interacting with a three-dimensional graphical environment is determined. Multiple viewing perspectives are provided to the user to allow the user to view and navigate through the environment at approximately eye level or “fly over” and view the environment from an overhead view. Labels corresponding to partitioned areas rotate to adjust to the changing perspective of the user and area color coding adjusts hierarchically dependent on the user's perspective. Partitions and the ceiling of the environment have variable translucency/transparency so as to provide the user with forward viewing capability of the environment and read labels in other areas. The interface controls the movement of the user's in a natural manner and movement is tracked to provide the user with a history of the user's previous navigation path. Addition information views are provided by the interface relating to different objects within the interface.

Abstract: System and method of locating objects positioned in front of a user interactive, computer controlled display area performed by calibrating the system to obtain a coordinate location mapping function and an intensity mapping function between the display area and the captured display area in the capture area of an image capture device. Once calibrated, objects can be located during real-time system operation by converting display area image data using the mapping functions to obtain expected captured display area data, capturing the display area image to obtain actual captured display area data, and comparing the expected and actual data to determine the location of objects in front of the display area in the capture area.