The present invention is a system for real time tracking of position and orientation, termed "pose", of a remote camera. While remote cameras have been used on a regular basis to inspect machinery for wear or damage, knowing the exact location of a camera is difficult. Off-line feature extraction is employed with on-line pose determination. The feature extraction precomputes features from a CAD model of the object visible in a selected set of views. The on-line pose determination starts from an initial pose estimate, determines the visible model features, projects them into a two-dimensional image coordinate system, matches each to the current camera image, and uses the differences between the predicted and matched feature positions in a gradient descent technique to iteratively refine the pose estimate. The on-line portion of the system is designed to execute at video frame rates, providing a continual indication of borescope tip pose.

Disclosed is a multimedia database for use in distributed network environments. A query processing module transforms user queries into search transformations that can be used for indexing; an attentional selection module records salient information represented in images by a hierarchy of feature maps, saliency maps and combined saliency maps; a declarative memory comprises active modules that update the representations acquired over time for the same images, as well as across images, to cluster, categorize and organize information extracted from different images by the attentional selection module; and an indexing mechanism utilizes the search transformations from the query processing module to search the declarative memory for an answer to a user query. The multimedia database is used in distributed network environments wherein a server can select and coordinate information flow between multiple database sites and user sites, provide effective multimedia representation, create indexes on multimedia content of said database sites to derive a set of target multimedia database sites and, enable database queries descriptions and final search results to be conveyed to a user, records information needed for database selection, generates useful query patterns based on memorization of responses patterns from various databases based on user queries, and directs interactive dialogue between a user and multimedia databases.

A process is disclosed for creating three-dimensional figures or forms starting from any flat surface image. The process includes the steps of selecting an illustration to be reproduced in three dimensions and then preparing an assistance plan for the assembly starting from the figures own, or cast, shadow. Thereafter, contour drawings are made of each piece, joining each point that defines a level, following the model's contour until arriving back at the point of departure. The design is then broken down by drawing each of the component pieces thereof individually and cataloging them and grouping them by material, texture and color; making the pieces obtained from the individual drawings, then grouping and cataloging by level each of the fabricated pieces. A base or theoretical point is space is determined over which the work will be assembled; marking at level zero, or the base, the position at which level one will be placed on the base. The assembly of the three-dimensional work is then commenced with the aid of the design so created, by joining corresponding pieces of level one to zero, those of level two to level one, etc., until arriving at the last level planned.

What is disclosed is a method for dynamically and automatically determining the threshold value for edge detection based on localized intensity information. Each pixel can be assigned a threshold to which its gradient or other intensity change information can be compared so as to detect whether or not the pixel belongs to an edge feature of the image or not. Further, the thresholding can be based upon the response of the human vision system so that visual appearance of the image to users is considered when analyzing localized intensity information. The localized thresholding technique can be applied to any edge detection scheme.

Method and apparatus for detecting a contour of an object within an image is provided. A user interface is used to select first and second points within the object. A processor detects first and second subcontours based on the first and second points, respectively; and the first and second subcontours are based on detected edges. The detected edges are representative of non-uniformities within the image. The processor defines subcontours around each of the points, and the subcontours are combined into a contour.