Abstract: Apparatus and method for a Parallel Query Z-coordinate Buffer are described. The apparatus and method perform a keep/discard decision on screen coordinate geometry before the geometry is converted or rendered into individual display screen pixels by implementing a parallel searching technique within a novel z-coordinate buffer based on a novel magnitude comparison content addressable memory (MCCAM) structure. The MCCAM provides means for performing simultaneous arithmetic magnitude comparisons on numerical quantities. These arithmetic magnitude comparisons include arithmetic less-than, greater-than, less-than-or-equal-to, and greater-than-or-equal-to operations between coordinate values of a selected graphical object and the coordinate values of other objects in the image scene which may or may not occult the selected graphical object.

Abstract: An image is generated from a database of three-dimensional object data where each the objects is formed from at least one polygon having at least one edge. Successively determinations are made as to whether a particular one of the object polygons designated as the test polygon is not visible to an observer located at a predetermined location by virtue of being hidden by other objects in the database. If the test polygon is determined to be not visible, then it does not need to be rendered by an image renderer and may be discarded. The decision is made by successively selecting one of the three-dimensional object in the database. After an object is selected, each of the object polygon is selected to determining whether the polygon is occulted by another object.

Abstract: Apparatus and method for detecting unconstrained collisions between three-dimensional moving objects are described. The apparatus and method addresses the problems associated with handling objects with substance passing through each other in three-dimensional space. When objects collide in a three-dimensional simulation, it is important to identify such collisions in real-time so that the behavior of the colliding objects may be adjusted appropriately. Native vertices are stored and novel structure is provided so that the stored words containing native vertices work together to form polygons, or other object primitives, that work together. For triangle object primitives, three vertices form the first triangle primitive, but a second triangle primitive is formed by receiving and storing only one additional vertex, the other two vertices needed to form the second triangle primitive being shared with the first triangle primitive.

Abstract: Method and apparatus for computing cross-correlations with application to image processing and video motion estimation, particularly in video compression applications, are described. Two-dimensional Fourier transform convolution techniques form a basis for novel techniques for performing two simultaneous two-dimensional cross correlations. The size of the input data blocks for the transformations are arbitrary. Apparatus for efficiently performing real-time cross correlations, including cross-correlations using Short Length Transforms (SLTs), using cascaded stages, multi-port memories, and multiple arithmetic units are also described. In video motion vector estimator application, data blocks within a current video frame are selected and converted to form a two-dimensional matrix of complex data. The complex matrix is transformed to the frequency domain to form the frequency domain representations of the selected data blocks.